Publication Search

Improvement amount Distributed Denial of Service (DDoS) attacks in cloud infrastructure and edge computing demands solution adaptive, distributed, and efficient detection in a way computing. Research This propose an optimized Federated Learning (FL) based DDoS detection model using Centroid Opposition-Based Bacterial Colony Optimization (COBCO) to training the Elman Neural Network (ENN). The proposed architecture consists of of two components Main: on the edge node side, a hybrid Convolutional Neural Network–Gated Recurrent Unit (CNN–GRU) model is used to extraction feature local from traffic data network, while on the server side, model parameters from each node are collected and used for training an optimized ENN with COBCO. Approach This aim increase accuracy detection at a time maintain efficiency local data communication and privacy. In progress experimental, model tested use three benchmark datasets: NSL-KDD, CICIDS2017, and CICDDoS2019. The preprocessing process includes feature encoding categorical, normalization numeric, class balancing using SMOTE, as well as validation cross (k-fold). Initial results show that combination of FL, CNN–GRU, and COBCO–ENN produces improvement significant in accuracy and time convergence compared to approach conventional such as PSO, GA, and non- federative models. In addition, the proposed model capable maintain performance detection tall although executed in edge environment with limitations source Power.  Study This give contribution important in development system scalable, privacy-preserving, and adaptive intelligent DDoS detection to dynamics Then cross modern network. Integration of FL and COBCO in ENN training shows potential big for used in implementation real in cloud-edge infrastructure. In addition, the proposed model demonstrates strong scalability and adaptability, making it highly suitable for dynamic and evolving network environments.

This study compares the performance of two deep learning models, namely Convolutional Long Short-Term Memory (ConvLSTM) and Long-term Recurrent Convolutional Network (LRCN), in the task of recognizing human activity from videos. Human activity recognition is an important field in computer vision with many applications, such as security monitoring, human-computer interaction, and social media-based video analysis. ConvLSTM is a model that combines convolution operations with long-term memory LSTM, thus capable of capturing spatial and temporal information simultaneously. This approach is ideal for processing video data sequences that have spatial and temporal dimensions. On the other hand, LRCN combines the power of spatial feature extraction from Convolutional Neural Network (CNN) and temporal sequence modeling through Recurrent Neural Network (RNN), specifically LSTM, to understand movement patterns in videos. The study used the UCF50 dataset consisting of 50 activity classes, but was limited to five classes for the focus of the experiment. The dataset was divided into 80% for training and 20% for testing, and the model was drilled for 50 epochs using early stopping to prevent overfitting. The results show that both models have high training performance. ConvLSTM achieved a training accuracy of around 98% and a validation accuracy of 90%, while LRCN achieved a training accuracy of 99.5% and a validation accuracy of 88%. Although ConvLSTM demonstrated good stability on the validation data, further testing using TikTok videos as real-world data showed that LRCN had a higher confidence level in recognizing activities, with most predictions achieving confidence scores above 80%. This difference in performance indicates that while ConvLSTM excels in generalizing on training data, LRCN is more robust to real-world data variations.

Attendance management is an essential component in educational institutions, companies, and organizations to monitor the presence and punctuality of participants. Traditional attendance systems, such as manual signatures or identification cards, are prone to various issues including human error, time inefficiency, and identity fraud. To address these challenges, this study aims to develop a smart attendance system using facial recognition technology based on Python and the OpenCV library. The system is designed to automatically detect and recognize faces in real time using a webcam or camera module. It employs computer vision techniques to capture facial images, extract unique features, and match them against a stored database of registered participants. Once the face is verified, the system records the attendance along with a timestamp, ensuring data accuracy and security. The development process involved several stages, including image acquisition, preprocessing, feature extraction, and classification. OpenCV was utilized for image processing tasks, while Python provided the programming framework to integrate all components. To enhance recognition accuracy, the system applied techniques such as histogram equalization for lighting normalization and Haar Cascade classifiers for initial face detection. An experimental evaluation was conducted under various conditions, including different lighting environments and facial orientations. The results demonstrated that the system achieved an accuracy rate of 96% under normal lighting conditions, with only a small decrease in performance under dim or uneven lighting. These findings indicate that the system is reliable for practical applications, especially in controlled environments. Conclusion: The Python-based facial recognition attendance system offers a more efficient, secure, and accurate alternative to conventional attendance methods. Future improvements may include the integration of deep learning models to enhance recognition robustness in diverse real-world scenarios.

Attendance management is an essential component in educational institutions, companies, and organizations to monitor the presence and punctuality of participants. Traditional attendance systems, such as manual signatures or identification cards, are prone to various issues including human error, time inefficiency, and identity fraud. To address these challenges, this study aims to develop a smart attendance system using facial recognition technology based on Python and the OpenCV library. The system is designed to automatically detect and recognize faces in real time using a webcam or camera module. It employs computer vision techniques to capture facial images, extract unique features, and match them against a stored database of registered participants. Once the face is verified, the system records the attendance along with a timestamp, ensuring data accuracy and security. The development process involved several stages, including image acquisition, preprocessing, feature extraction, and classification. OpenCV was utilized for image processing tasks, while Python provided the programming framework to integrate all components. To enhance recognition accuracy, the system applied techniques such as histogram equalization for lighting normalization and Haar Cascade classifiers for initial face detection. An experimental evaluation was conducted under various conditions, including different lighting environments and facial orientations. The results demonstrated that the system achieved an accuracy rate of 96% under normal lighting conditions, with only a small decrease in performance under dim or uneven lighting. These findings indicate that the system is reliable for practical applications, especially in controlled environments. Conclusion: The Python-based facial recognition attendance system offers a more efficient, secure, and accurate alternative to conventional attendance methods. Future improvements may include the integration of deep learning models to enhance recognition robustness in diverse real-world scenarios.

This study presents an advanced AI-powered framework to detect and prevent cyberbullying across diverse social media platforms using a multiclass classification approach. Addressing the growing complexity and linguistic diversity of online abuse, the research integrates various machine learning (RF, LR, SVM) and deep learning (Bi-LSTM, BERT) models trained on a balanced dataset covering bullying categories based on religion, age, ethnicity, gender, and neutral content. Data preprocessing, tokenization, feature extraction via TF-IDF and CountVectorizer, and class balancing using SMOTE were applied to enhance model accuracy. The proposed system further supports real-time detection through social media APIs, offering dynamic monitoring and intervention capabilities. Among the tested models, Random Forest and BERT achieved the highest classification performance with 94% accuracy. Despite its robust architecture, limitations include dependence on English-language datasets, exclusion of multimodal data (e.g., memes, audio), and API restrictions that challenge scalability. Future development will focus on incorporating vision-language models and optimizing the system for real-time, multilingual, and multimodal environments. This study contributes to digital safety efforts by proposing a scalable and adaptive detection system suitable for safeguarding users from evolving forms of online harassment.

Automatic object detection is one of the crucial aspects in the field of digital image processing that plays a vital role in various modern applications, ranging from security systems to pattern recognition in medical and industrial fields. This study aims to implement an automatic object detection method with a digital image representation-based approach using MATLAB software. The main focus is directed at the pixel-based image processing process, where each image element is processed to extract relevant visual information. In this study, stages are carried out starting from image acquisition, color conversion, image quality enhancement, threshold-based segmentation, to extraction of targeted object features. Digital images are analyzed through transformation into grayscale and binary forms to facilitate the detection process. The use of MATLAB provides flexibility in numerical and visual data processing, and supports various efficient image processing libraries.

The rapid development of financial technology (fintech), particularly digital wallet applications like OVO, has significantly transformed transaction patterns in society. However, issues such as server instability and unsatisfactory user experiences frequently emerge on social media platforms. This study aims to analyze user sentiments toward OVO on platform X (formerly Twitter) by comparing the performance of two machine learning algorithms: Naïve Bayes and Support Vector Machine (SVM). Data were collected through web scraping from 1,000 Indonesian-language tweets containing the keyword "OVO." The research methodology included text preprocessing (data cleaning, tokenization, stopword removal), feature extraction using TF-IDF, and sentiment classification (positive, negative, neutral). Evaluation results demonstrated that SVM achieved the highest accuracy of 85.2%, while Naïve Bayes reached 78.5%. SVM also outperformed in precision (87%) and recall (83%) due to its ability to handle non-linear data. These findings provide actionable recommendations for OVO developers to enhance server stability and features based on user feedback. Additionally, this study serves as a reference for future sentiment analysis research employing algorithmic comparisons.

Handwritten digit recognition is one of the key challenges in the field of digital image processing and artificial intelligence, with significant potential in various applications such as automatic form input systems, handwritten data correction, and attendance systems based on handwriting. This study aims to develop a web-based information system capable of automatically recognizing handwritten digits using the K-Nearest Neighbors (KNN) classification method. The system is designed through several main stages, including image preprocessing (conversion to grayscale, thresholding, and image size normalization), feature extraction using the zoning technique, and classification using the KNN algorithm. This research utilizes the MNIST dataset, which contains thousands of handwritten digit images ranging from 0 to 9. The system is developed using the Google Colab platform, supported by Python libraries such as OpenCV, NumPy, and Scikit-learn. Test results show that the system can achieve an accuracy of over 90% at certain K values, indicating that the KNN method is quite effective and efficient in recognizing handwritten digit patterns. This system is expected to be applicable for various digitization needs of handwritten numbers in education, administration, and information technology sectors

The threat of Distributed Denial of Service (DDoS) is increasing develop along with increasing use of the Internet of Things (IoT) and Software-Defined Networking (SDN) architecture . Although SDN provides convenience in management network , properties its centralized control make it prone to to flooding attacks that can paralyze controller performance . Detection method conventional , such as approach statistics and machine learning, still own limitations in matter accuracy , high false positive rate , and dependence on extracted features manually . To overcome problem said , research This propose a hybrid deep learning based DDoS detection and mitigation model that combines Convolutional Neural Network (CNN) to extraction feature spatial from RGB and Gated Recurrent Unit (GRU) images for understand temporal correlation between traffic data network . System tested through network test-bed Mininet based with Ryu/Floodlight controller, using simulation DDoS attacks (Hping3, LOIC) and normal traffic (video streaming, HTTP server). Traffic data cross recorded in PCAP format, processed become RGB image measuring 200×200 pixels, and labeled based on type traffic . Evaluation results with metric accuracy , precision, recall, F1-score, and MCC show that the CNN–GRU model has performance more superior compared to baseline approaches such as CNN-only, GRU-only, as well as classical ML methods such as SVM and Random Forest. In addition , the system capable apply mitigation adaptive through automatic flow rule creation on edge switches. Findings This confirm that effective deep learning- based spatial -temporal hybrid approach in increase detection early and response DDoS attacks on SDN networks adaptive and real-time.  

Mental health issues such as depression, anxiety, and stress continue to increase globally and are recognized as critical factors that influence social functioning, productivity, and overall quality of life. Conventional mental health services are often limited by barriers including high cost, geographical distance, and persistent stigma that discourage individuals from seeking timely help. The digital era provides an alternative through the integration of technology into mental health counseling, offering greater accessibility, flexibility, and anonymity. Nevertheless, a key limitation of many digital counseling platforms lies in their inability to fully capture and respond to the emotional nuances of users during interactions. This study aims to address that gap by developing a speech-based emotion detection framework designed to be integrated into digital counseling environments. The proposed methodology includes the collection and preprocessing of speech samples, feature extraction using acoustic parameters, and training machine learning models to classify emotions in real time. Experimental results demonstrate that this approach significantly improves the accuracy of emotion detection, enabling digital counseling systems to provide more adaptive and personalized support. Beyond counseling, the research highlights the broader applicability of speech emotion recognition in education, telemedicine, and interactive digital assistants, all of which benefit from improved sensitivity to human emotions. These findings underscore the potential of artificial intelligence to strengthen digital mental health interventions, ensuring services that are not only more efficient and inclusive but also capable of fostering long-term emotional well-being in diverse populations.

Image processing is a branch of computer science that is growing rapidly and is widely used in various fields, including in security systems. Face identification is one of the main applications of image processing that aims to recognize and distinguish individual faces in a system. The methods used in face identification involve various techniques, such as facial feature detection, characteristic extraction, and classification using machine learning algorithms. This article discusses the application of image processing in a security system based on face identification and the technology used to improve the accuracy and reliability of the system. The results of the study show that the combination of deep learning algorithms with image pre-processing techniques can increase the success rate of face identification in security systems.

Breast cancer is the most prevalent cancer among women worldwide, requiring early and accurate diagnosis to reduce mortality. This study proposes a hybrid classification pipeline that integrates Hybrid Statistical Feature Selection (HSFS) with unsupervised LSTM-guided feature extraction for breast cancer detection using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset. Initially, 20 features were selected using HSFS based on Mutual Information, Chi-square, and Pearson Correlation. To address class imbalance, the training set was balanced using the Synthetic Minority Over-sampling Technique (SMOTE). Subsequently, an LSTM encoder extracted non-linear latent features from the selected features. A fusion strategy was applied by concatenating the statistical and latent features, followed by re-selection of the top 30 features. The final classification was performed using a Support Vector Machine (SVM) with RBF kernel and evaluated using 5-fold cross-validation and a held-out test set. Experimental results showed that the proposed method achieved an average training accuracy of 98.13%, F1-score of 98.13%, and AUC-ROC of 99.55%. On the held-out test set, the model reached an accuracy of 99.30%, precision of 100%, and F1-score of 99.05%, with an AUC-ROC of 0.9973. The proposed pipeline demonstrates improved generalization and interpretability compared to existing methods such as LightGBM-PSO, DHH-GRU, and ensemble deep networks. These results highlight the effectiveness of combining statistical selection and LSTM-based latent feature encoding in a balanced classification framework.

Image classification is a key field in digital image processing with broad applications, such as object recognition and disease detection. The use of artificial neural network architectures, such as MobileNetV2, has significantly advanced pattern recognition in large datasets. However, in small datasets, challenges related to accuracy and generalization are often encountered. This study explores an RGB-based approach utilizing MobileNetV2 for image feature extraction and Support Vector Machine (SVM) as the classifier. MobileNetV2 is applied to extract features from RGB images, which are then further processed by SVM to determine image classes. The results indicate that this model achieves an accuracy of 91.67%, precision of 0.9163, recall of 0.9167, and F1-score of 0.9161. Based on the confusion matrix analysis, the model effectively distinguishes between classes, despite slight overlaps. This research contributes to the development of intelligent image classification systems that can be applied in various fields, including the food industry. With these achievements, the RGB approach integrating MobileNetV2 and SVM has proven effective in enhancing image classification accuracy, even with relatively small datasets. These findings open opportunities for applying similar methods in other image processing tasks that require high accuracy in object or disease detection and classification.

This research focuses on assessing the efficacy of a method that integrates Convolutional Neural Networks (CNN) with Decision Trees for the detection of phishing URLs. Phishing represents a major cyber threat, where cybercriminals attempt to deceive individuals into disclosing sensitive information via fraudulent websites. As the frequency of phishing attacks continues to rise, there is a pressing need for effective detection and prevention strategies. In this investigation, a dataset comprising both phishing and legitimate URLs was utilized to train a CNN-Decision Tree model. The training phase includes feature extraction from URLs using CNN, which excels at identifying intricate patterns within the data, followed by classification through Decision Trees, recognized for their capacity to deliver straightforward and comprehensible interpretations of classification outcomes. The model's performance was evaluated across nine distinct scenarios to assess its effectiveness under varying conditions. The results indicated that the hybrid CNN-Decision Tree model achieved a precision rate of 94%, a recall of 90%, and an F1-Score of 92%, with an overall accuracy of 93%. These findings suggest that the model is not only proficient in identifying phishing URLs but also maintains a commendable balance between precision and recall. This research highlights that the synergy of CNN and Decision Trees can serve as a potent solution for phishing URL detection, significantly contributing to the advancement of enhanced cybersecurity systems.

Due to the variety of types of flowers that exist and having and tracking each variety, making plant lovers and cultivators difficult to distinguish in determining the type of flower, it takes a very long time to find out the type of flower if you only rely on the five senses. With the application of the K-Nearest Neighbor algorithm and feature extraction of color and texture, it is very helpful in image processing to identify flowers more easily and shorten the time, with the greatest accuracy of 71% using the K-7 value, the flower was successfully carried out.

spam is posting unsolicited messages or advertising on social media, particularly Twitter. These messages are normally designed to sell specific products and services or links. In this research, we developed a fuzzy control system to detect Arabic spam tweets based on deep learning with a large language model. Initially, we performed text cleaning and further transformed text into vectors with the help of AraGpt and AraBert. Subsequently, we employed a multi-layer perceptron network model in feature extraction of essential features. Finally, we adopted the fuzzy logic control system for classifying spam tweets using features filtered from deep networks. Employing the proposed Fuzzy logic control system provided nearly a 100% comparative to only utilizing the deep neural networks, which yielded an almost 99% throughput for both large language models Aragpt and Arabert, with a 100% F1 score for the Aragpt model and 99% for Arabert model respectively.

Advances in information and internet technologies have significantly transformed the business environment, including the financial sector. The COVID-19 pandemic has further accelerated this digital adoption, expanding the e-commerce industry and highlighting the necessity for secure online transactions. Credit Card Fraud Detection (CCFD) stands critical as the prevalence of fraudulent activities continues to rise with the increasing volume of online transactions. Traditional methods for detecting fraud, such as rule-based systems and basic machine learning models, tend to fail to keep pace with fraudsters' evolving tactics. This study proposes a novel ensemble deep learning-based approach that combines Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and Multilayer Perceptron (MLP) with the Synthetic Minority Oversampling Technique and Edited Nearest Neighbors (SMOTE-ENN) to address class imbalance and improve detection accuracy. The methodology integrates CNN for feature extraction, GRU for sequential transaction analysis, and Multilayer Perceptron (MLP) as a meta-learner in a stacking framework. By leveraging SMOTE-ENN, the proposed approach enhances data balance and prevents overfitting. With synthetic data, the robustness and accuracy of the model have been improved, particularly in scenarios where fraudulent examples are scarce. The experiments conducted on real-world credit card transaction datasets have established that our approach outperforms existing methods, achieving higher metrics performance.

This study aims to optimize the implementation of the K-Nearest Neighbors (K-NN) algorithm for medical image classification by focusing on selecting the optimal KKK parameter and applying dimensionality reduction techniques to improve accuracy and efficiency. The data used was sourced from public medical image repositories such as The Cancer Imaging Archive (TCIA) and Medical Image Analysis datasets, covering various diseases, including brain tumors, lung cancer, and kidney lesions. The research process involves data collection, data preprocessing, dimensionality reduction using Principal Component Analysis (PCA), applying the K-NN algorithm with Euclidean, Minkowski, and Cosine distance metrics, and performance evaluation using accuracy, precision, recall, and F1-score. Experimental results demonstrate that K=5with the Euclidean distance metric provides the best performance, achieving an accuracy of 90%. Additionally, PCA effectively reduces computational time by 30% without significantly compromising accuracy. This study proves that K-NN is an effective method for medical image classification. However, further research is needed to integrate K-NN with deep learning models to enhance performance and feature extraction capabilities.

Skin cancer (SC) is a highly serious kind of cancer that, if not addressed swiftly, might result in the patient’s demise. Early detection of this condition allows for more effective therapy and prevents disease development. Deep Learning (DL) approaches may be used as an effective and efficient tool for SC detection (SCD). Several DL-based algorithms for automated SCD have been reported. However, more efficient models are needed to improve accuracy. As a result, this paper introduces a new strategy for SCD based on Grey Wolf optimization (GWO) methodologies and CNN. The proposed methodology has four stages: preprocessing, segmentation, feature extraction, and classification. The proposed method utilizes a Convolutional Neural Network (CNN) to extract features from Regions of Interest (ROIs). CNN is employed for feature categorization, whereas the GWO approach enhances accuracy by refining edge detection and segmentation. This technique utilizes a probabilistic model to accelerate the convergence of the GWO algorithm. Employing the GWO model to optimize the structure and weight vectors of CNNs can enhance diagnostic accuracy by a minimum of 5%, based on evaluation outcomes. The application of the proposed strategy and its performance comparison with other methods indicate that the proposed method with GWO predicted SC with an average accuracy of 95.11% and without GWO an Accuracy of 92.66%, respectively, enhancing accuracy by a minimum of 2.5% when we train our model with GWO.

Signature verification is crucial for confirming the authenticity of identities in both administrative and financial transactions, where signature forgery can lead to significant security risks. The Harris Corner Detector Algorithm is a widely used method for feature extraction in image processing; its application spans various domains, such as detection of signature forgery. While effective in identifying key features, noise significantly affects performance, especially with impulse noise like salt-and-pepper noise commonly found in signature images. To solve this problem, this study enhances the Harris Corner Detector Algorithm by applying a median filter before gradient calculation. This method removes noise without sacrificing the integrity of key features important in signature forgery detection. The study evaluates the original and the enhanced algorithm using standard image quality metrics. Peak Signal-to-Noise Ratio (PSNR) surged from an average of 13.6 dB to 43.28 dB, the Structural Similarity Index (SSIM) improved significantly from 78% to 94%, and the Mean Squared Error (MSE) dropped substantially from 16.74 to 3.84. These advancements resulted in a more reliable algorithm, exhibiting excellent resistance to noise while maintaining image structure, making the enhanced algorithm highly effective for accurate signature forgery detection.