Abstract

Today, the interface between the brain and the computer can be designed using intelligent tools. This two-way communication that is named the Brain–computer interface can make new changes in the world of science. Today, with the development of smartphones, the use of applications and social networks has formed an important part of people’s communication. Therefore, the tools must be designed in such a way as to cover the needs of all members of society. For example, for improving the quality of living of aged people, they need to use these facilities with other people. So designing intelligence tools should be such that they can be implemented with the mental decision of people. Also as aging has some effects on activities of daily routines or the human body and their brains, it’s important to settle the difficulties in communicating, walking, drive safely, the lifestyle of people, and their health. In this research, the challenging discussion of the effect of a brain–computer interface technology on aged people’s life system is discussed and the role of the user interface is examined. Also, deep learning is one of the most important algorithms to make the patterns of subjects. Robots to feed elderly people, intelligent wheelchairs that are controlled by mental decisions, applications to make decisions and help to memorizing information for elderly people with Alzheimer, cameras to synthesize eye movements for aged people with vision disorder people, devices that help to make decisions for elderly people who have had a stroke and getting communication disorders, are high-tech devices that help to people who are suffering from cognition errors or physical disability. The BCI applications which are based on deep learning algorithms can monitor brain activity. They have programmed signals that can make better decisions in different situations and can help to decrease the decision timing and improve the level of confidence and create a balance between different levels of people in society. Creating a balance between people improves the level of quality in every society and helps to increase the healthy life in society. In this chapter, we explore the relationship between the BCI applications which are based on deep learning algorithms and their applications for elderly people.

Keywords: Brain Computer Interface (BCI), diseases, intelligence application, mental decisions, machine learning, AI in health, elderly people, disability, cognitive science

4.1 Introduction

The aging process occurs in all humans over the age of 60. With age, physical, psychological, and social changes over time are identified [55]. Today, the results show that one of the biggest risk factors for most diseases occurs in the elderly [59]. Most of the daily deaths in the world are due to old age and the diseases that the elderly face. In modern countries, the mortality rate of older people is higher than that of young people [60, 61]. Age can lead to visual impairment and consequently reduced non-verbal communication [62], which is likely to cause depression and isolation among the elderly. Therefore, it is necessary to research the factors that cause disability faster and provide solutions to prevent premature aging and premature diseases in people. A society that faces premature aging has a very low rate of social vitality and life expectancy, and ultimately growth and development.

The majority or a significant number of people experience some of the characteristics of aging during their lifetime. Therefore, with the obtained experiences, aging can be reduced by presenting methods and factors affecting it. One of the consequences of increasing age from childhood to old age is decreasing of auditory and visual ability. Teens’ or young children’s ability to hear high-frequency sounds is lost [56]. Approximately half of the people over the age of 75 have hearing loss or presbyopia, which inhibits speech communication [57]. Decreased brain function also occurs with age and therefore dementia increases with age. According to statistics, approximately 3% of people aged 65–74 years and about 19% of people between 75 and 84 years, and also about half of the people over 85 years of age suffer from dementia [58].

As mentioned, maintaining social vitality and life expectancy among members of society is essential. People who have problems or illnesses for various reasons should be able to enjoy the same facilities as other people in the community. Therefore, with the development of technology and the design of smart tools, it is possible to help all members of society, especially the elderly and those with disabilities. The use of the “brain–computer interface (BCI)” seems to have been first coined by Jacques Vidal in 1973 [54]. BCI system is defined as the natural neural pathways to the output signal that bypasses the brain and translates into new types of output.

BCI to control external systems uses neural responses. BCI applications are the new way to improve the ability of doing daily works for disability people and the needy [8]. By new methods using on the applications, it is possible to help more and more [9]. Using different methods and algorithms can create a versatile smart tool.

4.2 Diagnosing Diseases

Neural networks can help in diagnosing patients’ problems. In fact, people with physical and mental disabilities have some of the nerve signals that carry commands to the brain and cannot function properly. Most elderly also suffer from this physical and mental problem. Their physical problem is due to old age and inability to walk and pain in their limbs and other parts of their body, and their mental problem is due to diseases such as Alzheimer’s or mental illness that they suffer from. These problems are due to the fact that over the years, their muscles have been weakened and over time they have faced weakness of the nerves. In this regard in [1], it is examined and proved that the design of applications based on neural networks have an important role in the care and health of the elderly. It seems that by examining neural algorithms, we can design applications that stimulate neural signals and see the result in the elderly.

Using of convolutional neural networks [10] is for image processing and vision processing, and also because medical image processing and disease diagnosis is one of the most important and challenging issues, this neural networks can be used to diagnosing diseases using the BCI applications [11]. Especially for the elderly who are more prone to physical injury, the use of accurate medical image processing methods is effective in diagnosing their disease. Older people may not be able to understand and express their problem for a variety of reasons.

Visual impairment or misunderstanding of conditions due to dementia or Alzheimer’s cause’s misdiagnosis of environmental conditions, so using convolutional neural networks can help detecting of eye movement of them. By recognizing eye movement, one can identify the purpose and needs of people who are unable to speak. Elderly people who cannot speak and don’t have the brain disability to understand can show their goal by looking and eye movement and detection of eye movement by BCI applications is one of the most important points that should be considered in designing applications.

Optimization algorithms can help to make better choices and clustering and prioritize the various commands that are created in the brain. Three-dimensional (3D) convolutional neural networks (CNN) is a model of convolutional in 3D that allow us in real time to process the information contained in a neural signal channels and also information is stored in the communication between a channel and its neighbors [14]. The final feature representation combines information from all channels [15], and creates a targeted BCI application.

In [2], some models to prevent harm to the elderly are presented. The role of airbags [2] in reducing the incidence of injury to the individual is significant. The elderly are at risk due to physical weakness and sometimes poor eyesight. They may be injured and fall while walking and doing daily activities. Therefore in designing BCI applications for the elderly, important factors such as calculating body temperature and heart rate should always be considered. In most cases, the increasing or decreasing heart rate occurred by falling or damage. Also, improper nutrition or forgetfulness in taking their medications create symptoms such as discoloration of the face and low blood sugar or other cases. Deep learning algorithms and color recognition algorithms can play an effective role in preventing this damage from happening. Momentary changes in the patient’s skin color, as well as the instantaneous recording of the patient’s pressure and temperature, are effective by BCI applications. Deep learning algorithms can recorded any changes in the applications and then the right decision is made for each patient. Decreased or increased blood sugar causes a change in heart rate or darkening of the skin or lips. Also, high blood sugar causes a dry throat and a feeling of thirst in the patient, which is determined by the patient’s facial expressions and eye conditions. The signals of the human brain react differently to these symptoms. So clustering techniques for the reactions and decision-making algorithms can help diagnose and solve the elderly person’s problem. So, it is necessary for sending calculated information to doctors by the real-time sensors, and in case of any changes, the patient should be transferred to the medical center immediately. Activating the GPS sensors is one of the most important sensors that should be considered in the BCI applications. Deep learning and the use of clustering algorithms with GPS sensors have significant effects in selecting the best performance at the moment of injury to the patient. Using of deep learning techniques in BCI applications can reduce injury to the patient in real-time by activating the detection sensors. We can prioritize methods that reduce injury by selecting and clustering several factors.

In [3], it is examined and implemented the measures such as the height of elderly, distance and the angle of them to the ground. Due to the fact that older people fall more due to physical disability, changes in the angle of the legs and back of the elderly person should be recorded in real-time sensors. It seems that in order to perform accurate calculations, the person’s height and scales such as the amount of curvature of the elderly person must be calculated, so that as soon as any changes occur in these situations, it can be photographed in 3D-positions and then alarmed to health centers. Hereon, using of intelligent learning methods helps in diagnosis. The measurement of the patient’s heart rate or behaviors in the elderly after a fall should be carefully measured. If there is a problem such as shortness of breath, smart devices should be activated around the elderly.

Anemia is one of the most common diseases among the elderly. This disease has various complications such as dizziness, lack of concentration, distraction, etc. [20]. Diagnosis of anemia can also be recognized by a person’s appearance. Symptoms such as discoloration of the face and nails, etc. are the first signs of anemia. In diagnosing various problems of anemia and trying to solve the problems of the elderly, it is necessary to carefully examine various factors. The combination of genetic algorithm and machine learning and neural networks and also clustering methods [19] can create a complete model that helps physicians to make more accurate decisions. These algorithms that are implemented on the BCI application activate the system in case of any problems. Optimizing the BCI algorithms that can evaluate the usability for hand therapy will help the World Health Organization (WHO) to provide better services [21]. The use of evolutionary methods can have important effects on achieving better results in this field.

Using optimization algorithms can make the best results by recording and examining the elderly person’s condition. In this method, various factors should be defined as parameters of the algorithm and also the relationship of factors with each other, such as the relationship between facial discolorations with decreasing or increasing blood pressure. Rising or falling heart rate due to falling as a function should be defined. Changing each parameter at different times can determine the patient’s condition at any time.

Because older people have heart problems or have had heart surgery, accurate diagnosis of heart rate among them is a crucial issue that needs to be evaluated more carefully, so activating heart rate sensors must be very accurate. Segmentation of heart rate sound using evolutionary algorithms can help in the optimal evaluated of heart rate [22].

The use of genetic algorithms in convolutional neural networks has shown that the detection and analysis of brain images have better results [28]. Various changes due to injury to the patient cause changes in brain signals. Brain signal processing along with brain image processing and facial image processing simultaneously can show excellent results from the patient’s condition and eventually the use of deep learning methods can evaluate the results and make the decision right after each event.

The “silent speech BCI system” [29] is an interesting definition for recognizing sounds. Using clustering and segmentation methods based on images on this system has shown that brain signals have a better response than comprehension. In general, it is critical to use patterns that analyze nerve signals. Any changes in mood, behavior, and speech cause a change in nerve signals. This is not just about the elderly. Everyone reacts differently to each event based on their age. Therefore, data analysis of nerve signals in the elderly can make better decisions for the elderly.

Data mining and the application of semantic data patterns play an important role in recognizing the meaning of signals.

Every person at any age reacts differently to changes in heart rate. Of course, it is very important to note that some reactions or pain in parts of the body are similar, but it should be considered that data mining methods can categorize the reactions of the elderly or the mentally retarded or people with Alzheimer’s. Hence it made a different decision for each person by intelligent applications. Systems that work with this technology also recognize limb images. It seems that this technology can have positive results for the elderly. Brain commands can be activated by displaying images of words. For example, by showing news or question sentences to the elderly who do not have good brain activity, it can be challenged. If the elderly do not have the ability to speak or talk, the brain command is displayed on the monitor. It seems that such BCI applications can be very useful in the future for many patients who have lost their speech due to any reason, especially due to stroke reason. Stroke was one of the most common causes of death in the world in 2011, which according to statistics is occurred about 6.2 million deaths [63]. A stroke occurs at any age, even in childhood, but the risk of developing this disease increases from the age of 30 and its cause varies according to age [64]. In the elderly and people over 45 years, various risk factors for stroke are higher [65]. According to the obtained results, it is necessary to design smart applications that can detect the symptoms of stroke among people, especially the elderly and those who are not able to express the problem and have in special condition. A number of symptoms at the time of stroke are common to all people that need to be considered in all applications, but due to different special conditions, especially the elderly who have different and more problems, stroke may have other complications or even with other symptoms may occur. Applications should offer different solutions for each age group to reduce the risk of serious injury or death. Intelligent clustering techniques combined with deep learning methods can help to identify and provide solutions tailored to each individual situation.

Patients with Alzheimer’s disease may also have their brain signals stimulated and their exacerbation delayed. One of the first signs in the diagnosis of Alzheimer’s is forgetting the latest events [66]. As the disease progresses, symptoms can include speech problems, getting lost in walking paths, mood swings, and loss of hope and motivation [66, 67]. Over time, the person at risk of injury often withdraws from family and society [66]. Gradually, the body’s functions are destroyed and eventually causes death [68]. Although the rate of progression of this disease can vary between individuals, life expectancy after diagnosis and providing solutions to prevent the rapid growth of this disease is about three to nine years [69, 70]. In these patients, their psychological symptoms should be further investigated. Most seniors who develop Alzheimer’s have this problem due to old age, getting away from the community, and reduced communication with others. Of course, part of this disease is inherited but this can be delayed with new methods in the age of technology. In this regard, it is necessary to implement an idea with cognitive sciences and a combination of cognitive and behavioral patterns to help people who are at the risk of Alzheimer’s disease for do not suffering from dementia. By challenging the minds of older people, the nervous systems are stimulated and brain activity does not cause aging and the destruction of the nervous system.

EEG (electroencephalography) can detect brain function using electrodes attached to the scalp. EEG is commonly used to diagnose brain disorders, especially epilepsy or seizures and other brain disorders. Brain cells function in all conditions, even when the person is asleep, and are identified by electrodes as wavy lines on the EEG.

EEG analysis is performed using data analysis and calculation methods that help researchers to better understand brain function and physicians in selecting and diagnosing the brain–computer interface (BCI) [71]. Also it creates a new communication channel [72].

Epilepsy causes the death of nerve cells. People with the disease are exposed to other diseases. With the loss of nerve cells, people may develop speech disorders or Alzheimer’s or other problems. Older people who are more prone to injury should avoid the factors that cause this problem. Regular monitoring of blood pressure and blood sugar regulation should be a priority for the elderly. A healthy diet should be considered for the elderly according to their body condition. Detection of symptoms related to epilepsy or seizures by detection algorithms can prevent the disease. The activities of brain cells can be examined and the results of brain cell function on the BCI application can be determined by the EEG analysis. In case of cell dysfunction, the BCI application should specify the patient’s condition. Pattern detection method and intelligent learning algorithms help to assess the patient’s condition.

One of the most common diseases among the elderly is dementia (mild cognition impairment). In [4], the types of dementia have been studied and using clustering methods has been identified to detect the dementia types and measurement items. The elderly with this disease have been divided into different groups. Using machine learning techniques for accurate division helps to select groups accurately. Each group receives applications tailored to them due to the different disabilities they have in their brains. For example, by conducting a study, elderly who talk difficulty and expressing words with delay or spelling-error distance value (SEDV) [5] can be placed in one group and it can be examined what other problems they may have, then it is provided other tools to strengthen their other problems too. By using deep learning algorithms, detecting dementia types with specific problems by brain–computer interfaces can be done and it helps to solve the patient’s problem by providing services through BCI applications.

4.3 Movement Control

Another problem that older people face is using a wheelchair to get around and do their daily activities. Nowadays, with the advancement of technology, using of electronic wheelchairs has become popular. The wheelchair can move easily without the need to use a hand or without pushing another person [6]. The main base of electronic wheelchairs is to detect the behavior and reactions of the brain signals. In [7], designing intelligence wheelchair using deep learning patterns is presented. It is necessary to determine the path with instructions that are made through the patient’s voice or eye movement towards the target. The use of noise detection algorithms, as well as the detection of brain commands according to the reactions that occur in the brain, helps to build ultra-intelligent wheelchairs.

Designing systems for remote object identification [16], and accurate delay calculation play an important role in route detection to prevent obstacles. Also using three-dimensional path detection algorithms [17] and RGB image processing using neural networks [18] to detect the objects or obstacles have crucial important. It seems that this architecture [17] can be implemented on the design of wheelchairs that work with the BCI application. Detection of an object in the path of the wheelchair is especially important for the elderly who are disabled to change the way by eyesight movement. In BCI applications it should be considered in real-time that if it doesn’t any receiving to brain signals, the section of path detection in BCI will be able. Various features must be considered for accurate real-time detection. Clustering algorithms can help with the right choice and using the optimization algorithm can make the best choice at the real-time.

A brain-inspired neural network [12] is a potential approach that can learn the signal in different directions with high time accuracy by estimating the complexity of movements. Deep learning and the use of the BI-SNN method can help correlate changes in body muscles and changes in brain signals in BCI programs [13]. Using BI-SNN technique on EEG in BCI applications can have better results in real-time reactions.

4.4 IoT

The Internet of Things is a new intelligence technique for making objects smarter. In this technology, with wireless networks and the Internet, home appliances can be moved or turned on and off without the need of human-to-human or human-to-computer. An important part of the application of this technology is in healthcare and for people who are disabled. It has a significant impact on improving the quality of their lives. The advantages of this technology are much higher than its disadvantages and it seeks to eliminate the disadvantages and especially increase the security in this technology. The internet of Health things (IHT) for monitoring the vital signs of patients in the hospital [23] is introduced. The available data are collected from patients. According to the vital signs that are present in the patient, the diagnosis is made to solve the problem. It is useful for the elderly. The elderly should have a more accurate data set because they have different problems than others. Designing this method of using the application can help the elderly more. The issue of IoT security in medicine is pointed [24] and Internet of Medical things (IoMT) provides a solution that can store data more securely. If this method is provided in the BCI application, it can help to maintain the patient’s health [25]. Elderly people with various diseases can use their own BCI applications. Depending on the symptoms, each person should use their own smart objects. Someone with Alzheimer’s should use reminder BCI application and someone with speech disorders or has had a heart attack or his brain cells have been destroyed due to old age should use smart objects that can control a person’s function. At the moment that the elderly needs help, smart objects should be used according to the specific situation. Activation of the smart object is done using detection techniques based on the target signals.

4.5 Cognitive Science

The elderly live mostly in quiet and unchangeable environments. They cannot go out of the house because of their disabilities. So it’s an important point to address in terms of psychology for improving the quality of their lifestyle. Knowing the mental state of each patient [27] and providing an environment that is in accordance with the taste of each patient can help increase self-confidence and raise the morale of the elderly and thus help the longevity of the elderly. Influence of interior design elements is a positive point for the elderly and it is seemed it is needed to empower the BCI applications [26]. We can use the cognitive science to learn more about the elderly in terms of their favorite color tastes. Cognitive scientists focus on how the nervous system, intelligence and behavior are studied. Designing intelligent systems and using the Internet of Things using cognitive science can be effective in designing a quality system.

By recognizing the facial moods, it is possible to identify the different situations of aging people. Detecting a state of happiness, sadness and even detecting the changing in the face color that can be the symbol of a problem in the patient’s body is essential with the highest accuracy rate [30]. Designing a face recognition BCI application that can achieve face images and the symptoms of any problem with high efficiency is one of the essential points in designing BCI applications. Using cognitive algorithms can have important role in designing of this tools.

Cognitive health is one of the topics in general brain health that discusses the ability of the elderly to think, learn and remember information. One of the most important daily tasks of people in order to take care of physical health is cognitive health. Dividing each person’s moods using clustering methods based on the age and gender criteria of each elderly person can help to provide a solution for his health. Therefore, different learning tools must be implemented according to the specific conditions. So it can provide services to everyone according to its own conditions. Designing smart objects smarter in order to recognize and provide services to each person using deep learning algorithms can be a positive point in making smart systems and applications smarter.

Applications games should also be designed for educational purposes. Brain games that can challenge the mind, are useful for every ages. Children increase their analytical power with games. In the same way, designing games that are appropriate for the age of young people or the elderly promotes their mind and especially using games in the many diseases of elderly can be prevented. Alzheimer’s disease or lack of self-confidence in the elderly due to their distance from technology are factors that should be considered in designing game ideas. Online games have the best ideas for gaming that expand communication between people. There are several benefits to designing online gaming applications for the elderly. MindGameku game [31] has been presented using convolutional neural network technique and deep learning and the acceptance of this game has increased by reviewing the results. It can be used for the elderly by examining this game and expanding it.

The GO game is a two-player game designed using deep neural networks [32]. It has important challenging effects on mind and will can use for elderly. Go is a strategy game that try to encircle the further territory. This game is one of the first board games that still has many fans [33]. If this game is presented in multiplayer, it can attract many people and also positive results will be obtained. This game with a special application for the elderly can be very useful for them.

Smart games should be tailored to the needs of the elderly and they challenge the minds of the elderly. The challenge of smart games should change daily. It should have aimed at improving and strengthening the patient mentally and physically. Elderly people who are sedentary can change their lifestyle with attractive and cheerful intelligence games. The elderly who are physically disabled can use daily challenging games that are related to their minds. Choosing the best intelligence game and changing the style of play by deep learning methods can be effective in the direction of the elderly lifestyle.

Games that are written or visual should be designed for older people with different conditions. Those who have hearing problems should use intelligence video games and those who have vision problems should use online games with audio techniques. Providing different methods in games allow most people to use. It seems that it is possible to design BCI applications that provide each game in a various multimedia technology [35] at the same time. The role of graphics and animations in designing game is very influential [34]. The most important advantage of these BCI games is that the elderly with different conditions can enjoy playing together at the same time, and the impacts of the services is very great for the elderly. Not separating people from each other because of certain problems they have, especially in the elderly or disabled, makes them live together actively and motivated.

4.6 Olfactory System

The human olfactory system is one of the essential systems in the human body [38]. The olfactory nerves may be damaged for a variety of reasons. These changes are more common in the elderly [36, 39]. One of the causes that has occurred in the last years is Covid19 disease. It effects on the olfactory loss of individuals [40]. Usually people with Alzheimer’s lose their sense of smell or sometimes their sense of smell changes [37]. Olfactory memory is an odor-evoked memory that is used on elderly and can used to detect some odor impairments [46]. Using of intelligent methods in the accurate diagnosis of this problem is effective. The applications that can monitor a patient’s olfactory impairment based on brain cell function can be a good option for diagnosing the disease.

An important discussion is to create conditions for the elderly who have olfactory disorders and may be harmed. The harms of this situation, which was very enjoyable for them in their youth, are not enjoying the smell of food.

Lack of sense of smell, in addition to not enjoying the taste and aroma, has other health effects. For example, Gas leaks [41] are one of the most dangerous things that can happen in homes. Gas leaks are one of the most common causes of death in homes, which can be prevented by rapid detection of gas odor. People with olfactory problems are more at risk. Elderly people with olfactory problems or physical disabilities cannot protect themselves in the event of an accident and they are vulnerable to lack of sense of smell. Therefore, by designing powerful applications, such problems should be prevented.

The use of smart sensors in detecting environmental conditions can prevent this from happening and also using of smart sensors in smartphones. Applications can alert health centers in the event of changes in temperature and odor. Intelligent olfactory system [42] is a very useful and excellent technology that can be useful for people who have an olfactory problem for any reason. This system with its conditions can simulate the olfactory nerves and the patient can understand the sense of smell around him. This system can reduce the disadvantages of lack of sense of smell to some extent. Neural networks have a significant impact on the development of intelligent olfactory systems [44]. In the design of intelligence systems, deep learning [43] and graph theories [45] and pattern recognition and clustering on olfactory intelligence systems [47] help to analyze various parameters. It provides better models for more accurate intelligent olfactory system design.

Wireless systems can be a good option for designing applications that are widely used. These systems use radio wave technology and can be activated via Bluetooth or the Internet. Using wireless systems in BCI applications is very useful. Designing BCI wireless applications [48] is a good option for applications used by the elderly. Maybe there are advantages and disadvantages to these applications. The advantage of these systems is the lack of physical connection and the disadvantage is that the elderly may not be able to active this application. The challenging issue that seems to be debated is whether these systems have negative influences on the functioning brains of the elderly because of the waves they have or not. Due to the effects that waves have on the brain, the use of wireless applications should be designed based on the conditions of each elderly person. Diagnosis of the use of wireless systems is selected with criteria. The program should be taught by clustering algorithms and deep learning what commands to execute according to each person’s situation.

The olfactory system using Wi-Fi can maintain high-quality olfactory signals for a limited time [53]. Designing a BCI application that can understand the environmental conditions by recording and maintaining signals can be useful for the elderly or disabled.

4.7 Brain-to-Brain (B2B) Communication Systems

Brain-to-brain (B2B) communication systems can facilitate the exchange of information between people by transmitting signals with non-invasive interface [50]. Also the multi-person brain-to-brain system [52] is more able to make more conversation. The systems learn to trust the signals sent [49]. The B2B social network [51] can be designed to make conversations between people. These systems transmit waves through the scalp and they are a way of hyper-interaction. It seems that the using of this system in applications is very necessary. This system can help to improve the condition of the elderly by communicating between people. B2B social networks help to communicate between people. The best conditions can be established in the design of these systems using different criteria. Depending on the circumstances of each individual and the clustering of individuals based on similar criteria, the interaction between individuals is created. The method of clustering in selecting relief centers can play an effective role in improving the situation of people in need. Implemented algorithms can be a good choice in this system based on the objective function. Patterns based on learning functions can also be used.

4.8 Hearing

A hearing aid is a device that helps hearing-impaired people to hear sound in its entirety or with higher quality. According to the results, hearing loss and aging are related. With age, the problem of hearing loss increases among the elderly. This problem has other negative consequences [77].

Research has shown that a small number of people with hearing loss use hearing aids [74]. It seems that the high cost and lack of health insurance for patients makes it impossible for them to use hearing aids.

With hearing loss, the communication between people decreases. The resulting is social isolation and depression, which reduces the quality of life. To reduce these injuries, using a hearing aid [73] can be helpful.

Smartphones played an important role in the design of modern hearing aids [79]. Early hearing aids guided sounds in front of the ear and blocked all other sounds. These hearing aids were placed behind or inside the ear. Modern devices try to make the sound audible by changing the ambient sound. These devices use signal processing to improve auditory and speech performance. The use of signal processing algorithms to reduce noise and reduce the frequency of sound plays an important role in the performance of these devices. User-friendly is also one of the important features that should be considered [78]. Also, using of the devices can be expanded the signal processing methods and also aging cause’s changes in the auditory nerves [103]. Therefore, choosing a hearing aid suitable for the age and condition of people helps to improve their condition.

Using smart hearing aids and hearing aids that work with Bluetooth or Wi-Fi can be a step towards smart hearing aids. Of course, it must be considered whether the waves that are in direct contact with the nerves of the ear based on the on or off of Wi-Fi cause more damage or not. All the efforts that researchers make to design the tools smarter are for the welfare of the people. It should be noted that modernization does not reduce the health of the elderly or disabled or those who are more at risk.

One of the things that can have a positive effect on the elderly is the intelligent operation of applications, in a way that changes the sound of music according to the level of hearing. So that people can easily hear the sound of movies or music or radio. This automatic change of sound according to the person’s hearing threshold should be so intelligent that no disturbance is felt in the person’s hearing. Designing BCI applications according to the hearing of an elderly person can help to create their vitality. Deep learning algorithms with cognitive methods on detecting a person’s moods provide them with situational selection patterns according to each person’s circumstances to motivate and make the person feel good.

Most elderly have hearing loss problems and use hearing aids or cochlear implants. They also use magnetic resonance imaging (MRI) more than other people. According to studies [82], MRI imaging is not suitable for those who have cochlear implants due to its waves and causes damage to their health. Because MRI is essential for the elderly, it is necessary to use another method to reduce their hearing problems to reduce damage to their health. Using some applications can be an alternative to cochlear implants [83]. BCI applications based on visual can have influences impacts on helping hearing loss [84]. Improving the performance of this auditory BCI and controlling the processing of hearing aids is essential.

An important point is that the popularity of using smart devices is growing among the elderly. Also a number of people with various problems have welcomed the use of smart controls that can make their work easier. Using voice interfaces in BCI applications can increase the usefulness of the application [80].

One of the most important points in hearing aids should be the usual combination with auditory attention detection (AAD) in BCI applications. This technology can be used to play music for hearing impaired people or people who have cochlear implants [81].

Most BCI systems based on visual stimuli use a number of auditory stimuli. These systems can be a good choice for people with visual or physical disabilities because they are not dependent on vision [85]. Synchronous or asynchronous in BCI applications can make differences in their performance. These systems are divided into two categories of synchronous and non-synchronous according to the response time and accuracy [86]. Devices that need to respond quickly to a function are a priority.

4.9 Diabetes

Diabetes is one of the hundreds of common diseases that the elderly suffer from. It should be detected and controlled using smart tools. Diagnosing diabetes by using applications can reduce the incidence of the problem. Introducing algorithms along with intelligent learning methods [87, 88] can help control this disease. Smart phones can help patients and medical centers by detecting and notifications for taking medications with reliable apps.

The symptoms of diabetes diseases can be diagnosed for patients who have only diabetes. But the elderly who have problems other than diabetes such as Alzheimer’s or speech impairment may be more at risk.

Diabetes in elderly people is often diagnosed with symptoms dementia and urinary incontinence [90]. The risk of cardiovascular disease in older people with diabetes is more than double that of non-diabetics. Therapeutic goals for controlling blood sugar, blood pressure, and cholesterol should be considered in the elderly [91].

4.10 Urinary Incontinence

Designing multipurpose applications is critical for these people. Using of neural signals, clustering methods and convolution neural networks can be effective in designing the applications [89].

In [75], it has been shown that some elderly people have urinary incontinence. One of the most common causes of incontinence is due to overactive bladder and stress, which disrupts the life system of people with the disease [76].

Urinary incontinence is more common among the elderly. Various factors affect this disease. Old age and lack of concentration and even sneezing and coughing can cause this to happen [93]. Strategies for controlling urinary incontinence have been identified [92]. It seem to alleviate this problem to some extent. Controlling urinary incontinence can have a positive effect on mood and positive life trends in the elderly. The methods of managing urinary incontinence using smart applications is examined [94]. These applications must meet several important criteria. Including respect for user privacy and maintaining psychological security between the patient and the medical center are the most important factors. It seems that providing an application that can calm the minds of people, especially the elderly who are more prone to psychological trauma, can play a role in treatment and control or prevention.

Improper closure of the bladder can cause problems called stress urinary incontinence (SUI). Stress incontinence is commonly seen in men after prostate surgery [96], and also in pregnant women, childbirth, obesity, and menopause. It is often with weak pelvic floor. It is leading to inadequate closure and stress incontinence [97–99]. Also the incidence of post-meno-pausal stress incontinence increases. It is especially in older women [100].

It is necessary to reduce the incidence of this problem by managing other problems, due to the various problems that cause urinary incontinence in the elderly.

Exercise can be effective in reducing stress and then reducing urinary incontinence. Exercise related to this problem in the elderly increases their physical vitality. “Kegel exercise”, known as pelvic floor exercise, causes the muscles to contract and relax constantly, thereby restoring the strength of the pelvic floor muscles [101]. This exercise should be performed simultaneously for several minutes several times during the day and its effect is determined about one to three months after the start of exercise [102]. They have profound influences for treatment the elderly. Using BCI applications to training and checking how to exercise can be advantaged for elderly. The effect of using applications in controlling incontinence on the improvement of pelvic floor muscles has been identified and it is hoped that the use of these applications will have a positive effect on reducing the disease and improving the patient’s health [95]. It is necessary to use of learning patterns that can help in designing a smart application. By diagnosing the person’s condition and recognizing the symptoms related to stress that are result the urinary incontinence, different ways should be offered to the person. The solutions should be according to the ability of the elderly by cognitive methods. Therefore, super-intelligent patterns can bring good results for the elderly.

4.11 Conclusion

The elderly are an important part of society their needs to be addressed. A society that can protect its elderly can thrive on science and technology and healthy living. Symptoms that develop over time due to old age should be identified and prevented or treated. These symptoms can be detected using modern methods. Designing smart programs that can detect physical or mental harm to the elderly can help to prevent it. In this chapter, the factors that are determined by old age were examined and methods and applications that could examine different criteria were introduced. It is possible to monitor the physical or mental disabilities of the elderly by designing BCI applications. It can help these people in case of injury. These applications also help to improve the physical and mental condition of the elderly by providing services.

References

1. 1. Mansoor, A., Usman, M.W., Jamil, N., Naeem, M.A., Deep learning algorithm for brain–computer interface. Sci. Program., 2020, Article ID 5762149, 2020.
2. 2. Guo, S., Xie, Y., Li, Y., Research on the prediction model of elderly fall, in: MATEC Web of Conferences, EDP Sciences, vol. 336, p. 07019, 2021.
3. 3. Mahdi, S.Q., Gharghan, S.K., Hasan, M.A., FPGA-based neural network for accurate distance estimation of elderly falls using WSN in an indoor environment. Measurement, 167, 108276, 2021.
4. 4. Fukushima, A., Morooka, R., Tanaka, H., Kentaro, H., Tugawa, A., Hanyu, H., Classification of dementia type using the brain–computer interface. Artif. Life Robot., 26, 2, 216–221, 2021.
5. 5. Kurihara, R., Tanaka, H., Umahara, T., BCI character input characteristics in patients with mild dementia, in: Human Interface Symposium, 2017.
6. 6. Xin, L., Gao, S., Tang, J., Xu, X., Design of a brain controlled wheelchair, in: 2018 IEEE 4th International Conference on Control Science and Systems Engineering (ICCSSE), IEEE, pp. 112–116, 2018.
7. 7. Zubair, Z.R.S., A deep learning based optimization model for based computer interface of wheelchair directional control. Tikrit J. Pure Sci., 26, 1, 108–112, 2021.
8. 8. Belkacem, A.N., Jamil, N., Palmer, J.A., Ouhbi, S., Chen, C., Brain computer interfaces for improving the quality of life of older adults and elderly patients. Front. Neurosci., 14, 692, 2020.
9. 9. Saha, S., Mamun, K.A., Ahmed, K., II, Mostafa, R., Naik, G.R., Darvishi, S., Khandoker, A.H., Baumert, M., Progress in brain computer interface: Challenges and potentials. Front. Syst. Neurosci., 15, 4, 2021.
10. 10. Le Cun, Y., LeNet-5, convolutional neural networks. 20, 5, 14, 2015. URL: http://yann.lecun.com/exdb/lenet.
11. 11. Kwon, J. and Im, C.-H., Subject-independent functional near-infrared spectroscopy-based brain–computer interfaces based on convolutional neural networks. Front. Hum. Neurosci., 15, 121, 2021.
12. 12. Ionescu, M., Paun, G., Yokomori, T., Spiking neural P systems. Fundam. Inform., 71, 2, 3, 279–308, 2006.
13. 13. Kumarasinghe, K., Kasabov, N., Taylor, D., Brain-inspired spiking neural networks for decoding and understanding muscle activity and kinematics from electroencephalography signals during hand movements. Sci. Rep., 11, 1, 1–15, 2021.
14. 14. Valenti, A., Barsotti, M., Bacciu, D., Ascari, L., A deep classifier for upperlimbs motor anticipation tasks in an online BCI setting. Bioengineering, 8, 2, 21, 2021.
15. 15. Ji, S., Xu, W., Yang, M., Yu, K., 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell., 35, 1, 221–231, 2012.
16. 16. Arnold, E., Omar, Y., Al-Jarrah, M.D., Fallah, S., Oxtoby, D., Mouzakitis, A., A survey on 3D object detection methods for autonomous driving applications. IEEE Trans. Intell. Transport. Syst., 20, 10, 3782–3795, 2019.
17. 17. Bird's eye view LiDAR point cloud based real-time 3D object detection for autonomous driving, in: 2021 IEEE International Intelligent Transportation Systems Conference (ITSC), 2809-2815, IEEE, 2021.
18. 18. Shrivastava, S., VR3Dense: Voxel representation learning for 3D object detection and monocular dense depth reconstruction. arXiv preprint arXiv:2104.05932, 2021.
19. 19. Kilicarslan, S., Celik, M., Sahin, Ş., Hybrid models based on genetic algorithm and deep learning algorithms for nutritional anemia disease classification. Biomed. Signal Process. Control, 63, 102231, 2021.
20. 20. Gambhir, I.S., Jain, A., Pujar, D., Srivastava, A., Chakrabarti, S.S., Prasad, S., Iron deficiency anemia in elderly patients-A cross-sectional study from a tertiary teaching and research hospital in North India. The Indian Journal of Gerontology, XXIX, I-IV. ISSN-0971-8060: 27.
21. 21. Zulauf-Czaja, A., Al-Taleb, M.K.H., Purcell, M., Petric-Gray, N., Cloughley, J., Vuckovic, A., On the way home: A BCI-FES hand therapy self-managed by sub-acute SCI participants and their caregivers: A usability study. J. Neuro Eng. Rehab., 18, 1, 1–18, 2021.
22. 22. Alonso-Arévalo, M.A., Cruz-Gutiérrez, A., Ibarra-Hernández, R.F., García-Canseco, E., Conte-Galván, R., Robust heart sound segmentation based on spectral change detection and genetic algorithms. Biomed. Signal Process. Control, 63, 102208, 2021.
23. 23. Da Costa, C.A., Pasluosta, C.F., Eskofier, B., Da Silva, D.B., Rosa Righi, R., Internet of Health Things: Toward intelligent vital signs monitoring in hospital wards. Artif. Intell. Med., 89, 61–69, 2018.
24. 24. Gatouillat, A., Badr, Y., Massot, B., Sejdić, E., Internet of medical things: A review of recent contributions dealing with cyber-physical systems in medicine. IEEE J. Internet Things, 5, 5, 3810–3822, 2018.
25. 25. Park, S., Cha, H.-S., Kwon, J., Kim, H., Im, C.-H., Development of an online home appliance control system using augmented reality and an ssvep-based brain–computer interface, in: 2020 8th International Winter Conference on Brain–Computer Interface (BCI), IEEE, pp. 1–2, 2020.
26. 26. Engineer, A., Sternberg, E.M., Najafi, B., Designing interiors to mitigate physical and cognitive deficits related to aging and to promote longevity in older adults: A review. Gerontology, 64, 6, 612–622, 2018.
27. 27. Kadakkuzha, B.M., Akhmedov, K., Capo, T.R., Carvalloza, A.C., Fallahi, M., Puthanveettil, S.V., Age-associated bidirectional modulation of gene expression in single identified R15 neuron of aplysia. BMC Genom., 141, 1–14, 2013.
28. 28. Lee, S., Kim, J., Kang, H., Kang, D.-Y., Park, J., Genetic algorithm based deep learning neural network structure and hyperparameter optimization. Appl. Sci., 11, 2, 744, 2021.
29. 29. Min, B., Kim, J., Park, H.-J., Lee, B., Vowel imagery decoding toward silent speech BCI using extreme learning machine with electroencephalogram. Biomed Res. Int., 2016, Article ID 2618265, 2016.
30. 30. Zhi, H. and Liu, S., Face recognition based on genetic algorithm. J. Vis. Commun. Image Rep., 58, 495–502, 2019.
31. 31. Li, M., Li, F., Pan, J., Zhang, D., Zhao, S., Li, J., Wang, F., The MindGomoku: An online P300 BCI game based on Bayesian deep learning. Sensors, 21, 5, 1613, 2021.
32. 32. Clark, C. and Storkey, A., Training deep convolutional neural networks to play go, in: International conference on machine learning, PMLR, pp. 1766– 1774, 2015.
33. 33. Shotwell, P., The game of go: Speculations on its origins and symbolism in ancient China. Changes, 2008, 1–62, 1994.
34. 34. Cattan, G., The use of brain–computer interfaces in games is not ready for the general public. Front. Comput. Sci., 3, 628773, 2021.
35. 35. Kuang, Z. and Tie, X., A survey of multimedia technologies and robust algorithms, 2021. arXiv preprint arXiv:2103.13477.
36. 36. Doty, R.L. and Kamath, V., The influences of age on olfaction: A review. Front. Physcol., 5, 20, 2014.
37. 37. Vilensky, J.A., Robertson, W., Suarez-Quian, C.A., The clinical anatomy of the cranial nerves: The nerves of “on old olympus towering top”, John Wiley & Sons, Wiley-Blackwell, 2015.
38. 38. Saladin, K.S. and Miller, L., Anatomy & physiology, WCB/McGraw-Hill, New York, 1998.
39. 39. Makowska, I., Kloszewska, I., Grabowska, A., Szatkowska, I., Rymarczyk, K., Olfactory deficits in normal aging and Alzheimer’s disease in the polish elderly population. Arch. Clin. Neuropsychol., 26, 3, 270–279, 2011.
40. 40. Whitcroft, K.L. and Hummel, T., Olfactory dysfunction in COVID-19: Diagnosis and management. JAMA, 323, 24, 2512–2514, 2020.
41. 41. Kletz, T.A., Learning from accidents: Routledge, 978-0-7506-4883-7, 2007.
42. 42. Gao, Z., Chen, S., Li, R., Lou, Z., Han, W., Jiang, K., Qu, F., Shen, G., An artificial olfactory system with sensing, memory and self-protection capabilities. Nano Energy, 86, 106078, 2021.
43. 43. Zhang, J., Tian, T., Wang, S., Liu, X., Shu, X., Wang, Y., Research on an olfactory neural system model and its applications based on deep learning. Neural Comput. Appl., 32, 10, 5713–5724, 2020.
44. 44. Gardner, J.W., Hines, E.L., Wilkinson, M., Application of artificial neural networks to an electronic olfactory system. Meas. Sci. Technol., 1, 5, 446, 1990.
45. 45. Meunier, D., Fonlupt, P., Saive, A.-L., Plailly, J., Ravel, N., Royet, J.-P., Modular structure of functional networks in olfactory memory. Neuroimage, 95, 264–275, 2014.
46. 46. Tzeng, W.-Y., Figarella, K., Garaschuk, O., Olfactory impairment in men and mice related to aging and amyloid-induced pathology. Pflügers Archiv-Eur. J. Physiol., 473, 5, 805–821, 2021.
47. 47. Sankaran, S., Khot, L.R., Panigrahi, S., Biology and applications of olfactory sensing system: A review. Sens. Actuators B: Chem., 171, 1–17, 2012.
48. 48. Lee, S., Shin, Y., Woo, S., Kim, K., Lee, H.-N., Review of wireless brain–computer interface systems. Brain-computer interface systems-recent progress and future prospects, 215–238, 2013.
49. 49. Jiang, L., Stocco, A., Losey, D.M., Abernethy, J.A., Prat, C.S., Rao, R.P.N., BrainNet: A multi-person brain-to-brain interface for direct collaboration between brains. Sci. Rep., 9, 1, 1–11, 2019.
50. 50. Grau, C., Ginhoux, R., Riera, A., Nguyen, T.L., Chauvat, H., Berg, M., Amengual, J.L., Pascual-Leone, A., Ruffini, G., Conscious brain-to-brain communication in humans using non-invasive technologies. PloS One, 9, 8, e105225, 2014.
51. 51. Hasson, U., Ghazanfar, A.A., Galantucci, B., Garrod, S., Keysers, C., Brain-to-brain coupling: A mechanism for creating and sharing a social world. Trends Cogn. Sci., 16, 2, 114–121, 2012.
52. 52. Hildt, E., Multi-person brain-to-brain interfaces: Ethical issues. Front. Neurosci., 13, 1177, 2019.
53. 53. Zhang, B., Zhuang, L., Qin, Z., Wei, X., Yuan, Q., Qin, C., Wang, P., A wearable system for olfactory electrophysiological recording and animal motion control. J. Neurosci. Method., 307, 221–229, 2018.
54. 54. Vidal, J.J., Toward direct brain–computer communication. Annu. Rev. Biophys. Bioeng., 2, 1, 157–180, 1973.
55. 55. Bowen, R.L. and Atwood, C.S., Living and dying for sex. Gerontology, 50, 5, 265–290, 2004.
56. 56. Rodríguez Valiente, A., Trinidad, A., García Berrocal, J.R., Górriz, C., Ramírez Camacho, R., Extended high-frequency (9–20 kHz) audiometry reference thresholds in 645 healthy subjects. Int. J. Audiol., 53, 8, 531–545, 2014.
57. 57. Walling, A. and Dickson, G., Hearing loss in older adults. Am. Family Phys., 85, 12, 1150–1156, 2012.
58. 58. Larson, E.B., Yaffe, K., Langa, K.M., New insights into the dementia epidemic. New Engl. J. Med., 369, 24, 2275, 2013.
59. 59. Belikov, A.V., Age-related diseases as vicious cycles. Ageing Res. Res., 49, 11–26, 2019.
60. 60. Saravanakumar Pichumani, T.V.P., Sundararajan, R.K.D., Nam, Y., Kadry, S., Ruzicka indexed regressive homomorphic ephemeral key Benaloh cryptography for secure data aggregation in WSN. J. Internet Technol., 22, 6, 1287– 1297, Nov. 2021.
61. 61. Guevvera, Y., World Health Organisation: Neonatal and perinatal mortality: Country, regional and global estimates. WHO Cebu: Sun, 9241563206, 2006.
62. 62. Worrall, L.E. and Hickson, L.M.H., Communication disability in aging: From prevention to intervention, 0-7693-0015-4, 2003.
63. 63. Tilwani, K., Jangid, P., Tilwani, R.K., Nagal, M., Comparative study of carotid-femoral pulse wave velocity and carotid intima-media thickness with age & gender in cerebrovascular accident (CVA) patients and healthy control individual. Int. J. Basic Appl. Physiol., 8, 1, 62, 2019.
64. 64. Ellekjær, H., Holmen, J., Indredavik, B., Terent, A., Epidemiology of stroke in: Innherred, Norway, 1994 to 1996: Incidence and 30-day case-fatality rate. Stroke, 28, 11, 2180–2184, 1997.
65. 65. Feldman, E.L., Cornblath, D.R., Porter, J., Dworkin, R., Scherer, S., National Institute of Neurological Disorders and Stroke (NINDS), in: Advances in understanding and treating neuropathy, 2008, 1–6, Bethesda, Maryland, 24–25 October 2006.
66. 66. Burns, A and Iliffe, S., Alzheimer’s disease. BMJ, 338, b158, 2009.
67. 67. Revi, M., Alzheimer’s disease therapeutic approaches, in: Genedis, 2018, pp. 105–116, Springer, Cham, 2020.
68. 68. Dhanaraj, R.K., Krishnasamy, L., Geman, O., Izdrui, D.R., Black hole and sink hole attack detection in wireless body area networks. Comput. Mater. Continua, 68, 2, 1949–1965, 2021.
69. 69. Querzfurth, H.W., Review article. Mechanism of disease Alzheimer’s disease. New Engl. J. Med., 362, 329–344, 2010.
70. 70. Todd, S., Barr, S., Roberts, M., Passmore, A.P., Survival in dementia and predictors of mortality: A review. Int. J. Geriatr. Psychiatry, 28, 11, 1109–1124, 2013.
71. 71. Pardey, J., Roberts, S., Tarassenko, L., A review of parametric modelling techniques for EEG analysis. Med. Eng. Phys., 181, 2–11, 1996.
72. 72. Ramoser, H., Muller-Gerking, J., Pfurtscheller, G., Optimal spatial filtering of single trial EEG during imagined hand movement. IEEE Trans. Rehabil. Eng., 8, 4, 441–446, 2000.
73. 73. MacDonald, A.A., Joyson, A., Lee, R., Seymour, D.G., Soiza, R.L., The effect of hearing augmentation on cognitive assessment scales at admission to hospital. Am. J. Geriatr. Psychiatry, 20, 4, 355–361, 2012.
74. 74. Popelka, M.M., Cruickshanks, K.J., Wiley, T.L., Tweed, T.S., Klein, B.E.K., Klein, R., Low prevalence of hearing aid use among older adults with hearing loss: The epidemiology of hearing loss study. J. Am.Geriatr. Soc., 46, 9, 1075–1078, 1998.
75. 75. Shah, D. and Badlani, G., Treatment of overactive bladder and incontinence in the elderly. Rev. Urol., 4, Suppl 4, S38, 2002.
76. 76. Sims, J., Browning, C., Lundgren-Lindquist, B., Kendig, H., Urinary incontinence in a community sample of older adults: Prevalence and impact on quality of life. Disabil. Rehabil., 33, 15–16, 1389–1398, 2011.
77. 77. Jaul, E. and Barron, J., Age-related diseases and clinical and public health implications for the 85 years old and over population. Public Health Front., 5, 335, 2017.
78. 78. Wei, Q., et al. Develop a low price wireless binaural hearing device using 2.4 GHz GFSK method., 3-06, 2012.
79. 79. Mills, M., Hearing aids and the history of electronics miniaturization. IEEE Ann. Hist. Comput., 33, 2, 24–45, 2011.
80. 80. Kopeć, W., Kowalski, J., Paluch, J., Jaskulska, A., Skorupska, K.H., Niewiński, M., Krzywicki, M., Biele, C., Older adults and brain–computer interface: An exploratory study, in: Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, pp. 1–5, 2021.
81. 81. Belo, J., Clerc, M., Schön, D., EEG-based auditory attention detection and its possible future applications for passive BCI. Front. Comput. Sci., 3, 661178, 2021.
82. 82. Fierens, G., Standaert, N., Peeters, R., Glorieux, C., Verhaert, N., Safety of active auditory implants in magnetic resonance imaging. J. Otol., 16, 3, 185– 198, 2021.
83. 83. Rutkowski, T.M. and Mori, H., Tactile and bone-conduction auditory brain computer interface for vision and hearing impaired users. J. Neurosci. Methods, 244, 45–51, 2015.
84. 84. Krishnasamy, L., Ramasamy, T., Dhanaraj, R., CHinnasamy, P., A geodesic deployment and radial shaped clustering (RSC) algorithm with statistical aggregation in sensor networks. Turk. J. Elec. Eng. Comput. Sci., 29, 3, 1464– 1478, 2021.
85. 85. da Silva Souto, C., Lüddemann, H., Lipski, S., Dietz, M., Kollmeier, B., Influence of attention on speech-rhythm evoked potentials: First steps towards an auditory brain–computer interface driven by speech. Biomed. Phys. Eng. Express, 2, 6, 065009, 2016.
86. 86. Bonci, A., Fiori, S., Higashi, H., Tanaka, T., Verdini, F., An introductory tutorial on brain–computer interfaces and their applications. Electronics, 10, 5, 560, 2021.
87. 87. Abaker, A.A. and Fakhreldeen, A.S., A comparative analysis of machine learning algorithms to build a predictive model for detecting diabetes complications. Informatica, 45, 1, 2021.
88. 88. Bharadwaj, H.K., Agarwal, A., Chamola, V., Lakkaniga, N.R., Hassija, V., Guizani, M., Sikdar, B., A review on the role of machine learning in enabling IoT based healthcare applications. IEEE Access, 9, 38859–38890, 2021.
89. 89. Swapna, G., Vinayakumar, R., Soman, K.P., Diabetes detection using deep learning algorithms. ICT Express, 4, 4, 243–246, 2018.
90. 90. Mordarska, K. and Godziejewska-Zawada, M., Diabetes in the elderly. Prz. Menopauzalny= Menopause Rev., 16, 2, 38, 2017.
91. 91. Kilvert, A. and Fox, C., Diagnosis and management of diabetes in older people. Pract. Diabetes, 34, 6, 195–199, 2017.
92. 92. Si Ching, L., II, Managing the elderly with urinary incontinence and dementia. Int. Arch. Urol. Complic., 3, 027, 2017.
93. 93. Dhanaraj, R.K. et al., Random forest bagging and x-means clustered antipattern detection from SQL query log for accessing secure mobile data. Wirel. Commun. Mobil. Comput., 2021, Article ID 2730246, 9 pages, 2021.
94. 94. Dantas, L.O., Carvalho, C., de Jesus Santos, B.L., Ferreira, C.H.J., Bo, K., Driusso, P., Mobile health technologies for the management of urinary incontinence: A systematic review of online stores in Brazil. Braz. J. Phys. Ther., 25, 4, 387–395, 2021.
95. 95. Nagib, L., Bellotto, A., Riccetto, C., Martinho, N.M., Camargos Pennisi, P.R., Blumenberg, C., Paranhos, L.R., Botelho, S., Use of mobile apps for controlling of the urinary incontinence: A systematic review. Neurourol. Urodyn., 39, 4, 1036–1048, 2020.
96. 96. Nitti, V.W., The prevalence of urinary incontinence. Rev. Urol., 3, Suppl 1, S2, 2001.
97. 97. Ramasamy, M.D., Periasamy, K., Krishnasamy, L., Dhanaraj, R.K., Kadry, S., Nam, Y., Multi-disease classification model using Strassen’s half of threshold (SHoT) training algorithm in healthcare sector. IEEE Access, 9, 112624– 112636, 2021.
98. 98. Rortveit, G., Hannestad, Y.S., Daltveit, A.K., Hunskaar, S., Age- and type-dependent effects of parity on urinary incontinence: The Norwegian EPINCONT study. Obstet. Gynecol., 98, 6, 1004–10, 2001 Dec.
99. 99. Lukacz, E.S., Lawrence, J.M., Contreras, R., Nager, C.W., Luber, K.M., Parity, mode of delivery, and pelvic floor disorders. Obstet. Gynecol., 107, 6, 1253– 60, 2006 Jun.
100. 100. Crepin, G., Biserte, J., Cosson, M., Duchene, F., Appareil génital féminin et sport de haut niveau, in: [The female urogenital system and high level sports], vol. 190, pp. 1479–91, discussion 1491–3, October 2006.
101. 101. Dumoulin, C., Cacciari, L.P., Hay-Smith, E.J.C., Pelvic floor muscle training versus no treatment, or inactive control treatments, for urinary incontinence in women. Cochrane Database Syst. Rev., 10, CD005654, 2018-10-04.
102. 102. Ramakrishnan, V., Chenniappan, P., Dhanaraj, R.K., Hsu, C.H., Xiao, Y., Al-Turjman, F., Bootstrap aggregative mean shift clustering for big data anti-pattern detection analytics in 5G/6G communication networks. Comput. Electr. Eng., 95, 107380, 2021.
103. 103. Wang, M., Zhang, C., Lin, S., Wang, Y., Seicol, B.J., Ariss, R.W., Xie, R., Biased auditory nerve central synaptopathy is associated with age-related hearing loss. J. Physiol., 599, 6, 1833–1854, 2021.