Dynamic content-cached satellite selection and routing for power minimization in LEO satellite networks by Jeongmin Seo, Dongho Ham, Jeongho Kwak

Get full text

Analysis of hotspots of urban eco-environmental problems: A case study of Shenzhen City by Yue Cai, Rencai Dong, Anxin Lian, Zerui Wang, Yiqiao Zhao, Qinrui Luo, Change Liu

“…The results show a positive correlation between the PM2.5 concentration distribution and the points of interest, road network density, number of dead-end roads, and average building height in Shenzhen. …”
Get full text

A Comparative Analysis of Traditional SARIMA and Machine Learning Models for CPI Data Modelling in Pakistan by Moiz Qureshi, Arsalan Khan, Muhammad Daniyal, Kassim Tawiah, Zahid Mehmood

Get full text

Addressing data imbalance in collision risk prediction with active generative oversampling by Li Li, Xiaoliang Zhang

“…Abstract Data imbalance is a critical factor affecting the predictive accuracy in collision risk assessment. …”
Get full text

Prediction of coalbed methane productivity based on neural network models by JIN Yi, ZHENG Chenhui, SONG Huibo, MA Jiaheng, YANG Yunhang, LIU Shunxi, ZHANG Kun, NI Xiaoming

“…Finally， according to the classification results， combined with the actual drainage data， the BP and LSTM neural network algorithms were used to predict the daily gas production of CBM wells.ResultsThe results show that： （1） Based on the grey correlation method model analysis， 10 parameters such as permeability， gas saturation and reservoir pressure gradient in the study area are the key factors affecting the gas production performance of coalbed methane； （2） Using fuzzy mathematics evaluation method to evaluate the enrichment of coalbed methane， the gas production effects of 34 wells in the study area is divided into three categories： favorable area， relatively favorable area and unfavorable area. （3）A coal reservoir daily gas production prediction model was established based on the LSTM algorithm， with a prediction error value between 4.06% and 14.79%， and the average error value of 11.09%. …”
Get full text

Assessing the Logistics Efficiency of Baltic Region Seaports Through DEA-BCC and Spatial Analysis by Vilma Locaitienė, Kristina Čižiūnienė

“…The model developed by the authors integrates the nearest neighbour method for cluster identification, data envelopment analysis using the Banker, Charnes, and Cooper (DEA-BCC) model to assess the overall technical, pure technical, and scale logistics efficiency, and spatial autocorrelation analysis to explore spatial interactions. …”
Get full text

Transforming oil market analysis: A novel GAN + LSTM predictive framework by Prity Kumari, G.Y. Chandan, Satish Kumar M

Get full text

PROPERTIES OF LEXICAL NETWORKS BUILT ON NATURAL AND RANDOM TEXTS by Oleh Kushnir, A. Drebot, D. Ostrikov, O. Kravchuk

Get full text

Explainable Offline‐Online Training of Neural Networks for Parameterizations: A 1D Gravity Wave‐QBO Testbed in the Small‐Data Regime by Hamid A. Pahlavan, Pedram Hassanzadeh, M. Joan Alexander

“…In contrast, offline training of this NN in a small‐data regime (18‐month) yields unrealistic QBOs. However, online re‐training of just two layers of this NN using ensemble Kalman inversion and only time‐averaged QBO statistics leads to parameterizations that yield realistic QBOs. …”
Get full text

Performance Analysis of a TDMA-based Wireless Sensor Networks Protocol with Cognitive Radio Capabilities by Israel Leyva Mayorga, Mario E. Rivero Ángeles, Chadwick Carreto Arellano, Vicent Pla

Get full text

A comparative analysis of the most common deterministic methods for the calculation of electricity losses in industrial networks by E. I. Gracheva, Z. M. Shakurova, R. E. Abdullazyanov

“…It is shown that for the method of graphical integration, initial data on the dependences of load schedules for each network element are required, and the method of calculating losses by average node loads can be used in networks with relatively constant loads. …”
Get full text

Comparative Analysis of Anpr and TIRTL Systems Using Artificial Neural Networks for Traffic Speed Management by Kumar Boddu Sudhir, Kumar Pala Gireesh, Kumar Kontham Pavan

Get full text

Hybrid Transformer–Convolutional Neural Network Approach for Non-Intrusive Load Analysis in Industrial Processes by Gengsheng He, Yu Huang, Ying Zhang, Yuanzhe Zhu, Yuan Leng, Nan Shang, Jincan Zeng, Zengxin Pu

Get full text

Groundwater Level Prediction and Earthquake Precursor Anomaly Analysis Based on TCN-LSTM-Attention Network by Xinfang Chen, Lijia Yang, Xin Liao, Hanqing Zhao, Shiwei Wang

Get full text

Public Space Optimization Strategy Through Social Network Analysis in Shenzhen’s Gongming Ancient Fair by Hang Ma, Mohan Wang, Jinqi Li, Han Liu

“…This study first employed social network analysis (SNA) to construct two networks of Gongming Ancient Fair, using the software Ucinet 6.755, including a public space network based on spatial connectivity and a public activity network based on pedestrian flow. …”
Get full text

Network Meta-Analysis of Once Weekly Selinexor-Bortezomib-Dexamethasone in Previously Treated Multiple Myeloma by Michael Dolph, Gabriel Tremblay, Adrienne M Gilligan, Hoyee Leong

Get full text

Estimating Aggregate Capacity of Connected DERs and Forecasting Feeder Power Flow With Limited Data Availability by Amir Reza Nikzad, Amr Adel Mohamed, Bala Venkatesh, John Penaranda

“…The method is tested using a North American utility feeder data, achieving an average accuracy of 95.56% for forecasting aggregate load power, 93.70% for feeder flow predictions, and 97.53% for estimating the aggregate capacity of DERs.…”
Get full text

Influence Maximization in Social Networks Using Improved Genetic Algorithm by Ali Chodari Khosroshahi, Saeid Taghavi Afshord, Bagher Zarei, Bahman Arasteh

“…Influence maximization is one of the important problems in network science, data mining, and social media analysis. …”
Get full text

IFNet: An Interactive Frequency Convolutional Neural Network for Enhancing Motor Imagery Decoding From EEG by Jiaheng Wang, Lin Yao, Yueming Wang

Get full text

Battery Life Evaluation Method Based on Temporal Convolution Network by SUN Yushu, AN Juan, HUANG Cunqiang, ZHANG Shunzhen, DANG Yanyang, PEI Wei, TANG Xisheng

“…For lithium-ion battery data from NASA, five features with the greatest impact on SOH are identified (in descending order of importance): cycle time, average voltage, voltage sample entropy, temperature sample entropy, and current.Results and DiscussionsTo address redundancy caused by overlapping information among these features, Kernel principal component analysis (KPCA) is applied for dimensionality reduction. …”
Get full text