International Journal on Recent and Innovation Trends in Computing and Communication
Not a member yet
8613 research outputs found
Sort by
E-Commerce Dynamics: Identifying the Behavioral Triggers in Online Shopping Among College Students
Full text linkThis research investigates the influence of marketing stimuli, website design, and emotional factors on impulsive and intentional online shopping behaviors among college students. Key findings indicate that discounts and promotions serve as the most significant triggers for both impulse and intentional purchases, while product recommendations, although impactful, demonstrate a lesser influence. Positive emotions mediate the relationship between discounts and impulse purchases, emphasizing the critical role of emotional engagement. Website design elements, such as visual appeal and ease of navigation, show minimal direct impact on purchase behavior. A cluster analysis revealed two consumer segments: one responsive to aggressive marketing and another preferring personalized strategies. These insights underline the importance of combining promotions, personalized recommendations, and emotionally engaging marketing tactics to effectively target diverse consumer preferences and enhance sales outcomes
Lora based Manhole Cover Status and Toxic Gas Monitoring with IoT Technologies
Full text linkCurrently smart city management is of critical importance in the urban infrastructure of growing countries. In this context, it is necessary to make the underground manholes and sewage systems smart and traceable. Open manhole covers pose security risks which may lead to various accidents and damages. Gas leaks, on the other hand, pose serious risks and endanger human health. In this study, a wireless device was developed to monitor the condition of manhole covers and track gas levels within them. This device, automatically monitors manhole gases, detects gas leaks, checks the status of the covers and through the Internet of Things (IoT) system it is connected to provides alarms to inform the authorities. The sensors used inside the device can detect the presence of toxic gases, thereby contributing to occupational health and environmental safety
Deep Learning Techniques for Image Recognition and Classification
Full text linkConvolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and hybrid models are the main topics of this research study on deep learning approaches for image recognition. CNNs are very accurate and efficient when it comes to static images; RNNs are good at sequential data jobs; GANs work well for generative applications; and Hybrid Models work better when it comes to complex tasks. Despite their complexity, hybrid models have potential, as demonstrated by a comparative analysis. To advance image recognition technology, future studies should improve these models' efficacy, stability, robustness, and real-time capabilities
Effect of Aggregate Gradation on Hydraulic Properties of Pervious Concrete and Fly Ash as SCM
Full text linkThis paper deals with the hydraulic properties of pervious concrete with the effect of coarse aggregate gradation and fly ash as SCM. Initially, mixes were categorized into three (i.e., PV1, PV2, and PV3) with 16.5-12mm, 12-10mm and 10-4.75mm, respectively. In each group, cement was replaced from 0 to 30%, which was about twenty-one mixes, including conventional mixes prepared with a constant w/c ratio as 0.35 and superplasticizer at 1%. Samples were tested for compressive strength and hydraulic properties like porosity and permeability. Permeability was tested against the constant head method and variable head method. The results show that the hydraulic properties of pervious concrete enhanced with the usage of larger-sized aggregates. Fly ash effects adversely on the percolation capacity of pervious concrete
Artificial Intelligence (AI) Based Data Center Networking
Full text linkAI data center networking is transforming with a great pace as per the requirement of present day computation arena. In this given research paper, the subject of focus is on Artificial Intelligence and Data Center Networking and associated trends and issues. There are plans of using AI technologies within data centers in a bid to optimize the flow of networks in resource utilization and other parameters. This also entails use of AI based algorithms for real time traffic control, health check and workload allocation in order to have a solid and unshakeable network. Thus, the integration of the computing continuum also introduces difficult issues like the ability to scale the fabric efficiently, security, and the necessity of dedicated hardware accelerators to handle AI workloads optimally. These are complex problems that need novel approaches to the architecture of the networks, SDN architecture and AI focused analytics to have efficient and adaptive AI data center networking. Of particular importance to the field of AI data center networking is the edge computing and real-time data processing breakthroughs. This technology smartly integrates real-time analyses at the network edge at an organization’s data centers, and can decrease the amount of time needed to respond to applications that necessitate quick decision making such as Self-driving vehicles and industrial IoT. It is lest felt in this research work that AI can make a difference in changing the conventional Data center networking into a dynamic architecture to meet a modern digital world. Futuristic advancements of artificial intelligence and development for research will promote the complexity and cohesion between data centers and networking applications in the computational world
Multi Level - Secret Data Embedding in Audio Steganography
Full text linkThis paper presents a novel methodology for the secure and efficient concealment of data in audio signals. The approach combines Spectrogram Pixel Value Modification (SPVM) with RSA encryption and compression using the Discrete Wavelet Transform (DWT). The ultimate goal of this proposed method is to augment data security and capacity while preserving the quality of the audio signal.
The proposed methodology initiates with RSA encryption, where the message to be obscured is encrypted using the recipient's public key, ensuring confidentiality during the data embedding process. The data is then compressed using DWT, which decomposes the signal into wavelet coefficients that provide both frequency and time localization.
To conceal the compressed and encrypted data, the wavelet coefficients are transformed into a spectrogram representation using an appropriate Fourier transform. The SPVM method is then employed to subtly modify the pixel values of the spectrogram by incorporating binary values derived from the compressed and encrypted data. This ensures seamless integration of hidden information without compromising the audio signal's integrity.
To retrieve the concealed message, the process is reversed. The SPVM method is reverted to extract the modified pixel values from the spectrogram. The extracted pixel values are converted back into wavelet coefficients, and the inverse DWT is applied to obtain the compressed and encrypted data. Finally, the recipient's private key is used to decrypt the data, revealing the original message.
The experimental results demonstrate the practicality and effectiveness of the proposed approach, showcasing its potential in secure data hiding applications, audio watermarking, and confidential communication. The combination of SPVM, RSA encryption, and DWT compression provides a comprehensive solution for robust and secure data embedding while ensuring high audio quality
Student Attendance Monitoring Using Android Application
Full text linkIn today’s world, a paper-based approach is used for marking attendance, where students sign attendance sheets. This data is then manually entered into the system. Managing student attendance during lectures is a difficult task, which becomes even more challenging during the report generation phase. Manual computation produces errors and wastes a lot of time.
The automated attendance Android application aims to provide a new, quick, and easy way of registering attendance
A Study on Electromyography Signal as a Controller
Full text linkHuman computer interaction (HCI) is the study of interfaces between human and computer. When an input keyboard is pressed the output is displayed in the monitor is a simple example of human and computer interaction. World Wide Web is yet another example of HCI. HCI is everywhere and has become an important aspect in human life. HCI have many subfields and one among them is the study of biosignals. Signals that are generated from living body during muscle contraction, eye movement, brain signal are biosignals and these signals have potential for developing an interface for human computer interaction. There are many such bio electric signals which can be made to use for developing interface and that can be done by acquiring these signals which will form a linkage with the computer technique. These types of signals are brain signal called Electroencephalogram (EEG), heart signal Electrocardiogram (ECG), eye movement signal Electrooculogram (EOG) and muscle signalElectromyogram (EMG). The paper focuses on the study of muscle signal controller as HCI, EMG signals are captured during contraction of a skeletal muscle. The signal is then amplified and converted into usable signals that will be fed as an input to computer and can be used for controlling certain devices
Identification of Security Issues and Finding their Solution in Cloud Computing
Full text linkThe advent of Cloud Computing has simplified on-demand access to IT services including data storage and administration. In addition, it seeks to secure systems and make them functional. With these benefits, there are significant security constraints for cloud providers. When it comes to cloud computing, one of the biggest obstacles is ensuring the safety of data and services. Considering this, several solutions have been put into place to boost cloud security by keeping an eye on everything from resources to services to networks to identify and stop intrusions as soon as they occur. The term "Intrusion Detection System" (IDS) refers to an improved technique used to regulate network traffic and identify abnormal activity. This paper presents the identification of Security Issues and Finding their Solution in Cloud Computing using machine learning techniques including Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (KNN), Multi-Layer Protocol (MLP). This model is trained and evaluated using NSL-KDD dataset. The experimental findings show the highest accuracy of 93.5% with the use of SVM model. As a result, the achieved results demonstrate strong performance concerning Accuracy, Precision, Recall, and F1-Score when compared to recent studies
A Deep Learning-Based Mobile Application for Classifying Rice Crop Diseases in Labo, Camarines Norte
Full text linkThe primary concern of the rice farming community is the early detection of rice crop disease. Rice crop disease can be detected with high accuracy with the availability of advanced digital cameras and smartphones to improved image acquisition modes and deep learning methods such as convolutional neural networks (CNN). This study used a qualitative approach employing focus group discussions with selected farmers and an online meeting with the Department of Agriculture (DOA). Also compared and evaluated different optimizers using several optimization techniques namely Stochastic Gradient Descent with Momentum (SGDM), Root Mean Squared Propagation (RMSProp), Nesterov-accelerated Adaptive Moment Estimation (Nadam), and Adaptive Moment Estimation (Adam) in different dataset partitioned by 80/20%, 60/40%, 50/50%, 40/60%, and 20/80% using cv2 module from OpenCV library. Furthermore, presents the hardware and software to developed a free, easy-to-use and widely accessible mobile application that can efficiently and accurately diagnose 22 types of diseases and a healthy leaf sample. The experiment results show that Nadam optimizer achieve a maximum accuracy of 97.67-100.00% in the 80/20 partition, 88.17-100% in the 60/40 partition, 84.93-100% in the 50/50 partition, 64.67-100% in the 40/60 partition, and 37.03-99.90% in the 20/80 dataset partition. Therefore, the android application “Rice Crop Diseases Classification” can accurately classify rice diseases using Nadam optimizers including healthy rice. Addiditonally, despite employing various dataset partitioning methods, it achieves the highest accuracy from both low and high records using 80 by 20% dataset partitioned