Dynamic heterogeneous network representation learning method based on Hawkes process by CHEN Lei, DENG Kun, LIU Xingyan

“…However, real heterogeneous information networks are very dynamic, and even minor changes in nodes and edges can affect the entire structure and semantics. …”
Get full text

Characterization and modelling of multi-step drawing process for thick steel sheets by Chatellier Joséphine, Pradille Christophe, Kerisit Christophe, Bouchard Pierre-Olivier

“…During the second step, the sheet is pushed entirely through an open die in order to straighten its edges. The process is modelled using the Abaqus finite element software including a comparison between a 3D model and a 2D axisymmetric one. …”
Get full text

Investigation of Interactions between Dislocation and Dislocation Loops in Fe33Ni33Cr Alloy by Molecular Dynamics Simulation by LONG Kaihong, WANG Dongjie, HUANG Chutian, JIA Lixia, HE Xinfu, DOU Yankun

“…Additionally, the effect of dislocation loop size on dislocation slip was studied by comparing the interaction process diagram and the corresponding points on the stress-strain curve. …”
Get full text

Task Offloading Scheme Based on Proximal Policy Optimization Algorithm by Yutong Ma, Junfeng Tian

“…The rapid development of mobile Internet technology has made users’ requirements for quality of service (QoS) continuously improve. The task unloading process of mobile edge computing has the problem that it is impossible to balance delay and energy consumption for task unloading under the condition of fluctuating network bandwidth. …”
Get full text

The Diverse Pathways for Cell Surface MT1-MMP Localization in Migratory Cells by Hannah Kelly, Masaki Inada, Yoshifumi Itoh

“…MT1-MMP is tightly regulated at different levels, and its localization to leading-edge membrane structures is an essential process for MT1-MMP to promote cellular invasion. …”
Get full text

Détermination d’une ligne de rivage de grande taille à l’aide de la multi résolution hiérarchique sur une image RSO by Alain Akono, Emmanuel Tonyé, Marie-Madeleine Djougo Passo, Narcisse Talla Tankam, Charly Dzepa

“…The presented methodology allows getting good estimations of coastline lengths from great size satellite images, and it is particularly useful to the follow-up of the coast erosion process.…”
Get full text

Highly Sensitive FBG Strain Sensor With Enhanced Measurement Range Based On Higher Order FWM by Chiranjit Ghosh, Vishnu Priye

“…The FWM products generated are tuned to the reflection edges of the FBG. The signals reflected from the edges of the FBG are then utilized in the subsequent FWM process to enhance the sensitivity of the system. …”
Get full text

Cooperative inference analysis based on DNN convolutional kernel partitioning by Jialin ZHI, Yinglei TENG, Xinyang ZHANG, Tao NIU, Mei SONG

“…With the popularity of intelligent chip in the application of edge terminal devices, a large number of AI applications will be deployed on the edge of networks closer to data sources in the future.The method based on DNN partition can realize deep learning model training and deployment on resource-constrained terminal devices, and solve the bottleneck problem of edge AI computing ability.Thekernel based partition method (KPM) was proposed as a new scheme on the basis of traditional workload based partition method (WPM).The quantitative analysis of inference performance was carried out from three aspects of computation FLOPS, memory consumption and communication cost respectively, and the qualitative analysis of the above two schemes was carried out from the perspective of flexibility, robustness and privacy of inference process.Finally, a software and hardware experimental platform was built, and AlexNet and VGG11 networks were implemented using PyTorch to further verify the performance advantages of the proposed scheme in terms of delay and energy consumption.It was concluded that, compared with the WPM scheme, the KPM scheme had better DNN reasoning acceleration effect in large-scale computing scenarios.And it has lower memory usage and energy consumption.…”
Get full text

Cooperative inference analysis based on DNN convolutional kernel partitioning by Jialin ZHI, Yinglei TENG, Xinyang ZHANG, Tao NIU, Mei SONG

“…With the popularity of intelligent chip in the application of edge terminal devices, a large number of AI applications will be deployed on the edge of networks closer to data sources in the future.The method based on DNN partition can realize deep learning model training and deployment on resource-constrained terminal devices, and solve the bottleneck problem of edge AI computing ability.Thekernel based partition method (KPM) was proposed as a new scheme on the basis of traditional workload based partition method (WPM).The quantitative analysis of inference performance was carried out from three aspects of computation FLOPS, memory consumption and communication cost respectively, and the qualitative analysis of the above two schemes was carried out from the perspective of flexibility, robustness and privacy of inference process.Finally, a software and hardware experimental platform was built, and AlexNet and VGG11 networks were implemented using PyTorch to further verify the performance advantages of the proposed scheme in terms of delay and energy consumption.It was concluded that, compared with the WPM scheme, the KPM scheme had better DNN reasoning acceleration effect in large-scale computing scenarios.And it has lower memory usage and energy consumption.…”
Get full text

Gender Classification Based on Iris Recognition Using Artificial Neural Networks by Basna Mohammed Salih, Adnan Mohsin Abdulazeez, Omer Mohammed Salih Hassan

Get full text

Research on Detection Methods for Dynamic Ship Targets in Complex Marine Environment From Visible Light Images by Yao Wang, Yi Jiang, Weigui Zeng, Silei Cao

“…It is of great significance for monitoring Marine environment and safeguarding maritime sovereignty. In the process of acquiring target information on ships at sea, the images captured typically contain information of dynamic targets within dynamic scenes. …”
Get full text

Exploring historical maps for insights into ecosystem extent and condition: a case study landscape in Poland by Marta Sylla, Iga Kołodyńska, Piotr Krajewski

Get full text

A Novel Skin Cancer Detection Approach Using Deep Learning Algorithm with Image Segmentation Filters by Awf A. Ramadhan, Omer S. Kareem, Diyar Q. Zeebaree

“…The model basically consists of two scenarios: binary classification (benign and malignant) of the data set without an image segmentation process and binary classification of the same data set after applying four image segmentation methods (threshold-based segmentation, edge-based segmentation, binary fill holes technique, and removing small objects). …”
Get full text

A A Comprehensive Review of Energy Optimization Techniques in the Internet of Things by Bassey Isong, Kedibone Moeti

Get full text

A Vision-Based Single-Sensor Approach for Identification and Localization of Unloading Hoppers by Wuzhen Wang, Tianyu Ji, Qi Xu, Chunyi Su, Guangming Zhang

“…Under the technological wave driven by the deep integration of Industry 4.0 and artificial intelligence, the bulk cargo unloading process is undergoing a significant transformation from manual operation to intelligent control. …”
Get full text

Low power IoT device communication through hybrid AES-RSA encryption in MRA mode by Qiang Chang, Tianqi Ma, Wenzhong Yang

“…The communication between sensor nodes and from sensors to end nodes necessitates additional robust security measures.This paper presents an enhanced approach to the RSA and AES algorithms, tailored for deployment on low-energy IoT devices commonly found in edge environments. The improved AES algorithm transitions from a single-threaded encryption and decryption process to a three-threaded design, reducing the ten-round operation to seven rounds to enhance both speed and energy efficiency. …”
Get full text

rule4ml: an open-source tool for resource utilization and latency estimation for ML models on FPGA by Mohammad Mehdi Rahimifar, Hamza Ezzaoui Rahali, Audrey C Therrien

Get full text

Image information optimization processing based on fractional order differentiation and WT algorithm. by Qiong Long

“…Image edge detection and image fusion are important technologies in the field of image processing, with wide application value. …”
Get full text

Navigation path extraction for garden mobile robot based on road median point by Wei Li

Get full text

Feature-Centric Video Transmission and Analytics in Large-Scale Internet of Video Things by Hongan Wei, Yuxiang Liu, Kejian Hu, Liqun Lin, Youjia Chen, Tiesong Zhao, Wanjian Feng

Get full text