ECAN-Detector: An Efficient Context-Aggregation Network for Small-Object Detection by Gaofeng Xing, Zhikang Xu, Yulong He, Hailong Ning, Menghao Sun, Chunmei Wang

“…The model first employs an additional shallow detection layer to extract high-resolution features that provide more detailed information for subsequent stages of the network, and then incorporates a dynamic scaled transformer (DST) that enriches spatial perception by adaptively fusing global semantics and local context. …”
Get full text

Distributed PV hosting capacity assessment method for distribution network considering planning of flexible resource by XU Jiayu, WANG Xiaobing, LI Bing, GU Jingda, ZHANG Qiushi, ZANG Tianlei

“…Firstly, based on the traditional multi-scenario construction method, the concept of time-sequence correlation is introduced establish the joint scenario set of source and load considering time sequence autocorrelation and cross-correlation. …”
Get full text

Efficient sepsis detection using deep learning and residual convolutional networks by Ahmed S. Almasoud, Ghada Moh Samir Elhessewi, Munya A. Arasi, Abdulsamad Ebrahim Yahya, Menwa Alshammeri, Donia Badawood, Faisal Mohammed Nafie, Mohammed Assiri

Get full text

Short-term power consumption forecasting using neural networks with first- and second-order differencing by Meftah Elsaraiti

“… Electricity consumption forecasting is critical for efficient energy management and planning. Traditional time series models, such as ARIMA (AutoRegressive Integrated Moving Average), have been widely used due to their simplicity and interpretability. …”
Get full text

Developing an efficient algorithm for robust school bus routing with heterogeneous fleet by Mohamad Ali Movafaghpour

“…Each scenario is generated in order to make the last found optimal solution into an infeasible one as much as possible.Findings: Experimental results show that deploying this novel algorithm for generating extreme scenarios, efficiently produces diverse scenarios. After the scenario generation algorithm is converged, the intersection of the feasible optimal solutions under diverse scenarios is extracted as robust sub-tours or robust trips.Originality/Value: It is the first time to apply the notions of robust optimization using the extreme scenarios generation scheme. …”
Get full text

Fuzzy logic in real-time decision making for autonomous drones by Abdelwahed Motwakel, Adnan Shaout, Arif Muntasa, Manar Ahmed Hamza, Anwer Mustafa Hilal, Sitelbanat Abdel-gaddir Alhadi, Elmouez Samir Abd Elhamee

“…The first experiment demonstrated an obstacle avoidance efficiency of 82.00%, an 8.00% reduction in energy consumption, a decision accuracy of 95.33%, and a mission success rate of 79.33%. …”
Get full text

Detection of Abnormal Item Based on Time Intervals for Recommender Systems by Min Gao, Quan Yuan, Bin Ling, Qingyu Xiong

“…In the paper, two common features of all attack models are analyzed at first. A revised bottom-up discretized approach is then proposed based on time intervals and the features for the detection. …”
Get full text

Towards Efficient Serverless MapReduce Computing on Cloud-Native Platforms by Xu Huang, Rong Gu, Yihua Huang

Get full text

In-Service Power Transformer Life Time Prospects: Review and Prospects by Edwell. T. Mharakurwa

“…The failure statistics analysis is presented first, followed by an examination of the transformer’s insulation degradation and aging mechanism. …”
Get full text

PP-QADMM: A Dual-Driven Perturbation and Quantized ADMM for Privacy Preserving and Communication-Efficient Federated Learning by Anis Elgabli

“…This design prevents the PS from performing model inversion, as the individual model updates are obfuscated within the transmitted combination. …”
Get full text

HIV competition dynamics over sexual networks: first comer advantage conserves founder effects. by Bence Ferdinandy, Enys Mones, Tamás Vicsek, Viktor Müller

“…The spread of the second strain occurred on a much slower time scale compared with the initial expansion of the first strain. …”
Get full text

Optimizing multimodal timetable synchronization of intercity railway and metro for the first service period during holidays by Yan Liu, Quan Zhang, Xuan Li, Yang Shi

“…A bi-objective model is proposed to maximize the temporal availability of metro network and minimize transfer waiting times for IR passengers traveling in early morning. …”
Get full text

Underwater Energy Consumption and Target Localization Balancing Driven by Network Coverage Optimization by Xiyun Ge, Xinyu Liu, Junbo Zhao, Yue Cheng, Jin Li

Get full text

H-mode characteristics and first experimental results of current drive with electron cyclotron waves on EAST by M.H. Li, W.Q. Ma, W.Y. Xu, H.D. Xu, C.B. Wu, J.L. Chen, J. Wang, T. Zhang, D.J. Wu, L.Y. Zhang, Z.G. Wu, Y. Savoye-Peysson, H.L. Zhao, S.Y. Lin, K.N. Geng, X.J. Wang, B.J. Ding, M. Wang, J.P. Qian, X.Z. Gong

“…Dedicated EC current drive (ECCD) experiments were performed in L-mode plasmas with relatively low density and the EC current ( I _EC ) has been determined unambiguously on EAST for the first time. The measured EC current reaches 83 kA, representing about 1/3 of the total plasma current and corresponding to a CD efficiency ( η _CD ) ∼ 0.15 (10 ^19 AWm ^−2 ). …”
Get full text

Corn variety identification based on improved EfficientNet lightweight neural network by Jinpu Xu, Jinpu Xu, Jinhao Lan, Guangjie Lv, Dexin Ma

“…Finally, the Swish activation function was used to improve the stability of gradient transfer, and the SCD_EFTNet model was proposed. Experiments show that the proposed model has obvious advantages compared with mainstream models in indicators such as Recall, Precision, mAP, and inference time, and its mAP reaches 98.11%. …”
Get full text

Efficient Single-Exposure Holographic Imaging via a Lightweight Distilled Strategy by Jiaosheng Li, Haoran Liu, Zeyu Lai, Yifei Chen, Chun Shan, Shuting Zhang, Youyou Liu, Tude Huang, Qilin Ma, Qinnan Zhang

“…However, most of the existing DL-based holographic reconstruction methods have high model complexity. In this study, we first design a lightweight model with fewer parameters through the synergy of deep separable convolution and Swish activation function and then employ it as a teacher to distill a smaller student model. …”
Get full text

Efficient Identification Method of Fractured Leaky Layers Based on Pressure Gauge Arrays by XING Xuesong, ZHOU Changsuo, WANG Yumei, WU Yi, SHI Jian, GU Jijun

Get full text

Edge-Optimized Lightweight YOLO for Real-Time SAR Object Detection by Caiguang Zhang, Ruofeng Yu, Shuwen Wang, Fatong Zhang, Shaojia Ge, Shuangshuang Li, Xuezhou Zhao

“…However, existing deep learning-based methods suffer from excessive model parameters and high computational costs, making them impractical for real-time deployment on edge computing platforms. …”
Get full text

Evaluating the Efficiency of Gray Wolf Optimization and Colonial Competition Algorithm in Load Balancing of Distributed Systems by Asghar Molaei-Yeznabad, Amirhossein Dehghani

Get full text

Classification of Nitrogen-Efficient Wheat Varieties Based on UAV Hyperspectral Remote Sensing by Yumeng Li, Chunying Wang, Junke Zhu, Qinglong Wang, Ping Liu

“…First, eight agronomic indicators closely related to wheat nitrogen efficiency were analyzed using t-SNE dimensionality reduction and hierarchical clustering, enabling the classification of 12 wheat varieties into nitrogen-efficient and nitrogen-inefficient varieties under different nitrogen stress conditions. …”
Get full text