Kamla Nehru Institute of Technology

With the rapid growth of digital content on the web, search engines and recommendation systems (RS) have become important tools to search and discover meaningful information efficiently. Traditional RSs often struggle to generate accurate and personalized recommendations due to the overwhelming expansion of online data, leading to information overload. Therefore, a better understanding of modern deep learning-based solutions is required to overcome these limitations. Deep learning techniques have emerged as a powerful method, utilizing their ability to model complex, nonlinear relationships and extract meaningful patterns from multidimensional datasets. Recent advancements such as Graph Neural Networks (GNNs), Transformers, and Reinforcement learning have further improved recommendation accuracy by capturing intricate user–item interactions and long-range dependencies. Consequently, deep learning-based RSs have gained popularity due to their ability of modeling user preferences, behaviors, and item characteristics at multiple levels, enhancing accuracy, personalization, and scalability. The objective of this review is to systematically explore these developments and provide an understanding of current trends. This review systematically studies various state-of-the-art deep learning-based RSs, focusing on their architectures, implementation progress, and practical applications. We analyze their effectiveness in extracting intrinsic user and item features, examine their strengths and limitations, and highlight emerging trends in the field. The primary contribution is to compare traditional and deep learning-based recommendation approaches with their key challenges and future research opportunities. Additionally, we discuss fundamental issues related to traditional and deep learning-based RS, which continue to hinder the widespread adoption of deep learning techniques in RSs. Overall, this survey presents a structured framework to guide future research and support the development of more robust, scalable, and efficient deep learning methodologies for RSs.

The rapid advancement of Wireless Sensor Networks (WSN) has led to the development of a wide variety of localization techniques. This enables various tasks, such as environmental, health, and crop monitoring, etc. Researchers have proposed numerous approaches ranging from classical range-based and range-free methods to more recent machine learning and optimization-driven solutions. These contributions are often presented in isolation, making it difficult to obtain a unified understanding of their relative strengths and limitations. Therefore, there is a need of a comprehensive survey that systematically organizes existing localization techniques into a coherent framework. The paper presents an extensive survey of range-free, range-based, machine-learning-based, and metaheuristics-based techniques. Further, the surveyed methods are systematically classified based on mathematical models, accuracy, sensitivity, measurement models, anchor utilization, energy efficiency, and scalability, etc. This survey aims to provide a comprehensive understanding of localization techniques and future research directions in node localization in WSNs.

The perturbation iteration Sumudu transform method (PISTM) is a cutting-edge hybrid method for finding the precise solution to the various types of time-fractional Fisher’s equations, including the nonlinear time-fractional diffusion equation in Fisher’s form. Numerous domains, including population dynamics, stochastic processes, genetic transmission, combustion theory, and flame simulation, utilize these equations. The validity and effectiveness of the method are demonstrated through convergence and error correction, which shows that the PISTM solutions are distinct and convergent. The outcomes demonstrate the efficacy and dependability of PISTM. The Method is accomplished by comparing the findings with the exact results through various tables and graphs. The outcomes demonstrate that the method is simple and efficient for obtaining the solution of nonlinear time-fractional Fisher’s equations.

Friction stir additive manufacturing (FSAM) is an emerging solid-state technique for producing high-strength aluminum composites with refined microstructures. However, challenges such as non-uniform reinforcement dispersion and weak interlayer bonding still limit the performance of multilayer FSAM components. In this study, AA7075 hybrid composites reinforced with zirconium dioxide (ZrO2) and graphene were fabricated using a groove-assisted multilayer FSAM technique. The primary objective of this work is to examine the influence of a tapered octagonal pin tool geometry on material flow behavior, microstructural evolution, reinforcement dispersion, and mechanical performance. Optical microscopy, scanning electron microscopy (SEM), and energy-dispersive spectroscopy (EDS) were used for microstructural characterization, while hardness, tensile, wear, and friction tests were conducted to evaluate mechanical and tribological properties. Fracture behavior and tool surface conditions were further analyzed using SEM-based fractography and tool wear observations. The results show that the tapered octagonal pin tool promotes improved material flow, leading to a relatively uniform distribution of ZrO2 and graphene reinforcements with limited agglomeration and improved interlayer bonding. The fabricated composite exhibited enhanced hardness (up to 187.5 VHN) and tensile strength (up to 325 MPa) compared with the base alloy. Fractographic analysis revealed predominantly ductile fracture characteristics, indicating effective load transfer between the matrix and reinforcements. In addition, the composite demonstrated improved wear resistance with a reduced coefficient of friction. Tool surface analysis indicated minimal tool degradation during the FSAM process. The findings highlight the role of tapered octagonal pin tool geometry in improving reinforcement dispersion and mechanical performance in FSAM-processed AA7075/ZrO2/Gr hybrid composites, providing insights for optimizing tool design in solid-state additive manufacturing.

This paper explores the mechanical properties of Polylactic Acid (PLA) composites reinforced with carbon fiber (CF) developed by Fused Deposition Modeling (FDM) technology, aiming to enhance the mechanical performance of PLA by incorporating varying percentages of carbon fiber. The study used PLA and carbon fiber with varying percentages (0