جامعة المعرفة
المصدر المعتمد للمعلومات البحثية والمخرجات هو قاعدة بيانات سكوبس (Elsevier Scopus) مع تدقيق بيانات الباحثين من عمادة البحث العلمي.

Research outputs

المخرجات البحثية

مقالات ومراجعات وأوراق مؤتمرات وفصول كتب، مفهرسة برقم DOI ومربوطة بباحثي الجامعة.

8 مُخرَج نتائج البحث عن «bidirectional LSTM»

مقالوصول مغلق20257استشهاد· Semantic Scholar

Reinforcement Learning for Dynamic Optimization of Lane Change Intention Recognition for Transportation Networks

IEEE Transactions on Intelligent Transportation Systems · مجلد 27 (2) · 2695-2705

Advance driver assistance systems (ADAS) swiftly and effectively detect oncoming cars’ lanes-changing intentions in intelligent transportation, supporting decision support and safety. Current techniques fail to account for vehicle interactions and trajectory data temporal dependencies; hence this research proposes a multi-model fusion-based lane-changing intention recognition framework for intelligent transportation. Using actual vehicle trajectory data from a dataset, the suggested model is verified and contrasted with several well used baseline models. According to the experimental findings, the lane change intention detection technique can greatly increase prediction accuracy by fusing attention processes, reinforcement learning-based CRF, and vehicle interaction data. The system’s main components are input processing and lane-changing intention recognition. Vehicle trajectory data is cleaned, labelled, sliced, and one-hot encoded during input processing BiLSTM-F model detects driver lane-change intent, enhanced by incorporating attention mechanism to the Bidirectional Long Short-Term Memory (BiLSTM) network, the model may give changing weights to input processing section output. This lets the model focus on lane-changing intention-affecting factors. Finally, a Reinforcement Learning-based Conditional Random Field (CRF) efficiently determines the globally optimal lane-changing intention. This field fully represents input data temporal interdependence. The model was trained and tested on the public NGSIM dataset. Validation results show it can achieve up to 97.19% accuracy and predict a vehicle’s lane change intention with 94.16% accuracy, two seconds before the actual maneuver occurs. The suggested model outperforms baseline lane-changing intention recognition models in terms of accuracy, loss performance, F1 score, and stability.

reinforcement learningconditional random fieldsattention mechanismbidirectional LSTM
مقالوصول مفتوح202415استشهاد· Semantic Scholar

Artificial Intelligence-driven Remote Monitoring Model for Physical Rehabilitation

Journal of Disability Research · مجلد 3 (1)

In recent times, the quality of life of several individuals has been affected by chronic diseases. Traditional forms of rehabilitation occasionally involve face-to-face sessions, which restricts accessibility and presents challenges for real-time monitoring. Lack of comprehensive understanding of the aspects impacts long-term patient engagement and adherence to remote rehabilitation programs. Individuals and healthcare systems incur a significant portion of the costs associated with rehabilitation treatment. A home-based rehabilitation program reduces the rehabilitation cost. However, the clinicians’ absence may affect the effectiveness of rehabilitation programs. There is a demand for an artificial intelligence-based remote monitoring model for evaluating the physical movements of individuals. Therefore, the study proposes a framework for generating scores for physical rehabilitation exercises. It supports the home-based rehabilitation program by assessing the individual’s movements. The authors employ the You Only Look Once V5–ShuffleNet V2-based image processor for generating scores using the variations between the joints. In addition, they build bidirectional long short-term memory networks for delivering a score for each exercise. Finally, the two outcomes are compared using the modulated rank averaging method for presenting the final score. The authors evaluate the performance of the proposed model using the KiMoRe dataset. The comparative analysis outcome suggested that the proposed model obtained an exceptional mean absolute deviation, mean absolute percentage error, and root mean square error of 0.425, 1.120, and 0.985, respectively. It highlighted the significance of the proposed framework in assessing the individual’s physical movement. Further studies will improve the performance of the proposed framework.

movement assessmentYOLOv5ShuffleNetV2bidirectional LSTM
مقالوصول مفتوح202412استشهاد· Semantic Scholar

Empowering Cybersecurity Using Enhanced Rat Swarm Optimization With Deep Stack-Based Ensemble Learning Approach

IEEE Access · مجلد 12 · 62492-62501

Cybersecurity is a vital technology and measures intended to protect networks, computers, information, and programs from threats and illegal access, modification, or damage. A security model covers a network and a computer safety method. Each system has antivirus software, firewalls, and an intrusion detection system (IDS). IDS helps in discovering and identifying illegal system behavior such as usage, copying, alteration, and damage. By estimating network traffic anomalies and patterns, deep learning (DL) models can enhance the detection abilities of IDS when compared to traditional rule-based methods. These models learn complex representations from data, authorizing them to recognize subtle and developing attack patterns. Techniques like recurrent neural network (RNN) and convolutional neural network (CNN) can be applied to progress consecutive or spatial features in network data, correspondingly. This manuscript empowers Cybersecurity by utilizing an Enhanced Rat Swarm Optimizer with a Deep Stack-Based Ensemble Learning (ERSO-DSEL) model. The ERSO-DSEL approach leverages feature selection (FS) with EL strategies to boost cybersecurity. In the ERSO-DSEL system, Z-score normalization is employed to measure the input data. Besides, an improved equilibrium optimizer (IEO) based FS approach is applied to choose a set of features. For cyberattack recognition, the ERSO-DSBEL approach uses the DSEL approach comprising three models namely deep neural network (DNN), long short-term memory (LSTM), and bidirectional LSTM (Bi-LSTM). Furthermore, the hyperparameter selection of these DL models takes place using the ERSO system. The solution result of the ERSO-DSBEL model is executed on a benchmark IDS database. A wide-contrast study reported that the ERSO-DSBEL model accomplishes an enhanced accuracy outcome of 99.67% over other models of cybersecurity.

intrusion detection systemsfeature selectionhyperparameter optimizationbidirectional LSTM
مقالوصول مغلق20249استشهاد· Semantic Scholar

Deep Learning Model for Interpretability and Explainability of Aspect-Level Sentiment Analysis Based on Social Media

IEEE Transactions on Computational Social Systems · مجلد 12 (3) · 1307-1318

The interactive attention graph convolution network (IAGCN), a novel model proposed in this article, will revolutionize aspect-level sentiment analysis (SA). IAGCN effectively addresses these key features, in contrast to prior research that ignored the meaning of aspect terms and their relationship with context. The model combines a modified dynamic weighting layer with bidirectional long short-term memory (BiLSTM) to accurately acquire context. It takes use of graph convolutional networks (GCNs) to encrypt syntactic information from the syntactic dependency tree. Furthermore, a method for interactive attention is employed to discover the intricate relationships between context and aspect terms, which results in the reconstruction of those terms’ representations. Comparing the proposed IAGCN model to baseline models, impressive gains are made. Across five datasets, the model beats previous methods with an amazing improvement in F1 scores that ranges from 1.34% to 4.04% and an impressive improvement in accuracy that ranges from 0.56% to 1.75%. Additionally, the IAGCN model outperforms the global vectors (GloVe)-based strategy when the potent pretrained model bidirectional encoder representations from transformers (BERT) is included in the challenge, resulting in even greater improvements. The F1 score considerably increases from 2.59% to 7.55%, and accuracy increases from 1.47% to 3.95%, making the IAGCN model a standout performer in aspect-level SA.

aspect-based sentiment analysisinterpretabilityexplainabilitygraph convolutional networks
مقالمفتوح (مستودع)20245استشهاد· Semantic Scholar

Optimizing hybrid deep learning models for drug‐target interaction prediction: A comparative analysis of evolutionary algorithms

Expert Systems · مجلد 42 (2)

Abstract In the realm of Drug‐Target Interaction (DTI) prediction, this research investigates and contrasts the efficacy of diverse evolutionary algorithms in fine‐tuning a sophisticated hybrid deep learning model. Recognizing the critical role of DTI in drug discovery and repositioning, we tackle the challenges of binary classification by reframing the problem as a regression task. Our focus lies on the Convolution Self‐Attention Network with Attention‐based bidirectional Long Short‐Term Memory Network (CSAN‐BiLSTM‐Att), a hybrid model combining convolutional neural network (CNN) blocks, self‐attention mechanisms, and bidirectional LSTM layers. To optimize this complex model, we employ Differential Evolution (DE), Particle Swarm Optimization (PSO), Memetic Particle Swarm Optimization Algorithm (MPSOA), Fire Hawk Optimization (FHO), and Artificial Hummingbird Algorithm (AHA). Through thorough comparative analysis, we evaluate the performance of these evolutionary algorithms in enhancing the CSAN‐BiLSTM‐Att model's effectiveness. By examining the strengths and weaknesses of each algorithm, our study aims to provide valuable insights into DTI prediction, identifying the most effective evolutionary algorithm for hyperparameter tuning in advanced deep learning models. Notably, Fire‐hawk optimization (FHO) emerges as particularly promising, achieving the highest Concordance Index (C‐index) as 0.974 for KIBA datasets and 0.894 for DAVIS datasets and demonstrating exceptional accuracy in ranking continuous predictions across both the datasets.

drug-target interaction predictionevolutionary algorithmshyperparameter optimizationhybrid deep learning model
مقالوصول مفتوح20223استشهاد· Semantic Scholar

Intelligent Smart Grid Stability Predictive Model for Cyber-Physical Energy Systems

Computer Systems Science and Engineering · مجلد 44 (2) · 1219-1231

A cyber physical energy system (CPES) involves a combination of processing, network, and physical processes. The smart grid plays a vital role in the CPES model where information technology (IT) can be related to the physical system. At the same time, the machine learning (ML) models find useful for the smart grids integrated into the CPES for effective decision making. Also, the smart grids using ML and deep learning (DL) models are anticipated to lessen the requirement of placing many power plants for electricity utilization. In this aspect, this study designs optimal multi-head attention based bidirectional long short term memory (OMHA-MBLSTM) technique for smart grid stability prediction in CPES. The proposed OMHA-MBLSTM technique involves three subprocesses such as pre-processing, prediction, and hyperparameter optimization. The OMHA-MBLSTM technique employs min-max normalization as a pre-processing step. Besides, the MBLSTM model is applied for the prediction of stability level of the smart grids in CPES. At the same time, the moth swarm algorithm (MHA) is utilized for optimally modifying the hyperparameters involved in the MBLSTM model. To ensure the enhanced outcomes of the OMHA-MBLSTM technique, a series of simulations were carried out and the results are inspected under several aspects. The experimental results pointed out the better outcomes of the OMHA-MBLSTM technique over the recent models.

cyber-physical energy systemsmulti-head attentionbidirectional LSTMhyperparameter optimization