Proceedings of the 8th International Conference on Computing and Artificial Intelligence最新文献_第2页

Attention-Based Densely Connected Convolutional Network for Chromosome Classification 基于注意力的密集连接卷积网络染色体分类

Proceedings of the 8th International Conference on Computing and Artificial Intelligence Pub Date : 2022-03-18 DOI: 10.1145/3532213.3532294

Zhe Gong, Bo Peng, Ao Shen, Yan Gong, Jingzhong Zhang, Song Lang, Yanwei Zhang, Linyu Xu, Hanqing Zheng, Yakang Dai, C. Pang

{"title":"Attention-Based Densely Connected Convolutional Network for Chromosome Classification","authors":"Zhe Gong, Bo Peng, Ao Shen, Yan Gong, Jingzhong Zhang, Song Lang, Yanwei Zhang, Linyu Xu, Hanqing Zheng, Yakang Dai, C. Pang","doi":"10.1145/3532213.3532294","DOIUrl":"https://doi.org/10.1145/3532213.3532294","url":null,"abstract":"Karyotype analysis provides an important basis for diagnosis of genetic diseases. Currently, karyotyping requires considerable manual work and expertise experience, which is very time-consuming. Deep learning has been used in karyotype analysis in recent years. However, the specific information of chromosome length, centromere position, and length ratio in the image has not been paid extra attention in previous deep learning based karyotype analysis methods. In this study, we proposed an attention-based densely connected convolutional network (DenseNet) to automatically classify chromosomes. Specific image features has been paid attention and useless image features have been suppressed by adding channel attention to DenseNet. The accuracy of the proposed method achieved 93.12%, which is better than compared methods. The results show that the proposed chromosome classification method performs well in karyotype analysis, which has potential application in diagnosing genetic diseases caused by chromosome abnormalities.","PeriodicalId":333199,"journal":{"name":"Proceedings of the 8th International Conference on Computing and Artificial Intelligence","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130166814","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: 1

Towards a Performance Optimization of Mobile Automated Fingerprint Identification System (MAFIS) for the Philippine National Police 面向菲律宾国家警察的移动自动指纹识别系统(MAFIS)的性能优化

Proceedings of the 8th International Conference on Computing and Artificial Intelligence Pub Date : 2022-03-18 DOI: 10.1145/3532213.3532270

W. Rey, Ronaldo Juanatas

{"title":"Towards a Performance Optimization of Mobile Automated Fingerprint Identification System (MAFIS) for the Philippine National Police","authors":"W. Rey, Ronaldo Juanatas","doi":"10.1145/3532213.3532270","DOIUrl":"https://doi.org/10.1145/3532213.3532270","url":null,"abstract":"As technology progresses, many businesses and institutions adopt the Web application format. Concurrent visits increase as the user group grows, resulting in a poor end-user experience of the Web app. This study will examine the performance variables influencing the MAFIS web application system at various stages to optimize a web app structure with excellent accessibility, sync, growth, and low cost. The MAFIS was optimized based on the variables impacting the performance of the web system, and the provision of the web app was altered to mark it well-matched for the system needs. This research paper discusses MAFIS performance testing parameters, performance testing methods, and performance improvement approaches. On this premise, the research elaborates the optimization strategy from different perspectives: backend, information repository, and gateway access, based on the primary system organization of a high concurrency Web app. The validated results reveal that the system's performance has improved by 39% from 60% to 99%, the system's structures from 93% to 98% improving by 5% with an overall letter rating of A from C. System performance optimization considering load speed, load time, interactivity, responsiveness, and visual stability achieves improved good results.","PeriodicalId":333199,"journal":{"name":"Proceedings of the 8th International Conference on Computing and Artificial Intelligence","volume":"322 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133933452","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: 2

Design and Generalization of Enterprise Knowledge Graph 企业知识图谱的设计与推广

Proceedings of the 8th International Conference on Computing and Artificial Intelligence Pub Date : 2022-03-18 DOI: 10.1145/3532213.3532252

Chun-Ming Tang, Peng Tao, Yan Li

引用次数: 0

DeepTpNet: A Deep Learning Approach to Identify Cancer Subtypes Based on Multi-omics Data DeepTpNet:基于多组学数据识别癌症亚型的深度学习方法

Proceedings of the 8th International Conference on Computing and Artificial Intelligence Pub Date : 2022-03-18 DOI: 10.1145/3532213.3532214

Chenxi Zhu, Chunyu Wang, Yajuan Feng, Wei Huang

引用次数: 0

PU-LNGCN: Multi-scale Design of Point Cloud Upsampling Using Graph Convolutional Networks 基于图卷积网络的点云上采样多尺度设计

Proceedings of the 8th International Conference on Computing and Artificial Intelligence Pub Date : 2022-03-18 DOI: 10.1145/3532213.3532321

Haoran Ma, Jianming Wang, Yukuan Sun, Qi Wang

{"title":"PU-LNGCN: Multi-scale Design of Point Cloud Upsampling Using Graph Convolutional Networks","authors":"Haoran Ma, Jianming Wang, Yukuan Sun, Qi Wang","doi":"10.1145/3532213.3532321","DOIUrl":"https://doi.org/10.1145/3532213.3532321","url":null,"abstract":"Learning and analyzing 3D point clouds with deep neural networks is challenging due to the irregular and unordered nature of the data. Therefore, as the task of converting sparse and unordered point clouds into dense and complete ones, point cloud upsampling has attracted extensive attention. In this paper, we specially design a structure-based graph convolutional network called Local Neighborhood Graph Convolutional Network (LNGCN) to fully exploit structural information of graph. We introduce the proposed LNGCN and further propose a novel multi-scale feature extraction block called Multiscale LNGCN to encode rich information of point cloud data at different granular levels. By aggregating features at multiple scales, this feature extractor enables further performance improvement in the final upsampled point clouds. We combine the Multiscale LNGCN block into current point upsampling pipelines and propose a new architecture called PU-LNGCN. By using extensive quantitative and qualitative experiments, we show that PU-LNGCN can handle noisy and non-uniformly distributed point clouds as well as real scanned data by LiDAR sensors very well. PU-LNGCN outperforms previous methods and achieves state-of-the-art performance.","PeriodicalId":333199,"journal":{"name":"Proceedings of the 8th International Conference on Computing and Artificial Intelligence","volume":"182 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124595860","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

A Multi-Task Model for Sea-Sky Scene Perception with Information Intersection 基于信息交叉的海天场景感知多任务模型

Proceedings of the 8th International Conference on Computing and Artificial Intelligence Pub Date : 2022-03-18 DOI: 10.1145/3532213.3532333

Qiang Wu, Qiyong Yang, Xin Zheng

{"title":"A Multi-Task Model for Sea-Sky Scene Perception with Information Intersection","authors":"Qiang Wu, Qiyong Yang, Xin Zheng","doi":"10.1145/3532213.3532333","DOIUrl":"https://doi.org/10.1145/3532213.3532333","url":null,"abstract":"∗ Sea-sky scene is one of the most commonly used scenes of automatic perception technology. An accurate and comprehensive perceptive system, which mainly includes sea surface object detection and sea-sky line positioning tasks, can provide effective assistance to the marine rescue and defense. However, existing related single-task methods only focused on one of them separately. Accomplish the entire perception task by multiple algorithms will cause instability and redundancy of the system. In this paper, we proposed a Multi-Task Model for Sea-Sky Scene Perception which contains several parts to complete both of sub-tasks through one end-to-end inference. Our sea-sky line positioning part is built on the Anchor Classification based lane detection method. The sea surface object detection part is similar to the general detector called Generalized Focal Loss V2 (GFLV2) with a customize task-level information intersection module. Furthermore, by introducing information interaction at feature-level, a shared extractor through end-to-end training, our model achieves a promising performance in both latency and precision. Its superiority has been proved by the comparison result on a self-collected sea-sky scene dataset with several SOTAs of each single task.","PeriodicalId":333199,"journal":{"name":"Proceedings of the 8th International Conference on Computing and Artificial Intelligence","volume":"147 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124695428","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: 1

Unmanned Vehicle Localization Algorithm Incorporating Visual-Inertial SLAM and Mapped Road Information 结合视觉惯性SLAM和道路地图信息的无人驾驶车辆定位算法

Proceedings of the 8th International Conference on Computing and Artificial Intelligence Pub Date : 2022-03-18 DOI: 10.1145/3532213.3532341

Yinan Wang, Rongchuan Cao, Shuguang Li, C. Shan, Hong Cheng

{"title":"Unmanned Vehicle Localization Algorithm Incorporating Visual-Inertial SLAM and Mapped Road Information","authors":"Yinan Wang, Rongchuan Cao, Shuguang Li, C. Shan, Hong Cheng","doi":"10.1145/3532213.3532341","DOIUrl":"https://doi.org/10.1145/3532213.3532341","url":null,"abstract":"Visionbased localisation techniques and detection technologies are key algorithms for the localisation and navigation of unmanned vehicles. Especially in scenarios where GPS signals are missing, SLAM techniques that rely on vision, inertial navigation system (INS) and other sensors have important applications. Among them, vision combined with IMU SLAM system has the advantage of realistic scale which is lacking in monocular vision and the computational power compared to multivisual vision, so it is suitable for the application in unmanned vehicle system. In this paper, we propose a fusion localisation algorithm that combines a visual-inertial SLAM system and map road information, processing road information in a map under structured roads, and detecting lane lines and locating its own local position by a monocular camera; applying a strategy of position prediction and update for mapSLAM fusion localisation. It solves the problem of accumulating errors in a pure SLAM system without loopback, and provides accurate globallocal positioning results for unmanned vehicle positioning and navigation.","PeriodicalId":333199,"journal":{"name":"Proceedings of the 8th International Conference on Computing and Artificial Intelligence","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128448454","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

LR-SGD: Layer-based Random SGD For Distributed Deep Learning LR-SGD:基于层的分布式深度学习随机SGD

Proceedings of the 8th International Conference on Computing and Artificial Intelligence Pub Date : 2022-03-18 DOI: 10.1145/3532213.3532215

Zhongyue Zhang, Yanqing Hu, Qing Ye

{"title":"LR-SGD: Layer-based Random SGD For Distributed Deep Learning","authors":"Zhongyue Zhang, Yanqing Hu, Qing Ye","doi":"10.1145/3532213.3532215","DOIUrl":"https://doi.org/10.1145/3532213.3532215","url":null,"abstract":"Distributed training is an effective way to accelerate the training of a large-scale deep neural network(DNN) model, while the data communication between computational workers is always a bottleneck because of the frequent parameter communication at each iteration. To alleviate this problem, many communication-efficient distributed training algorithms based on synchronized stochastic gradient descent(SSGD) are proposed to reduce the amount of the exchanged data by compressing or quantizing the gradients such as the top-k SGD, TernGrad. However, these methods introduce extra intensive computation because of the frequent operation on tensor and memory accessing. Especially when the faster communication backends such as nccl(i.e, NVIDIA Collective Communications Library) or faster communication hardware is proffered in the near future, they no longer have a time advantage. In this paper, we propose an efficient sparsification method, layer-based random SGD (LR-SGD), that randomly select a certain number of layers of the DNN model to be exchanged instead of some elements of each tensor, which reduces communication while keep the performance close to the SSGD. Particularly, we use a hyper parameter k (i.e., indicates the number of layers to be selected) to adjust the compressing ratio while two probabilistic models are utilized to select the layers being exchanged. To validate the proposed method, we conduct several experiments on different datasets with two different scale DNN models on a stimulative cluster. The results demonstrate that the layer-based random sparsification method effectively reduce the communication overhead while maintain the high accuracy. Our code is available at https://github.com/prototype-zzy/LR-SGD.","PeriodicalId":333199,"journal":{"name":"Proceedings of the 8th International Conference on Computing and Artificial Intelligence","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127458512","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: 2

Linear Substitution Pruning: Consider All Filters Together 线性替换剪枝:一起考虑所有滤波器

Proceedings of the 8th International Conference on Computing and Artificial Intelligence Pub Date : 2022-03-18 DOI: 10.1145/3532213.3532224

Kai Liu, Cong Liu

引用次数: 0

Prohibited items detection on X-ray images with multi-task learning 基于多任务学习的x射线图像违禁物品检测

Proceedings of the 8th International Conference on Computing and Artificial Intelligence Pub Date : 2022-03-18 DOI: 10.1145/3532213.3532298

Linquan Xu, Zhipeng Ji, Xiang-Dong Zhou, Yu Shi

{"title":"Prohibited items detection on X-ray images with multi-task learning","authors":"Linquan Xu, Zhipeng Ji, Xiang-Dong Zhou, Yu Shi","doi":"10.1145/3532213.3532298","DOIUrl":"https://doi.org/10.1145/3532213.3532298","url":null,"abstract":"Inspection by X-ray has a wide range of applicability in airports, subways, railway stations, bus stations, and shipping ports. However, using X-ray images during security inspections is challenging because the X-ray image containing prohibited items (positive samples) in the real-world security inspection scenario is much smaller than those that do not contain prohibited items (negative samples). This results in low detection efficiency of the auto security inspection and many false detections. Considering this problem, this paper proposes detecting and recognizing prohibited items on X-ray images in real-world security inspections based on multi-task learning (MTL). This method uses an image classification network to filter out most X-ray images that do not contain prohibited items, thus reducing false detections and improving detection efficiency. MTL simultaneously trains the image classification network and the detection network of prohibited items. In addition, the backbone of the MTL network adopts a model sharing method that can reduce model parameters and improve the convergence speed of the model. Based on a dataset of security inspection X-ray images where the ratio of negative samples to positive samples is 100 (SIXray100), we performed data augmentation, estimated the target anchor of the training set, and used the concept of multi-scale training to complete the model training. Compared with the class-balanced hierarchical refinement method (CHR) that proposed a benchmark in detection, our method shows an improvement of 2% to 5%. Moreover, as the number of test images increases, our approach will obtain results that significantly exceed those from previous research. At the same time, this paper’s strategy for detecting prohibited items and its shared neural network framework have significant application value in engineering.","PeriodicalId":333199,"journal":{"name":"Proceedings of the 8th International Conference on Computing and Artificial Intelligence","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125441637","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