The suspension of institutions around the world in early 2020 due to the COVID-19 virus did not stop the learning process. E-learning concepts and digital technologies enable students to learn from a safe distance while continuing their educational pursuits. Currently, the Internet of Things (IoT) is one of the most rapidly increasing technologies in today’s digital world; and e-learning is one of the most powerful learning methods available. In today’s world, smart devices and new technologies assist teachers in concentrating on new models of student learning while avoiding time wastage. By examining the characteristics of the Internet of Things and the challenges that exist in the field of e-learning, the potential functions, benefits, and advancements of utilizing the Internet of Things in online education are identified and discussed. This article examines the existing and future condition of the Internet of Things world as it pertains to the topic of education and sophisticated capabilities available through the Internet of Things that enable the application of e-learning after an architecture has been designed. Students’ pulse rates, brain waves, and skin resistance are measured in real time by a collection of IoT sensors, including cameras, microphones, and wearable gadgets. By utilizing the proposed architecture, universities can change their distance learning tactics to maximize resources and boost efficiency without changing their overall academic activities. According to the study’s findings, e-learning has a favorable and statistically significant impact on students’ flexibility, learning experience, educational productivity, and overall quality of education.

Skin cancer has a significant impact on the lives of many individuals annually and is recognized as the most prevalent type of cancer. In the United States, an estimated annual incidence of approximately 3.5 million people receiving a diagnosis of skin cancer underscores its widespread prevalence. Furthermore, the prognosis for individuals afflicted with advancing stages of skin cancer experiences a substantial decline in survival rates. This paper is dedicated to aiding healthcare experts in distinguishing between benign and malignant skin cancer cases by employing a range of machine learning and deep learning techniques and different feature extractors and feature selectors to enhance the evaluation metrics. In this paper, different transfer learning models are employed as feature extractors, and to enhance the evaluation metrics, a feature selection layer is designed, which includes diverse techniques such as Univariate, Mutual Information, ANOVA, PCA, XGB, Lasso, Random Forest, and Variance. Among transfer models, DenseNet-201 was selected as the primary feature extractor to identify features from data. Subsequently, the Lasso method was applied for feature selection, utilizing diverse machine learning approaches such as MLP, XGB, RF, and NB. To optimize accuracy and precision, ensemble methods were employed to identify and enhance the best-performing models. The study provides accuracy and sensitivity rates of 87.72% and 92.15%, respectively.

By increasing the complexity of the Internet of Things (IoT) applications, fault prediction become an important challenge in interactions between human, and smart devices. Fault prediction is one of the key factors to achieve better arranging the IoT applications. Most of the current research studies evaluated the fault prediction methods using simulation environments. However, formal verification of the correctness of a fault prediction method has not been reported yet. This paper presents a behavioral modeling and formal verification of a hybrid machine learning-based fault prediction model with Multi-Layer Perceptron (MLP) and Particle Swarm Optimization (PSO) algorithms. In particular, the PSO is used for feature selection. Then, the fault prediction is considered as a behavior to be verified formally. The fault prediction behavior is divided into two types of behaviors: dimension reduction behavior and prediction behavior. For each of the behaviors, one formal model is designed. The behavioral models designed are mapped into the Labeled Transition System (LTS). The Process Analysis Toolkit (PAT) model checker is employed to evaluate the behavioral models. The accuracy of the fault prediction method is done by some existing specifications such as deadlock-free and reachability properties in terms of linear temporal logic formulas. Also, the verification of the fault prediction behaviors is used to detect the defect metrics of information-centric IoT applications. Experimental results showed that our proposed verification method has minimum verification time and memory usage for evaluating critical specification rules than other research studies.

The rapid development of technology has made the Internet of Things an integral element of modern society. Modern Internet of Things’ implementations often use Fog computing, an offshoot of the Cloud computing that offers localized processing power at the network’s periphery. The Internet of Things serves as the inspiration for the decentralized solution known as Fog computing. Features such as distributed computing, low latency, location awareness, on-premise installation, and support for heterogeneous hardware are all facilitated by Fog computing. End-to-end security in the Internet of Things is challenging due to the wide variety of use cases and the disparate resource availability of participating entities. Due to their limited resources, it is out of the question to use complex cryptographic algorithms for this class of devices. All Internet of Things devices, even those connected to servers online, have constrained resources such as power and processing speed, so they would rather not deal with strict security measures. This paper initially examines distributed Fog computing and creates a new authentication framework to support the Internet of Things environment. The following authentication architecture is recommended for various Internet of Things applications, such as healthcare systems, transportation systems, smart buildings, smart energy, etc. The total effectiveness of the method is measured by considering factors such as the cost of communication and the storage overhead incurred by the offered integrated authentication protocol. It has been proven that the proposed technique will reduce communication costs by at least 11%.

This paper seeks to enhance the performance of Mel Frequency Cepstral Coefficients (MFCCs) for detecting abnormal heart sounds. Heart sounds are first pre-processed to remove noise and then segmented into S1, systole, S2, and diastole intervals, with thirteen MFCCs estimated from each segment, yielding 52 MFCCs per beat. Finally, MFCCs are used for heart sound classification. For that purpose, a single classifier and an innovative ensemble classifier strategy are presented and compared. In the single classifier strategy, the MFCCs from nine consecutive beats are averaged to classify heart sounds by a single classifier (either a support vector machine (SVM), the k nearest neighbors (kNN), or a decision tree (DT)). Conversely, the ensemble classifier strategy employs nine classifiers (either nine SVMs, nine kNN classifiers, or nine DTs) to individually assess beats as normal or abnormal, with the overall classification based on the majority vote. Both methods were tested on a publicly available phonocardiogram database. The heart sound classification accuracy was 91.95% for the SVM, 91.9% for the kNN, and 87.33% for the DT in the single classifier strategy. Also, the accuracy was 93.59% for the SVM, 91.84% for the kNN, and 92.22% for the DT in the ensemble classifier strategy. Overall, the results demonstrated that MFCCs were more effective than other features, including time, time-frequency, and statistical features, evaluated in similar studies. In addition, the ensemble classifier strategy improved the accuracies of the DT and the SVM by 4.89% and 1.64%, implying that the averaging of MFCCs across multiple phonocardiogram beats in the single classifier strategy degraded the important cues that are required for detecting the abnormal heart sounds, and therefore should be avoided.

Patients must always communicate with their doctor for checking their health status. In recent years, wireless body sensor networks (WBSNs) has an important contribution in Healthcare. In these applications, energy-efficient and secure routing is really critical because health data of individuals must be forwarded to the destination securely to avoid unauthorized access by malicious nodes. However, biosensors have limited resources, especially energy. Recently, energy-efficient solutions have been proposed. Nevertheless, designing lightweight security mechanisms has not been stated in many schemes. In this paper, we propose a secure routing approach based on the league championship algorithm (LCA) for wireless body sensor networks in healthcare. The purpose of this scheme is to create a tradeoff between energy consumption and security. Our approach involves two important algorithms: routing process and communication security. In the first algorithm, each cluster head node (CH) applies the league championship algorithm to choose the most suitable next-hop CH. The proposed fitness function includes parameters like distance from CHs to the sink node, remaining energy, and link quality. In the second algorithm, we employs a symmetric encryption strategy to build secure connection links within a cluster. Also, we utilize an asymmetric cryptography scheme for forming secure inter-cluster connections. Network simulator version 2 (NS2) is used to implement the proposed approach. The simulation results show that our method is efficient in terms of consumed energy and delay. In addition, our scheme has good throughput, high packet delivery rate, and low packet loss rate.