This paper makes four scientific contributions to the field of fall detection in the elderly to contribute to their assisted living in the future of Internet of Things (IoT)-based pervasive living environments, such as smart homes. First, it presents and discusses a comprehensive comparative study, where 19 different machine learning methods were used to develop fall detection systems, to deduce the optimal machine learning method for the development of such systems. This study was conducted on two different datasets, and the results show that out of all the machine learning methods, the k-NN classifier is best suited for the development of fall detection systems in terms of performance accuracy. Second, it presents a framework that overcomes the limitations of binary classifier-based fall detection systems by being able to detect falls and fall-like motions. Third, to increase the trust and reliance on fall detection systems, it introduces a novel methodology based on the usage of k-folds cross-validation and the AdaBoost algorithm that improves the performance accuracy of the k-NN classifier-based fall detection system to the extent that it outperforms all similar works in this field. This approach achieved performance accuracies of 99.87% and 99.66%, respectively, when evaluated on the two datasets. Finally, the proposed approach is also highly accurate in detecting the activity of standing up from a lying position to infer whether a fall was followed by a long lie, which can cause minor to major health-related concerns. The above contributions address multiple research challenges in the field of fall detection, that we identified after conducting a comprehensive review of related works, which is also presented in this paper.

A Study of Fall Detection in Assisted Living: Identifying and Improving the Optimal Machine Learning Method

Artificial intelligence and internet of things in screening and management of autism spectrum disorder

With the rapid growth of the Internet of Healthcare Things, a massive amount of data is generated by a broad variety of medical devices. Because of the complex relationship in large-scale healthcare data, researchers who bring a revolution in the healthcare industry embrace Artificial Intelligence (AI). In certain cases, it has been reported that AI can do better than humans at performing healthcare tasks. The data-driven black-box model, on the other hand, does not appeal to healthcare professionals as it is not transparent, and any biasing can hamper the performance the prediction model for the real-life operation. In this paper, we proposed an AI model for early detection of autism in children. Then we showed why AI with explainability is important. This paper provides examples focused on the Autism Spectrum Disorder dataset (Autism screening data for toddlers by Dr Fadi Fayez Thabtah) and discussed why explainability approaches should be used when using AI systems in healthcare.

An XAI Based Autism Detection: The Context Behind the Detection

The Internet of Things (IoT) has emerged as a technology capable of connecting heterogeneous nodes/objects, such as people, devices, infrastructure, and makes our daily lives simpler, safer, and fruitful. Being part of a large network of heterogeneous devices, these nodes are typically resource-constrained and became the weakest link to the cyber attacker. Classical encryption techniques have been employed to ensure the data security of the IoT network. However, high-level encryption techniques cannot be employed in IoT devices due to the limitation of resources. In addition, node security is still a challenge for network engineers. Thus, we need to explore a complete solution for IoT networks that can ensure nodes and data security. The rule-based approaches and shallow and deep machine learning algorithms– branches of Artificial Intelligence (AI)– can be employed as countermeasures along with the existing network security protocols. This paper presented a comprehensive layer-wise survey on IoT security threats, and the AI-based security models to impede security threats. Finally, open challenges and future research directions are addressed for the safeguard of the IoT network.

/pdf/security-threats-and-artificial-intelligence-based-2qjruosllv.pdf

Security Threats and Artificial Intelligence Based Countermeasures for Internet of Things Networks: A Comprehensive Survey

An earthquake is a tremor felt on the surface of the earth created by the movement of the major pieces of its outer shell. Till now, many attempts have been made to forecast earthquakes, which saw some success, but these attempted models are specific to a region. In this paper, an earthquake occurrence and location prediction model is proposed. After reviewing the literature, long short-term memory (LSTM) is found to be a good option for building the model because of its memory-keeping ability. Using the Keras tuner, the best model was selected from candidate models, which are composed of combinations of various LSTM architectures and dense layers. This selected model used seismic indicators from the earthquake catalog of Bangladesh as features to predict earthquakes of the following month. Attention mechanism was added to the LSTM architecture to improve the model’s earthquake occurrence prediction accuracy, which was 74.67%. Additionally, a regression model was built using LSTM and dense layers to predict the earthquake epicenter as a distance from a predefined location, which provided a root mean square error of 1.25.

/pdf/attention-based-bi-directional-long-short-term-memory-5cfvgki52g.pdf

Attention-Based Bi-Directional Long-Short Term Memory Network for Earthquake Prediction

Fall causes trauma or critical injury among the geriatric population which is a second leading accidental cause of post-injury mortality around the world. It is crucial to keep elderly people under supervision by ensuring proper privacy and comfort. Thus the elderly fall detection and prediction using wearable/ non-wearable sensors become an active field of research. In this work, a novel pipeline for fall detection based on wearable accelerometer data has been proposed. Three publicly available datasets have been used to validate our proposed method, and more than 7700 cross-disciplinary time-series features were investigated for each of the datasets. After following a series of feature reduction techniques such as mutual information, removing highly correlated features using the Pearson correlation coefficient, Boruta algorithm, we have obtained the dominant features for each dataset. Different classical machine learning (ML) algorithms were utilized to detect falls based on the obtained features. For individual datasets, the simple ML classifiers achieved very good accuracy. We trained our pipeline with two of the three datasets and tested with the remaining one dataset until all three datasets were used as the test set to show the generalization capability of our proposed pipeline. A set of 39 high-performing features is selected, and the classifiers were trained with them. For all the cases, the proposed pipeline showed excellent efficiency in detecting falls. This architecture performed better than most of the existing works in all the used publicly available datasets, proving the supremacy of the proposed data analysis pipeline.

/pdf/towards-an-accelerometer-based-elderly-fall-detection-system-44ozramrzz.pdf

Towards an Accelerometer-Based Elderly Fall Detection System Using Cross-Disciplinary Time Series Features

In this digital age, social media is an essential part of life. People share their moments and emotions through it. Consequently, detecting emotions in their behavior can be an effective way to determine their emotional disposition, which can then be used to control their negative thinking by making them see the positive aspects of the world. This study proposes an emotion detection-based mood control framework that reorganizes social media posts to match the user’s mental state. An emotion detection model based on Attention mechanism, Bidirectional Long Short Term Memory (LSTM), and Convolutional Neural Network (CNN) has been proposed which can detect six emotions from Bangla text with 66.98% accuracy. It also demonstrates how emotion detection frameworks can be implemented in other languages as well.

An Attention-Based Mood Controlling Framework for Social Media Users

Fall can be life-taking for elderly people. Early recognition of fall events can reduce the impact among this people. Fall detection has become an active research area now a days. Many researches have been carried out using a lot of sensors and deep learning algorithms that are costly and computationally expensive. In this work, a fall detection system with a simple accelerometer and interdisciplinary time domain features were introduced. Three publicly available datasets were used and five machine learning classifiers were finally introduced to classify fall events. Dimensionality reduction using principal component analysis was also studied in this work. Finally, machine learning classifiers were optimized using social group optimization to find out best performing hyperparameters. The proposed architecture showed great robustness and efficiency as it achieved almost perfect accuracy, sensitivity and specificity in all three datasets.

Md. Jaber Al Nahian

Papers

Towards an Accelerometer-Based Elderly Fall Detection System Using Cross-Disciplinary Time Series Features

Attention-Based Bi-Directional Long-Short Term Memory Network for Earthquake Prediction

An Attention-Based Mood Controlling Framework for Social Media Users

Social Group Optimized Machine-Learning Based Elderly Fall detection Approach Using Interdisciplinary Time-Series Features