ASSESSMENT OF CHANGES IN THE GROUND CHARACTERISTICS OF HAIL DURING ANACTIVE IMPACT ON HAIL PROCESSES by N. V. Teunov

“…Multiple linear regression equations were constructed for the relationship between the ground characteristics of hail (average diameter, average surface density of kinetic energy, average concentration) and atmospheric parameters. …”
Get full text

Design of an improved graph-based model integrating LSTM, LoRaWAN, and blockchain for smart agriculture by Ravi Kumar Munaganuri, Narasimha Rao Yamarthi, Sai Chandana Bolem

“…LSTM networks are chosen here for their high performance in timestamp series prediction tasks with an mean average error (MAE) of 0.02 m3/m3 over a 7-day forecast horizon. …”
Get full text

Multi-Objective Improved Differential Evolution Algorithm-Based Smart Home Energy Management System Considering Energy Storage System, Photovoltaic, and Electric Vehicle by Mina GhasemiGarpachi, Moslem Dehghani, Mokhtar Aly, Jose Rodriguez

“…Home energy management systems (HEMSs) are becoming increasingly popular as smart homes become more prevalent, along with their ability to reduce peak network loads and generate and store green energy locally. …”
Get full text

Enhancing Stock Price Forecasting With a Hybrid SES-DA-BiLSTM-BO Model: Superior Accuracy in High-Frequency Financial Data Analysis by Talabathula Jayanth, A. Manimaran, G. Siva

“…Deep Learning (DL) approaches, particularly Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks, have shown notable promise in enhancing prediction accuracy for stock prices. …”
Get full text

A Human Pose Estimation Algorithm with Scale Invariant by SUN Ruiyang, YANG Huixin, ZHAO Lanfei

“…Thirdly, resolution attention mechanism is introduced into multi-resolution feature fusion, leading to enhance invariance in scales. Finally, optimized network is designed to reduce quantisation error caused by sampling. …”
Get full text

Anti-Jamming RIS Communications Using DQN-Based Algorithm by Pham Duy Thanh, Hoang Thi Huong Giang, Ic-Pyo Hong

“…To this end, we formulate an anti-jamming communication optimization problem as a Markov decision process (MDP) framework and then design a deep Q network (DQN)-based algorithm to generate an optimal policy. …”
Get full text

Detection of multiple pesticide residues on the surface of broccoli based on hyperspectral imaging by GUI Jiangsheng, GU Min, WU Zixian, BAO Xiao’an

“…The results showed that the optimal model is the SPA-ELM model, and the accuracy of training set is 98.33%, and the correct rate of test set is 96.67%, suggesting that it is feasible to use the principal component analysis algorithm and the artificial neural network algorithm to identify the pesticide residues on the surface of broccoli. …”
Get full text

Enhancing water saturation predictions from conventional well logs in a carbonate gas reservoir with a hybrid CNN-LSTM model by Ali Gohari Nezhad, Mohammad Emami Niri

“…The methodology includes data pre-processing to de-noise and transform data into a proper format, feature engineering followed by feature selection based on domain knowledge, models’ training, testing, and optimizing. XGBoost hyperparameters were tuned using grid search, and each neural network model was optimized using a genetic algorithm. …”
Get full text

Enhancing On-Device DNN Inference Performance With a Reduced Retention-Time MRAM-Based Memory Architecture by Munhyung Lee, Taehan Lee, Junwon Yeo, Hyukjun Lee

“…As applications using deep neural networks (DNNs) are increasingly deployed on mobile devices, researchers are exploring various methods to achieve low energy consumption and high performance. …”
Get full text

Deployment strategy for static chargers in WRSN by Hao HE, Yong-rui CHEN, Wei-dong YI, Ming LI

“…The traditional deployment strategy of static chargers in wireless rechargeable sensor networks (WRSN) covers all the area.The basic idea is to cover all the positions of nodes.A mathematical model of distance between a charger and the farthest node was established,the relationship between the number of nodes and the mathematical expectation of minimum radius of charging was analyzed,and deployment strategy for static chargers was proposed.The method based on the locations of all nodes that need to be charged in the area,used the smallest enclosing circle (SEC) algorithm and finds the optimal location of the charger through Euclidean delivery boy algorithm.It will decrease charging radius,reduce the minimum required transmitted power,thereby saving the average charging energy consumption.The experimental results demonstrated that the less the number locations that the nodes existed,the more energy will be saved.…”
Get full text

A novel multi-task learning model based on Transformer-LSTM for wind power forecasting by Rongquan Zhang, Siqi Bu, Yuxia Zheng, Gangqiang Li, Xiupeng Wan, Qiangqiang Zeng, Min Zhou

“…Finally, to improve the prediction accurateness, a new heuristic algorithm, namely hybrid Cauchy mutation-based Elk herd and sand cat swarm optimization, is proposed to optimize the model hyperparameters. …”
Get full text

Squeeze-Excitation Transformer With Residual Bi-GRU Model for Distributed UWB Based Continuous Gesture Recognition and its Application to Human-UAV Interactions by Chih-Lyang Hwang, Felix Gunawan, Chih-Han Chen

“…The details of model training, optimization strategies, and data preprocessing techniques are presented to improve the performance. …”
Get full text

Pose measurement method for coal mine drilling robot based on deep learning by Jiangnan LUO, Jianping LI, Hongxiang JIANG, Deyi ZHANG

“…In terms of drilling position measurement, the average distance error was 6.39 mm, the radial distance error was 5.34 mm, and the average angle error was 1.6°. …”
Get full text

FedRoute: A Multi-Server Federated Meta-DRL Routing Scheme for Tactical Air-Ground WSNs by Andrews A. Okine, Nadir Adam, Faisal Naeem, Georges Kaddoum

“…In FedRoute, local DRL models are meta-trained with the routing agents’ exploration data before federated averaging, resulting in meta-optimized regional routing models. …”
Get full text

Segmentation of the iliac crest from CT-data for virtual surgical planning of facial reconstruction surgery using deep learning by Stefan Raith, Tobias Pankert, Jônatas de Souza Nascimento, Srikrishna Jaganathan, Florian Peters, Mathias Wien, Frank Hölzle, Ali Modabber

“…Transfer learning was applied for model training optimization. Evaluation metrics included the Dice Similarity Coefficient, Symmetrical Average Surface Distance, and a modified 95% Hausdorff Distance focusing on regions relevant for transplantation. …”
Get full text

Real-time mobile broadband quality of service prediction using AI-driven customer-centric approach by Ayokunle A. Akinlabi, Folasade M. Dahunsi, Jide J. Popoola, Lawrence B. Okegbemi

“…Following hyperparameter tuning to improve the model's performance, the selected model was deployed in a real-world network environment to classify QoS into "Above Average," "Average," and "Below Average," categories. …”
Get full text

Securing Urban Landscape: Cybersecurity Mechanisms for Resilient Smart Cities by Qiang Lyu, Sujuan Liu, Zhouyuan Shang

“…This article explores a novel approach to enhancing cybersecurity in smart cities by integrating Convolutional Neural Networks (CNNs) with Genetic Algorithms (GAs). The primary objective is to develop a robust cybersecurity framework capable of effectively detecting and responding to a wide range of cyber threats in interconnected urban infrastructures. …”
Get full text

Fault diagnosis of ZDJ7 railway point machine based on improved DCNN and SVDD classification by Zengshu Shi, Yiman Du, Xinwen Yao

“…Meanwhile, the global average pooling layer (GAP) is used instead of the fully connected layer to improve the generalization ability of the network. …”
Get full text

Empirical Evaluation and Analysis of YOLO Models in Smart Transportation by Lan Anh Nguyen, Manh Dat Tran, Yongseok Son

Get full text

SAR-SPA: Incorporating Target Scattering Characteristic Parameters in Adversarial Example Generation for SAR Imagery by Jiahao Cui, Jiale Duan, Binyan Luo, Hang Cao, Wang Guo, Haifeng Li

“…Deep neural networks (DNNs)-based SAR target recognition models are susceptible to adversarial examples, which significantly reduce model robustness. …”
Get full text