International Journal on Recent and Innovation Trends in Computing and Communication
Not a member yet
8613 research outputs found
Sort by
Fuzzy Fractional-Order PID Congestion Control Based on African Buffalo Optimization in Computer Networks
Get PDFCongestion is the primary factor that slows down data transfer in communication networks. Transmission Control Protocol and Active Queue Management (TCP/AQM) collaborated to resolve this issue. The fuzzy-Fractional-Order-PID (FFOPID) controller is developed in this paper to control the linearized TCP/AQM model. The strategy is founded on a combination of fractional-order PID and fuzzy logic controllers. The primary objective of the proposed controller is to maintain the queue length of the router within the appropriate queue threshold for a congestion model. The control parameters are tuned using African Buffalo optimisation (ABO). The suggested controller is compared to other controllers (PID, Fuzzy-PID, and Fractional-order PID) to demonstrate the controller's efficiency, and all of these controllers are optimised using African Buffalo Optimisation (ABO). In MATLAB (R2017b), the simulation of the linearized model is introduced. Comparing the results of the Fuzzy-Fractional-Order-PID controller with those of other controllers in the same network scenarios reveals that the Fuzzy-FOPID is robust for a wide variety of TCP flows
AI-Powered Strategic Marketing: A Three-Stage Framework for Enhanced Customer Engagement
Get PDFThe authors present a new three-step framework for marketing strategy implementation that uses machine learning (ML) techniques. This program leverages the many benefits of artificial intelligence (AI) in three ways: machine AI that automates routine business tasks, logical AI for data-driven decisions , and AI for microanalyzing human emotions and interactions ) , and showing how it can revolutionize execution in the marketing research sector, machine AI streamlines the data collection process, while cognitive AI performs comprehensive market research. However, the story on AI goes deeper in understanding consumer behaviour and emotions. Moving on to the marketing planning (STP) phase, machine AI helps segment through automatic recognition, while intellectual AI recommends target segments based on robust data analysis AI perception helps by crafting resonance and positioning strategies with customer sentiment meets it. In the marketing action phase, machine AI facilitates the standardization of marketing programs, ensuring consistency across campaigns. Cognitive AI enables personalized marketing efforts by tailoring strategies to individual preferences and behaviors. The spirit of AI encourages national innovation by deeply understanding and responding to customer sentiment, thus creating lasting relationships. These frameworks are applied across a range of marketing sectors, organized around the traditional 4Ps/4Cs model, which outlines how to strategically integrate AI into marketing practices
Effects of Elevated Temperature on Lightweight Concrete: Flexural Behaviour of Reinforced Concrete Beams and Performance Against Impact and Abrasion
Get PDFThis research investigates the effects of elevated temperature on lightweight concrete, the flexural behaviour of reinforced concrete (RCC) beams, and the performance of lightweight concrete against impact and abrasion. Elevated temperatures can significantly influence the mechanical properties and durability of lightweight concrete, leading to strength reduction, thermal stresses, changes in microstructure, and potential loss of structural integrity. The flexural behaviour of RCC beams under loading involves nonlinear responses, crack formation, moment-curvature relationships, reinforcement yielding, and shear effects, all of which play crucial roles in beam performance and failure mechanisms. Lightweight concrete, while offering advantages such as reduced weight, may exhibit lower impact resistance and abrasion resistance compared to conventional concrete. However, proper mix design, material selection, and surface treatments can mitigate these drawbacks. This study emphasizes the importance of understanding the behaviour of lightweight concrete under various conditions and highlights strategies to enhance its performance in practical applications. Experimental investigations and standardized testing methods are essential for evaluating the response of lightweight concrete to elevated temperature, flexural loading, impact, and abrasion, providing valuable insights for design and construction practices
Binary 32-Bit Adder Design Using Carry Look Ahead Adder in Electric
Get PDFAdders are a part of integrated circuits of today almost everywhere. Smaller and lower-power arithmetic circuits are also required by the rapidly evolving computing industry, in addition to faster arithmetic units. To satisfy its needs, the adder needs to be both speedy and effective in the chip area. We used the Carry Look Ahead Adder (CLA) to build a 32-bit adder utilizing eight 4-bit adders for our project. Because it propagates carry before the sum output is reached, it takes less time than other adders and performs brilliantly, earning it the nickname "fast adders." We used LT Spice simulation to create the CLA's schematic and architecture. 45nm technology was used, with an area of 898.6 ?m2 and a power efficiency of 0.215 watt
Simulation and Assessment of Stock Market Forecasting Using Machine Learning Methodology
Get PDFThis paper explores the application of neural network-based machine learning methodologies for stock market forecasting, an area of significant interest due to its potential to yield high returns. The study employs deep learning models, particularly Long Short-Term Memory (LSTM) networks, recognized for their ability to process time series data and capture temporal dependencies that are crucial in understanding stock market behaviors. The methodology involves collecting extensive historical stock price data, including open, close, high, low prices, and volume traded. This data is preprocessed to normalize the values and convert them into a format suitable for LSTM networks. The neural network architecture is designed with multiple layers, including dropout layers to prevent overfitting, and is trained on a substantial dataset to predict future stock prices based on past patterns. The performance of the LSTM model is evaluated using metrics such as root mean squared error (RMSE) and mean absolute error (MAE), comparing its predictive accuracy with traditional statistical methods and simpler machine learning models. The results indicate that LSTM networks can significantly improve the accuracy of stock market forecasts, demonstrating the model's efficacy in capturing complex stock price movements and providing a reliable tool for investors and financial analysts. The study not only confirms the viability of using sophisticated machine learning techniques in financial markets but also opens avenues for further research into neural network optimizations for enhanced predictive performance
Investigating the Efficacy of Hyper Parameter Tuned Machine Learning in Malware Detection
Get PDFThis paper investigates the efficacy of hyperparameter tuning in enhancing machine learning models for malware detection. Given the escalating threats posed by sophisticated malware, traditional detection methods often fall short, necessitating more advanced and adaptive technologies. This study utilizes several popular machine learning algorithms—including decision trees, support vector machines (SVMs), and neural networks—optimized through rigorous hyperparameter tuning to maximize their detection capabilities.
The methodology centers on a comparative analysis of models pre and post hyperparameter adjustments, employing techniques such as grid search and random search to identify optimal configurations. The dataset comprises a diverse array of malware samples, ensuring comprehensive training and testing scenarios. Each model's performance is evaluated based on accuracy, precision, recall, and F1-score—metrics that collectively gauge the models' abilities to correctly identify malware without misclassifying benign applications
Develop Prototypes and Scheduling Strategies for Cloud Computing
Get PDFCloud computing usage is rapidly increasing and turning into a driving force among all modern-day industries offer it to customers worldwide. It gave a notable deal of thought to the enormous amount of energy consumed in the datacenters. Consequently, it’s far essential to decrease the loss of energy efficiency, meet battery life, meet performance requirements, decrease electricity consumption, maximize earnings, and to use resources most efficiently. Utilizing a scheduling approach to find the ideal undertaking execution sequence based on an individual’s need and with the least amount of execution time and cloud resources is the most effective way to decrease energy. The paper aims to advocate a brand-new method for cloud computing to reduce energy consumption in the environment and adhere to Service Level Agreement (SLA) and Quality of Service (QoS) norms. Utilizing energy- and energy-scheduling algorithms will assist in enhancing and limiting the procedure for mapping within incoming tasks and datacenter servers and acquiring the best use of recourses from the data centre to obtain superior computing overall performance, reducing the demand on the network and the datacenters' energy use. In order to maximise efficiency due to bandwidth usage and conserve energy used in the datacenter, Process time and system total make span should be kept to a minimum. This paper investigates energy-conscious cloud computing datacenter designs with a variety of scheduling methods and suggests a novel task scheduling method with based on file location during live migration proceeding. The evaluation and proposal of a new SLM algorithm in numerous situations in the usage of CloudSim toolkit, then outcome indicates a vastly increased energy efficiency reading levels and total make span related to the particle swarm optimization technique (PSO) and the ant colony method (ACO) demonstrates an important development in the statistics for energy use, Degrees, and Overall Makespan. The overall amount of time needed to perform all jobs is known as the span of time
Study of Wireless Transfer of Energy from a Higher Source of Energy Machine to a Low Energy Machine
Get PDFThe wireless energy transfer (WET), which is a promising technology that enables devices to power themselves without the need for a physical connection, has been identified as a potential game-changing innovation. This paper explores the various aspects of this technology and its origins, tracing its origins back to Nikola Tesla’s pioneering work. This article explores the various types of WET transmission methods, such as inductive, RF, beamforming, and magnetic resonance. Through a comprehensive analysis of these techniques, we can identify their limitations and strengths and guide our selection based on the specific requirements of our applications. This concluding research work covers the present and upcoming developments of WET, emphasizing its crucial role in fostering a more sustainable and connected energy sector
Smart Parking System with research on Thread Communication Protocol
Get PDFNowadays, enhancements in technology and areas in the automobile community has resulted in almost every individual making use of an automobile entity, due to this there has been significant increase in industrial and personal advancements but this has also resulted in increase in traffic, congestion, pollution and many more areas of concern. Smart parking systems (SPS) has been a topic of discussion for several years. Blockchain, IoT and network solutions have been proposed in order to ease the use of parking systems and tackle inconveniences caused due to lack of parking spaces. A major route of research in this domain is the use of IoT devices and wireless communication protocols to back it up. Many devices such as sensors, actuators, RFID’s, Zigbee communication protocol, NB-IoT communication protocol, Edge computing and much more have contributed to significant positive changes in the parking sector. In this paper, we intend on implementing a new communication protocol which eases the use of connectivity between IoT devices in an environment known as Thread Mesh protocol which was introduced in 2015 by Thread inc. Even though there has been extensive research done on IoT based SPS’s, security seems to be a major concern in majority of IoT devices and protocols, Thread communication protocol aims at reducing the risk of security attacks in a smart parking-system due to its in-built cryptography, commissioning, adaptation to PAN (Personal Area Network) and many more features that we intend on discussing and implementing in this paper
The Role of Complex Big Data in Shaping the Future of Enterprise Decision-Making
Get PDFComplex big data are the disruptive forces that alter how business processes are planned, operated, and competed in an increasingly digital world. This paper delves into the multifaceted role of advanced data analytics in producing competitive advantage, operational efficiency, and strategic insights in different industries. Digital engagements through the Internet of Things devices, social media and complex technological ecosystems greatly generate an unprecedented volume, speed, and variety of data that shapes the modern enterprise landscape. Data-driven approaches that employ AI, machine learning, and advanced analytics to generate actionable insights from complex and multifaceted datasets are rapidly supplanting conventional decision-making models. Due to tremendous technological advancement, organizations have been able to overcome traditional analytical limitations. Cloud-based infrastructure, advanced machine learning algorithms, and distributed computing architectures have enabled businesses to process and analyze large datasets in real-time, delivering insights into consumer behavior, market dynamics, operational performance, and strategic opportunities that were previously unimaginable. Beyond mere information processing, complex big data carries strategic implications. With the use of predictive and prescriptive analytics, businesses can now predict market trends, optimize resource allocation, minimize risks, and offer personalized customer experiences. These abilities signify a paradigm shift in decision-making from reactive to proactive. However, the integration of complex big data into business strategies is not without challenges. It becomes complex to manage organizational, ethical, and technological issues while addressing the needs of hackers trying to compromise the security of data, privacy due to data, investments made in technological infrastructure, and the availability of human resources with the ability to interpret analytical outcomes. The trends in data usage have become advanced as evidenced by this. More sophisticated machine learning and artificial intelligence algorithms enable more precise predictive models. New technologies such as edge computing and quantum computing will only add to data processing capabilities, bringing new insights that were hitherto unavailable. According to research, the effective exploitation of complex big data by businesses would lead to significant competitive advantage. By converting raw data into strategic intelligence, an organization can accomplish several objectives. Enhance operational efficiency. Improve customer experience. Streamline marketing strategies. Optimize resource utilization. Anticipate and mitigate potential risks. Interdisciplinary research at the interface of data science, strategic management, and technological innovation increasingly supports the feasibility of enterprise decision-making. The interdependent relationship between strategic organizational thinking and advanced technological capabilities is an important area for further research. As digital transformation accelerates, the importance of complex big data in strategic enterprise decision-making will continue to grow. Organizations that invest in cutting-edge technological infrastructure, develop robust data analytics capabilities, and cultivate a data-driven organizational culture will be best positioned to thrive in a dynamic and increasingly complex global business environment. This paper provides a holistic review of the current state, challenges, and future opportunities of complex big data in enterprise decision-making for researchers, technologists, and business leaders seeking to understand and leverage this transformative technological paradigm