International Journal of Informatics and Communication Technology (IJ-ICT)
Not a member yet
494 research outputs found
Sort by
Mapping academic outcomes to student routines using machine learning: a data-driven approach
Get PDFIn today’s environment, students often struggle with time management and dealing with emotions like frustration and anxiety, which may have an adverse impact on their academic achievement. This research aims to enhance time management and educational support for college students by leveraging demographic characteristics and performance in specific assignments to develop a predictive model for academic performance. The study evaluates various regression algorithms to identify the most accurate method for predicting students’ semester grade point average (SGPA) based on their activities. This predictive model aims to optimize students’ learning experiences and mitigate challenges such as frustration and anxiety. The findings highlight the potential of personalized educational assistance in improving student learning outcomes. Various machine learning algorithms, including decision trees, support vector regression (SVR), ridge regression, lasso regression, XGBoost, and gradient boosting, were implemented in Python for this study. Results show that XGBoost achieved the lowest root mean square error (RMSE) of 9.39 with a 60:40 data split ratio, outperforming other algorithms, while decision trees exhibited the highest RMSE. The findings emphasize the potential of personalized educational assistance to improve learning outcomes by helping students adjust study habits to address weaknesses and reduce anxiety. Future studies can explore integrating real-time data and additional features such as emotional wellbeing and extracurricular activities to further improve the model’s predictive capabilities
Design and development of machine learning-based web application for oil palm yield prediction
Get PDFThe prediction of crop yields is influenced by various factors such as weather conditions, agronomic practices, and management strategies. Accurately predicting oil palm yield is crucial for sustainable production, as it plays a significant role in global food security. Challenges such as climate change and nutrient deficiencies have adversely affected yields, highlighting the necessity for a specialized web application tailored to the oil palm industry. This study presents a machine-learning-based web application that utilizes a deep learning model to estimate oil palm yields by integrating key parameters, including weather, agronomy, and satellite data. The application features a user-friendly interface and a dashboard for comparing predicted and actual yields, enhancing user engagement and facilitating collaboration among stakeholders. By deploying this tool on the cloud, plantation managers can make informed decisions early in the yield prediction process, ultimately improving plantation management and profitability. This web application is designed to provide valuable insights to stakeholders, contributing to effective decision-making in the oil palm sector
Dynamic monitoring for enhancing QoS and security in distributed systems
Get PDFDistributed systems are integral to modern digital infrastructure, supporting communication and data exchange across various sectors. Ensuring security while maintaining quality of service (QoS) in such environments presents a significant challenge. This study introduces a dynamic network monitoring system (DNMS) that incorporates adaptive monitoring mechanisms and dynamic security metrics to safeguard distributed systems. The proposed architecture utilizes an event analyzer (EA) to evaluate and classify system events based on criticality, enabling secure transmission decisions and efficient threat detection. Experimental evaluations demonstrate the DNMS achieves a low processing overhead of 12%, supports a high data handling capacity of 5,000 requests per second, and maintains a latency of just 150 milliseconds. Additionally, it ensures strong compliance with regulatory standards-achieving 95% alignment with GDPR and 97% with ISO 27001- and high threat detection accuracy, with 98% for phishing, 94% for malware, and 96% for insider threats. These results confirm the framework’s effectiveness in enhancing adaptive security, offering scalable and regulation-compliant solutions for complex distributed environments
Development of machine learning techniques for automatic modulation classification and performance analysis under AWGN and fading channels
Get PDFAutomatic modulation classification (AMC) is essential in modern wireless communication for optimizing spectrum usage and adaptive signal processing. This study explores the use of various machine learning (ML) methods for AMC, focusing on their performance in additive white Gaussian noise (AWGN) and fading channels. This study evaluates of ML classifiers such as support vector machines (SVM), K-nearest neighbors (KNN), decision trees (DT), and ensemble methods with a dataset spanning signalto-noise ratios (SNRs) from -30 dB to +30 dB. Higher-order statistical features including moments and cumulants are used to train the classifiers for AMC. Performance is measured in terms of classification accuracy and computational efficiency across different SNR levels. The findings show that linear SVM, fine KNN, and fine trees consistently achieved high classification accuracy, even at low SNRs. From the analysis, it is observed that linear SVM and fine KNN achieve over 96% accuracy at 0 dB SNR. These classifiers demonstrate significant robustness, maintaining performance in challenging noise conditions. The research highlights the promise of ML techniques in improving AMC, providing a detailed comparison of classifiers and their strengths
A meta-learning framework for leaf disease detection using vision transformer-based feature extraction, PCA, and tuned SVM classifier
No full textA hybrid meta-learning approach is proposed for effective leaf disease detection by integrating vision transformer (ViT), principal component analysis (PCA), and support vector classifier (SVC). The objective of this study is to accurately classify plant leaf conditions into three categories: healthy, angular leaf spot, and bean rust. The dataset consists of 1,167 labeled leaf images, divided into training (974 images), validation (133 images), and testing (60 images) sets. A pretrained ViT model is employed for feature extraction, producing a feature vector of shape (974, 64) for the training data. To mitigate the curse of dimensionality and improve classification performance, PCA is applied, reducing the features to 41 principal components while retaining 98% of the original variance and accuracy 97.85%. For the classification task, an SVC is used and fine-tuned using the Optuna hyperparameter optimization framework to enhance accuracy and generalization. A distributed deep learning strategy is incorporated to accelerate training and scale computation, while the tf.data API is utilized to construct an efficient and scalable data input pipeline. The hybrid model demonstrates strong classification performance on the test set, indicating that combining deep transformer-based feature extraction with dimensionality reduction and optimized classical machine learning classifiers is effective for plant disease identification. This approach offers a robust and computationally efficient solution for precision agriculture, enabling automated and accurate leaf disease diagnosis and supporting early intervention strategies in crop management
Integrating smart technologies for sustainable crop management in hydroponics
Get PDFHydroponics has become a game-changing technique in agriculture's constantly changing terrain, upending traditional soil-based farming. The smart hydroponics management system, a cutting-edge method intended to maximize plant development and resource use, is presented in this study. The approach aims to push the limits of conventional farming, drawing inspiration from sustainable horticultural concepts as well as the principles described in Howard M. Resh's book on hydroponic production. This abstract integrates cuttingedge sensor technology and automation methodologies to capture the core of the smart hydroponics management system. It presents the system as a complete answer to the problems facing modern agriculture, rather than just a technique of cultivation. By drawing comparisons with seminal works in computer vision, the unique character of the system is highlighted, demonstrating a dedication to advanced and flexible agricultural techniques
DeepRetina: a multimodal framework for early diabetic retinopathy detection and progression prediction
Get PDFDiabetic retinopathy (DR) remains one of the top causes of vision loss globally, and early detection and accurate progression prediction are critical in its management. This paper introduces DeepRetina, a deep learning framework that integrates state-of-the-art multimodal retinal imaging techniques with patient-specific clinical data for the improved diagnosis and prognosis of DR. DeepRetina harnesses cutting-edge convolutional neural networks (CNNs) and attention mechanisms to jointly analyze optical coherence tomography (OCT) scans and fundus photographs. The architecture further includes a temporal module that investigates the longitudinal changes in the retina. DeepRetina fuses these heterogeneous data sources with patient clinical information in pursuit of early detection of DR and provides personalized predictions for the progression of the disease. We use a specially designed CNN architecture to process high-resolution retinal images, coupled with a self-attention mechanism that focuses on the most relevant features. This recurrent neural network (RNN) module empowers it to integrate time-series data that captures the evolution of retinal abnormalities. Another neural network branch considering patientspecific clinical data, such as demographic information, medical history, and laboratory test results, was taken into account and concatenated with the imaging features for a holistic analysis. DeepRetina achieved 95% sensitivity, 98% specificity for early DR detection, and a 0.92 area under the curve (AUC) for 5-year progression prediction, outperforming existing methods
A comparative study and design investigation: scalable magnitude comparators across technology nodes
Get PDFIn recent times, the convergence of innovative design technologies such as very large-scale integration (VLSI), cadence design systems, and fieldprogrammable gate array (FPGA) has become crucial to address the growing demand for enhanced efficiency, scalability, and reduced power consumption in electronic designs. This paper introduces a novel approach to designing non-pipelined and pipelined scalable magnitude comparators (MCs), which integrates 4-bit MCs. The frontend implementation of the MCs is achieved using quartus prime, an FPGA board. The backend implementation is done using cadence design system, evaluated across the three distinct CMOS technology nodes. The literature review highlights the influence of technology scaling on area, power consumption, and propagation delay, analyzing various comparator designs and their associated trade-offs. The results provide valuable insights into the design and optimization of MCs for future applications in image processing and nano computing
Digital platforms and cloud computing for smart cities: a review
Get PDFThe rapid urbanization of the modern world initiated the emergence of digital cities, where advanced technologies converge to optimize urban living and address the limitations of a rapidly growing population. Central to this transformation are digital platforms and cloud computing. These interconnected technologies aid in shaping the future of urban landscapes, fostering sustainability, efficiency, and improved quality of life. Digital platforms serve as the backbone of smart cities, enabling seamless integration and management of various urban services and systems. One significant application of digital platforms in smart cities is the implementation of intelligent transportation systems (ITS). By integrating real-time traffic data, public transit information, and ride-sharing services, these platforms facilitate efficient transportation management, reduce congestion, and decrease carbon emissions. Cloud computing serves as a key enabler for managing the massive data flows generated by smart city infrastructures. The scalability and flexibility offered by cloud-based solutions allow cities to manage their resources efficiently and access computing power on demand without the need for extensive physical infrastructure. Cloud computing enhances smart city development by enabling collaborative data access and interaction among diverse stakeholders, from government agencies to private firms and residents
Neurophysiological impact of Vedic chanting on human brainwaves: a spectral electroencephalogram analysis using Gabor transform
Get PDFElectroencephalogram (EEG) analysis explores brainwave changes resulting from Vedic chanting (VC) in this experimental study. In this study participants received Vedic recitations from the Rig Veda (RV), Yajur Veda (YV), Sama Veda (SV), and Atharva Veda (AV) which were evaluated through alpha wave (8-12 Hz) measurement to evaluate relaxation response effects known to cause cognitive relaxation and mindfulness. The research captured EEG signals from twenty participants who belonged to four age categories between twenty and fifty years using a fourteen-channel EEG recording system. The signals underwent wavelet-based denoising procedures and Gabor transform (GT) enabled their spectral analysis. Scientists calculated the relaxation factor (RF) for understanding Vedic chant effects on human beings. Vedic Sama provided maximum relaxation effects leading to a 25% RF enhancement whereas YV produced a 20% increase and RV generated 15% enhancement and AV yielded 10% relaxation. The participants between 30 and 45 years old experienced the largest relaxation effects yet their left-brain hemisphere enhanced alpha waves stronger than their right brain region. The statistical methods supported that these results showed meaningful variations. Neural relaxation results from VC practice according to research evidence which shows SV provides the most powerful relaxation effects