BSc from al-Nahrain university college of engineering / electronic and communications engineering department
MSc from al-Nahrain university college of engineering / electronic and communications engineering department
PhD from technology university / electrical engineering department
Machine learning-based intelligent video surveillance in smart city framework Mohammed A. J. Maktoof, Ibraheem H.. M., Mohammed A. Abdul Razzaq, Ahmed Abbas, Ali Majdi Fusion Practice and Applications, 2023 The proposed method of using Machine Learning in Motion Detection and Pedestrian Tracking-assisted Intelligent Video Surveillance Systems (ML-IVSS) can be seen as an application of intelligent fusion techniques. ML-IVSS combines the power of motion detection, pedestrian tracking, and machine learning to create a more accurate and efficient surveillance system for smart cities. By fusing these techniques, ML-IVSS can effectively detect unusual behaviors such as trespassing, interruption, crime, or fall-down, and provide accurate depth data from surveillance footage to protect residents. Intelligent fusion techniques can help improve the accuracy and effectiveness of surveillance systems in smart cities, making them safer and more secure for residents. Combination channel models are used at first, and an object area with prominent features is selected for surveillance. Scaled modification and extraction of features are carried out on the presumed object's region. Identifying the low-level characteristic is the first step in incorporating it into neural architectures for deep feature learning. A smart CCTV data set is used to evaluate the proposed method's performance. According to the numerical analysis, the proposed ML-IVSS model outperforms other traditional approaches in terms of abnormal behaviour detection (98.8%), prediction (97.4%), accuracy (96.9%), F1-score (97.1%), precision (95.6%), and recall (96.2%).
Prediction of Stock Market Price using Bi-directional Recurrent Neural Network R Archana Reddy, Kassem Al-Attabi, Bollampelly Chandana, Ibraheem Hatem Mohammed, Bhuvaneswary IEEE 1st International Conference on Ambient Intelligence Knowledge Informatics and Industrial Electronics Aikiie 2023, 2023 Recently, an accurate prediction of stock market returns is a very challenging task due to volatile and non-linear nature of the financial stock markets. The advent of artificial intelligence and enhanced processing power has led to the realisation that preprogrammed techniques are more effective at forecasting stock values. The stock market is currently one of the most researched and fastest developing subj ects, and predicting its behaviour is crucial. The primary challenge in this area of research remains improving forecast precision. Strong shareholder returns are made possible by stock price forecasting. Despite this, researchers use these algorithms to predict continuing market trends based on Stock Technical Indicators (STIs), due to recent advancements in machine learning techniques. This study analyses Yahoo Finance data from STIs over a decade to predict stock prices using a Bi- directional Recurrent Neural Network (BI-RNN). Initially, the analysed STIs were used as input for an autoencoder during the dimensionality reduction procedure, which reduced the correlation between the STIs. These STIs and the Yahoo Finance data were then provided to BI-RNN. Next, in order to forecast stock prices, the BI-RNN's outcome attributes were fed into the soft max layer. From the results, it clearly shows that proposed Bi-RNN shown better results in terms of a minimal MAPE value of 0.41, MAE of 4.42, RMSE of 0.10, and MSE of 212.25 in the experiments, the proposed strategy surpassed traditional methods.
An Improved Whale Optimization Algorithm Based Secure and Energy-Aware Clustering in Vehicular Ad hoc Network Kassem Al-Attabi, Srinivas Aluvala, B.M Manjula, Ibraheem Hatem Mohammed, Santhosh Bodduppalli International Conference on Integrated Intelligence and Communication Systems Iciics 2023, 2023 The Vehicular Ad hoc Network (VANET) is a mobile network which enables a numerous intelligent transportation system. The secure routing is significant to prevent mobile devices from other threats so, the effective characteristics in VANET are utilized to attain an efficient secure routing path. The high vehicle distribution and node mobility compromises the network scalability and topology. So, creating the reliable and scalable vehicle communication, network physical layout formation, unstable link to enable robust are difficult task in traffic network. In this research, novel optimization algorithm is considered with transmission range, speed direction, grid size and node density during the clustering. The Improved Whale optimization Algorithm for clustering in VANET (IWOA) is proposed for selecting an optimal Cluster Head (CH). Primarily, the optimal CH are selected by using IWOA and then the route path is selected. The simulations are performed and then the experiments are conducted on the IWOA. The performance of IWOA is evaluated using throughput, Packet Delivery Ratio (PDR) and latency by various rounds of 30, 40, 50, 60 and 70. The IWOA attained high throughput of 6. 87mbps and PDR of 0.93 with less latency of 0.10s which is superior than other existing algorithms.
Prediction of Startup Performance Using Bidirectional Long Short-Term Memory with Parametric Switch Activation Function Putta Srivani, Gopu Sowjanya, Bura Vijay Kumar, Kassem AL-Attabi, Ibraheem Hatem Mohammed IEEE 1st International Conference on Ambient Intelligence Knowledge Informatics and Industrial Electronics Aikiie 2023, 2023 Predicting start-up success has garnered increasing attention in recent years. Numerous predictive models and methodologies have been devised to ascertain the probability of a start-up's triumph contingent on diverse aspects. Large datasets have been analysed using machine learning techniques like logistic regression, decision trees, and neural networks to find patterns that can help predict startup success. Predicting the success of a start-up, however, is a difficult undertaking because the business environment is unpredictable and changeable. Efficient resource utilization is crucial for economic development and has a direct impact on reducing unemployment rates. In order to minimize resource wastage and mitigate the risk of failure, the research identified and examined specific factors that influence the success or failure of small-scale companies. In the current research, the Crunch Base dataset is utilized to predict the failure or success of start-ups by employing the Bidirectional Long Short-Term Memory (Bi-LSTM) with Parametric Switch Activation (PSA) function model. The Bi-LSTM unit, a type of Recurrent Neural Network (RNN), incorporates the Feed Forward Neural (FFN) Network for classification purposes. The suggested Bi-LSTM model achieved a higher accuracy rate of 72.26% compared to existing methods. The suggested Bi-LSTM model achieved a higher accuracy rate of 72.26% compared to existing methods.
E-commerce Product Review Analysis based on Multi-class Support Vector Machine Laith H. Alzubaidi, Ibraheem Hatem Mohammed, Gotte Ranjith kumar, B Sarada, N. Radha IEEE 1st International Conference on Ambient Intelligence Knowledge Informatics and Industrial Electronics Aikiie 2023, 2023 Recently, an extensive number of consumers can choose their best options from automated retailers and compare products in online stores. Sentiment analysis is frequently employed in applications meant to demonstrate and provide client service as the voice of the user. On E-commerce websites, user reviews provide helpful information about the product. Sentiment analysis of the text reviews helps forecast product sales by assessing user sentiment regarding the product. The Word Embedding Attention approach assigns additional weight to words that have a strong association with a specific class. Sentiment analysis machine learning models provide a thorough depiction of capabilities and far surpass conventional feature-based methods. The obj ective of this research is to improve sentiment analysis performance by creating a weighted ensemble with a Multi-class Support Vector Machine (MSVM) model utilising novel word embedding techniques. Because of the weighted ensemble's higher generalisation skills, MSVM produces superior results. When comparing existing methods for sentiment analysis, the Weighted ensemble with MSVM has produced higher results in terms of accuracy, precision, f-score, and recall. The Weighted ensemble with an MSVM has achieved 99.87 % accuracy, 99.39% precision, 99.03% f-score, and 99.690/0 recall in sentiment analysis when comparing existing methods such as LSTM+FL, APSO-LSTM, ABCDM, SSentiA, and Hybrid CNN+LSTM.
Chaotic Sparrow Search Algorithm with Deep Learning for Anomaly Detection in Internet of Things Ibraheem Hatem Mohammed, Bura Vijay Kumar, Bukya Mohan Babu, Bollipelly PruthviRaj Goud, Kassem Al-Attabi International Conference on Integrated Intelligence and Communication Systems Iciics 2023, 2023 Anomaly Detection (AD) systems play a crucial role in identifying potential cyber-attacks or data breaches by recognizing patterns of irregular data within the Internet of Things (IoT). Standard Machine Learning (ML) techniques often prove inefficient in the face of unpredictable network behaviors and diverse anomalous methods. Deep Learning (DL) has appeared as an efficient as well as robust approach for AD, capable of classifying abnormal behaviors or patterns in data. A Chaotic Sparrow Search Algorithm with DL utilizing Recurrent Neural Network (RNN-CSSA) is proposed for AD in IoT aided sustainable smart cities. A primary objective of RNN-CSSA technique is to accurately detect anomalies in IoT aided smart cities. To achieve this, the RNN-CSSA system employs Binary Pigeon optimization Algorithm (BPEO) for effective feature selection. Additionally, CSSA technique utilizes the RNN approach for classifying anomalies. The evaluations results of the RNN-CSSA algorithm utilized the benchmark databases such as UCI-SECOM and UNSW NB-15. The results exhibit an effectiveness of proposed RNN-CSSA methodology, achieving accuracies of 99.54% and 99.55% in UNSW NB-15 and UCISECOM, when compared with existing models.
Intrusion Detection System in IoT using Grey Wolf Optimization-Based Support Vector Machine K Ramakrishna, Nagendar Yamsani, Ibraheem Hatem Mohammed, Hafeena Mohammad, Kassem Al-Attabi International Conference on Integrated Intelligence and Communication Systems Iciics 2023, 2023 The Internet of Things (IoT) is appearing as a new technology for the development of different critical applications. To prevent adversarial attacks, fraud, and network intrusion, the Intrusion Detection System (IDS) has become a major component of organizations. In this research, the Grey Wolf optimization based Support Vector Machine (GWO-SVM) is proposed for the intrusion detection system using machine learning. Initially, the data is obtained by the Bot-IoT dataset and then min-max normalization is performed to normalize the acquired data. The different feature extraction approaches such as LeeNET, Gray-Level Co-occurrence matrix (GLCM), and Local Ternary Pattern (LTP) are used to extract appropriate features from the obtained data. The GWO approach is used for feature selection which examines appropriate features for classification. Finally, the SVM classification is performed to identify and classify intrusion detection accurately and effectively. The proposed GWO-SVM achieves a better accuracy of 99.67%, precision of 99.50%, recall of 99.47%, and f1-score of 99.60% respectively.
Implementation of sawtooth wavelet thresholding for noise cancellation in one dimensional signal International Journal of Nanoelectronics and Materials, 2019
Industry, Institute, or Organisation Collaboration
