In the realm of Wireless Sensor Networks (WSN), approaches to managing power are generally divided into two main strategies: reducing power consumption and optimizing power distribution. Power reduction strategies focus on creating a path for data packets between the sink and destination nodes that minimizes the distance and, consequently, the number of hops required. In contrast, power optimization strategies seek to enhance data transfer efficiency without splitting the network into disconnected segments. Adjusting the data path to balance power often leads to longer routes, which can shorten the network's lifespan. Conversely, opting for the shortest possible path tends to result in a densely packed network structure. The newly proposed Adaptable Power Allocation Framework (APAF) aims to improve energy-efficient routing by simultaneously addressing both power balance optimization and the management of the data packet path. Unlike conventional routing methods, which primarily focus on the shortest path, APAF designs the data pathway by taking into account both the least amount of data transmission and the equilibrium of power distribution and balancing. Through a focus on power balance optimization and intelligent data path management, it demonstrates its effectiveness in improving energy-efficient routing. This study introduces the Adaptable Power Allocation Framework (APAF), which improves energy-efficient routing in WSNs by balancing power consumption and optimizing the data path. APAF is compared with traditional methods (LEACH, Swarm Optimization), showing a 20-30% improvement in data loss reduction and extending network lifespan.

Wireless sensor networks (WSNs) are critical in a wide range of applications, including environmental monitoring, industrial automation, and other areas. However, their effectiveness is frequently restricted due to sensor nodes' low energy resources. The Low-Energy Adaptive Clustering Hierarchy (LEACH) protocol is commonly used to improve energy efficiency in WSNs. Despite its benefits, LEACH has substantial downsides, such as uneven energy distribution and poor cluster head selection, which results in a shorter network lifetime. To address these limitations, we presented the Extended Low Energy Adaptive Clustering Hierarchy (X-LEACH) protocol, which includes enhanced cluster head selection methods and balanced energy utilization. This paper presents a comparative analysis of X-LEACH performance using extensive simulation experiments. The primary aim of this study is to carry a comparative analysis to evaluate X-LEACH's performance across various network scenarios, including sparsely and densely populated nodes, increased number of rounds, and increasing the initial energy of nodes. Critical performance metrics such as the number of dead nodes per round, number of live nodes per round, total remaining energy per round, packet delivery ratio per round throughput per round, and the number of cluster heads formed per round were used. The study analysed the performance of X-LEACH with the traditional LEACH and SEP as the benchmark protocols protocol. Simulation results indicate that X-LEACH significantly improves energy efficiency and network lifespan compared to LEACH and SEP protocols in all the scenarios. 

The use of Android devices has increased rapidly in recent years, increasing the chance of hacking and crime. Hackers target smartphones for various purposes, including getting sensitive information, financial fraud, identity theft, and other crimes. As a result, Android users must be aware of these possible dangers and take necessary measures to secure their smartphones. Because smartphones are the primary repository of personal sensitive information, smartphone designers must include security measures and encourage users to install freely available security software. Most studies have evaluated facial recognition as the most secure feature. This paper shows the uses of a facial recognition application to protect user files that contain sensitive information. The application uses machine-learning algorithms, specifically a Convolutional Neural Network (CNN) for face recognition that detects the user's face, tries to access the file, compares it with the basic image in the local file, and gives the result of whether to open the file or reject depending on the compared image. The application addresses critical concerns and improves file privacy features on Android devices, ensuring user file safety, and achieving success with 99% accuracy. It can also distinguish the faces of women wearing a shawl and people wearing glasses.

Attackers keep launching different attacks on computer networks. Signature-based and Machine Learning (ML)-based techniques have been used to build models for promptly identifying these attacks in networks. However, ML-based approaches are more popular than their counterparts because of their ability to detect zero-day attacks.  In the Internet of Things (IoT), devices are interconnected and this called for the need to guide such networks against intrusions. This study aims at building effective ML models from a recently released IoT-based Smart Home dataset. The study revealed patterns and characteristics of the IoT dataset, pre-processed it and then selected discriminant features using Binary Bat Algorithm (BBA). The pre-processing of the Smart Home IoT dataset for the study was carried out based on the issues identified during the exploratory analyses. The experimental evaluation carried out revealed that all the learning algorithms achieved promising classification results. For instance, Decision Trees recorded 98.60% accuracy, KNN produced 99.60% accuracy while Random Forest (RF) and AdaBoost-based models recorded 100.00% and 99.91% respectively. In all other metrics, RF-based attack classification model slightly recorded the best results. The study concluded that the EDA, innovative data pre-processing, BBA-based feature selection improved the classification performances of the ML approaches used in this study.

Malware outperforms conventional signature-based techniques by posing a dynamic and varied threat to digital environments. In cybersecurity, machine learning has become a potent device, providing flexible and data-driven models for malware identification. The significance of choosing the optimal method for this purpose is emphasized in this review paper. Assembling various datasets comprising benign and malicious samples is the first step in the research process. Important data pretreatment procedures like feature extraction and dimensionality reduction are also included. Machine learning techniques, ranging from decision trees to deep learning models, are evaluated based on metrics like as accuracy, precision, recall, F1-score, and ROC-AUC, which determine how well they distinguish dangerous software from benign applications. A thorough examination of numerous studies shows that the Random Forest algorithm is the most effective in identifying malware. Because Random Forest can handle complex and dynamic malware so well, it performs very well in batch and real-time scenarios. It also performs exceptionally well in static and dynamic analysis circumstances. This study emphasizes how important machine learning is, and how Random Forest is the basis for creating robust malware detection. Its effectiveness, scalability, and adaptability make it a crucial tool for businesses and individuals looking to protect sensitive data and digital assets. In conclusion, by highlighting the value of machine learning and establishing Random Forest as the best-in-class method for malware detection, this review paper advances the subject of cybersecurity. Ethical and privacy concerns reinforce the necessity for responsible implementation and continuous research to tackle the changing malware landscape.