دكتور علي صباح عبدالامير السعدي

The proliferation of malicious and deceptive information on the internet poses an important problem in automated detection, especially because of language heterogeneity, classes imbalance, and the practicality of the computational requirements of the large transformer models. This paper examines an ensemble classifier, a multi-view text classification system that is analytically trained. The architecture proposed will combine complementary feature representations whereby Convolutional Neural Networks (CNN) are combined with Bidirectional Long Short-Term Memory networks (BiLSTM) and TF-IDF features to represent global statistical term significance. The framework employs Fast Learning Network (FLN) with the weights on the output obtained as result of an analytic calculation based on the MoorePenrose pseudoinverse, as opposed to a conventional gradient-based classification head. The analytical classifier is further expanded by bootstrap aggregation to make it stronger and less variable, and the ensemble thus becomes FLN-Bagging. The strategy is tested on two benchmark datasets, which vary in their properties: the imbalanced Cyber Troll dataset (20,001 tweets) and the FA-KES fake news dataset (804 news articles). The experimental results indicate that the FLN classifier has an accuracy of 93.84% and 95.72% on Cyber Troll and FA-KES respectively, which are improved to 94.58% and 96.63% with FLN-Bagging. The scores of ROCAUC are 0.93 and 0.99 on the two sets, respectively. Multi-run appraisals and controlled ablation experiments also indicate that the ensemble extension is always more effective in enhancing performance stability. These results indicate that analytically trained ensemble classifiers can provide competitive predictive accuracy and at reduced cost of classifier-stage computation, potentially of useful value as an alternative to gradient-based classification heads in multi-view natural language processing (NLP) system particularly when the task is task-specific or resource-constrained. © 2026, Politeknik Negeri Padang. All rights reserved.

Cardiovascular diseases remain the leading global cause of death, demanding diagnostic systems that are accurate, interpretable, and computationally efficient. Traditional machine learning approaches frequently struggle with class imbalance, high-dimensional noise, and restricted generalization in clinical datasets. To tackle such issues, we propose a hybrid framework that combines SVM–SMOTE and neighborhood cleaning rule (NCL) for class rebalancing, a sparse autoencoder (SAE) with random forest (RF) selection for non-linear feature optimization, and a class-weighted multilayer perceptron (MLP) for final classification. We validate our framework on the Z-Alizadeh Sani (54 features) and Cleveland (13 features) datasets under stratified fivefold cross-validation, the model attains mean accuracies of 94.02 ± 2.77 % and 94.36 ± 1.47 %, with AUC–ROC = 0.988 and 0.982, outperforming prior baselines [4, 10, 14] by 7.6%–20.8%, and Bootstrap 95% confidence intervals and McNemar/DeLong tests (p < 0.001) confirms significance. Noteably, the ablation study demonstrates the contribution of each module (e.g., a 12% accuracy improvement without sampling). The optimized MLP reduced false negatives to ~5%, while training 40% faster than CNN–LSTM alternatives. The proposed framework provides a statistically robust and interpretable solution for predicting cardiovascular disease.

Information retrieval is a difficult process due to the overabundance of information on the web. Nowadays, search result responds to user queries with too many results although only a few are relevant. Therefore, the existing clustering methods that fail in clustering snippets (short texts) of web documents due to the low frequencies of document terms should be deeply investigated. One of the approaches that can be used to solve this problem is the expansion of document terms with semantically similar terms. Hence, a list of terms with their closest and accurate semantically similar words (word representation) must be built. This study aims to design and develop a new framework to enhance the performance of web search result clustering (WSRC). The research also presents a new unsupervised distributed word representation scheme where each word is represented by a vector of its semantically related words; such as scheme expands snippets and user queries. The proposed framework consists of several activities, such as (1) various standard datasets (Open Directory Project [ODP]-239 and MORESQUE) that are used for evaluating search result clustering algorithms for most cited dataset works, (2) text pre-processing, (3) document representation based on a new wiki-based k-nearest neighbors (KNN) representation method, (4) effect of the proposed model on the performance of traditional clustering methods (k-means, k-medoids, single-linkage, and complete-linkage) for WSRC, and (5) evaluation stage of the proposed method. Results indicate that enhanced clustering methods, according to the new wiki-KNN based representation method in comparison with the baseline methods, show a significant improvement in WSRC. Furthermore, the new data representation scheme has enhanced the overall performance of clustering methods.

Abstract Existing text clustering methods utilize only one representation at a time (single view), whereas multiple views can represent documents. The multiview multirepresentation method enhances clustering quality. Moreover, existing clustering methods that utilize more than one representation at a time (multiview) use representation with the same nature. Hence, using multiple views that represent data in a different representation with clustering methods is reasonable to create a diverse set of candidate clustering solutions. On this basis, an effective dynamic clustering method must consider combining multiple views of data including semantic view, lexical view (word weighting), and topic view as well as the number of clusters. The main goal of this study is to develop a new method that can improve the performance of web search result clustering (WSRC). An enhanced multiview multirepresentation consensus clustering ensemble (MMCC) method is proposed to create a set of diverse candidate solutions and select a high-quality overlapping cluster. The overlapping clusters are obtained from the candidate solutions created by different clustering methods. The framework to develop the proposed MMCC includes numerous stages: (1) acquiring the standard datasets (MORESQUE and Open Directory Project-239), which are used to validate search result clustering algorithms, (2) preprocessing the dataset, (3) applying multiview multirepresentation clustering models, (4) using the radius-based cluster number estimation algorithm, and (5) employing the consensus clustering ensemble method. Results show an improvement in clustering methods when multiview multirepresentation is used. More importantly, the proposed MMCC model improves the overall performance of WSRC compared with all single-view clustering models.

In multilabel classification, each sample can be allocated to multiple class labels at the same time. However, one of the prominent problems of multilabel classification is missing labels (incomplete labels) in multilabel text. The multilabel classification performance is reduced significantly with the presence of missing labels. In order to address the incomplete or missing label problem, this study proposes two methods: an aggregated feature and label graph-based missing label handling method (GB-AS), and a unified graph-based missing label propagation method (UG-MLP). GB-AS is used to obtain an initial label matrix based on the similarity of both document levels: feature-based weighting representation and label-based weighting representation. On the other hand, UG-MLP is introduced to construct a mixed graph that combines GB-AS and label correlations into a single groundwork. A high-order label correlation is learned from the incomplete training data and applied to supplement the missing label matrix, which guides the creation of multilabel classification models. The combination of the mixed graphs by UG-MLP is aimed to obtain the benefits of both graphs to increase the classification performance. To evaluate UG-MLP, the metrics of precision, recall and F-measure were used on three benchmark datasets, namely, the Reuters-21578, Bibtex and Enron datasets. The experimental results show that UG-MLP outperformed GB-AS as well as other state-of-the-art approaches. Therefore, we can infer from the findings that by plotting a unified graph based on joining aggregated feature and label weightings together with the label correlation, the performance of multilabel classification can be improved.

Simultaneous multiple labelling of documents, also known as multilabel text classification, will not perform optimally if the class is highly imbalanced. Class imbalanced entails skewness in the fundamental data for distribution that leads to more difficulty in classification. Random over-sampling and under-sampling are common approaches to solve the class imbalanced problem. However, these approaches have several drawbacks; the under-sampling is likely to dispose of useful data, whereas the over-sampling can heighten the probability of overfitting. Therefore, a new method that can avoid discarding useful data and overfitting problems is needed. This study proposes a method to tackle the class imbalanced problem by combining multilabel over-sampling and under-sampling with class alignment (ML-OUSCA). In the proposed ML-OUSCA, instead of using all the training instances, it draws a new training set by over-sampling small size classes and under-sampling big size classes. To evaluate our proposed ML-OUSCA, evaluation metrics of average precision, average recall and average F-measure on three benchmark datasets, namely, Reuters-21578, Bibtex, and Enron datasets, were performed. Experimental results showed that the proposed ML-OUSCA outperformed the chosen baseline random resampling approaches; K-means SMOTE and KNN-US. Thus, based on the results, we can conclude that designing a resampling method based on the class imbalanced together with class alignment will improve multilabel classification even better than just the random resampling method.

بدأ أثر المرأة في علوم الحوسبة مع آدا لوفلايس، التي وضعت أول خوارزمية حاسوبية في التاريخ. وتواصل دور المرأة مع رائدات مثل غريس هوبر وكاثرين جونسون في تطوير البرمجة والحوسبة والعلوم. ومع تطور التكنولوجيا، أصبحت المرأة شريكًا أساسيًا في مجالات الذكاء الاصطناعي، تعلم الآلة، وعلوم البيانات. واليوم، تسهم النساء في تطوير تقنيات الذكاء الاصطناعي وتعزيز الابتكار والعدالة والمسؤولية في استخدامها.

يقيم قسم علوم الحاسوب ندوة علمية بعنوان "الذكاء الاصطناعي بين الحلم والواقع: فرص وتحديات الثورة الرقمية" ضمن نشاطات شهر تشرين الاول والمزمع اقامتها يوم الثلاثاء الموافق 20/10/2026 الساعة العاشرة صباحا وعلى قاعة الدراسات العليا في قسم علوم الحاسبات. انتقل الذكاء الاصطناعي من كونه حلمًا علميًا إلى واقع يؤثر في التعليم والطب والصناعة والبحث العلمي والحياة اليومية. ويوفر فرصًا كبيرة للابتكار، وتحليل البيانات، وأتمتة المهام، وتحسين عملية اتخاذ القرار. وفي المقابل، يواجه تحديات مثل الخصوصية، والتحيز الخوارزمي، وأمن المعلومات، وتأثيره في سوق العمل. لذلك، يتطلب مستقبل الذكاء الاصطناعي تحقيق توازن بين الابتكار والمسؤولية والأخلاقيات.

يقيم قسم علوم الحاسوب ندوة علمية بعنوان "اين يكمن الذكاء الاصطناعي: المستقبل والتحديات" ضمن نشاطات شهر نيسان والمزمع اقامتها يوم الثلاثاء الموافق 07/04/2026 الساعة العاشرة صباحا وعلى مختبر الذكاء الاصطناعي في قسم علوم الحاسبات.

يقيم قسم اللغة العربية وبالتعاون مع قسم علوم الحاسوب ندوة علمية. يتمثل دور الذكاء الاصطناعي في معالجة اللغة العربية في تطوير نماذج متطورة مثل BERT لتحليل النصوص وتصنيفها بدقة تتفوق على الطرق التقليدية. وتساعد هذه التقنيات في التغلب على تعقيدات اللغة مثل غياب التشكيل وتعدد اللهجات عبر الفهم السياقي العميق. ويهدف هذا التطور إلى تحسين تطبيقات الترجمة الآلية وتحليل المشاعر بما يخدم المحتوى الرقمي العربي.

إقامة ندوة علمية بعنوان "الذكاء الاصطناعي والأمن السيبراني: المستقبل والتحديات" وذلك بالتعاون مع شعبة النشاطات الطلابية وهي ضمن نشاطات شهر تشرين الثاني ضمن نشاط الذكاء الاصطناعي والامن السبراني المزمع اقامتها يوم الاثنين الموافق 25/11/2024 الساعة العاشرة صباحا وعلى قاعة الدراسات العليا في قسم الحاسبات

المادة: الذكاء الاصطناعي نظري القسم: علوم حاسبات المرحلة: الثالثة اليوم: الاثنين والثلاثاء من كل اسبوع الساعة 10:30 صباحا