A novel method based on lesion expansion to assess plant disease severity by Feng Qin, Haiguang Wang, Qian Jiang, Hongli Wang

“…This study provided a new idea and method for accurate severity assessment of plant diseases and provided support for the automatic and intelligent assessment of plant disease severity.…”
Get full text

Hybrid modeling of adsorption process using mass transfer and machine learning techniques for concentration prediction by Jing Lv, Lei Wang

Get full text

Four-Dimensional Path Planning Methodology for Collaborative Robots Application in Industry 5.0 by Ilias Chouridis, Gabriel Mansour, Vasileios Papageorgiou, Michel Theodor Mansour, Apostolos Tsagaris

“…An offline 4D path planning algorithm is proposed to find the optimal path in an environment with static and dynamic obstacles. …”
Get full text

Digital twin empowered lightweight and efficient blockchain for dynamic internet of vehicles by Haoye Chai, Supeng Leng, Jianhua He, Ke Zhang

“…The decentralized LPMA-DDPG algorithm is helpful for implementing the optimal DT construction strategy in practical ITS.…”
Get full text

Curing simulation and data-driven curing curve prediction of thermoset composites by Chenchen Wu, Ruming Zhang, Pengyuan Zhao, Liang Li, Dingguo Zhang

“…Then, the temperature–time and the resulting degree-of-cure-time curves obtained from finite element simulations were created for training the prediction models using machine learning approaches of support vector regression (SVR), back propagation (BP) neural network and BP neural network optimized by genetic algorithm (GA-BP). The validation and evaluation indices illustrate that the degree-of-cure curve prediction model trained by the GA-BP neural network yields the highest accuracy.…”
Get full text

An Improved Crop Disease Identification Method Based on Lightweight Convolutional Neural Network by Tingzhong Wang, Honghao Xu, Yudong Hai, Yutian Cui, Ziyuan Chen

“…In order to improve the training learning rate, Adam optimizer combining momentum algorithm and RMSprop algorithm is used to dynamically adjust the learning rate; the combination of the two algorithms makes the loss function converge to the lowest point faster. …”
Get full text

Bio-inspired multispectral camouflage material for microwave, infrared, and visible bands based on single hierarchical metasurface by Liu Shiju, Zhou Congyang, Tan Ruiyang, Han Mengqi, Wu Zhijing, Chen Ping

“…The structural parameters were calculated and optimized through an equivalent circuit model-based artificial intelligence algorithm. …”
Get full text

Power quality solutions for rail transport using AI-based unified power quality conditioners by D. K. Nishad, A. N. Tiwari, Saifullah Khalid, Sandeep Gupta

“…Abstract This paper proposes an artificial intelligence-based Unified Power Quality Conditioner (AI-UPQC) and a unique Dynamic K-factor PI (DKPI) algorithm for PI-UPQC to address power quality issues in electrified railway systems. …”
Get full text

Secure Latency-Aware Task Offloading Using Federated Learning and Zero Trust in Edge Computing for IoMT by Waleed Almuseelem

“…Within FL, an improved on-policy temporal difference control algorithm is leveraged for local model training. Moreover, this algorithm determines the optimal offloading strategy based on the global model while considering trustworthiness, the heterogeneous nature of tasks, resource availability, and latency. …”
Get full text

A novel interval valued bipolar fuzzy hypersoft topological structures for multi-attribute decision making in the renewable energy sector by Muhammad Imran Harl, Muhammad Saeed, Muhammad Haris Saeed, Muhammad Salman Habib, Seung-June Hwang

“…The algorithm is applied to select optimal renewable energy source based on their economic, environmental, and technical aspects. …”
Get full text

Utilising AI technique to identify depression risk among doctoral students by Changhong Teng, Chunmei Yang, Qiushi Liu

“…Based on the data from the 2019 Nature Global Doctoral Student Survey, we first screened 13 highly relevant features from a total of 37 features potentially related to the risk of depression among doctoral students by Random Forest algorithm. Subsequently, we trained the optimal prediction model to predict the doctoral students with depression risk using a Multilayer Perceptron (MLP), achieving an accuracy of 89.09% on the test set. …”
Get full text

Three-Dimensional Trajectory Tracking Control for Stratospheric Airship Based on Deep Reinforcement Learning by Xixiang Yang, Fangchao Bai, Xiaowei Yang, Yuelong Pan

“…The Boltzmann random distribution of reward value and probability of wind direction angle were taken as the action selection criteria of the Q-learning algorithm, the cerebellar model articulation controller (CMAC) neural network was constructed for the discrete action value, and the optimal action sequence was fast obtained. …”
Get full text

Cluster channel equalization using adaptive sensing and reinforcement learning for UAV communication by Xin Liu, Shanghong Zhao, Yanxia Liang, Shahid Karim

“…This algorithm leverages the U-Net model to sense channel states in real time and intelligently adjusts data forwarding strategies based on fuzzy values generated by the fuzzy reinforcement Q-learning. …”
Get full text

Deep Learning-Based Sound Source Localization: A Review by Kunbo Xu, Zekai Zong, Dongjun Liu, Ran Wang, Liang Yu

“…Future research should prioritize physics-informed modeling to embed acoustic propagation mechanisms, unsupervised domain adaptation to reduce reliance on labeled data, and sensor-algorithm co-design to optimize hardware-software synergy. …”
Get full text

A Multi-Mode Switching Energy Management Strategy Based on Travel Habits for Range-Extended Electric Vehicle by Zhenhai Gao, Guoqing Zhang, Hanwu Liu, Cheng Chang, Jingwen Dong, Rongrong He, Yu Cai

“…REEV has the advantages of high power, high efficiency and long driving range, and it is the core technology. An intelligent and efficient EMS must take into account all driving conditions to maximize power utilization while allowing the engine to work in the high-efficiency area to minimize fuel consumption. …”
Get full text

Monitoring of Transformer Hotspot Temperature Using Support Vector Regression Combined with Wireless Mesh Networks by Naming Zhang, Guozhi Zhao, Liangshuai Zou, Shuhong Wang, Shuya Ning

Get full text

Mitigating spatial hallucination in large language models for path planning via prompt engineering by Hongjie Zhang, Hourui Deng, Jie Ou, Chaosheng Feng

“…To address this, we propose S2ERS, an LLM-based technique that integrates entity and relation extraction with the on-policy reinforcement learning algorithm Sarsa for optimal path planning. We introduce three key improvements: (1) To tackle the hallucination of spatial, we extract a graph structure of entities and relations from the text-based maze description, aiding LLMs in accurately comprehending spatial relationships. (2) To prevent LLMs from getting trapped in dead ends due to context inconsistency hallucination by long-term reasoning, we insert the state-action value function Q into the prompts, guiding the LLM’s path planning. (3) To reduce the token consumption of LLMs, we utilize multi-step reasoning, dynamically inserting local Q-tables into the prompt to assist the LLM in outputting multiple steps of actions at once. …”
Get full text

A Study of Transmission Point Selection for Multi-Connectivity in Multi-Band Wireless Networks by Eunkyung Kim, Dongwan Kim, Changbeom Choi

Get full text

Efficient Detection of Microplastics on Edge Devices With Tailored Compiler for TinyML Applications by Alessandro Cerioli, Lorenzo Petrosino, Daniele Sasso, Clement Laroche, Tobias Piechowiak, Luca Pezzarossa, Mario Merone, Luca Vollero, Anna Sabatini

Get full text

A Novel Model with GA Evolving FWNN for Effluent Quality and Biogas Production Forecast in a Full-Scale Anaerobic Wastewater Treatment Process by Zehua Huang, Renren Wu, XiaoHui Yi, Hongbin Liu, Jiannan Cai, Guoqiang Niu, Mingzhi Huang, Guangguo Ying

“…The analysis results indicate that the FWNN with the optimal algorithm had a high speed of convergence and good quality of prediction, and the FWNN model was more advantageous than the traditional intelligent coupling models (NN, WNN, and FNN) in prediction accuracy and robustness. …”
Get full text