Query scheduling based on cloud-edge multi-data warehouse architecture and cost prediction model by GAO Xuning, YANG Song, LI Mingzhe, ZHANG Yanfeng

“…With the development of cloud computing and big data, traditional local data warehouses are difficult to expand and have low data processing efficiency, As a result, the data warehouse of cloud edge architecture comes into being. …”
Get full text

Query scheduling based on cloud-edge multi-data warehouse architecture and cost prediction model by GAO Xuning, YANG Song, LI Mingzhe, ZHANG Yanfeng

“…With the development of cloud computing and big data, traditional local data warehouses are difficult to expand and have low data processing efficiency, As a result, the data warehouse of cloud edge architecture comes into being. …”
Get full text

Omnigradient Based Total Variation Minimization for Enhanced Defocus Deblurring of Omnidirectional Images by Yongle Li, Jingtao Lou

“…Traditional gradient computation cannot be directly applied to omnidirectional image processing. …”
Get full text

The “What” and “How” of Pantomime Actions by Raymond R. MacNeil, James T. Enns

“…Historically, the TVS framework has considered pantomime actions as expressions of conscious perceptual processing in the ventral stream, but an emerging view is that they are jointly influenced by ventral and dorsal stream processing. …”
Get full text

Explainable AI: Efficiency Sequential Shapley Updating Approach by Ovanes Petrosian, Jinying Zou

Get full text

Self-supervised speech representation learning based on positive sample comparison and masking reconstruction by Wenlin ZHANG, Xuepeng LIU, Tong NIU, Qi CHEN, Dan QU

“…To solve the problem that existing contrastive prediction based self-supervised speech representation learning methods need to construct a large number of negative samples, and their performance depends on large training batches, requiring a lot of computing resources, a new speech representation learning method based on contrastive learning using only positive samples was proposed.Combined with reconstruction loss, the proposed method could obtain better representation with lower training cost.The proposed method was inspired by the idea of the SimSiam method in image self-supervised representation learning.Using the siamese network architecture, two random augmentations of the input speech signals were processed by the same encoder network, then a feed-forward network was applied on one side, and a stop-gradient operation was applied on the other side.The model was trained to maximize the similarity between two sides.During training processing, negative samples were not required, so small batch size could be used and training efficiency was improved.Experimental results show that the representation model obtained by the new method achieves or exceeds the performance of existing mainstream speech representation learning models in multiple downstream tasks.…”
Get full text

Managing Uncertainty: Company’s Adaptive Capabilities during Covid-19 by Iva Atanassova, Peter Bednar

Get full text

Self-supervised speech representation learning based on positive sample comparison and masking reconstruction by Wenlin ZHANG, Xuepeng LIU, Tong NIU, Qi CHEN, Dan QU

“…To solve the problem that existing contrastive prediction based self-supervised speech representation learning methods need to construct a large number of negative samples, and their performance depends on large training batches, requiring a lot of computing resources, a new speech representation learning method based on contrastive learning using only positive samples was proposed.Combined with reconstruction loss, the proposed method could obtain better representation with lower training cost.The proposed method was inspired by the idea of the SimSiam method in image self-supervised representation learning.Using the siamese network architecture, two random augmentations of the input speech signals were processed by the same encoder network, then a feed-forward network was applied on one side, and a stop-gradient operation was applied on the other side.The model was trained to maximize the similarity between two sides.During training processing, negative samples were not required, so small batch size could be used and training efficiency was improved.Experimental results show that the representation model obtained by the new method achieves or exceeds the performance of existing mainstream speech representation learning models in multiple downstream tasks.…”
Get full text

Edge intelligence empowered internet of vehicles: concept, framework, issues, implementation, and prospect by Kai JIANG, Yue CAO, Huan ZHOU, Xuefeng REN, Yongdong ZHU, Hai LIN

“…As an emerging inter discipline field, edge intelligence pushes AI to the side close to the traffic data source.Edge intelligence makes use of the computing power, storage resources, and perception ability of edge to provide a more intelligent and efficient resource allocation and processing mechanism while providing a real-time response, intelligent decision-making and network autonomy, realizing the critical leap for internet of vehicles from access “pipelining” to the intelligent enabling platform of information.However, the successful implementation of edge intelligence in internet of vehicles is still in its infancy, and there exists a demand for a comprehensive survey in this young field from a broader perspective.Based on this context of internet of vehicles, the background, concepts and key technologies of edge intelligence were introduced.Then, a holistic overview of service types based on internet of vehicles was taken, and the entire processes of model training and inference in edge intelligence were elaborated.Finally, to promote the potential research directions, the key open challenges of edge intelligence in the internet of vehicles were analyzed, and the coping strategies were discussed.…”
Get full text

SOFTWARE FOR SUPERCOMPUTER SKIF “ProLit-lC” and “ProNRS-lC” FOR FOUNDRY AND METALLURGICAL PRODUCTIONS by A. N. Chichko, D. M. Kukuj, V. E. Sobolev, S. G. Lihouzov, Ju. V. Jatskevich, O. I. Chichko

“…The influence of number of  processors of  multinuclear computer system SKIF on acceleration and time of  modeling of technological processes, connected with production of castings and slugs, is shown.…”
Get full text

Analysis of activation and dissipation energies in Jeffery-Hamel flow (JHF) through non-parallel stretchable channels by Ikram Ullah, Subhan Ullah, Marouan Kouki, Hamda Khan, Zareen A. Khan

Get full text

Multiscale Molecular Dynamics Simulations with the MiMiC Framework by Andrea Levy, Andrej Antalík, Jógvan Magnus Haugaard Olsen, Ursula Rothlisberger

“…With a particular interest in the dynamics of such processes, we developed MiMiC, a framework for efficient multiscale molecular dynamics simulations suited for high-performance computing. …”
Get full text

SECURE METRIC DIMENSION OF ALTERNATE SNAKE GRAPHS by Basma Mohamed, Iqbal M. Batiha, Nidal Anakira, Mohammad Odeh, Mohammad Shehab, Huda Odetatllah

“…A set is secure if each outside vertex can replace an inside one while preserving resolvability. Computing this parameter is NP-complete and has applications in routing, image processing, and network verification. …”
Get full text

Offsite Evaluation of Localization Systems: Criteria, Systems, and Results From IPIN 2021 and 2022 Competitions by Francesco Potorti, Antonino Crivello, Soyeon Lee, Blagovest Vladimirov, Sangjoon Park, Yushi Chen, Long Wang, Runze Chen, Fang Zhao, Yue Zhuge, Haiyong Luo, Antoni Perez-Navarro, Antonio R. Jimenez, Han Wang, Hengyi Liang, Cedric De Cock, David Plets, Yan Cui, Zhi Xiong, Xiaodong Li, Yiming Ding, Fernando Javier Alvarez Franco, Fernando Jesus Aranda Polo, Felipe Parralejo Rodriguez, Adriano Moreira, Cristiano Pendao, Ivo Silva, Miguel Ortiz, Ni Zhu, Ziyou Li, Valerie Renaudin, Dongyan Wei, Xinchun Ji, Wenchao Zhang, Yan Wang, Longyang Ding, Jian Kuang, Xiaobing Zhang, Zhi Dou, Chaoqun Yang, Sebastian Kram, Maximilian Stahlke, Christopher Mutschler, Sander Coene, Chenglong Li, Alexander Venus, Erik Leitinger, Stefan Tertinek, Klaus Witrisal, Yi Wang, Shaobo Wang, Beihong Jin, Fusang Zhang, Chang Su, Zhi Wang, Siheng Li, Xiaodong Li, Shitao Li, Mengguan Pan, Wang Zheng, Kai Luo, Ziyao Ma, Yanbiao Gao, Jiaxing Chang, Hailong Ren, Wenfang Guo, Joaquin Torres-Sospedra

Get full text

Entity-level cross-modal fusion for multimodal chinese agricultural diseases and pests named entity recognition by Jingzhong Huang, Xia Hao, Yu Wang, Ruizhi Song, Zenan Mu, Wen Chu, Georgios Papadakis, Sijie Niu, Xuchao Guo

“…(NER), as one of the popular directions in natural language processing, plays a critical role in fields such as information extraction and agricultural knowledge graph construction. …”
Get full text

Federated duelling deep Q‐network based collaborative energy scheduling for a power distribution network by Yanhong Yang, Wei Pei, Tianyi Xu, Dawei Wang, Abdelbari Redouane

Get full text

Structure and Principles of Operation of a Quaternion VLSI Multiplier by Aleksandr Cariow, Mariusz Naumowicz, Andrzej Handkiewicz

Get full text

SOFTWARIZATION OF THE PRODUCTION: THE INDUSTRY 4.0 APPROACH by Logica BANICA, Cristian STEFAN, Ionela NEDEA, Elena SOARE

“…Industry 4.0 is a very broad domain that includes: production processes, competitiveness, business decisions, partner and consumer relationships, all centered around cyber-physical systems. …”
Get full text

Intelligent Fault Diagnosis of Bearing Based on Convolutional Neural Network and Bidirectional Long Short-Term Memory by Dazhang You, Linbo Chen, Fei Liu, YePeng Zhang, Wei Shang, Yameng Hu, Wei Liu

Get full text

Evolution of wireless sensor network design from technology centric to user centric: An architectural perspective by Akhilendra Pratap Singh, Ashish Kr Luhach, Xiao-Zhi Gao, Sandeep Kumar, Diptendu Sinha Roy

Get full text