STEM: spatial speech separation using twin-delayed DDPG reinforcement learning and expectation maximization by Muhammad Salman Khan (7202543)

“…<p>Although many high-performing speech separation models have been proposed recently, little attention has been paid to making them lightweight. In this paper, a novel speech separation algorithm is proposed that integrates the twin-delayed deep deterministic (TD3) policy gradient reinforcement learning (RL) agent with the expectation maximization (EM) algorithm for clustering the spatial cues of individual sources separated on azimuth. …”

A conjugate self-organizing migration (CSOM) and reconciliate multi-agent Markov learning (RMML) based cyborg intelligence mechanism for smart city security by S. Shitharth (12017480)

“…Here, the Quantized Identical Data Imputation (QIDI) mechanism is implemented at first for data preprocessing and normalization. …”

Development of a deep learning-based group contribution framework for targeted design of ionic liquids by Sadah Mohammed (18192859)

“…Finally, the algorithm is employed in a CO₂ capture case study to generate and select the best-performing novel ILs, which exhibit behavior consistent with established ILs in the literature.…”

Topology and parameter estimation in power systems through inverter-based broadband stimulations by Margossian, Harag

“…To process and evaluate this data, a novel aggregation method based on weighed least squares will be proposed in this study. …”
Get full text
Get full text
Get full text
Get full text

Geographical Area Network—Structural Health Monitoring Utility Computing Model by Hasan Tariq (18131842)

“…Every gateway is routing the data to SHM-UCM servers running a geo-spatial patch health assessment and prediction algorithm. …”

Agent-Based Reactive Geographic Routing Protocol for Internet of Vehicles by Mazouzi, Mohamed

“…The design of an efficient routing algorithm for Internet of Vehicles (IoV) is a challenging research issue due to the inherent characteristics of IoV network, such as high-speed mobility of nodes, frequent topology change, link instability, and the presence of radio obstacles. …”
Get full text
Get full text
Get full text
Get full text

Spectral energy balancing system with massive MIMO based hybrid beam forming for wireless 6G communication using dual deep learning model by Ramesh Sundar (19326046)

“…The proposed approach of DDN is trained with proper data sequences used for communication and the training phase is conducted with the norms of numerous channel variants. …”

Exploring Digital Competitiveness through Bayesian Belief Networks by Qazi, Abroon

“…The results emphasize the importance of a holistic strategy that considers these interconnections rather than isolated improvements. By providing a data-driven prioritization of key factors, this study offers policymakers a novel framework for resource allocation and strategic interventions. …”
Get full text

Enhancing Student Services: Machine Learning Chatbot Intent Recognition for High School Inquiries by Assayed, Suha Khalil

Get full text
Get full text

ARDENT: A Proactive Agent-Based Routing Protocol for Internet of Vehicles by Mazouzi, Mohamed

“…The design of an efficient routing algorithm for the Internet of Vehicles (IoV) poses several problems due to its special characteristics, including nodes high-speed mobility, frequent topology change, link instability, and the presence of radio obstacles. …”
Get full text
Get full text
Get full text
Get full text

A multi-pretraining U-Net architecture for semantic segmentation by Cagla Copurkaya (22502042)

“…For the validation of the proposed model, we used data from 21,000 cell nuclei at a resolution of 1000 by 1000 pixels. …”

Online Control and Optimization of Directional Drilling by unknown

“…Gravitational Search Algorithm (GSA) is developed to search for optimal settings of the proposed controller. …”
Get full text

RFID localization using single reader antenna. (c2014) by Msheik, Hamze

“…In this work we propose a novel RFID based Localization methodology. Our scheme is based on Power Map Matching algorithm. …”
Get full text
Get full text

Joint computing, communication and cost-aware task offloading in D2D-enabled Het-MEC by Abbas, Nadine

“…Due to the exploding traffic demands and the diversity of novel applications requiring extensive computation and radio resources, research has been active to devise mechanisms for responding to these challenges. …”
Get full text
Get full text
Get full text
Get full text

Multi-Modal Emotion Aware System Based on Fusion of Speech and Brain Information by M. Ghoniem, Rania

“…For classifying unimodal data of either speech or EEG, a hybrid fuzzy c-means-genetic algorithm-neural network model is proposed, where its fitness function finds the optimal fuzzy cluster number reducing the classification error. …”
Get full text
Get full text

Structural similarity evaluation between XML documents and DTDs by Tekli, J.

“…We consider the various DTD operators that designate constraints on the existence, repeatability and alternativeness of XML elements/attributes. Our approach is based on the concept of tree edit distance, as an effective and efficient means for comparing tree structures, XML documents and DTDs being modeled as ordered labeled trees. …”
Get full text
Get full text
Get full text
Get full text

Making progress with the automation of systematic reviews: principles of the International Collaboration for the Automation of Systematic Reviews (ICASR) by Elaine Beller (44602)

“…Recent advances in natural language processing, text mining and machine learning have produced new algorithms that can accurately mimic human endeavour in systematic review activity, faster and more cheaply. …”

Prediction of Multiple Clinical Complications in Cancer Patients to Ensure Hospital Preparedness and Improved Cancer Care by Regina Padmanabhan (14231606)

“…Other highlights are (1) a novel set of easily available features for the prediction of the aforementioned clinical complications and (2) the use of data augmentation methods and model-scoring-based hyperparameter tuning to address the problem of class disproportionality, a common challenge in medical datasets and often the reason behind poor event prediction rate of various predictive models reported so far. …”

Multi-UAV-Enabled Mobile Edge Computing IoT Systems: Joint Association and Resource Allocation Framework by Abu Farha, Yazan Mahmoud

Get full text

Ensemble Deep Random Vector Functional Link Neural Network for Regression by Minghui Hu (2457952)

“…The esc-edRVFL is identified as the best-performing algorithm through a comprehensive evaluation of 31 UCI datasets.…”