Paper Title

A COMPREHENSIVE REVIEW ON MACHINE LEARNING AND GENETIC ALGORITHMS IN NETWORK BEHAVIOR OPTIMIZATION

Abstract

In machine learning the process of selecting features is an important task. This is a method of selecting a subset of relevant or significant variables and features. Neural networks and genetic algorithms are the two sophisticated machine learning techniques presently attracting attention from scientists, engineers, and statisticians, among others. They have gained popularity in recent years. Optimization is aimed toward deviating from the limitations attributed to machine learning in order to solve complex and challenging problems. Feature selection is applicable in multiple areas such as Diabetes Prediction, anomaly detection, Bioinformatics, image processing, etc. where high dimensional data is generated. This study gives a literature review on different feature selection methods. Emphasizing the need for standardized data, low-cost ML applications for smallholder farmers and interdisciplinary collaboration. Future research also needs to work on data integration features, real-time data monitoring, and eliminating socio-economic barriers to ML usage for that sustainable and responsible solution for the agricultural sector. The genomes often contain repetitive sequences and duplicated regions, which can lead to ambiguities during assembly. Thus, the process of reconstructing a complete genome from a set of reads necessitates the use of efficient assembly programs.
KEYWORDS : machine learning, genetic algorithms, Diabetes Prediction, data integration features, nature-inspired algorithms, Bioinformatics.

Paper Title

A COMPARATIVE STUDY OF AI TOOLS FOR REAL-TIME NETWORK ANOMALY DETECTION AND RESOLUTION

Abstract

This study presents a comprehensive overview of existing methods for anomaly detection in IoT networks using machine learning (ML). A detailed analysis of various ML algorithms, both supervised (e.g., Random Forest, Gradient Boosting, SVM) and unsupervised (e.g., Isolation Forest, Autoencoder), was conducted. One of the key elements of IoT systems is effective anomaly detection, which identifies abnormal behavior in devices or entire systems. The performance of the selected algorithms was evaluated using commonly used metrics. The complexity of cyber-attacks makes it difficult to develop efficient tools to detect them. Signature-based intrusion detection has been the common method used for detecting attacks and providing security. However, with the emergence of Artificial Intelligence (AI), particularly Machine Learning, Deep Learning and ensemble learning, promising results have been shown in detecting attacks more efficiently. Telecommunication networks are becoming increasingly dynamic and complex due to the massive amounts of data they process. Traditional methods of anomaly detection, which rely on rule-based systems, are no longer effective in today’s fast-evolving telecom landscape. Thus, making AI useful in addressing these shortcomings. This study critically examines the role of Artificial Intelligence (AI), particularly deep learning, in modern anomaly detection systems for telecom networks. Additionally, emerging AI technologies such as Generative Adversarial Networks (GANs) and Reinforcement Learning (RL) are highlighted for their potential to enhance anomaly detection.
KEYWORDS : Artificial Intelligence (AI), anomaly detection systems, AI technologies, cyber-attacks, Generative Adversarial Networks (GANs).

Paper Title

A STRUCTURED APPROACH TO LEGACY DATABASE TRANSFORMATION IN HYBRID CLOUD ENVIRONMENTS

Abstract

A comprehensive review of literature suggests seven levels of complexity in transforming legacy systems, including, being a stand-alone system, being part of a larger system, and data incompatibility, each depicting unique criteria. Using a mixed-method approach, we surveyed and interviewed stakeholders across five Saudi Arabian universities. These systems were built for a different era, lacking the agility and scalability required to support modern business demands. Most of the new systems and applications are built to be cloud native applications but many large organizations still depend on legacy systems that have been built tens of years ago. Nonetheless, very little is known as to what degree these complexities implicate the implementation of digital transformation efforts in public administration (PA). Legacy systems remain critical to the operations of many organizations but often pose significant challenges in a fast-paced, technology-driven landscape. In addition, a comprehensive understanding of the systems to be transformed, the policies which they are serving, and the broader PA setting in which they are implemented were deemed central to succeeding in digital transformation efforts. Cloud modernization-the process of migrating these systems to the cloud-has emerged as a key solution. By incorporating AI, organizations can enhance the effectiveness of cloud modernization initiatives. AI brings automation, advanced analytics, and real-time decision-making capabilities that streamline migration and improve operational outcomes.
KEYWORDS : mixed-method approach, public administration (PA), transforming legacy systems, technology-driven landscape, real-time decision-making.

Paper Title

NEW NUMERICAL METHODS STUDY OF DIFFERENTIAL EQUATIONS

Abstract

This research paper explores the latest developments in numerical methods for solving differential equations. Differential equations are fundamental in describing various physical, biological, and engineering phenomena. As computational power continues to grow, researchers are constantly innovating numerical techniques to provide accurate and efficient solutions to these equations. This paper reviews recent studies, compares various methods, and proposes novel approaches to address challenges in solving differential equations numerically.
KEYWORDS : new numerical, methods, differential equations

Paper Title

IMPACT OF TEMPERATURE AND RAINFALL VARIABILITY ON FODDER AVAILABILITY AND ITS CONSEQUENCES ON LIVESTOCK NUTRITION IN JHAJJAR

Abstract

This study investigates the impact of temperature and rainfall variability on fodder availability and the resulting consequences for livestock nutrition in the district. Jhajjar experiences a semi-arid climate, making its fodder production highly sensitive to climatic fluctuations. Rising temperatures and erratic rainfall patterns have led to decreased pasture yields, shortened growing seasons, and a shift in fodder crop composition. These changes have significantly reduced the quantity and nutritional quality of available fodder, adversely affecting livestock health, milk yield, and overall productivity. Smallholder farmers, who rely heavily on rain-fed fodder sources, are disproportionately affected. The study emphasizes the urgent need for adaptive strategies, including climate-resilient fodder crops, improved storage techniques, and policy support for sustainable fodder management. Addressing these challenges is vital for securing livestock-dependent livelihoods and ensuring food security in climate-vulnerable regions like Jhajjar.
KEYWORDS : Temperature variability, Rainfall variability, Fodder availability, Livestock nutrition, Climate change, Jhajjar, Haryana

Paper Title

APPLICATIONS OF FIXED POINTS TO THE SOLUTION OF LINEAR AND NONLINEAR INTEGRAL EQUATIONS

Abstract

Fixed point theory has become a powerful tool in the analysis and solution of both linear and nonlinear integral equations. The fundamental idea revolves around determining a point in a given space where a mapping (or operator) stabilizes, i.e., the point maps to itself. This approach finds extensive applications in solving integral equations, where the unknown function is often expressed in terms of itself through an integral operator. For linear integral equations, fixed point methods such as Banach\'s Fixed Point Theorem are utilized to establish the existence and uniqueness of solutions under appropriate conditions. In the case of nonlinear integral equations, more generalized fixed point principles, including Schauder and Krasnoselskii’s theorems, offer powerful techniques for proving the existence of solutions, even in the absence of linearity. The application of fixed point theory to these equations not only guarantees the existence and uniqueness of solutions but also provides efficient iterative methods for their numerical approximation. This abstract aims to highlight the theoretical and computational significance of fixed points in addressing challenges associated with linear and nonlinear integral equations, showcasing their role in diverse fields such as physics, engineering, and applied mathematics.
KEYWORDS : applications, fixed points, solution, linear and nonlinear integral equations

Paper Title

HYDROLOGICAL EFFICIENCY OF PERVIOUS CONCRETE PAVEMENTS INCORPORATING MARGINAL AGGREGATES

Abstract

This research explores the hydrological efficiency of pervious concrete pavements incorporating marginal aggregates. With urban areas facing increasing challenges from stormwater management, groundwater depletion, and urban flooding, pervious concrete offers an innovative low-impact development (LID) solution. The study evaluates permeability, infiltration rates, water storage capacity, and pollutant removal efficiency of pervious concrete made with marginal aggregates. Results reveal that marginal aggregates, despite their non-standard properties, can be effectively used in pervious concrete to achieve satisfactory hydrological performance. This research demonstrates that such pavements can play a crucial role in sustainable stormwater management, urban water quality improvement, and groundwater recharge.
KEYWORDS : Pervious concrete, hydrological efficiency, marginal aggregates, permeability, infiltration, stormwater management, groundwater recharge

Paper Title

FAULT-TOLERANT AND EFFICIENT DATA AGGREGATION TECHNIQUES IN RESOURCE-CONSTRAINED WSN ENVIRONMENTS

Abstract

Data aggregation is a fundamental process that enhances data analysis and decision-making across various industries. Organizations can gain valuable insights, improve efficiency, and make informed decisions by collecting and summarizing data from multiple sources. Whether it\'s used in business intelligence, healthcare, marketing, finance, or environmental studies, the benefits of data aggregation are far-reaching. Our experimental results show that our approach reduces the communication cost, transmission cost, energy consumption at the nodes and cluster heads, and delivers highly-refined and fused data to the base station. Embracing this process is essential for any organization looking to harness the power of data. However, the data privacy and security are challenging the proliferation of clustering wireless sensor network (CWSN) due to its highly constrained resources and violably deployed environments, which make it infeasible to directly apply traditional cryptography and therefore vulnerable to various attacks. This study proposes a scheme that provides efficient privacy-preserving data fusion as well as malicious data tolerance by mining concealed data within groups. And the dynamically organized groups in each cluster improves resilience against large number of node compromise comparing with the existing data aggregation schemes.
KEYWORDS : Data aggregation, clustering wireless sensor network (CWSN), decision-making, communication cost, environments.

Paper Title

A SUSTAINABLE IOT-ENABLED WSN FRAMEWORK FOR PROACTIVE FOREST FIRE DETECTION AND MITIGATION

Abstract

Recently, Internet of Things (IoT) technologies are developing technology with a variety of applications. The Internet of Things (IoTs) is defined as a network of ordinary objects such as Internet TVs, smartphones, actuators and sensors that are smartly connected together to enable new types of communication between people and things as well as between things themselves. Wireless sensor networks (WSNs) play an important part in Internet of Things (IoT) technology. A contribution to wireless sensor networks and IoT applications is wireless sensor nodes’ construction with high-speed CPUs and low-power radio links. The IoT-based wireless Sensor network (WSN) is a game-changing smart monitoring solution. ZigBee standard is an important wireless sensor network (WSN) and Internet of Things (IoT) communication protocol in order to facilitate low-power, low-cost IoT applications and to handle numerous network topologies. This research presented a review on the energy efficient and routing topologies of ZigBee WSN, applications of IoT enabled Wireless Sensor Network as well IoT WSN security challenges.
KEYWORDS : Internet of Things (IoT) technologies, Wireless Sensor Network, low-power radio links, Internet TVs, smartphones, actuators.

Paper Title

ROLE OF THE DIFFERENTIAL TRANSFORM METHOD IN MODELLING REAL-WORLD DYNAMICAL SYSTEMS

Abstract

This study investigates the use of the differential transform method (DTM) for integrating the Rössler system of the fractional order. Preliminary studies of the integer-order Rössler system, with reference to other well-established integration methods, made it possible to assess the quality of the method and to determine optimal parameter values that should be used when integrating a system with different dynamic characteristics. Among different numerical and semi-analytical methods for solving initial and boundary value problems, the differential transform method (DTM) has received notable attention. It has developed and experienced generalizations for implementing other types of mathematical problems such as optimal control, calculus of variations, and integral equations. The first method is based on the differential transform method (DTM), which seeks an analytical solution in the form of a certain functional series. The second method, on the other hand, is based on the physics-informed neural network (PINN), where artificial intelligence in the form of a neural network is used to solve the differential equation. In addition to describing both methods, this study also presents numerical examples along with a comparison of the obtained results. Comparing the two methods, DTM produced marginally more accurate results than PINNs. While PINNs exhibited slightly higher errors, their performance remained commendable.
KEYWORDS : differential transform method (DTM), different numerical and semi-analytical methods, artificial intelligence, well-established integration methods, optimal control.