Development and Evaluation of Neural Network Architectures for Model Predictive Control of Building Thermal Systems by Jevgenijs Telicko, Andris Krumins, Agris Nikitenko

Get full text

Efficient Parallel Video Processing Techniques on GPU: From Framework to Implementation by Huayou Su, Mei Wen, Nan Wu, Ju Ren, Chunyuan Zhang

“…Through the analysis to the kernels, we found that speedup ratios of the compute intensive algorithms are proportional with the computation power of the GPU. …”
Get full text

DGCLCMI: a deep graph collaboration learning method to predict circRNA-miRNA interactions by Chao Cao, Mengli Li, Chunyu Wang, Lei Xu, Quan Zou, Yansu Wang, Wu Han

“…Comprehensive experiments on three well-established datasets across seven metrics demonstrate that our algorithm significantly outperforms previous models, achieving an average AUC of 0.960. …”
Get full text

Multi-Step Prediction of TBM Tunneling Speed Based on Advanced Hybrid Model by Defu Liu, Yaohong Yang, Shuwen Yang, Zhixiao Zhang, Xiaohu Sun

“…Finally, several subsequences were fed into a Long Short-Term Memory (LSTM) network optimized by the Sparrow Search Algorithm (SSA) for multi-step training and prediction, and the predicted results of each subsequence were added up to obtain the final result. …”
Get full text

A survey of neural architecture search by Mingjie HE, Jie ZHANG, Shiguang SHAN

“…Recently,deep learning has achieved impressive success on various computer vision tasks.The neural architecture is usually a key factor which directly determines the performance of the deep learning algorithm.The automated neural architecture search methods have attracted more and more attentions in recent years.The neural architecture search is the automated process of seeking the optimal neural architecture for specific tasks.Currently,the neural architecture search methods have shown great potential in exploring high-performance and high-efficiency neural architectures.In this paper,a survey in this research field and categorize existing methods based on their performance estimation methods,search spaces and architecture search strategies were presented.Specifically,there were four performance estimation methods for computation cost reduction,two typical neural architecture search spaces and two types of search strategies based on discrete and continuous spaces respectively.Neural architecture search methods based on continuous space are becoming the trend of researches on neural architecture search.…”
Get full text

Integrated Operational Planning of Battery Storage Systems for Improved Efficiency in Residential Community Energy Management Using Multistage Stochastic Dual Dynamic Programming:... by Pattanun Chanpiwat, Fabricio Oliveira, Steven A. Gabriel

“…This study introduces a novel approach for optimizing residential energy systems by combining linear policy graphs with stochastic dual dynamic programming (SDDP) algorithms. …”
Get full text

Energy Demand Response in a Food-Processing Plant: A Deep Reinforcement Learning Approach by Philipp Wohlgenannt, Sebastian Hegenbart, Elias Eder, Mohan Kolhe, Peter Kepplinger

“…During operation, RL only needs 2ms per optimization compared to 19s for MILP, making it a promising optimization tool for edge computing. …”
Get full text

XTNSR: Xception-based transformer network for single image super resolution by Jagrati Talreja, Supavadee Aramvith, Takao Onoye

“…Abstract Single image super resolution has significantly advanced by utilizing transformers-based deep learning algorithms. However, challenges still need to be addressed in handling grid-like image patches with higher computational demands and addressing issues like over-smoothing in visual patches. …”
Get full text

Regularized Kaczmarz Solvers for Robust Inverse Laplace Transforms by Marta González-Lázaro, Eduardo Viciana, Víctor Valdivieso, Ignacio Fernández, Francisco Manuel Arrabal-Campos

“…Quantitative evaluation via mean squared error (MSE), Wasserstein distance, total variation, peak signal-to-noise ratio (PSNR), and runtime demonstrates that Wasserstein–Kaczmarz attains an optimal balance of speed (0.53 s per inversion) and accuracy (MSE = <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>4.7</mn><mo>×</mo><msup><mn>10</mn><mrow><mo>−</mo><mn>8</mn></mrow></msup></mrow></semantics></math></inline-formula>), while TRAIn achieves the highest fidelity (MSE = <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mn>1.5</mn><mo>×</mo><msup><mn>10</mn><mrow><mo>−</mo><mn>8</mn></mrow></msup></mrow></semantics></math></inline-formula>) at a modest computational cost. …”
Get full text

Random Natural Gradient by Ioannis Kolotouros, Petros Wallden

“…While the QNG-based optimization is promising, in each step it requires more quantum resources, since to compute the QNG one requires $O(m^2)$ quantum state preparations, where $m$ is the number of parameters in the parameterized circuit. …”
Get full text

Anomaly detection in cropland monitoring using multiple view vision transformer by Xuesong Liu, Yansong Liu, He Sui, Chuan Qin, Yuanxi Che, Zhaobo Guo

“…In the future, this study plans to explore integrating data from thermal, infrared, or LIDAR sensors, enhance the interpretability of the vision transformer model, and optimize the deep learning pipeline to reduce computational complexity.…”
Get full text

Physics-Based AI-Driven Surrogate Modeling for Structural Displacement Prediction in Mechanical Systems With Limited Sensor Data by Ali Hashemi, Javad Beheshti, Mahdieh Mohammadi

“…The methodology significantly reduces sensor requirements and computational overhead, offering a practical, scalable solution for structural health monitoring (SHM) in complex mechanical systems. …”
Get full text

A Statistical Analysis Based Probabilistic Routing for Resource-Constrained Delay Tolerant Networks by Jixing Xu, Jianbo Li, Shan Jiang, Chenqu Dai, Lei You

“…Based on statistical analysis, we compute and update the expected intermeeting times between nodes. …”
Get full text

ClassRoom-Crowd: A Comprehensive Dataset for Classroom Crowd Counting and Cross-Domain Baseline Analysis by Wenqian Jiang, Xiaohua Huang, Qun Zhao, Sheng Liu

Get full text

Hybrid neural network method for damage localization in structural health monitoring by Fatahlla Moreh, Yusuf Hasan, Zarghaam Haider Rizvi, Sven Tomforde, Frank Wuttke

Get full text

Enhancing surface detection: A comprehensive analysis of various YOLO models by G. Deepti Raj, B. Prabadevi

Get full text

Investigating Internet of Things and Artificial Intelligence-Based Approaches to Smart Irrigation System Optimisation for Agricultural Water Resource Management by Balassem Zaid Ajzan, Alkhafaij Mahdi Abdulkhudur, Raju Nadimpalli Venkata Ganapathi

Get full text

Overview of Applications and Research Directions of Deep Learning Methods for Wind Power Prediction by LIU Tan, LIU Na, LIU Guiping, LIU Kunjie, LIU Min, ZHUANG Xufei, ZHANG Zhonghao

Get full text

Enhancing 4G/LTE Network Path Loss Prediction with PSO-GWO Hybrid Approach by Messaoud Garah, Nabil Boukhennoufa

Get full text

High-efficiency sparse convolution operator for event-based cameras by Sen Zhang, Fusheng Zha, Fusheng Zha, Xiangji Wang, Mantian Li, Wei Guo, Pengfei Wang, Xiaolin Li, Lining Sun

“…Event-based cameras are bio-inspired vision sensors that mimic the sparse and asynchronous activation of the animal retina, offering advantages such as low latency and low computational load in various robotic applications. However, despite their inherent sparsity, most existing visual processing algorithms are optimized for conventional standard cameras and dense images captured from them, resulting in computational redundancy and high latency when applied to event-based cameras. …”
Get full text