PhishFusionNet: A Wide and Deep Phishing Detection with a Hybrid Learning Approach Ali A. Alani, Adil Al-Azzawia Cybernetics and Information Technologies, 2026 Phishing is a type of cyber threat that targets organizations and individuals worldwide, causing billions of dollars in losses. So far, most successful anti-phishing methods require experts to extract features from phishing sites and third-party detection systems to detect them. This paper presents a PhishFusionNet model, an effective wide-and-deep learning framework for identifying phishing URLs with a high degree of generalization and accuracy. The proposed model successfully discovers both sequential and global patterns within URLs. This is achieved by integrating character-level embeddings that represent the deep component with handcrafted URL features that capture the wide component. We have tested our proposed model on over six million real-world labelled URLs. The results of the test on such a large-scale dataset with an optimal accuracy of 98.9 % have demonstrated that our model outperforms many other tested approaches. Based on these results, we believe that our proposed model is an effective, reliable, and scalable solution for cybersecurity and real-time phishing-detection applications.
Design A Secure Customize Search Engine Based on Link 's Metadata Analysis Ali A. Alani, Adil Al-Azzawia 2025 5th International Conference on Innovative Research in Applied Science Engineering and Technology Iraset 2025, 2025 The fast growth of the Internet and the ever-growing size of online data have created significant challenges in providing users with the most relevant and more secure search results. Traditional search engines often struggle to deliver accurate information and are vulnerable to security threats, such as phishing attacks and other online risks. The lack of customized search engines tailored to identify unsecure website in real time without depending on the black list approach calls attention to a significant gap in addressing various user needs and navigating intricate datasets effectively specially to overcome zero-day attack. This paper aim to proposes a Secure Custom Search Engine (SCSE) system to handle these limitations by enhancing the relevance and security of retrieved search results through metadata-driven analysis. The security-checking process examines key metadata features like SSL certificate details, HTTPS usage, WHOIS country, website age, and other relevant indicators to classify links as either suspicious or legitimate. The results show that the system enhances boosts user safety by identifying suspicious links based on metadata analysis.
A Model for Qur'anic Sign Language Recognition Based on Deep Learning Algorithms Hany A. AbdElghfar, Abdelmoty M. Ahmed, Ali A. Alani, Hammam M. AbdElaal, Belgacem Bouallegue, et al. Journal of Sensors, 2023 Deaf and dumb Muslims cannot reach advanced levels of education due to the impact of obstruction on their educational attainment. This leads to their inability to learn, recite, and understand the meanings and interpretations of the Holy Qur’an as easily as ordinary people, which also prevents them from applying Islamic rituals such as prayer that require learning and reading the Holy Qur’an. In this paper, we propose a new model for Qur’anic sign language recognition based on convolutional neural networks through data preparation, preprocessing, feature extraction, and classification stages. The proposed model is aimed at recognizing the movements of the Arabic sign language by recognizing the hand gestures that refer to the dashed Qur’anic letters in order to help the deaf and dumb learn their Islamic rituals. The experiments have been conducted on a part of a large Arabic sign language dataset called ArSL2018, which represents the 14 dashed letters in the Holy Qur’an, so that this part contains only 24,137 images. The experimental results demonstrate that the proposed model performs better than the other existing models.
ArSL-CNN: A convolutional neural network for arabic sign language gesture recognition Ali A. Alani, Georgina Cosma Indonesian Journal of Electrical Engineering and Computer Science, 2021 <p class="IJASEITAbtract">Sign language (SL) is a visual language means of communication for people who are Deaf or have hearing impairments. In Arabic-speaking countries, there are many Arabic sign languages (ArSL) and these use the same alphabets. This study proposes ArSL-CNN, a deep learning model that is based on a convolutional neural network (CNN) for translating Arabic SL (ArSL). Experiments were performed using a large ArSL dataset (ArSL2018) that contains 54049 images of 32 sign language gestures, collected from forty participants. The results of the first experiments with the ArSL-CNN model returned a train and test accuracy of 98.80% and 96.59%, respectively. The results also revealed the impact of imbalanced data on model accuracy. For the second set of experiments, various re-sampling methods were applied to the dataset. Results revealed that applying the synthetic minority oversampling technique (SMOTE) improved the overall test accuracy from 96.59% to 97.29%, yielding a statistically signicant improvement in test accuracy (p=0.016, α&lt;0=05). The proposed ArSL-CNN model can be trained on a variety of Arabic sign languages and reduce the communication barriers encountered by Deaf communities in Arabic-speaking countries.</p>
Classifying Imbalanced Multi-modal Sensor Data for Human Activity Recognition in a Smart Home using Deep Learning Ali A. Alani, Georgina Cosma, Aboozar Taherkhani Proceedings of the International Joint Conference on Neural Networks, 2020 In smart homes, data generated from real-time sensors for human activity recognition is complex, noisy and imbalanced. It is a significant challenge to create machine learning models that can classify activities which are not as commonly occurring as other activities. Machine learning models designed to classify imbalanced data are biased towards learning the more commonly occurring classes. Such learning bias occurs naturally, since the models better learn classes which contain more records. This paper examines whether fusing real-world imbalanced multi-modal sensor data improves classification results as opposed to using unimodal data; and compares deep learning approaches to dealing with imbalanced multi-modal sensor data when using various resampling methods and deep learning models. Experiments were carried out using a large multi-modal sensor dataset generated from the Sensor Platform for HEalthcare in a Residential Environment (SPHERE). The data comprises 16104 samples, where each sample comprises 5608 features and belongs to one of 20 activities (classes). Experimental results using SPHERE demonstrate the challenges of dealing with imbalanced multi-modal data and highlight the importance of having a suitable number of samples within each class for sufficiently training and testing deep learning models. Furthermore, the results revealed that when fusing the data and using the Synthetic Minority Oversampling Technique (SMOTE) to correct class imbalance, CNN-LSTM achieved the highest classification accuracy of 93.67% followed by CNN, 93.55%, and LSTM, i.e. 92.98%.
Activity recognition from multi-modal sensor data using a deep convolutional neural network Aboozar Taherkhani, Georgina Cosma, Ali A. Alani, T. M. McGinnity Advances in Intelligent Systems and Computing, 2019 Multi-modal data extracted from different sensors in a smart home can be fused to build models that recognize the daily living activities of residents. This paper proposes a Deep Convolutional Neural Network to perform the activity recognition task using the multi-modal data collected from a smart residential home. The dataset contains accelerometer data (composed of three perpendicular components of acceleration and the strength of the accelerometer signal received by four receivers), video data (15 time-series related to 2D and 3D center of mass and bounding box extracted from an RGB-D camera), and Passive Infra-Red sensor data. The performance of the Deep Convolutional Neural Network is compared to the Deep Belief Network. Experimental results revealed that the Deep Convolutional Neural Network with two pairs of convolutional and max pooling layers achieved better classification accuracy than the Deep Belief Network. The Deep Belief Network uses Restricted Boltzmann Machines for pre-training the network. When training deep learning models using classes with a high number of training samples, the DBN achieved 65.97% classification accuracy, whereas the CNN achieved 75.33% accuracy. The experimental results demonstrate the challenges of dealing with multi-modal data and highlight the importance of having a suitable number of samples within each class for sufficiently training and testing deep learning models.
PhishFusionNet: A Wide and Deep Phishing Detection with a Hybrid Learning Approach AAA Adil Al-Azzawi Cybernetics And Information Technologies 26 (1), 140-158 , 2026 2026
Design A Secure Customize Search Engine Based on Link's Metadata Analysis AA Alani, A Al-Azzawia 2025 5th International Conference on Innovative Research in Applied Science … , 2025 2025 Citations: 1
Phishing Attacks Detection and Prevention Techniques: An Overview AA Alani, A Al-Azzawia Journal of Al-Qadisiyah for Computer Science and Mathematics 17 (1), 166-178 , 2025 2025 Citations: 1
Optimizing web page retrieval performance with advanced query expansion: leveraging ChatGPT and metadata-driven analysis AA Alani, A Al-Azzawi The Journal of Supercomputing 81 (4), 569 , 2025 2025 Citations: 4
QSLRS-CNN: Qur'anic sign language recognition system based on convolutional neural networks HA AbdElghfar, AM Ahmed, AA Alani, HM AbdElaal, B Bouallegue, ... The Imaging Science Journal 72 (2), 254-266 , 2024 2024 Citations: 22
A model for qur’anic sign language recognition based on deep learning algorithms HA AbdElghfar, AM Ahmed, AA Alani, HM AbdElaal, B Bouallegue, ... Journal of Sensors 2023 (1), 9926245 , 2023 2023 Citations: 26
ArSL-CNN: a convolutional neural network for Arabic sign language gesture recognition AA Alani, G Cosma Indonesian journal of electrical engineering and computer science 22 , 2021 2021 Citations: 58
COVID-CNNnet: Convolutional Neural Network for Coronavirus Detection AA Alani, AA Alani, KAMAAL Ani International Journal of Data Science 2 (1), 9-18 , 2021 2021 Citations: 1
Classifying imbalanced multi-modal sensor data for human activity recognition in a smart home using deep learning AA Alani, G Cosma, A Taherkhani 2020 international joint conference on neural networks (IJCNN), 1-8 , 2020 2020 Citations: 45
A hybrid model for classification of biomedical data using feature filtering and a convolutional neural network S Salesi, AA Alani, G Cosma 2018 Fifth International Conference on Social Networks Analysis, Management … , 2018 2018 Citations: 4
Big Data Analytics for Healthcare Organizations A Case Study of the Iraqi Healthcare Sector AA Alani, FD Ahmed, AM Mazlina, A Mohd Sharifuddin Advanced Science Letters 24 (10), 7783-7789 , 2018 2018 Citations: 4
Activity recognition from multi-modal sensor data using a deep convolutional neural network A Taherkhani, G Cosma, AA Alani, TM McGinnity Science and information conference, 203-218 , 2018 2018 Citations: 18
On-line voltage stability monitoring using an Ensemble AdaBoost classifier SS Maaji, G Cosma, A Taherkhani, AA Alani, TM McGinnity 2018 4th international conference on information management (ICIM), 253-259 , 2018 2018 Citations: 20
Fingerprint classification using a deep convolutional neural network B Pandya, G Cosma, AA Alani, A Taherkhani, V Bharadi, TM McGinnity 2018 4th international conference on information management (ICIM), 86-91 , 2018 2018 Citations: 80
Hand gesture recognition using an adapted convolutional neural network with data augmentation AA Alani, G Cosma, A Taherkhani, TM McGinnity 2018 4th International conference on information management (ICIM), 5-12 , 2018 2018 Citations: 86
Arabic Handwritten Digit Recognition Based on Restricted Boltzmann Machine and Convolutional Neural Networks AA Alani Information 8 (4), 142 , 2017 2017 Citations: 73
Modified AODV routing protocol to detect the black hole attack in MANET MSAA Mahmood, TM Hasan, MSDS Ibrahim International Journal of Advanced Research in Computer Science and Software … , 2015 2015 Citations: 6
Hiding Information Using Circular Distribuition AA Alani Journal of the college of education 1 (1), 101-114 , 2015 2015 Citations: 1
The Way Forward For Distance Learning In Countries with Low ICT Implementation: The Iraq Case DMBO Ali A. Alani 2nd National Graduate Conference 2 (2), 1-4 , 2014 2014
A Survey on Readiness and Preference in Adopting Distance Learning: Case at University Of Technology, Iraq DMBO Ali A. Alani 2nd National Graduate Conference 2 (2), 1-4 , 2014 2014
MOST CITED SCHOLAR PUBLICATIONS
Hand gesture recognition using an adapted convolutional neural network with data augmentation AA Alani, G Cosma, A Taherkhani, TM McGinnity 2018 4th International conference on information management (ICIM), 5-12 , 2018 2018 Citations: 86
Fingerprint classification using a deep convolutional neural network B Pandya, G Cosma, AA Alani, A Taherkhani, V Bharadi, TM McGinnity 2018 4th international conference on information management (ICIM), 86-91 , 2018 2018 Citations: 80
Arabic Handwritten Digit Recognition Based on Restricted Boltzmann Machine and Convolutional Neural Networks AA Alani Information 8 (4), 142 , 2017 2017 Citations: 73
ArSL-CNN: a convolutional neural network for Arabic sign language gesture recognition AA Alani, G Cosma Indonesian journal of electrical engineering and computer science 22 , 2021 2021 Citations: 58
Classifying imbalanced multi-modal sensor data for human activity recognition in a smart home using deep learning AA Alani, G Cosma, A Taherkhani 2020 international joint conference on neural networks (IJCNN), 1-8 , 2020 2020 Citations: 45
A model for qur’anic sign language recognition based on deep learning algorithms HA AbdElghfar, AM Ahmed, AA Alani, HM AbdElaal, B Bouallegue, ... Journal of Sensors 2023 (1), 9926245 , 2023 2023 Citations: 26
QSLRS-CNN: Qur'anic sign language recognition system based on convolutional neural networks HA AbdElghfar, AM Ahmed, AA Alani, HM AbdElaal, B Bouallegue, ... The Imaging Science Journal 72 (2), 254-266 , 2024 2024 Citations: 22
On-line voltage stability monitoring using an Ensemble AdaBoost classifier SS Maaji, G Cosma, A Taherkhani, AA Alani, TM McGinnity 2018 4th international conference on information management (ICIM), 253-259 , 2018 2018 Citations: 20
Activity recognition from multi-modal sensor data using a deep convolutional neural network A Taherkhani, G Cosma, AA Alani, TM McGinnity Science and information conference, 203-218 , 2018 2018 Citations: 18
Modified AODV routing protocol to detect the black hole attack in MANET MSAA Mahmood, TM Hasan, MSDS Ibrahim International Journal of Advanced Research in Computer Science and Software … , 2015 2015 Citations: 6
Optimizing web page retrieval performance with advanced query expansion: leveraging ChatGPT and metadata-driven analysis AA Alani, A Al-Azzawi The Journal of Supercomputing 81 (4), 569 , 2025 2025 Citations: 4
A hybrid model for classification of biomedical data using feature filtering and a convolutional neural network S Salesi, AA Alani, G Cosma 2018 Fifth International Conference on Social Networks Analysis, Management … , 2018 2018 Citations: 4
Big Data Analytics for Healthcare Organizations A Case Study of the Iraqi Healthcare Sector AA Alani, FD Ahmed, AM Mazlina, A Mohd Sharifuddin Advanced Science Letters 24 (10), 7783-7789 , 2018 2018 Citations: 4
Develop A Hybrid E-Learning Model For Distance Learning Implementation: Case Study University Of Technology In Iraq DMBO Ali A. Alani The Arab Journal of Quality in Education 1 (1), 57-71 , 2014 2014 Citations: 2
Design A Secure Customize Search Engine Based on Link's Metadata Analysis AA Alani, A Al-Azzawia 2025 5th International Conference on Innovative Research in Applied Science … , 2025 2025 Citations: 1
Phishing Attacks Detection and Prevention Techniques: An Overview AA Alani, A Al-Azzawia Journal of Al-Qadisiyah for Computer Science and Mathematics 17 (1), 166-178 , 2025 2025 Citations: 1
COVID-CNNnet: Convolutional Neural Network for Coronavirus Detection AA Alani, AA Alani, KAMAAL Ani International Journal of Data Science 2 (1), 9-18 , 2021 2021 Citations: 1
Hiding Information Using Circular Distribuition AA Alani Journal of the college of education 1 (1), 101-114 , 2015 2015 Citations: 1
PhishFusionNet: A Wide and Deep Phishing Detection with a Hybrid Learning Approach AAA Adil Al-Azzawi Cybernetics And Information Technologies 26 (1), 140-158 , 2026 2026
The Way Forward For Distance Learning In Countries with Low ICT Implementation: The Iraq Case DMBO Ali A. Alani 2nd National Graduate Conference 2 (2), 1-4 , 2014 2014
