Disorders of the nervous system and mental health are among the most prevalent, complex, and devastating health challenges globally, with a significant impact on quality of life. Recently, advances in deep learning-based multimodal methodologies have transformed the classification and detection of these disorders through the utilization of diverse data types including neuroimaging, bio-signals, and clinical evaluations. These multimodal techniques provide a more holistic understanding of complex conditions, addressing the limitations of traditional unimodal methods, which often fail to capture the multifaceted nature of these disorders. Despite the growing body of research, a comprehensive review focusing on the application of deep learning-based multimodal approaches to both neurological and mental health disorders remains lacking. This review fills this gap by offering an in-depth analysis of recent advancements in machine learning and deep learning-based multimodal classification for ten major disorders: five neurological and five mental health-related. It examined key modalities, explored fusion strategies, and provided insights into the strengths and weaknesses of existing multimodal approaches. Additionally, this review highlighted the challenges associated with multimodal data integration, such as data imbalance, model interpretability, and the need for large-scale, high-quality datasets. Furthermore, the review discussed emerging trends and future directions, emphasizing the potential of advanced fusion and computational techniques to enhance the clinical applicability of these models. By synthesizing the current state of research, this review aims to guide future studies and contribute to the development of more accurate, reliable, and accessible diagnostic tools for neurological and mental health disorders.

This paper proposes an efficient approach for person-independent facial expression recognition based on the fusion of Histogram of Oriented Gradients (HOG) descriptor and Cuttlefish Algorithm (CFA). The proposed approach employs HOG descriptor due to its outstanding performance in pattern recognition, which results in features that are robust against small local pose and illumination variations. However, it produces some irrelevant and noisy features that slow down and degrade the classification performance. To address this problem, a wrapper-based feature selector, called CFA, is used. This is because CFA is a recent bio-inspired feature selection algorithm, which has been shown to effectively select an optimal subset of features while achieving a high accuracy rate. Here, support vector machine classifier is used to evaluate the quality of the features selected by the CFA. Experimental results validated the effectiveness of the proposed approach in attaining a high recognition accuracy rate on three widely adopted datasets: CK+ (97.86%), RaFD (95.15%), and JAFFE (90.95%). Moreover, the results also indicated that the proposed approach yields competitive or even superior results compared to state-of-the-art approaches.

The rapid advancement in the Internet of things applications generates a considerable amount of data and requires additional computing power. These are serious challenges that directly impact the performance, latency, and network breakdown of cloud computing. Fog Computing can be depended on as an excellent solution to overcome some related problems in cloud computing. Fog computing supports cloud computing to become nearer to the Internet of Things. The fog's main task is to access the data generated by the IoT devices near the edge. The data storage and data processing are performed locally at the fog nodes instead of achieving that at cloud servers. Fog computing presents high-quality services and fast response time. Therefore, Fog computing can be the best solution for the Internet of things to present a practical and secure service for various clients. Fog computing enables sufficient management for the services and resources by keeping the devices closer to the network edge. In this paper, we review various computing paradigms, features of fog computing, an in-depth reference architecture of fog with its various levels, a detailed analysis of fog with different applications, various fog system algorithms, and also systematically examines the challenges in Fog Computing which act as a middle layer between IoT sensors or devices and data centers of the cloud.

Facial expression recognition as a recently developed method in computer vision is founded upon the idea of analyzing the facial changes in which are witnessed due to emotional impacts on an individual. This paper provides a performance evaluation of a set of supervised classifiers used for facial expression recognition based on minimum features selected by chi-square. These features are the most iconic and influential ones that have tangible value for result determination. The highest-ranked six features are applied on six classifiers including multi-layer perceptron, support vector machine, decision tree, random forest, radial based function, and K-Nearest neighbor to figure out the most accurate one when the minimum number of features are utilized. This is done via analyzing and appraising the classifiers’ performance. CK+ is used as the research’s dataset. random forest with a total accuracy ratio of 94.23% is illustrated as the most accurate classifier amongst the rest.

Facial expression recognition (FER) has achieved an extreme role in research area since the 1990s. This paper provides a comparative approach for FER based on three feature selection methods which are correlation, gain ration, and information gain for determining the most distinguished features of face images using multi-classification algorithms which are multilayer perceptron, Naïve Bayes, decision tree, and K-nearest neighbour (KNN). These classifiers are used for the mission of expression recognition and for comparing their proportional performance. The main aim of the provided approach is to determine the most effective classifier based on the minimum acceptable number of features by analyzing and comparing their performance. The provided approach has been applied on CK+ dataset. The experimental results show that KNN is proven to be better classifier with 91% accuracy using only 30 features.

Internet of Things (IoT) and Cloud computing are extremely distinct technologies which are by now playing an important role in our life. It is expected that adopting and using them would be more and more common, that makes them significant components for the Future Internet (FI). The upcoming internet-associated revolution is almost there with the existence of the IoT. IoT empowers connection and communications among tons of devices between themselves to exchange information, knowledge, and data that promotes the quality of our daily lives. Alternatively, appropriate, upon-request, and adaptable network access is provided by Cloud Computing, as a result, makes it possible to contribute computing resources which helps dynamic data be integrated from a variety of data sources. However, Cloud Computing and IoT in FI cannot be implemented without an abundance of issues and problems. In this research paper, we will be endeavoring to outline and put light on the prime and main concepts of the Cloud Computing and IoT.

The importance of process monitoring applications continues to grow. Generally, many of the developments in process monitoring are being driven by access to more and more data. Process monitoring is important to understand the variation in a process and to assess its current state. Process monitoring and controlling an organization is of high importance for all process management initiatives. The parallel execution of numerous threads can perform significant increases in performance and overall efficiency in the computer systems. In many computer systems, numerous performance counters are available. For example, performance counters may provide a count of the number of threads executing at a given time. This paper presented an overview of the main research works in the field of the process and thread controlling and monitoring related to physical memory to measure the performance of the operating system. The main finding is that developing strategies needed to make it easy to deal with the monitoring of a large number of data. Furthermore, the used strategies produced improvements of up to 25% and achieved very good results. Besides, the performance of applications with process control executed much faster than without.