2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)最新文献_第2页

Q-learning based algorithm for small-world network generation 基于q学习的小世界网络生成算法

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778655

Shuai Li, Shengnan Lin, Yang Su

引用次数: 0

Design of Intentional Eye-blink Signal Acquisition and Control System Based on Pressure Sensor 基于压力传感器的有意识眨眼信号采集与控制系统设计

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778374

Xueqi Shao, Haonan Ning, Wenjun Yang, Y. Niu

引用次数: 0

Multi-objective Sparrow Search Algorithm Based on Knee Points for Task Offloading in Multi-Cloudlet 基于膝点的多目标麻雀搜索算法在多云环境下的任务卸载

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778362

Guiyi Wei, Anding Wang, Chaijun Chen, Kai Huang

{"title":"Multi-objective Sparrow Search Algorithm Based on Knee Points for Task Offloading in Multi-Cloudlet","authors":"Guiyi Wei, Anding Wang, Chaijun Chen, Kai Huang","doi":"10.1109/ICSP54964.2022.9778362","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778362","url":null,"abstract":"Computation offloading is a promising technique to improve the quality of service for mobile users in mobile edge computing. However, efficient computation offloading is an NP- hard problem when the mobile user is in a multi-cloudlet scenario. To solve this problem, we construct a multi-objective optimization model which minimizes the delay and cost of all tasks under the constraints of user's requirements. For this purpose, a multi-objective intelligent algorithm, referred as Multi-objective Sparrow Search Algorithm (MSSA) is proposed, which derived from single-objective Sparrow Search Algorithm (SSA). First, we design an adaptive strategy to identify keen points and a ranking rule based on keen points to facilitate the evolution of the population. Second, to address the problem that SSA is prone to fall into local solutions, we design a scaling factor to adjust the population adaptively and propose a formula with better searching capability. Meanwhile, Gaussian mutation is added to explore more precisely in later stage. Then, an elite strategy is introduced to retain high-quality solutions. Finally, experimental results show that our proposed algorithm outperforms NSGA2 and SPEA2 in diversity, convergence and stability. In addition, our algorithm achieves better tradeoff between delay and cost compared to the benchmark experiments.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116110500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Face Landmark Detection Based on Deep Learning Processor Unit on ZYNQ MPSoC 基于ZYNQ MPSoC上深度学习处理器单元的人脸地标检测

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778436

Weizhuang Liu, Kejun Tan

{"title":"Face Landmark Detection Based on Deep Learning Processor Unit on ZYNQ MPSoC","authors":"Weizhuang Liu, Kejun Tan","doi":"10.1109/ICSP54964.2022.9778436","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778436","url":null,"abstract":"Convolutional neural network (CNN) has a wide range of applications in face detection and recognition, image classification and semantic segmentation, but it is very difficult to deploy CNN on FPGA embedded platform. The Deep Learning Processor Unit (DPU) released by Xilinx is different from the previous deployment of FPGA, which can accelerate the realization of CNN deployment on FPGA platform and supports a variety of classical CNN structures. In this paper, the face and landmark detection CNN is deployed on ZCU102 platform using DPU based on idea of hardware and software co-design. According to the network features supported by DPU, Normalize network features in VGG-SSD were adjusted to BatchNormalize network features, Convolution was added in LeNet and a double-layer convolution structure was adopted, and the model was pruned to reduce resource consumption and computation. Dual-core DPU and deep flow architecture were used to improve data throughput. The experimental results show that the average detection time of single frame video image face and landmark detection is 26ms, and this design improves the acceleration effect significantly, and has good scalability.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116122231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Chinese Named Entity Recognition Based on Character Level Multi Feature Fusion 基于字符级多特征融合的中文命名实体识别

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778828

Jianqiang Zhao, Wantong Zhu, Cheng Chen

{"title":"Chinese Named Entity Recognition Based on Character Level Multi Feature Fusion","authors":"Jianqiang Zhao, Wantong Zhu, Cheng Chen","doi":"10.1109/ICSP54964.2022.9778828","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778828","url":null,"abstract":"For the task of named entity recognition, this paper proposes a character-level multi-feature fusion named entity recognition method based on the IDCNN model, which can adjust the receptive field range through parameters. A distributed representation method combining radicals and character features is proposed to solve the problem of insufficient representation of Chinese characters' latent features. The character-level feature representation is input into IDCNN for feature extraction. IDCNN can make full use of the parallel ability of GPU under the premise of extracting long-distance semantic information, and finally improve the accuracy of entity label prediction through the CRF layer. In order to verify the effectiveness of the model, this paper conducts experiments on the commonly used MSRA data sets and Resume data sets. The experimental results show that the results of the model on MSRA and Resume data sets surpass those of Lattice LSTM, LR-CNN, and PLET. Compared with the PLET model with the best results, the F1 value of the model in this paper is increased by 0.55% and 0.03%, respectively.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"134 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116526806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Feasibility Analysis of Quantum Key Distribution Technology in Unique Code Application 量子密钥分发技术在唯一码应用中的可行性分析

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778486

Xin Xie, Guo-Liang Chen

引用次数: 0

Research on Remote Sensing Image Classification Algorithm Based on EfficientNet 基于effentnet的遥感图像分类算法研究

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778437

Hang Yin, Cheng Yang, Jiayi Lu

引用次数: 1

Lung Function Decline Predicting Using Improved EfficientNet 使用改进的EfficientNet预测肺功能衰退

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778391

Yuxuan Tian

引用次数: 1

Multi-objective Constrained Genetic Algorithm Based on Pareto and Hierarchical Sorting 基于Pareto和层次排序的多目标约束遗传算法

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778587

Kuan Hu, Lin Zhang, Xinlong Chang, Xuemeng Zhu

引用次数: 0

Pedestrian Angle Recognition Based on JDE Multi-object Tracking Algorithm 基于JDE多目标跟踪算法的行人角度识别

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778590

C. Yang, Tongyao Xu, Minghong Lv, Yi Yu, Xiaoming Jiang

{"title":"Pedestrian Angle Recognition Based on JDE Multi-object Tracking Algorithm","authors":"C. Yang, Tongyao Xu, Minghong Lv, Yi Yu, Xiaoming Jiang","doi":"10.1109/ICSP54964.2022.9778590","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778590","url":null,"abstract":"We often execute multi-object tracking algorithms and pedestrian angle recognition algorithms independently when we solve complex problems that need to track multiple pedestrians and identify their angles simultaneously. Firstly, the multi-target tracking algorithm is used to locate the target and determine the target’s identity. Then the pedestrian angle recognition model is used to recognize the pedestrian angle. This strategy is complicated and inefficient since the two models repeatedly extract target features. This paper realizes the combination of multi-object tracking algorithm and pedestrian angle recognition algorithm in response to this problem. Specifically, we added a new classification branch based on the JDE multi-object tracking algorithm. It enables the model to perform pedestrian angle recognition while detecting and embedding feature extraction. Finally, experiments show that the improved algorithm can perform pedestrian tracking and pedestrian angle recognition simultaneously. The algorithm’s ability to track large and medium targets is the same as the JDE multi-object tracking algorithm. Compared with the Hydraplus model, the improved algorithm has a higher recognition accuracy. Besides, the algorithm can achieve real-time performance.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114469669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0