Temporal dependent rate-distortion optimization based on distortion backward propagation by Hongwei GUO, Ce ZHU, Xu YANG, Lei LUO

“…Rate-distortion optimization (RDO) is a crucial technique in block based hybrid video encoders.However, the widely used independent RDO is far from obtaining optimal coding performance.To improve the rate-distortion (R-D) performance of high efficiency video coding (HEVC), a temporal dependent RDO algorithm was proposed.Firstly, the formula to calculate temporal distortion propagation factor was derived by using an exponential R-D function.Then, the coding distortion and motion compensation predicted error were obtained by pre-encoding, and the temporal distortion propagation factor was estimated by using distortion backward propagation.Finally, the Lagrange multiplier and quantization parameter of coding tree unit were adaptively adjusted to optimize bit resources allocation.Experimental results show that compared with the original RDO method in HEVC under the low-delay configuration, the proposed algorithm achieves an average 4.4% bit rate reduction for all test sequences, and up to 13.0% bit rate reduction for test sequence BasketballDrill, at the same reconstructed video quality.…”
Get full text

Consistent Quality in Video Coding: A Perceptual RDO and Neural Network-Based QP Prediction Approach by Tien Vu Huu, Huy Bui Quoc, Minh Do Ngoc, Xiem HoangVan

“…Following the estimated QP, we propose a RDO process to guarantee the compression efficiency of the proposed codec while maintaining the decoded video with quality consistency. …”
Get full text

Leveraging Edge Intelligence for Solar Energy Management in Smart Grids by Trong-Minh Hoang, Tuan-Anh Pham, van-Nhan Nguyen, Duc-Thang Doan, Nhu-Ngoc Dao

“…The proposed model leveraged TCN’s capability to capture long-range temporal dependencies and GRU’s efficiency in sequential data processing. To optimize performance for edge computing environments, we employed Neural Architecture Search, model pruning, and quantization techniques, reducing both model size and complexity. …”
Get full text

Effects of Hybridizing the U-Net Neural Network in Traffic Lane Detection Process by Aron Csato, Florin Mariasiu

“…Future research should investigate model compression techniques, such as knowledge distillation, pruning, or quantization, to improve efficiency without sacrificing accuracy.…”
Get full text

Design and Optimization of an FPGA-Based Infrared Dim Small Target Detection Network Under a Sky Cloud Background by Yongbo Cheng, Xuefeng Lai, Yucheng Xia

“…The network enhances detection performance through sequential-differential inputs, false-alarm-object learning, and multi-anchor assignment while reducing computational overhead through sequential-differential acceleration and convolutional pooling. Deployment efficiency is improved via image channel optimization, mixed quantization, and refining the infrared image calibration set. …”
Get full text

High-speed railway track components inspection framework based on YOLOv8 with high-performance model deployment by Youzhi Tang, Yu Qian

“…Our research introduces an efficient model inference pipeline based on a producer-consumer model, effectively utilizing parallel processing and concurrent computing to enhance performance. …”
Get full text

Dual-Branch Neural Network-Based In-Loop Filter for VVC Intra Coding Using Spatial-Frequency Feature Fusion by Zhen Feng, Xu Liu, Cheolkon Jung

“…Thus, the dual-branch architecture processes the input data efficiently according to its unique characteristics, while reducing mutual interference. …”
Get full text

Research on YOLOv3 model compression strategy for UAV deployment by Fei Xu, Litao Huang, Xiaoyang Gao, Tingting Yu, Leyi Zhang

“…The experimental results show that the compression scheme proposed in this paper can effectively reduce the number of parameters by 97.5 % and the calculation amount by 82.3 %, and can maintain the original detection efficiency of UAVs.…”
Get full text

Robust DOA Estimation via a Deep Learning Framework with Joint Spatial–Temporal Information Fusion by Yonghong Zhao, Xiumei Fan, Jisong Liu

“…In addition, it offers distinct advantages in terms of generalization and computational efficiency.…”
Get full text

Optimized AI and IoT-Driven Framework for Intelligent Water Resource Management by Mahmoud Badee Rokaya Mahmoud, Dalia Ismaeil Ibrahim Hemdan, Samah Hazzaa Alajmani, Raneem Yousif Alyami, Ghada Elmarhomy, Hassan Hashim, El-Sayed Atlam

“…Moreover, ontology-based feature structuring enhances interpretability, while hyperparameter tuning (GridSearchCV, Bayesian Optimization) and model compression techniques (pruning, quantization, knowledge distillation) ensure computational efficiency. …”
Get full text

High-Bit-Depth Geometry Representation and Compression in MPEG Immersive Video System by Yoonseob Lee, Kwan-Jung Oh, Gwangsoon Lee, Byung Tae Oh

“…Immersive video has been rapidly evolving as a new form of media for virtual reality (VR) applications, increasing demand for efficient compression and transmission techniques. …”
Get full text

A Comparative Analysis of Compression and Transfer Learning Techniques in DeepFake Detection Models by Andreas Karathanasis, John Violos, Ioannis Kompatsiaris

“…Pruning, knowledge distillation, quantization, and adapter modules are explored to enable efficient real-time DeepFake detection. …”
Get full text

Pruning and optimization of optical neural network as a binary optical trigger by Bokun Zhao, Xuening Dong, Kaveh Rahbardar Mojaver, Brett H. Meyer, Odile Liboiron-Ladouceur

“…Optical neural networks implemented with Mach-Zehnder Interferometer (MZI) arrays are a promising solution to enable fast and energy-efficient machine learning inference, yet finding a practical application has proven challenging due to sensitivity to thermal noise and loss. …”
Get full text

Real-Time Acoustic Scene Recognition for Elderly Daily Routines Using Edge-Based Deep Learning by Hongyu Yang, Rou Dong, Rong Guo, Yonglin Che, Xiaolong Xie, Jianke Yang, Jiajin Zhang

“…This architecture provides an efficient, reliable, and user-friendly solution for real-time acoustic scene monitoring in elderly care.…”
Get full text

High-Fold 3D Gaussian Splatting Model Pruning Method Assisted by Opacity by Shiyu Qiu, Chunlei Wu, Zhenghao Wan, Siyuan Tong

“…To address this, 3D Gaussian Splatting (3DGS) has emerged as an efficient alternative, utilizing Gaussian-based representations and rasterization techniques to achieve faster rendering speeds without sacrificing image quality. …”
Get full text

Engineering a multi model fallback system for edge devices by Gaurav Kadve, Abishi Chowdhury, Vishal Krishna Singh, Amrit Pal

“…The growing deployment of machine learning applications in edge environments, such as IoT devices and embedded systems, has highlighted the need for efficient, resource-aware systems for edge environments. …”
Get full text

FPG-AI RNN: A Technology-Agnostic Framework for the Automatic Acceleration of LSTM/GRU-Based Models on FPGAs by Tommaso Pacini, Pietro Nannipieri, Silvia Moranti, Luca Fanucci

“…FPGAs have emerged as an efficient technology for accelerating these algorithms, especially in resource- and power-constrained platforms such as edge devices. …”
Get full text

High-Performance and Lightweight AI Model with Integrated Self-Attention Layers for Soybean Pod Number Estimation by Qian Huang

“…<b>Methods:</b> To address these challenges, this study presents a set of lightweight, efficient AI models designed to overcome these limitations. …”
Get full text

A Digital Simulation Model of Broadband Phased Array RF System and Its Application by Jia Ding, Huaizong Shao, Jianxing Lv, Fake Ding

“…The model research and integrated simulation software construction of the broadband phased array RF system provide an efficient and accurate simulation tool for system design and optimization.…”
Get full text

A novel method for power transformer fault diagnosis considering imbalanced data samples by Jun Chen, Yong Wang, Lingming Kong, Yilong Chen, Mianzhi Chen, Qian Cai, Gehao Sheng

“…Additionally, the accuracy for minority sample classes is improved by at least 15% compared to other models.DiscussionThe integration of NCA and KNN with correction factors not only mitigates the effects of sample imbalance but also significantly enhances the operational efficiency and diagnostic accuracy of power transformer fault diagnosis. …”
Get full text