Convolutional neural network model over encrypted data based on functional encryption by Chen WANG, Jiarun LI, Jian XU

“…Currently, homomorphic encryption, secure multi-party computation, and other encryption schemes are used to protect the privacy of sensitive data in outsourced convolutional neural network (CNN) models.However, the computational and communication overhead caused by the above schemes would reduce system efficiency.Based on the low cost of functional encryption, a new convolutional neural network model over encrypted data was constructed using functional encryption.Firstly, two algorithms based on functional encryption were designed, including inner product functional encryption and basic operation functional encryption algorithms to implement basic operations such as inner product, multiplication, and subtraction over encrypted data, reducing computational and communication costs.Secondly, a secure convolutional computation protocol and a secure loss optimization protocol were designed for each of these basic operations, which achieved ciphertext forward propagation in the convolutional layer and ciphertext backward propagation in the output layer.Finally, a secure training and classification method for the model was provided by the above secure protocols in a module-composable way, which could simultaneously protect the confidentiality of user data as well as data labels.Theoretical analysis and experimental results indicate that the proposed model can achieve CNN training and classification over encrypted data while ensuring accuracy and security.…”
Get full text

Rolling Force Prediction of Hot Rolling Based on GA-MELM by Jingyi Liu, Xinxin Liu, Ba Tuan Le

“…In this paper, a rolling force prediction method based on genetic algorithm (GA), particle swarm optimization algorithm (PSO), and multiple hidden layer extreme learning machine (MELM) is proposed, namely, PSO-GA-MELM algorithm, which takes MELM as the basic model for rolling force prediction. …”
Get full text

Distribution Ratio Prediction of Major Components in 30%TBP/kerosene-HNO3 System Based on Machine Learning by YU Ting1, ZHANG Yinyin2, ZHANG Ruizhi3, JIN Wenlei2, LUO Yingting2, ZHU Shengfeng3, HE Hui1, YE Guoan1, GONG Helin4

“…These models were trained based on different datasets, and their hyper-parameters were optimized using algorithms such as grid search, Bayesian optimization, and K-fold cross-validation. …”

Robust SAR Change Detection Using Hierarchical Clustering With Adaptive Parameter Tuning by Ahidjo Abdoulaye, Alejandro C. Frery, Mingyang Ma, Shaohui Mei

“…The methodology consists of computing a difference image using a logarithmic ratio operator, optimizing clustering parameters, computing high-change probability clusters, and generating a refined change map. …”
Get full text

Design a low-noise 5GHz wideband microwave power amplifier using 90nm CMOS technology with area reduction employing an active inductor by Taha Naufal Fadhil, A.Z. Yonis

“…Lastly, this work illustrates how genetic algorithm optimization has drastically changed LNA design. …”
Get full text

A Novel Method for Decoding Any High-Order Hidden Markov Model by Fei Ye, Yifei Wang

Get full text

Application of Three-Dimensional Hierarchical Density-Based Spatial Clustering of Applications with Noise in Ship Automatic Identification System Trajectory-Cluster Analysis by Shih-Ming Wang, Wen-Rong Yang, Qian-Yi Zhuang, Wei-Hong Lin, Mau-Yi Tian, Te-Jen Su, Jui-Chuan Cheng

Get full text

Training Large Models on Heterogeneous and Geo-Distributed Resource with Constricted Networks by Zan Zong, Minkun Guo, Mingshu Zhai, Yinan Tang, Jianjiang Li, Jidong Zhai

“…To achieve this goal, we formulate the model partitioning problem among heterogeneous hardware and introduce a hierarchical searching algorithm to solve the optimization problem. Besides, a mixed-precision pipeline method is used to reduce the cost of inter-cluster communications. …”
Get full text

The Role of Artificial Intelligence (AI) in the Future of Forestry Sector Logistics by Leonel J. R. Nunes

“…Methods: This study combines a literature review and case analysis to assess the impact of AI on forestry logistics. Machine Learning algorithms, optimization systems, and monitoring tools based on the Internet of Things (IoT) and computer vision were analyzed to assess impacts in areas such as transportation planning, inventory management, and forest monitoring. …”
Get full text

Calcium dynamics in habenular astrocytes regulate active coping within behavioral transitions by Léo Michel, Denys Osypenko, Patricia Molina, Kadir A. Mutlu, Salvatore Lecca, Chihiro Hisatsune, Katsuhiko Mikoshiba, Toko Kikuchi, Emre Yaksi, Andrea Volterra, Manuel Mameli

Get full text

Deep reinforcement learning applications and prospects in industrial scenarios by JING TAN, Ligang YANG, Xiaorui LI, Zhaolin YUAN, Yunduan CUI, Chao YAO, Zongjie WANG, Xiaojuan BAN

“…Central to these systems are control algorithms, which enable the automation of operations, optimization of process parameters, and reduction of operational costs. …”
Get full text

Statistical mechanics of dynamical system identification by Andrei A. Klishin, Joseph Bakarji, J. Nathan Kutz, Krithika Manohar

“…To establish this analogy, we define the hyperparameter optimization procedure as a two-level Bayesian inference problem that separates variable selection from coefficient inference and enables the computation of the posterior parameter distribution in closed form. …”
Get full text

An Evolutionary Deep Reinforcement Learning-Based Framework for Efficient Anomaly Detection in Smart Power Distribution Grids by Mohammad Mehdi Sharifi Nevisi, Mehrdad Shoeibi, Francisco Hernando-Gallego, Diego Martín, Sarvenaz Sadat Khatami

“…Statistical <i>t</i>-tests confirm the superiority of DRL-NSABC over other algorithms, while achieving a variance of 0.00014. Moreover, DRL-NSABC demonstrates the fastest convergence, reaching near-optimal accuracy within the first 100 epochs. …”
Get full text

Multi task detection method for operating status of belt conveyor based on DR-YOLOM by Yongan LI, Tengjie CHEN, Hongwei WANG, Zhihao ZHANG

“…The results show that compared to mainstream single detection algorithms, DR-YOLOM multi task detection algorithm has better comprehensive detection ability, and this algorithm can ensure high target recognition accuracy, segmentation accuracy, and appropriate inference speed with a small number of parameters. …”
Get full text

A Novel Minimization Method for Sensor Deployment Via Heuristic 2-Sat Solution by Waleed Ahmed, Ali Muhammad Ali Rushdi

“…Other algorithms like Pseudo-Boolean SAT Solvers can also be used for the minimization purpose. …”
Get full text

Local Outlier Detection Method Based on Improved K-means by Yu ZHOU, Hao XIA, Xuezhen YUE, Peichong WANG

“…When there is no significant decrease in the cost function value with an increase in the number of cluster centers, the position of the “elbow” is observed to determine the optimal number of clusters. After determining the initial cluster centers and the number of clusters <italic>k</italic>, the dataset is clustered using the K-means clustering algorithm to obtain <italic>k</italic> clusters and their corresponding cluster centers. …”
Get full text

An improved deep learning approach for automated detection of multiclass eye diseases by Feudjio Ghislain, Saha Tchinda Beaudelaire, Romain Atangana, Tchiotsop Daniel

Get full text

Processing of Polymers Stress Relaxation Curves Using Machine Learning Methods by Anton S. Chepurnenko, Tatiana N. Kondratieva, Ebrahim Al-Wali

Get full text

Weibull-Type Incubation Period and Time of Exposure Using <i>γ</i>-Divergence by Daisuke Yoneoka, Takayuki Kawashima, Yuta Tanoue, Shuhei Nomura, Akifumi Eguchi

Get full text

Trajectory Tracking Control of a Six-Degree-of-Freedom Manipulator Based on EAVOA-LADRC by Xinxin Shi, Haihao Yu

“…Therefore, a linear self-imposed perturbation parameter tuning method based on the Enhance African Vulture Optimization Algorithm (EAVOA) is proposed. In order to solve the problem that the AVOA is unbalanced between the exploration stage and the development stage, and is prone to fall into the local optimal solution, the Kent Chaos initialization, Cauchy inverse learning, optimization of the F computation, and introduction of inhibition coefficients are proposed as the improvement strategies. …”
Get full text