The remarkable advancements in biotechnology and public healthcare infrastructures have led to a momentous production of critical and sensitive healthcare data. By applying intelligent data analysis techniques, many interesting patterns are identified for the early and onset detection and prevention of several fatal diseases. Diabetes mellitus is an extremely life-threatening disease because it contributes to other lethal diseases, i.e., heart, kidney, and nerve damage. In this paper, a machine learning based approach has been proposed for the classification, early-stage identification, and prediction of diabetes. Furthermore, it also presents an IoT-based hypothetical diabetes monitoring system for a healthy and affected person to monitor his blood glucose (BG) level. For diabetes classification, three different classifiers have been employed, i.e., random forest (RF), multilayer perceptron (MLP), and logistic regression (LR). For predictive analysis, we have employed long short-term memory (LSTM), moving averages (MA), and linear regression (LR). For experimental evaluation, a benchmark PIMA Indian Diabetes dataset is used. During the analysis, it is observed that MLP outperforms other classifiers with 86.08% of accuracy and LSTM improves the significant prediction with 87.26% accuracy of diabetes. Moreover, a comparative analysis of the proposed approach is also performed with existing state-of-the-art techniques, demonstrating the adaptability of the proposed approach in many public healthcare applications.

The primary objective of this study is to accumulate, summarize, and evaluate the state-ofthe- art for spatio-temporal crime hotspot detection and prediction techniques by conducting a systematic literature review (SLR). The authors were unable to find a comprehensive study on crime hotspot detection and prediction while conducting this SLR. Therefore, to the best of author’s knowledge, this study is the premier attempt to critically analyze the existing literature along with presenting potential challenges faced by current crime hotspot detection and prediction systems. The SLR is conducted by thoroughly consulting top five scientific databases (such as IEEE, Science Direct, Springer, Scopus, and ACM), and synthesized 49 different studies on crime hotspot detection and prediction after critical review. This study unfolds the following major aspects: 1) the impact of data mining and machine learning approaches, especially clustering techniques in crime hotspot detection; 2) the utility of time series analysis techniques and deep learning techniques in crime trend prediction; 3) the inclusion of spatial and temporal information in crime datasets making the crime prediction systems more accurate and reliable; 4) the potential challenges faced by the state-of-the-art techniques and the future research directions. Moreover, the SLR aims to provide a core foundation for the research on spatio-temporal crime prediction applications while highlighting several challenges related to the accuracy of crime hotspot detection and prediction applications.

Smart city infrastructure has a significant impact on improving the quality of humans life. However, a substantial increase in the urban population from the last few years poses challenges related to resource management, safety, and security. To ensure the safety and security in the smart city environment, this paper presents a novel approach by empowering the authorities to better visualize the threats, by identifying and predicting the highly-reported crime zones in the smart city. To this end, it first investigates the Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) to detect the hot-spots that have a higher risk of crime occurrence. Second, for crime prediction, Seasonal Auto-Regressive Integrated Moving Average (SARIMA) is exploited in each dense crime region to predict the number of crime incidents in the future with spatial and temporal information. The proposed HDBSCAN and SARIMA based crime prediction model is evaluated on ten years of crime data (2008-2017) for New York City (NYC). The accuracy of the model is measured by considering different time scenarios such as the year-wise, (i.e., for each year), and for the total considered duration of ten years using an 80:20 ratio. The 80% of data was used for training and 20% for testing. The proposed approach outperforms with an average Mean Absolute Error (MAE) of 11.47 as compared to the highest scoring DBSCAN based method with MAE 27.03.

From the past few decades, Human activity recognition (HAR) is one of the vital research areas in computer vision in which much research is ongoing. The researcher's focus is shifting towards this area due to its vast range of real-life applications to assist in daily living. Therefore, it is necessary to validate its performance on standard benchmark datasets and state-of-the-art systems before applying it in real-life applications. The primary objective of this Systematic Literature Review (SLR) is to collect existing research on video-based human activity recognition, summarize, and analyze the state-of-the-art deep learning architectures regarding various methodologies, challenges, and issues. The top five scientific databases (such as ACM, IEEE, ScienceDirect, SpringerLink, and Taylor & Francis) are accessed to accompany this systematic study by summarizing 70 different research articles on human activity recognition after critical review. Human activity recognition in videos is a challenging problem due to its diverse and complex nature. For accurate video classification, extraction of both spatial and temporal features from video sequences is essential. Therefore, this SLR focuses on reviewing the recent advancements in stratified self-deriving feature-based deep learning architectures. Furthermore, it explores various deep learning techniques available for HAR, challenges researchers to face to build a robust model, and state-of-the-art datasets used for evaluation. This SLR intends to provide a baseline for video-based human activity recognition research while emphasizing several challenges regarding human activity recognition accuracy in video sequences using deep neural architectures.

Pedestrians are often encountered walking in the company of some social relations, rather than alone. The social groups thus formed, in variable proportions depending on the context, are not randomly organised but exhibit distinct features, such as the well-known tendency of 3-member groups to be arranged in a V-shape. The existence of group structures might thus impact the collective dynamics of the crowd, possibly in a critical way when emergency situations are considered. After turning a blind eye to these group aspects for years, endeavours to model groups in crowd simulation software have thrived in the past decades. This fairly short review opens on a description of their empirical characteristics and their (more controversial) impact on the global flow. Then, it aims to offer a pedagogical discussion of the main strategies to model such groups, within different types of models, in order to provide guidance for prospective modellers.

Over the past few years, mobile robots are widely used in various industries because they can navigate in dynamic environments and carry out everyday tasks efficiently. Path planning undoubtedly plays an important role in mobile robot navigation, thus becoming one of the most researched topics in the field of robotics. The metaheuristic algorithms have been extensively studied in recent years to solve the path planning problems the same way as the optimization problems were solved, or in other words, plan the optimum path for the robot to navigate from the starting point to the destination. In this research, a mobile robot is launched to find its path from the starting point to the destination in three different simulated environments using a proposed hybrid metaheuristic algorithm between Particle Swarm Optimization and Fringe Search Algorithm, named PSOFS, and its simultaneous localization and mapping (SLAM) capability. During runtime, the path is optimized by considering the path length. The performance of PSOFS for local path planning is compared against two existing algorithms by evaluating the path smoothness as well as robot safety. The results showed that PSOFS has successfully generated shorter, smoother, and safer paths than the algorithms for mobile robot navigation in unknown indoor environments.