International Journal of Communication Networks and Information Security (IJCNIS)
Not a member yet
1021 research outputs found
Sort by
Exploring Service Robots and Wireless Sensor Networks for Smart Home Constructions
No full textThe development of smart home environments has now progressed to a stage where everyday household devices and objects can be interconnected, offering residents new and innovative ways to manage and control their living spaces. With advancements in digital electronics, compact sensor nodes capable of short-range communication have been developed. These sensor nodes are not only cost-effective and energy-efficient but also multifunctional. They combine sensing, data processing, and communication components and operate under the framework of Wireless Sensor Networks (WSN), which function through the collaborative efforts of multiple nodes. Despite the substantial research in WSN applications, there remains significant untapped potential in further developing and maintaining these networks. This paper explores the potential of integrating WSNs with service robots in smart home applications. Service robots can function as mobile nodes, enhancing sensory data, restoring or improving network connectivity, and gathering information from wireless sensor nodes. Conversely, WSNs can enhance the sensory capabilities of service robots, creating a more intelligent environment for them to operate in
Machine Learning Based Framework for Unmasking Bogus Reviews in Online Shopping
No full textThis research introduces a robust machine learning framework that utilizes the K-Nearest Neighbors (KNN) algorithm to detect fake reviews in Amazon product feedback. The model capitalizes on KNN's ability to assess the proximity of data points, integrating a diverse range of features derived from the textual content, temporal patterns, and contextual elements of reviews. By thoroughly analyzing these features, the model is able to identify subtle discrepancies that distinguish genuine feedback from deceptive ones. Rigorous validation on real-world datasets demonstrates the model's high accuracy in detecting fake reviews, while also maintaining a balance between effectiveness and computational efficiency. The model's design ensures it is adaptable across various product categories and scales well within Amazon's vast ecosystem, addressing the complexities of diverse product offerings. Furthermore, the approach is engineered to be resilient against evolving deceptive tactics and variations across different regions and time periods, showcasing its robustness and long-term applicability. The study highlights the importance of adopting KNN-based methodologies as a critical tool in the ongoing battle to preserve the integrity of online feedback systems. By enhancing the reliability of reviews, this framework empowers consumers with trustworthy information, enabling them to make informed purchasing decisions. The findings of this research advocate for the broader implementation of KNN-driven approaches to fortify consumer trust and ensure the credibility of e-commerce platforms
ENHANCING STUDENT PERFORMANCE PREDICTION USING BIDIRECTIONAL LONG SHORT-TERM MEMORY NETWORKS WITH SECRETARY BIRD OPTIMIZATION
No full textThe complexities of student related issues were captured by internal and external setup of educational institutions which designed to anticipate student performance accurately to render timely and effective engagement, and significant challenges. Due to suboptimal data handling and feature selection methods many traditional algorithms is in underperformed level. This study utilized Secretary Bird Optimization (SBO) algorithm for Bidirectional Long Short-Term Memory (BiLSTM) to predict students performance. This model evaluatoon starts with preprocessing, SBO feature selection, feature learning carried out by BiLSTM networks. The real dataset was utilized for evaluation of SBO with BiLSTM networks. Integration of these advanced techniques produced high accuracy over existing methods. This models attained accuracy of 97.51% and precision of 95.21% , 95.87 for recall and 97.10 for f1-Score . This research work results were recorded that SBO-BiLSTM networks validate and predict students performance and their outcome in timely with higher accuracy
Performance Analysis of High Strength Pavement Quality Concrete with GGBS, Polypropylene Fiber and Silica Fume
No full textThis study investigates the presentation of high strength pavement quality concrete with preventive percentage of Silica fume and GGBS Focusing on Workability and mechanical properties. High strength pavement quality concrete (HSPQC) necessitates low water-to–cement ratio, high quality raw material, and the incorporation of mineral admixture and high-performance activities. The durability of high strength pavement quality concrete is crucial in structural design, being extensively used in rigid road construction due to its high-volume stability, compressive strength, and workability.
In this paper an experimental investigation is done to determine the Suitability of GGBS and silica fume as a replacement of cement. Aiming to improve the concrete performance,the combine use of silica fume and polypropylene fiber and also GGBS and polypropylene fiber was investigated. While each of these materials contributes independently to improving concrete performance. The effect of adding polypropylene fiber with different shape and volume fractions on the compressive strength, modulus of rupture, flexural strength of concrete was investigated. Crimped and twisted polypropylene fiber were used with 0.6 % volume fraction. It was found that the compressive strength, flexural strength of concrete increased by adding 0.6 % volume fraction of polypropylene fiber. Pavement Concrete is a brittle material when it undergoes heavy load, crack will form and to reduce this improve high strength in concrete certain admixture are used. To produce high strength, concrete these ground granulated blast furnace slag and silica fume is used. it has a higher portion of the strength enhancing calcium silicate hydrates (CSH) than concrete made with Portland cement only and a reduced content of free lime which does not contribute to concrete strength, concrete made with GGBS continues to gain strength overtime, and has been shown to double its 28 days’ strength over periods of 10 to 12 years and silica fume made with concrete to gain early strength. The aim is to evaluate HSPQC containing supplementary cementitious material such as silica fume and GGBS, which are increasingly necessary in the construction industry. Effort to enhance concrete performance have been shown that replacing cement with material like GGBS and silica fume along with mineral admixture and chemical admixtures, can improve strength and durability
The Influence of Emotional Design and Demographic Characteristics on Homestay Inn Satisfaction
No full textObjective The burgeoning homestay inn industry has diversified and personalized accommodation offerings. This study investigates the interplay between demographic variables (such as consumers' gender, age group, educational attainment, occupation type, and income level) and emotional needs (encompassing the utilitarian, visual-aesthetic, and reflective dimensions). The aim is to assist homestay inn in delivering more precisely tailored services and designs. Methods Employing a cross-sectional research approach, this study gathered data from a sample of 916 homestay inns consumers across the nation via online surveys. The data underwent analysis through SPSS, encompassing descriptive statistics, correlation analysis, and regression analysis. Initially, the research focused on delineating the basic characteristics of the respondents and their emotional needs. Subsequently, it probed the existence of correlations between demographic variables and emotional needs. Lastly, the robustness of the regression model was assessed. Results The findings reveal that the primary demographic of homestay inn patrons skews towards younger individuals aged 30-45, with a higher educational background (college degree and above) and higher income brackets (5001-10000 yuan), albeit with diverse occupational profiles. The average score for emotional needs hovered around 8 points, suggesting a generally positive reception towards emotional design among respondents. A statistically significant correlation was observed between demographic variables and emotional design. Nevertheless, the regression model's explanatory power proved limited, indicating the need for more in-depth exploration to unravel the complexities of these relationships
Energy-efficient Structural Alterations for High-Rise Buildings
No full textIn recent years, reducing the amount of energy used in buildings has gained importance in the fields of design and urban planning. Regulations were developed for every climate zone, aiming to reduce sunlight-based presentation for structures in hot climates and to increase sun-based introduction for structures in cold climates. This system typically predicts the season with the worst weather, sometimes ignoring the fact that urban regions at scope 25° can experience temperatures below warm comfort limits in the winter and that metropolitan areas at scope 48° commonly experience temperatures over warm comfort limits in the summer. This analysis argues that a comprehensive approach to managing vitality-efficient structural frameworks is necessary. Its exterior glass partitions and inside composite divider define its nonexclusive vitality effective structure. In this study, we are also replacing a certain amount of concrete in concrete for R.C.C. folks with low carbon impression material. The ETABS tool is taken into consideration in this research project for modeling and dynamic analysis
An Efficient ANN-Based Soft Computing Approach for Energy Optimization in Wireless Sensor Networks
No full textWireless Sensor Networks (WSNs) are increasingly employed across various domains, yet they encounter substantial challenges related to energy consumption and data security. This study presents a novel approach that integrates Artificial Neural Networks (ANNs) with advanced clustering techniques to address these challenges and optimize energy efficiency in WSNs. The proposed ANN-based system dynamically adjusts threshold values to effectively monitor and manage sensor node energy levels, thereby extending the network's operational lifespan. Additionally, it incorporates an encryption algorithm to secure data transactions, encrypting data at the source and requiring an authorized receiver for decryption at the destination, thus enhancing data security. Compared to existing algorithms such as HEED (Hybrid Energy-Efficient Distributed Clustering), DEEC (Distributed Energy-Efficient Clustering), and TEEN (Threshold-sensitive Energy Efficient Sensor Network Protocol), the proposed framework demonstrates notable improvements in energy efficiency, network lifetime, and data security. Comprehensive simulations and experiments validate the effectiveness of this hybrid approach, underscoring its potential as a sustainable and secure solution for WSNs
Reinforcement Learning for Dynamic Vehicle Routing Problem: A Case Study with Real-World Scenarios
No full textThe Vehicle Routing Problem (VRP) is a foundational challenge in logistics and transportation, requiring the optimization of routes for vehicles to deliver goods or services efficiently. With the advent of new technologies and methodologies, the field of VRP is evolving rapidly. One of the most promising new trends in VRP is the integration of machine learning (ML) techniques to enhance decision- making processes and improve solution quality. This article delves into the application of machine learning in VRP, exploring how these techniques can optimize routing strategies by predicting demand patterns, identifying efficient routes in real-time, and dynamically adjusting to changes. By focusing on this trend, the paper highlights the transformative potential of machine learning in applied mathematics for solving complex VRP instances
Accelerating Computer Vision Innovation: A No-Code Platform Leveraging Pre-Trained Models
No full textThe No-Code Computer Vision Platform revolutionizes computer vision technology by eliminating the need for extensive coding knowledge. Unlike traditional approaches, this platform offers an intuitive drag-and-drop interface, making it accessible to users with varying technological backgrounds. Key features include a vast library of pre-trained models, real-time data processing capabilities, and an efficient result monitoring dashboard. Leveraging transfer learning, users can optimize models without deep learning expertise. By democratizing computer vision, this platform empowers domain specialists and business analysts across sectors. Its automation features and decision support capabilities enhance user experiences, making it a valuable innovation tool. As organizations recognize the strategic importance of visual data, this platform opens up exciting possibilities
Hybrid Convolutional Neural Network Model to ascertain the Objects in Dynamic Cluttered Environment
No full textThe field of computer vision has made significant strides in object detection in recent years, primarily because of the introduction of deep learning techniques, specifically Convolutional Neural Networks (CNNs). We have introduced a novel method for the multi-object detection in multi-scene cluttered environment in the proposed work. In order to build multi-scale andmulti-scene object detection, in our work we have provides a multi-scale neural network basedonthehigherresponse of FastR-CNNarchitecture. For the experimental work,we have considered different categories of different objects. The dataset is designed to facilitate the development of object detection techniques. It comprises 12,165 object chips, each consisting of 256 pixels in both azimuth and range dimensions. This dataset encompasses diverse primary backgrounds and object sizes. Furthermore, well-known cutting-edge object detectors that have been trained on real-world images are modified to serve as baselines, guaranteeing the availability of reliable and practical reference points. Experimental results indicate that these object detectors not only enhance various quantitative metrics but also achieve unprecedented levels of accuracy, surpassing the capabilities observed in prior studies