Towards Robust Speech Models: Mitigating Backdoor Attacks via Audio Signal Enhancement and Fine-Pruning Techniques by Heyan Sun, Qi Zhong, Minfeng Qi, Uno Fang, Guoyi Shi, Sanshuai Cui

“…Second, we apply an adaptive fine-pruning algorithm to selectively deactivate malicious neurons while preserving the model’s linguistic capabilities. …”
Get full text

Multi-Feature Long Short-Term Memory Facial Recognition for Real-Time Automated Drowsiness Observation of Automobile Drivers with Raspberry Pi 4 by Michael Julius R. Moredo, James Dion S. Celino, Joseph Bryan G. Ibarra

“…The model was trained on the NTHU-DDD dataset and optimized using long short-term memory (LSTM) deep learning algorithms implemented using TensorFlow version 2.14.0. …”
Get full text

Protein docking by the underestimation of free energy funnels in the space of encounter complexes. by Yang Shen, Ioannis Ch Paschalidis, Pirooz Vakili, Sandor Vajda

“…We describe a docking method based on stochastic global minimization of funnel-shaped energy functions in the space of rigid body motions (SE(3)) while accounting for flexibility of the interface side chains. …”
Get full text

Lightweight obstacle detection for unmanned mining trucks in open-pit mines by Guangwei Liu, Jian Lei, Zhiqing Guo, Senlin Chai, Chonghui Ren

“…In addition, this paper also adopts the amplitude-based layer adaptive sparse pruning algorithm (LAMP) to further compress the model size while maintaining efficient detection performance. …”
Get full text

Coal mining equipment lifecycle management system architecture and key technology by Yihui PANG, Jinglong BI, Pengzhe YUAN, Baofu ZHAO, Ziwei DING

“…An optimization algorithm and software platform for comprehensive mining equipment selection were developed, and a method for constructing a series spectrum and coding system for coal mining equipment was proposed. …”
Get full text

A Novel Smart Molecular Fuzzy Decision Support System for Solid-State Battery Investments in Grid-Level Renewable Energy Storage by Gang Kou, Hasan Dincer, Serhat Yuksel, Edanur Ergun, Serkan Eti

“…For this purpose, a new decision-making model is developed that includes expert weighting with the entropy game, evaluation balancing with the Q-learning algorithm, calculation of criterion weights with the least squares optimization (LSO) and alternative ranking with the molecular ranking (MORAN) method. …”
Get full text

Deep learning-based energy efficient LSFD weights prediction for user centric cell free massive MIMO system by Moustafa Mohamed, Salwa El-Ramly, Bassant Abdelhamid

“…These models are trained using dataset generated from heuristic sparse LSFD optimization algorithm, this allows the models to learn the sparsity nature of the system and apply AP-UE association based on the values of the predicted LSFD weights at the receiver side while using the large scale fading coefficients as the models’ input. …”
Get full text

Distributed RL-Based Resource Allocation and Task Offloading for Vehicular Edge of Things Computing by Ghada Afifi, Bassem Mokhtar

“…We formulate a belief-based optimization problem to maximize the QoE of vehicular users while providing performance guarantees that account for geospatial uncertainty associated with the availability of embedded resources. …”
Get full text

Faster Convergence With Less Communication: Broadcast-Based Subgraph Sampling for Decentralized Learning Over Wireless Networks by Daniel Perez Herrera, Zheng Chen, Erik G. Larsson

“…Decentralized stochastic gradient descent (D-SGD) is a widely adopted optimization algorithm for decentralized training of machine learning models across networked agents. …”
Get full text

Economic sizing and placement of hydrogen fueling and electric vehicles charging stations powered by renewable and battery systems in smart distribution network by Mehdi Veisi

“…The solution is derived using Benders decomposition algorithm to achieve optimal results. The primary innovation highlighted in this paper includes integrating renewable resources and battery systems to power the refueling station, leveraging reactive power control for improved station performance, and addressing both operational and economic objectives in the distribution system. …”
Get full text

Reinforcement Learning-Driven Secrecy Energy Efficiency Maximization in RIS-Enabled Communication Systems by Akram Y. Sarhan, Osamah A. Abdullah, Hayder Al-Hraishawi, Faisal S. Alsubaei

“…We introduce an innovative framework that utilizes the deep deterministic policy gradient (DDPG) algorithm to address the challenges of the MDP. Our extensive simulations show that our method works much better than current techniques using deterministic policy gradients, like the proximal policy optimization (PPO) framework, in improving SEE. …”
Get full text

Iterative Assessment of Edge Criticality: Efficiency Enhancement or Hidden Insufficiency Detection by Vasily Lubashevskiy, Hamza Ejjbiri, Ihor Lubashevsky

“…The second is the Optimization-based approach, which treats network decomposition as an integral process and optimizes the edge sequence for network decomposition using genetic-like algorithms. …”
Get full text

Multi-Agent Deep Reinforcement Learning Cooperative Control Model for Autonomous Vehicle Merging into Platoon in Highway by Jiajia Chen, Bingqing Zhu, Mengyu Zhang, Xiang Ling, Xiaobo Ruan, Yifan Deng, Ning Guo

“…To enhance training efficiency, we develop a dual-layer multi-agent maximum Q-value proximal policy optimization (MAMQPPO) method, which extends the multi-agent PPO algorithm (a policy gradient method ensuring stable policy updates) by incorporating maximum Q-value action selection for platoon gap control and discrete command generation. …”
Get full text

A UAV Image Stitching Method for Complex Urban Environments by W. Niu, D. Qiu, R. Wu, R. Wu, Z. Wang, Y. Shi

“…To address the issues of uneven feature point distribution, environmental interference, and insufficient real-time performance in UAV image stitching in complex urban environments, this paper proposes an improved ORB algorithm based on Gaussian scale-space optimization and dynamic grid division, combined with a global geometric consistency optimization strategy. …”
Get full text

Energetically self-sufficient robot group study kit by M. A. Rovbo, A. A. Malyshev

“…In addition to performing the target task, ancillary tasks such as maintaining the battery level, communication with other team members in a multi-agent system, should be considered in the control algorithm of the robot, which allows to study the distribution of priorities between these objectives, as shown in the example of multicriteria optimization. …”
Get full text

Modernizing the Design Process for US Organ Allocation Policy: Toward a Continuous Distribution Policy for Kidneys by Elijah Pivo, PhD(c), James Alcorn, JD, Dimitris Bertsimas, PhD, Sarah E. Booker, MPH, Keighly Bradbrook, PhD, Thomas G. Dolan, MS, Lindsay V. Larkin, BA, Kayla R. Temple, BA, Nikolaos Trichakis, PhD

“…Methods. A new simulation algorithm was developed that reduces the time required to simulate 1 y of allocation from >6 h down to about 15 s while using the same simulation model as the preexisting simulator used by the Organ Procurement and Transplantation Network. …”
Get full text

Integrated Energy Management in Small-Scale Smart Grids Considering the Emergency Load Conditions: A Combined Battery Energy Storage, Solar PV, and Power-to-Hydrogen System by Hossein Jokar, Taher Niknam, Moslem Dehghani, Pierluigi Siano, Khmaies Ouahada, Mokhtar Aly

“…Compared to conventional evolutionary methods like particle swarm optimization, non-dominated sorting genetic algorithm III, and biogeography-based optimization, the proposed model exhibits remarkable improvements, outperforming them by 11.4%, 5.6%, and 11.6%, respectively. …”
Get full text

Fast and fair split computing for accelerating deep neural network (DNN) inference by Dongju Cha, Jaewook Lee, Daeyoung Jung, Sangheon Pack

“…To address these issues, we formulate an optimization problem to determine one or two split points that minimize inference latency while ensuring fair offloading among MDs. …”
Get full text

Deep Reinforcement Learning-Based Multi-Agent System with Advanced Actor–Critic Framework for Complex Environment by Zihao Cui, Kailian Deng, Hongtao Zhang, Zhongyi Zha, Sayed Jobaer

“…We introduce an advanced multi-agent deep reinforcement learning (DRL) framework, specifically a Multi-Agent Proximal Policy Optimization (MA-PPO), designed to optimize target acquisition while operating within defined ammunition and time constraints. …”
Get full text

A critical evaluation of Pure Pursuit, MPC and MPCC: Balancing simplicity, performance and constraints by Kong Xiangyiming, Fisher Callen, Evans Benjamin

“…The computational demands of optimization-based algorithms result in a computation delay where the algorithm calculates for the vehicle's position one iteration behind its actual movement. …”
Get full text