Parkinson’s disease (PD) is a slow-progressing condition with symptoms such as tremors in the hands, arms, legs, and face that get worse gradually. PD patients might have difficulties in movement and completing daily activities as the condition progresses. Despite the fact that there really is no fixed remedy for Parkinson’s disease, the symptoms of the disease can be alleviated with the use of some medications. The patient can live a normal life by reducing the symptoms that the condition causes. At this point, it’s critical to avoid early disease identification and development. In this study, time-frequency based feature extraction strategy such as signal energy, signal variance, signal frequency, empirical mode decomposition (EMD) along with population-based incremental learning (PBIL) Optimization algorithm and convolutional neural network and bidirectional long short-term memory (CNN-BiLSTM) has been used as a classifier to detect walking disorder in Parkinson’s disease patients. The suggested model has given 89.4% and 93.5% precision over freezing of gait (FOG) dataset and Juutinen’s dataset respectively. It is concluded that the suggested model’s classification results has been outperformed the classification results obtained using the data’s original features. The proposed system can be used to further refining the analytic system for longer measures in free-living environments that can be helpful in daily life activities especially in medical field..

Movement Disorders Detection in Parkinson’s Patients using Hybrid Classifier

This paper describes an RGBD (Red Green Blue Depth) image daily life activity identification system that can monitor and detect human activities without the need of optical markers or motion sensors. In this paper, we have developed a practical methodology for detecting human activity in the daily environment. For feature extraction technique, we suggested a noble method for recognition of ADL activities based on symmetry principle. By extracting silhouette from depth images and performing mapping operations over RGB images, we have been able to extract the skeleton information of the human body in RGBD images and identify ADL activities using four critical parameters: angle formation between hand and upper half of the body, angle between center body point and hand, angle formation between hand and lower half of the body, and angle between two hands of the single silhouette. We employed the linearly dependent concept (LDC) and long short-term memory-recurrent neural networks (LSTM-RNN) for feature selection and classification, compared the results to existing approaches. The objective of our research is to not only find an effective and useful collection of features from the silhouette, but also to outperform current approaches. Finally, the suggested method’s testing results showed a 2.5 percent increase in accuracy with a 92.83 percent success rate, as well as a reduction in relative error to 2.47 percent of the original dataset. 

Fundamental Recognition of ADL Assessments Using Machine Learning Engineering

Parkinson’s disease (PD) is a slow-progressing condition with symptoms such as tremors in the hands, arms, legs, and face that get worse gradually. PD patients might have difficulties in movement and completing daily activities as the condition progresses. Despite the fact that there really is no fixed remedy for Parkinson’s disease, the symptoms of the disease can be alleviated with the use of some medications. The patient can live a normal life by reducing the symptoms that the condition causes. At this point, it’s critical to avoid early disease identification and development. In this study, time-frequency based feature extraction strategy such as signal energy, signal variance, signal frequency, empirical mode decomposition (EMD) along with population-based incremental learning (PBIL) Optimization algorithm and convolutional neural network and bidirectional long short-term memory (CNN-BiLSTM) has been used as a classifier to detect walking disorder in Parkinson’s disease patients. The suggested model has given 89.4% and 93.5% precision over freezing of gait (FOG) dataset and Juutinen’s dataset respectively. It is concluded that the suggested model’s classification results has been outperformed the classification results obtained using the data’s original features. The proposed system can be used to further refining the analytic system for longer measures in free-living environments that can be helpful in daily life activities especially in medical field.. 

Human Activity tracking is the process of detection and understanding of the human activity. It can be done by analyzing human motion behavior data extracted from different smartphone-embedded sensors. Recognizing human activity has become widely popular and particularly attracted many researchers in different industries. Activity recognition has become increasingly important in many areas, especially for the recognition of fitness, sports, and health monitoring. This paper propose a robust model that is trained and tested on remotely extracted data from the smartphone-embedded inertial sensor. Initially, the system clean the input data and then performs windowing and segmentation. After pre-processing, a number of features are extracted. Further, the Lukasiewicz similarity measure (LS) based features selection is used to reduce the features set by removing the least important features. In the next step, the Yeo-Johnson power transformation method is utilized to optimize the selected features. The optimized features set is then forwarded to the multi-class support vector machines (SVM) classifier. The system was designed and experimented with over a well-known dataset named WISDM. The presented model performed well by achieving a mean accuracy rate of 94%.

Human Activity Recognition via Smartphone Embedded Sensor using Multi-Class SVM

Cognitive function declines with age, and when cognitive deterioration reaches a critical value and pathological changes occur, the brain neurons are irreversible. The aging of working memory even has profound adverse effects on older adults. This study aims to understand the psychological and physiological characteristics of older adults and to achieve mobile application design solutions that train working memory. According to the user study, the factors influencing the design of mobile applications for working memory training for older adults were mainly focused on six dimensions: training content, motivation, emotion, interaction, current state, and experience. Design opportunities were transformed, and seven new design strategies were obtained. Nine product functions with the highest priority were selected: daily practice, challenge mode, level-by-level difficulty selection, novice teaching, practice mode, sharing function, two-player mode, ranking, and desktop components. Finally, an interactive prototype was designed for usability testing, and the product solution was iterated based on expert evaluation and user feedback. The results indicate that the interface design provides a good user experience when applied daily. The process and results will be applied to make more solutions for training cognitive functions to be used in different situations.

/pdf/designing-a-mobile-application-for-working-memory-training-3ai9jwoo.pdf

Designing a Mobile Application for Working Memory Training through Understanding the Psychological and Physiological Characteristics of Older Adults

Virtual reality is an emerging field in the whole world. The problem faced by people today is that they are more indulged in indoor technology rather than outdoor activities. Hence, the proposed system introduces a fitness solution connecting virtual reality with a gaming interface so that an individual can play first-person games. The system proposed in this paper is an efficient and cost-effective solution that can entertain people along with playing outdoor games such as badminton and cricket while sitting in the room. To track the human movement, sensors Micro Processor Unit (MPU6050) are used that are connected with Bluetooth modules and Arduino responsible for sending the sensor data to the game. Further, the sensor data is sent to a machine learning model, which detects the game played by the user. The detected game will be operated on human gestures. A publicly available dataset named IM-Sporting Behaviors is initially used, which utilizes triaxial accelerometers attached to the subject’s wrist, knee, and below neck regions to capture important aspects of human motion. The main objective is that the person is enjoying while playing the game and simultaneously is engaged in some kind of sporting activity. The proposed system uses artificial neural networks classifier giving an accuracy of 88.9%. The proposed system should apply to many systems such as construction, education, offices and the educational sector. Extensive experimentation proved the validity of the proposed system. 

Body Worn Sensors for Health Gaming and e-Learning in Virtual Reality

Now-a-days, children are more indulged in indoor activities instead of outdoor games. This plays a very negative role on their minds along with physical laziness and obesity. The proposed system that solves this issue uses virtual reality gaming interface and activity recognition system for the users to play outdoor games in their rooms. People can wear the headsets along with wearables and can enjoy 3D games while exercising. The system uses sensors (MPU6050) connected with nRF24L01 modules and Arduino responsible for sending the sensor data to the game. Moreover, the data by sensor is processed using a machine learning model, which predicts the game played by the user. The proposed system aims at recognizing six basic games in the IMSporting behaviors dataset, which utilizes triaxial accelerometers connected to the subject’s knee, wrist, and below neck areas to capture human activities i.e., badminton, basketball, table tennis, skipping, cycling and football. WISDM dataset is used to recognize activities such as jogging and walking. The system has achieved an accuracy of 92% by using median filter as a pre-processing technique, Fourier transform features extraction and artificial neural networks classifier. The system can be applied to many fields like education, offices, construction and sports. Extensive experimentation proved the validity of the proposed system.

Mir Mushhood Afsar

Papers

Body Worn Sensors for Health Gaming and e-Learning in Virtual Reality

Virtual Reality Game Based Interaction with Exergaming using Wearable Sensors