International Journal of Intelligent Systems and Applications (IJISA)
ISSN: 2074-904X (Print)
ISSN: 2074-9058 (Online)
DOI: https://doi.org/10.5815/ijisa
Website: https://www.mecs-press.org/ijisa
Published By: MECS Press
Frequency: 6 issues per year
Number(s) Available: 143
IJISA is committed to bridge the theory and practice of intelligent systems. From innovative ideas to specific algorithms and full system implementations, IJISA publishes original, peer-reviewed, and high quality articles in the areas of intelligent systems. IJISA is a well-indexed scholarly journal and is indispensable reading and references for people working at the cutting edge of intelligent systems and applications.
IJISA has been abstracted or indexed by several world class databases: Scopus, Google Scholar, Microsoft Academic Search, CrossRef, Baidu Wenku, IndexCopernicus, IET Inspec, EBSCO, JournalSeek, ULRICH's Periodicals Directory, WorldCat, Scirus, Academic Journals Database, Stanford University Libraries, Cornell University Library, UniSA Library, CNKI Scholar, ProQuest, J-Gate, ZDB, BASE, OhioLINK, iThenticate, Open Access Articles, Open Science Directory, National Science Library of Chinese Academy of Sciences, The HKU Scholars Hub, etc..
IJISA Vol. 18, No. 3, Jun. 2026
REGULAR PAPERS
KL-triggered Continual Adaptation for Nonstationary Resource Allocation: An Off-policy Actor–critic Approach with Nash Social Welfare
This paper proposes a drift-aware off-policy deterministic actor–critic framework for constrained continuous resource allocation in non-stationary environments. Feasible allocations are ensured by a simplex-parameterized policy using softmax normalization with budget scaling, avoiding projection or Lagrangian tuning. The reward integrates Nash social welfare via mean log-utility, efficiency, fairness, and constraint-violation penalties with adaptive weights. To improve sample efficiency, we adopt prioritized experience replay based on TD error and state novelty. Non-stationarity is detected by KL divergence between recent and historical state-visitation distributions; detected drift triggers buffer refresh and incremental fine-tuning, while Elastic Weight Consolidation mitigates catastrophic forgetting. Experiments across six application-motivated domains (food, medical, housing, education services, employment support, and elderly care) demonstrate improved utilization and welfare with reduced inequality and low decision latency compared with optimization, heuristic, and DRL baselines. Results are reported over multiple runs with mean ± standard deviation and corrected significance tests.
[...] Read more.Advances in Multimodal Biometric Authentication: A Classifier Fusion and Deep Learning Perspective
The rapid advancements in deep learning and classifier fusion techniques offer promising solutions to enhance the accuracy and robustness of biometric authentication systems in this paper we propose the integration of these methodologies, specifically in multimodal biometric systems that utilize face and fingerprint recognition. The research investigates various deep learning architectures, highlighting their effectiveness in processing diverse biometric datasets. Additionally, it examines classifier fusion techniques, which combine multiple classifiers to improve person identification performance. A significant focus of this research is on spoofing and anti-spoofing measures. Biometric systems, especially those involving facial and fingerprint recognition, are vulnerable to spoofing attacks such as the use of photographs, videos, or artificial fingerprints to impersonate legitimate users. We developed various anti-spoofing strategies that are integrated into the biometric authentication process to mitigate these risks. These include techniques like texture analysis, motion analysis, and liveness detection, which help differentiate between genuine biometric traits and spoofed samples. We benchmarked a comparative analysis of deep learning models and classifier fusion, demonstrated their strengths, weaknesses, and best practices. Additionally, performance evaluations focus on key metrics such as accuracy, computational efficiency, scalability, and the system’s ability to resist spoofing attacks. Ultimately, the paper emphasizes the potential of these advanced techniques to revolutionize biometric systems, with a particular focus on future research directions for optimizing these methodologies, particularly in the context of improving robustness against spoofing and enhancing the overall security of biometric authentication systems. overall system Equal Error Rate (EER), the True Acceptance Rate at a specified False Acceptance Rate (e.g., TAR @ 0.1% FAR), and the accuracy of the anti-spoofing module.
[...] Read more.Color Difference Histogram Capsule Network (CDH-CapsNet) for Plant Disease Recognition
Plant diseases adversely affect the quantity and quality of food production, contributing to food insecurity. Prompt identification, diagnosis, and intervention can significantly minimize economic and ecological losses. By reducing the use of agrochemicals through timely disease detection, the environmental impact can be mitigated. Traditional manual methods for recognizing plant diseases are prevalent but are often limited, time-consuming, costly, and ineffective. Convolutional Neural Network (CNN) architectures have demonstrated excellent capabilities in detecting plant diseases and other complex images, but they lack spatial or rotational invariance and require extensive data in various forms to be effective. This is typically achieved by applying data augmentation, as the datasets in the field of agriculture are often limited. Capsule Networks address CNN's limitations, but their encoder network is inefficient at feature extraction, hence does not perform well on complex images. This study seeks to modify and improve CapsNet by combining a Color Difference Histogram (CDH) with a Capsule Network that includes extra two convolutional, three max pooling layers, three batch normalization layers, and reduced the primary capsule channels in the original CapsNet to 16 from 32 for efficient plant disease detection in apples, bananas, grapes, corn, mangoes, pepper, potatoes, rice, tomato, and on the CIFAR-10 dataset. This approach improved the original CapsNet in terms of validation accuracies by 5.83%, 14.82%, 5.9%, 4.42%, 20.87%, 40.12%, 4.41%, 0.76%, 9.49%, and 13.97% on apple, banana, grape, corn, mango, pepper, potato, rice, tomato, and CIFAR-10 datasets respectively. The CDH-CapsNet achieved better results in terms of accuracy, sensitivity, F1-Score, precision, specificity, Receiver Operating Characteristic (ROC), Precision-Recall (PR) values, parameter count, and disk size, surpassing the original CapsNet and CapsNet models presented in available research. The original CapsNet and CDH-CapsNet exhibited strong performance on datasets such as the Rice dataset, possibly because of high-quality images and low intra-class variance. The findings suggest that this efficient and computationally less demanding supportive tool can significantly enhance plant disease classification by offering a lightweight, scalable solution that can be adapted for field use in resource-constrained settings, contributing to efforts aligned with the SDG 2 goal. However, environmental factors such as inconsistent lighting and complex backgrounds encountered in practical
scenarios may affect the model's effectiveness. Subsequent studies will aim to overcome these issues and broaden the model's applicability.
Binary Particle Swarm Optimization with RAF Based Feature selection in Convolutional Network for Cardiovascular Disease Classification
Accurate prediction of cardiovascular disease (CVD) is essential for timely intervention and improved patient outcomes. This paper presents a hybrid model, BPSO-RAF-CNN that integrates Binary Particle Swarm Optimization (BPSO) with a Regularized Accuracy-Based Fitness Function (RAF) and a Convolutional Neural Network (CNN) to improve prediction performance through optimized feature selection. The approach begins with feature engineering on cardiovascular data, followed by BPSO-RAF to identify the most important, predictively salient and compact feature subset, lowering dimensionality and improving generalization. These selected features are then fed into a CNN for final classification. Extensive experiments demonstrate that BPSO-RAF-CNN outperforms traditional classifiers (Logistic Regression, SVM, Naive Bayes, Decision Tree, Random Forest) achieving an accuracy of 87.05%, Precision 89.71%, Recall 83.77%, F1-score of 86.05%. And Specificity 90.22%, all with a standard deviation 0.5%. The model also shows good performance across 10-fold cross-validation, indicating strong generalization.
[...] Read more.A Hybrid Active and Semi-Supervised Learning Framework for Classification with Minimal Labeled Data
Modern machine learning models typically require large amounts of precisely labeled data to perform effectively. However, obtaining such labels is time-consuming and costly, especially in specialized domains such as medical image analysis and document classification, where unlabeled data is abundant but expert annotation is scarce. This paper addresses the problem of learning from very few labeled examples by jointly leveraging weak supervision, active learning (AL), and semi-supervised learning (SSL). A hybrid framework is proposed in which a small set of informative samples is actively selected for manual annotation using an entropy-based acquisition function combined with weak label disagreement scoring, while a large pool of unlabeled or weakly labeled data is exploited through SSL based on the FixMatch algorithm. The approach iteratively corrects noisy labels and refines the model with minimal human involvement. The framework is evaluated using a ResNet-18 classifier on the CIFAR-10 benchmark dataset and is compared against two baselines: pure active learning and pure semi-supervised learning. Each method is run independently across three random seeds at the key active learning rounds, and accuracy is reported as mean ± standard deviation. Across three independent seeds, the hybrid framework consistently leads both baselines at intermediate labelling budgets, with the largest absolute gap at Round 15 (+1.27 percentage points over pure active learning, +1.35 percentage points over pure SSL). The framework also offers a clear label-efficiency advantage: at Round 15, with |D_L | = 6500 labels, the hybrid method already reaches 0.6792 ± 0.0097 test accuracy – exceeding the accuracies that pure active learning (0.6730 ± 0.0139) and pure SSL (0.6687 ± 0.0056) attain only at Round 20 with |D_L | = 7000. By Round 20 all three methods saturate near a common data ceiling, indicating that the integrated use of weak supervision, active learning, and consistency-based SSL is most valuable when the annotation budget is genuinely constrained.
[...] Read more.Automated Brain Tumor Detection Using Hybrid CNN - Models from T1 – weighted MRI Scans
Detecting and classifying brain tumours is essential for early diagnosis and effective treatment planning, significantly enhancing patient outcomes. This research presents a deep learning-based approach that utilizes T1-weighted MRI data to automatically identify and classify brain tumours, distinguishing between normal and abnormal cases. The proposed methodology consists of four key steps: pre-processing, segmentation, feature extraction, and classification. In the pre-processing stage, image quality is enhanced using Contrast Limited Adaptive Histogram Equalization (CLAHE) to boost contrast, along with a Gaussian filter to reduce noise. Tumour segmentation is achieved through thresholding, which effectively isolates the tumour regions. For feature extraction, a Convolutional Neural Network (CNN) captures high-dimensional features that are vital for classification. To accurately differentiate between normal and abnormal tumours, an Artificial Neural Network (ANN) is employed for classification. The effectiveness of the proposed technique is evaluated based on performance metrics such as time, accuracy, and peak signal-to-noise ratio (PSNR). The obtained parameters are compared with existing techniques to highlight improvements in detection and classification performance. Among the tested images, the best result achieved a PSNR of 13.015 dB, an accuracy of 99.231%, and a computational time of 1.267 ms, demonstrating the efficiency and reliability of the proposed method for brain tumor detection and classification. Overall, this approach provides an effective and automated method for detecting brain tumours, aiding in clinical decision-making and diagnosis.
[...] Read more.Hybrid Machine Learning Approaches for DNA Classification: A Stacking Classifier Perspective
This paper presents a hybrid machine learning model for the classification of DNA sequences by combining different machine learning algorithms, including K-Nearest Neighbors (KNN), Support Vector Classifier (SVC), Decision Tree, Random Forest, Light Gradient Boosting Machine (LGBM), and XGBoost (XGB). This model has been developed using the stacking ensemble method, associated with a majority voting mechanism to achieve improved overall classification accuracy. In this study, the Promoter Gene Sequences dataset from the UCI Machine Learning Repository was used to concentrate on classifying promoter versus non-promoter sequences. The results indicated an accuracy of 96.25%, showcasing the hybrid model’s ability to classify DNA sequences effectively. This research provides valuable insights into ensemble machine-learning techniques in DNA classification, with possible applications in genomics research, medical diagnostics, agricultural biotechnology, and forensic science. The hybrid model’s thriving implementation demonstrates the potential for more accurate and reliable DNA sequence classification methods.
[...] Read more.Smart Agriculture: Leveraging Machine Learning for Crop Recommendation, Fertilizer Optimization, and Yield Prediction
Agriculture remains the primary occupation for a majority of the Indian population, yet granting much emphasis to subjective decision-making of traditional farming texts will lead to inefficiency, wastage of resources, and decrease in crop yields. To mitigate these problems, we are in an acute need for technology-based and data-oriented methods that may optimize agricultural practices for sustainable development. The growing demand for sustainable agricultural practices in the face of climate change, soil degradation, and rising food demand presents a significant challenge in India. Small and marginal farmers are almost never given timely and accurate advice on crops and fertilizers, for which the farmers suffer low productivity and the environment its degradation. Herein is outlined a complete suite of machine learning-driven systems to satisfy crop recommendation, fertilizer optimization, and yield prediction needs. The main objective is to generate intelligent, data-driven recommendations based on historical crop data, soil properties, weather data, and crop measurements so that farmers may use these data to make best possible decisions. Random Forest models are utilized to enhance the precision of recommendations, achieving an accuracy of 62.67% for crop and fertilizer recommendation and 98.6% for yield prediction. By giving recommendations based on data and practice, this study hopes to revolutionize traditional agricultural methods and hence improve the farmer's living standards, create employment for others, and push the economy ahead in rural areas, visualizing sustainable agricultural development.
[...] Read more.Stage-wise Sieving with Optimized CNN Ensemble for Enhanced ECG Arrhythmia Detection
Accurate detection of ECG arrhythmias plays a critical role in enabling timely diagnosis and treatment of cardiovascular diseases, which remain the leading cause of mortality worldwide. However, achieving high classification performance remains challenging due to class imbalance, signal variability, and resource constraints in real-time deployments. This study aims to enhance ECG arrhythmia detection accuracy through an optimized ensemble approach combining multiple CNN models with a novel stage-wise sieving strategy.
Methodology: Three lightweight CNN models (ShuffleNet, MobileNet-v2, ResNet-18) were integrated into a multi-stage binary classification framework. Each stage systematically eliminated accurately classified arrhythmia classes. The novelty of the proposed approach lies in introducing a stage-wise sieving strategy that incrementally removes well-classified classes, combined with an optimized ensemble fusion of multiple CNN models guided by metaheuristic optimization techniques to boost performance. Optimization techniques, including Particle Swarm Optimization, Whale Optimization Algorithm, Grey Wolf Optimizer, Ant Colony Optimization, and Firefly Algorithm, were applied to improve model fusion. The approach was validated using combined public datasets (PTB-XL, MIT-BIH, and Shaoxing ECG databases). Results: The proposed stage-wise sieving ensemble significantly improved overall classification accuracy by 17.95%, reaching 96.29% accuracy using the Grey Wolf Optimizer. Classes previously misclassified, such as Conduction Disturbance and Hypertrophy, exhibited accuracy improvements of up to 32.44% and 25.19%, respectively.
Conclusion: The proposed optimized ensemble approach significantly enhances ECG arrhythmia detection performance and demonstrates feasibility for real-time deployment on resource-constrained platforms such as Raspberry Pi.
A Fuzzy Decision Framework for High-Dimensional Course Selection
In this study, a novel decision support model integrating spherical fuzzy sets enhanced with autoencoder-based dimensionality reduction, MEREC weighting, and CODAS ranking methods is proposed for high-dimensional, uncertain multi-criteria decision problems. The spherical fuzzy set structure allows decision makers to express their evaluations using three levels of membership (membership, non-membership, and hesitation). Thus, it produces linguistic evaluations appropriately to the nature of uncertainty. In the numerical analysis, five elective courses, Python Programming, Java Programming, C# Console Programming, Visual Programming with C#, and Web-Based Programming, were evaluated based on 41 selection criteria. The latent structures among these criteria were analyzed using the Autoencoder architecture, yielding 17 latent features with a reconstruction mean squared error of 0.016 as determined by an elbow-based reconstruction loss analysis, indicating negligible information loss beyond this dimension. The weights for these dimensions were objectively calculated using the MEREC method, which is based on the distinctiveness of each dimension in the decision process. The CODAS method was applied to rank the courses and provide decision support using the calculated weights. In the final stage, a comprehensive sensitivity analysis was performed to test the impact of changes in both dimension weights and decision-maker weights on the results Sensitivity analysis further confirmed the robustness of the proposed framework, with the top-ranked alternative preserved under ±10% criteria weight perturbations. The numerical results illustrate the practical applicability of the proposed framework and validate its effectiveness in handling complex evaluation structures. Although the proposed framework is demonstrated through a programming course selection problem, the methodology is generic and can be readily applied to other complex decision-making scenarios involving high-dimensional, uncertain, and interrelated criteria.
[...] Read more.Hybrid TCN-transformer Model with Multi-head Attention for Stock Price Forecasting
In this research, a Temporal Convolutional Network (TCN) is combined with a Transformer model with multi-head attention to present a novel approach to stock price forecasting. The primary objective is to address the challenges of recognizing complex patterns and long-term interdependence inherent in the volatility of financial time series data. By fusing the powerful attention mechanisms of Transformers with the sequential processing capabilities of TCNs, the hybrid model provides a powerful solution. This method performs better than conventional deep learning models, including Long Short-Term Memories and standalone TCNs, according to extensive testing on historical stock market data. The outcomes highlight the efficacy of this approach for trustworthy stock market forecasting by demonstrating notable gains in prediction accuracy and model stability.
[...] Read more.Factorial Design-Based Optimization of Fuzzy Logic Controller Parameters for Autonomous Robot Navigation in Static Environments
This study investigates interaction effects among rule sets, sensor fusion strategies, and membership functions on the navigational performance of a nonholonomic wheeled mobile robot in static, unknown environments using fuzzy logic controller. Employing a 3×3×3 factorial design, factors including rule set size (27, 18, and 14 rules), fusion level (minimal, moderate, and dense), and membership function shape (triangular, trapezoidal, and Gaussian) were varied. Each of the 27 configurations were evaluated in triplicate using a MATLAB/CoppeliaSim co‐simulation, with traversal time as the performance metric. An analysis of variance (ANOVA) revealed that each of the three main factors had a significant impact on traversal time (p < 0.001). Notably, there were also meaningful interactions between rule set size and membership function, as well as between rule set size and sensor fusion (p < 0.01), suggesting that system performance is closely tied to how these parameters are combined. Among the tested configurations, setup with a 14-rule base, Level 2 sensor fusion, and a triangular membership function consistently achieved the fastest average traversal times. These interactions likely arise from computational perceptual trade-offs. Increasing rule set size enhances decision granularity but introduces inference delay, whose effects vary depending on how smoothly membership functions partition the input space and how densely sensor data are fused. In practice, this implies that controller performance depends on achieving a balance between linguistic complexity, sensor integration depth, and fuzzification. The findings therefore emphasize the importance of joint parameter tuning and offer design insight for balancing computational cost against navigational precision in embedded fuzzy logic controllers.
[...] Read more.Analysis of Cyberbullying Incidence among Filipina Victims: A Pattern Recognition using Association Rule Extraction
Cyberbullying is an intentional action of harassment along the complex domain of social media utilizing information technology online. This research experimented unsupervised associative approach on text mining technique to automatically find cyberbullying words, patterns and extract association rules from a collection of tweets based on the domain / frequent words. Furthermore, this research identifies the relationship between cyberbullying keywords with other cyberbullying words, thus generating knowledge discovery of different cyberbullying word patterns from unstructured tweets. The study revealed that the type of dominant frequent cyberbullying words are intelligence, personality, and insulting words that describe the behavior, appearance of the female victims and sex related words that humiliate female victims. The results of the study suggest that we can utilize unsupervised associative approached in text mining to extract important information from unstructured text. Further, applying association rules can be helpful in recognizing the relationship and meaning between keywords with other words, therefore generating knowledge discovery of different datasets from unstructured text.
[...] Read more.Fuzzy Controller Design using FPGA for Sun Tracking in Solar Array System
The output power produced by high-concentration solar thermal and photovoltaic systems is directly related to the amount of solar energy acquired by the System, and it is therefore necessary to track the sun’s position with a high degree of accuracy. This paper presents sun tracking generating power system designed and implemented in real time. A tracking mechanism composed of photovoltaic module, stepper motor ,sensors, input/output interface and expert FLC implemented on FPGA, that to track the sun and keep the solar cells always face the sun in most of the day time. The proposed sun tracking fuzzy controller has been tested using Matlab/Simulink program; the simulation results verify the effectiveness of the proposed controller and shows an excellent result.
[...] Read more.Blockchain with Internet of Things: Benefits, Challenges, and Future Directions
The Internet of Things (IoT) has extended the internet connectivity to reach not just computers and humans, but most of our environment things. The IoT has the potential to connect billions of objects simultaneously which has the impact of improving information sharing needs that result in improving our life. Although the IoT benefits are unlimited, there are many challenges facing adopting the IoT in the real world due to its centralized server/client model. For instance, scalability and security issues that arise due to the excessive numbers of IoT objects in the network. The server/client model requires all devices to be connected and authenticated through the server, which creates a single point of failure. Therefore, moving the IoT system into the decentralized path may be the right decision. One of the popular decentralization systems is blockchain. The Blockchain is a powerful technology that decentralizes computation and management processes which can solve many of IoT issues, especially security. This paper provides an overview of the integration of the blockchain with the IoT with highlighting the integration benefits and challenges. The future research directions of blockchain with IoT are also discussed. We conclude that the combination of blockchain and IoT can provide a powerful approach which can significantly pave the way for new business models and distributed applications.
[...] Read more.Predicting Stock Market Behavior using Data Mining Technique and News Sentiment Analysis
Stock market prediction has become an attractive investigation topic due to its important role in economy and beneficial offers. There is an imminent need to uncover the stock market future behavior in order to avoid investment risks. The large amount of data generated by the stock market is considered a treasure of knowledge for investors. This study aims at constructing an effective model to predict stock market future trends with small error ratio and improve the accuracy of prediction. This prediction model is based on sentiment analysis of financial news and historical stock market prices. This model provides better accuracy results than all previous studies by considering multiple types of news related to market and company with historical stock prices. A dataset containing stock prices from three companies is used. The first step is to analyze news sentiment to get the text polarity using naïve Bayes algorithm. This step achieved prediction accuracy results ranging from 72.73% to 86.21%. The second step combines news polarities and historical stock prices together to predict future stock prices. This improved the prediction accuracy up to 89.80%.
[...] Read more.Data Mining of Students’ Performance: Turkish Students as a Case Study
Artificial neural networks have been used in different fields of artificial intelligence, and more specifically in machine learning. Although, other machine learning options are feasible in most situations, but the ease with which neural networks lend themselves to different problems which include pattern recognition, image compression, classification, computer vision, regression etc. has earned it a remarkable place in the machine learning field. This research exploits neural networks as a data mining tool in predicting the number of times a student repeats a course, considering some attributes relating to the course itself, the teacher, and the particular student. Neural networks were used in this work to map the relationship between some attributes related to students’ course assessment and the number of times a student will possibly repeat a course before he passes. It is the hope that the possibility to predict students’ performance from such complex relationships can help facilitate the fine-tuning of academic systems and policies implemented in learning environments. To validate the power of neural networks in data mining, Turkish students’ performance database has been used; feedforward and radial basis function networks were trained for this task. The performances obtained from these networks were evaluated in consideration of achieved recognition rates and training time.
[...] Read more.Graph Coloring in University Timetable Scheduling
Addressing scheduling problems with the best graph coloring algorithm has always been very challenging. However, the university timetable scheduling problem can be formulated as a graph coloring problem where courses are represented as vertices and the presence of common students or teachers of the corresponding courses can be represented as edges. After that, the problem stands to color the vertices with lowest possible colors. In order to accomplish this task, the paper presents a comparative study of the use of graph coloring in university timetable scheduling, where five graph coloring algorithms were used: First Fit, Welsh Powell, Largest Degree Ordering, Incidence Degree Ordering, and DSATUR. We have taken the Military Institute of Science and Technology, Bangladesh as a test case. The results show that the Welsh-Powell algorithm and the DSATUR algorithm are the most effective in generating optimal schedules. The study also provides insights into the limitations and advantages of using graph coloring in timetable scheduling and suggests directions for future research with the use of these algorithms.
[...] Read more.Sentiment Analysis: A Perspective on its Past, Present and Future
The proliferation of Web-enabled devices, including desktops, laptops, tablets, and mobile phones, enables people to communicate, participate and collaborate with each other in various Web communities, viz., forums, social networks, blogs. Simultaneously, the enormous amount of heterogeneous data that is generated by the users of these communities, offers an unprecedented opportunity to create and employ theories & technologies that search and retrieve relevant data from the huge quantity of information available and mine for opinions thereafter. Consequently, Sentiment Analysis which automatically extracts and analyses the subjectivities and sentiments (or polarities) in written text has emerged as an active area of research. This paper previews and reviews the substantial research on the subject of sentiment analysis, expounding its basic terminology, tasks and granularity levels. It further gives an overview of the state- of – art depicting some previous attempts to study sentiment analysis. Its practical and potential applications are also discussed, followed by the issues and challenges that will keep the field dynamic and lively for years to come.
[...] Read more.Machine Learning for Weather Forecasting: XGBoost vs SVM vs Random Forest in Predicting Temperature for Visakhapatnam
Climate change, a significant and lasting alteration in global weather patterns, is profoundly impacting the stability and predictability of global temperature regimes. As the world continues to grapple with the far-reaching effects of climate change, accurate and timely temperature predictions have become pivotal to various sectors, including agriculture, energy, public health and many more. Crucially, precise temperature forecasting assists in developing effective climate change mitigation and adaptation strategies. With the advent of machine learning techniques, we now have powerful tools that can learn from vast climatic datasets and provide improved predictive performance. This study delves into the comparison of three such advanced machine learning models—XGBoost, Support Vector Machine (SVM), and Random Forest—in predicting daily maximum and minimum temperatures using a 45-year dataset of Visakhapatnam airport. Each model was rigorously trained and evaluated based on key performance metrics including training loss, Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), R2 score, Mean Absolute Percentage Error (MAPE), and Explained Variance Score. Although there was no clear dominance of a single model across all metrics, SVM and Random Forest showed slightly superior performance on several measures. These findings not only highlight the potential of machine learning techniques in enhancing the accuracy of temperature forecasting but also stress the importance of selecting an appropriate model and performance metrics aligned with the requirements of the task at hand. This research accomplishes a thorough comparative analysis, conducts a rigorous evaluation of the models, highlights the significance of model selection.
[...] Read more.Machine Learning in Cyberbullying Detection from Social-Media Image or Screenshot with Optical Character Recognition
Along with the growth of the Internet, social media usage has drastically expanded. As people share their opinions and ideas more frequently on the Internet and through various social media platforms, there has been a notable rise in the number of consumer phrases that contain sentiment data. According to reports, cyberbullying frequently leads to severe emotional and physical suffering, especially in women and young children. In certain instances, it has even been reported that sufferers attempt suicide. The bully may occasionally attempt to destroy any proof they believe to be on their side. Even if the victim gets the evidence, it will still be a long time before they get justice at that point. This work used OCR, NLP, and machine learning to detect cyberbullying in photos in order to design and execute a practical method to recognize cyberbullying from images. Eight classifier techniques are used to compare the accuracy of these algorithms against the BoW Model and the TF-IDF, two key features. These classifiers are used to understand and recognize bullying behaviors. Based on testing the suggested method on the cyberbullying dataset, it was shown that linear SVC after OCR and logistic regression perform better and achieve the best accuracy of 96 percent. This study aid in providing a good outline that shapes the methods for detecting online bullying from a screenshot with design and implementation details.
[...] Read more.Non-Functional Requirements Classification Using Machine Learning Algorithms
Non-functional requirements define the quality attribute of a software application, which are necessary to identify in the early stage of software development life cycle. Researchers proposed automatic software Non-functional requirement classification using several Machine Learning (ML) algorithms with a combination of various vectorization techniques. However, using the best combination in Non-functional requirement classification still needs to be clarified. In this paper, we examined whether different combinations of feature extraction techniques and ML algorithms varied in the non-functional requirements classification performance. We also reported the best approach for classifying Non-functional requirements. We conducted the comparative analysis on a publicly available PROMISE_exp dataset containing labelled functional and Non-functional requirements. Initially, we normalized the textual requirements from the dataset; then extracted features through Bag of Words (BoW), Term Frequency and Inverse Document Frequency (TF-IDF), Hashing and Chi-Squared vectorization methods. Finally, we executed the 15 most popular ML algorithms to classify the requirements. The novelty of this work is the empirical analysis to find out the best combination of ML classifier with appropriate vectorization technique, which helps developers to detect Non-functional requirements early and take precise steps. We found that the linear support vector classifier and TF-IDF combination outperform any combinations with an F1-score of 81.5%.
[...] Read more.Analysis of Cyberbullying Incidence among Filipina Victims: A Pattern Recognition using Association Rule Extraction
Cyberbullying is an intentional action of harassment along the complex domain of social media utilizing information technology online. This research experimented unsupervised associative approach on text mining technique to automatically find cyberbullying words, patterns and extract association rules from a collection of tweets based on the domain / frequent words. Furthermore, this research identifies the relationship between cyberbullying keywords with other cyberbullying words, thus generating knowledge discovery of different cyberbullying word patterns from unstructured tweets. The study revealed that the type of dominant frequent cyberbullying words are intelligence, personality, and insulting words that describe the behavior, appearance of the female victims and sex related words that humiliate female victims. The results of the study suggest that we can utilize unsupervised associative approached in text mining to extract important information from unstructured text. Further, applying association rules can be helpful in recognizing the relationship and meaning between keywords with other words, therefore generating knowledge discovery of different datasets from unstructured text.
[...] Read more.Graph Coloring in University Timetable Scheduling
Addressing scheduling problems with the best graph coloring algorithm has always been very challenging. However, the university timetable scheduling problem can be formulated as a graph coloring problem where courses are represented as vertices and the presence of common students or teachers of the corresponding courses can be represented as edges. After that, the problem stands to color the vertices with lowest possible colors. In order to accomplish this task, the paper presents a comparative study of the use of graph coloring in university timetable scheduling, where five graph coloring algorithms were used: First Fit, Welsh Powell, Largest Degree Ordering, Incidence Degree Ordering, and DSATUR. We have taken the Military Institute of Science and Technology, Bangladesh as a test case. The results show that the Welsh-Powell algorithm and the DSATUR algorithm are the most effective in generating optimal schedules. The study also provides insights into the limitations and advantages of using graph coloring in timetable scheduling and suggests directions for future research with the use of these algorithms.
[...] Read more.Data Mining of Students’ Performance: Turkish Students as a Case Study
Artificial neural networks have been used in different fields of artificial intelligence, and more specifically in machine learning. Although, other machine learning options are feasible in most situations, but the ease with which neural networks lend themselves to different problems which include pattern recognition, image compression, classification, computer vision, regression etc. has earned it a remarkable place in the machine learning field. This research exploits neural networks as a data mining tool in predicting the number of times a student repeats a course, considering some attributes relating to the course itself, the teacher, and the particular student. Neural networks were used in this work to map the relationship between some attributes related to students’ course assessment and the number of times a student will possibly repeat a course before he passes. It is the hope that the possibility to predict students’ performance from such complex relationships can help facilitate the fine-tuning of academic systems and policies implemented in learning environments. To validate the power of neural networks in data mining, Turkish students’ performance database has been used; feedforward and radial basis function networks were trained for this task. The performances obtained from these networks were evaluated in consideration of achieved recognition rates and training time.
[...] Read more.Predicting Stock Market Behavior using Data Mining Technique and News Sentiment Analysis
Stock market prediction has become an attractive investigation topic due to its important role in economy and beneficial offers. There is an imminent need to uncover the stock market future behavior in order to avoid investment risks. The large amount of data generated by the stock market is considered a treasure of knowledge for investors. This study aims at constructing an effective model to predict stock market future trends with small error ratio and improve the accuracy of prediction. This prediction model is based on sentiment analysis of financial news and historical stock market prices. This model provides better accuracy results than all previous studies by considering multiple types of news related to market and company with historical stock prices. A dataset containing stock prices from three companies is used. The first step is to analyze news sentiment to get the text polarity using naïve Bayes algorithm. This step achieved prediction accuracy results ranging from 72.73% to 86.21%. The second step combines news polarities and historical stock prices together to predict future stock prices. This improved the prediction accuracy up to 89.80%.
[...] Read more.Non-Functional Requirements Classification Using Machine Learning Algorithms
Non-functional requirements define the quality attribute of a software application, which are necessary to identify in the early stage of software development life cycle. Researchers proposed automatic software Non-functional requirement classification using several Machine Learning (ML) algorithms with a combination of various vectorization techniques. However, using the best combination in Non-functional requirement classification still needs to be clarified. In this paper, we examined whether different combinations of feature extraction techniques and ML algorithms varied in the non-functional requirements classification performance. We also reported the best approach for classifying Non-functional requirements. We conducted the comparative analysis on a publicly available PROMISE_exp dataset containing labelled functional and Non-functional requirements. Initially, we normalized the textual requirements from the dataset; then extracted features through Bag of Words (BoW), Term Frequency and Inverse Document Frequency (TF-IDF), Hashing and Chi-Squared vectorization methods. Finally, we executed the 15 most popular ML algorithms to classify the requirements. The novelty of this work is the empirical analysis to find out the best combination of ML classifier with appropriate vectorization technique, which helps developers to detect Non-functional requirements early and take precise steps. We found that the linear support vector classifier and TF-IDF combination outperform any combinations with an F1-score of 81.5%.
[...] Read more.Machine Learning in Cyberbullying Detection from Social-Media Image or Screenshot with Optical Character Recognition
Along with the growth of the Internet, social media usage has drastically expanded. As people share their opinions and ideas more frequently on the Internet and through various social media platforms, there has been a notable rise in the number of consumer phrases that contain sentiment data. According to reports, cyberbullying frequently leads to severe emotional and physical suffering, especially in women and young children. In certain instances, it has even been reported that sufferers attempt suicide. The bully may occasionally attempt to destroy any proof they believe to be on their side. Even if the victim gets the evidence, it will still be a long time before they get justice at that point. This work used OCR, NLP, and machine learning to detect cyberbullying in photos in order to design and execute a practical method to recognize cyberbullying from images. Eight classifier techniques are used to compare the accuracy of these algorithms against the BoW Model and the TF-IDF, two key features. These classifiers are used to understand and recognize bullying behaviors. Based on testing the suggested method on the cyberbullying dataset, it was shown that linear SVC after OCR and logistic regression perform better and achieve the best accuracy of 96 percent. This study aid in providing a good outline that shapes the methods for detecting online bullying from a screenshot with design and implementation details.
[...] Read more.Plant Disease Detection Using Deep Learning
Agricultural development is a critical strategy for promoting prosperity and addressing the challenge of feeding nearly 10 billion people by 2050. Plant diseases can significantly impact food production, reducing both quantity and diversity. Therefore, early detection of plant diseases through automatic detection methods based on deep learning can improve food production quality and reduce economic losses. While previous models have been implemented for a single type of plant to ensure high accuracy, they require high-quality images for proper classification and are not effective with low-resolution images. To address these limitations, this paper proposes the use of pre-trained model based on convolutional neural networks (CNN) for plant disease detection. The focus is on fine-tuning the hyperparameters of popular pre-trained model such as EfficientNetV2S, to achieve higher accuracy in detecting plant diseases in lower resolution images, crowded and misleading backgrounds, shadows on leaves, different textures, and changes in brightness. The study utilized the Plant Diseases Dataset, which includes infected and uninfected crop leaves comprising 38 classes. In pursuit of improving the adaptability and robustness of our neural networks, we intentionally exposed them to a deliberately noisy training dataset. This strategic move followed the modification of the Plant Diseases Dataset, tailored to better suit the demands of our training process. Our objective was to enhance the network's ability to generalize effectively and perform robustly in real-world scenarios. This approach represents a critical step in our study's overarching goal of advancing plant disease detection, especially in challenging conditions, and underscores the importance of dataset optimization in deep learning applications.
[...] Read more.Optimized Round Robin Scheduling Algorithm Using Dynamic Time Quantum Approach in Cloud Computing Environment
Cloud computing refers to a sophisticated technology that deals with the manipulation of data in internet-based servers dynamically and efficiently. The utilization of the cloud computing has been rapidly increased because of its scalability, accessibility, and incredible flexibility. Dynamic usage and process sharing facilities require task scheduling which is a prominent issue and plays a significant role in developing an optimal cloud computing environment. Round robin is generally an efficient task scheduling algorithm that has a powerful impact on the performance of the cloud computing environment. This paper introduces a new approach for round robin based task scheduling algorithm which is suitable for cloud computing environment. The proposed algorithm determines time quantum dynamically based on the differences among three maximum burst time of tasks in the ready queue for each round. The concerning part of the proposed method is utilizing additive manner among the differences, and the burst times of the processes during determining the time quantum. The experimental results showed that the proposed approach has enhanced the performance of the round robin task scheduling algorithm in reducing average turn-around time, diminishing average waiting time, and minimizing number of contexts switching. Moreover, a comparative study has been conducted which showed that the proposed approach outperforms some of the similar existing round robin approaches. Finally, it can be concluded based on the experiment and comparative study that the proposed dynamic round robin scheduling algorithm is comparatively better, acceptable and optimal for cloud environment.
[...] Read more.Blockchain with Internet of Things: Benefits, Challenges, and Future Directions
The Internet of Things (IoT) has extended the internet connectivity to reach not just computers and humans, but most of our environment things. The IoT has the potential to connect billions of objects simultaneously which has the impact of improving information sharing needs that result in improving our life. Although the IoT benefits are unlimited, there are many challenges facing adopting the IoT in the real world due to its centralized server/client model. For instance, scalability and security issues that arise due to the excessive numbers of IoT objects in the network. The server/client model requires all devices to be connected and authenticated through the server, which creates a single point of failure. Therefore, moving the IoT system into the decentralized path may be the right decision. One of the popular decentralization systems is blockchain. The Blockchain is a powerful technology that decentralizes computation and management processes which can solve many of IoT issues, especially security. This paper provides an overview of the integration of the blockchain with the IoT with highlighting the integration benefits and challenges. The future research directions of blockchain with IoT are also discussed. We conclude that the combination of blockchain and IoT can provide a powerful approach which can significantly pave the way for new business models and distributed applications.
[...] Read more.Machine Learning for Weather Forecasting: XGBoost vs SVM vs Random Forest in Predicting Temperature for Visakhapatnam
Climate change, a significant and lasting alteration in global weather patterns, is profoundly impacting the stability and predictability of global temperature regimes. As the world continues to grapple with the far-reaching effects of climate change, accurate and timely temperature predictions have become pivotal to various sectors, including agriculture, energy, public health and many more. Crucially, precise temperature forecasting assists in developing effective climate change mitigation and adaptation strategies. With the advent of machine learning techniques, we now have powerful tools that can learn from vast climatic datasets and provide improved predictive performance. This study delves into the comparison of three such advanced machine learning models—XGBoost, Support Vector Machine (SVM), and Random Forest—in predicting daily maximum and minimum temperatures using a 45-year dataset of Visakhapatnam airport. Each model was rigorously trained and evaluated based on key performance metrics including training loss, Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), R2 score, Mean Absolute Percentage Error (MAPE), and Explained Variance Score. Although there was no clear dominance of a single model across all metrics, SVM and Random Forest showed slightly superior performance on several measures. These findings not only highlight the potential of machine learning techniques in enhancing the accuracy of temperature forecasting but also stress the importance of selecting an appropriate model and performance metrics aligned with the requirements of the task at hand. This research accomplishes a thorough comparative analysis, conducts a rigorous evaluation of the models, highlights the significance of model selection.
[...] Read more.