2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE)最新文献_第3页

Arrhythmia Classifier Using Convolutional Neural Network with Adaptive Loss-aware Multi-bit Networks Quantization 基于自适应损失感知多比特网络量化的卷积神经网络心律失常分类器

2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE) Pub Date : 2021-11-01 DOI: 10.1109/ICAICE54393.2021.00095

Hanshi Sun, Ao Wang, Ninghao Pu, Zhiqing Li, Jung Y. Huang, Hao Liu, Zhiyu Qi

{"title":"Arrhythmia Classifier Using Convolutional Neural Network with Adaptive Loss-aware Multi-bit Networks Quantization","authors":"Hanshi Sun, Ao Wang, Ninghao Pu, Zhiqing Li, Jung Y. Huang, Hao Liu, Zhiyu Qi","doi":"10.1109/ICAICE54393.2021.00095","DOIUrl":"https://doi.org/10.1109/ICAICE54393.2021.00095","url":null,"abstract":"Cardiovascular disease (CVDs) is one of the universal deadly diseases, and the detection of it in the early stage is a challenging task to tackle. Recently, deep learning and convolutional neural networks have been employed widely for the classification of objects. Moreover, it is promising that lots of networks can be deployed on wearable devices. An increasing number of methods can be used to realize ECG signal classification for the sake of arrhythmia detection. However, the existing neural networks proposed for arrhythmia detection are not hardware-friendly enough due to a remarkable quantity of parameters resulting in memory and power consumption. In this paper, we present a 1-D adaptive loss-aware quantization, achieving a high compression rate that reduces memory consumption by 23.36 times. In order to adapt to our compression method, we need a smaller and simpler network. We propose a 17-layer end- to-end neural network classifier to classify 17 different rhythm classes trained on the MIT - BIH dataset, realizing a classification accuracy of 93.5%, which is higher than most existing methods. Due to the adaptive bitwidth method making important layers get more attention and offered a chance to prune useless parameters, the proposed quantization method avoids accuracy degradation. It even improves the accuracy rate, which is 95.84 %, 2.34 % higher than before. Our study achieves a 1-D convolutional neural network with high performance and low resources consumption, which is hardware-friendly and illustrates the possibility of deployment on wearable devices to realize a real-time arrhythmia diagnosis.","PeriodicalId":388444,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123200393","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: 3

Skin Cancer Classification Based On Convolutional Neural Network 基于卷积神经网络的皮肤癌分类

2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE) Pub Date : 2021-11-01 DOI: 10.1109/icaice54393.2021.00108

Jiaqi Li

{"title":"Skin Cancer Classification Based On Convolutional Neural Network","authors":"Jiaqi Li","doi":"10.1109/icaice54393.2021.00108","DOIUrl":"https://doi.org/10.1109/icaice54393.2021.00108","url":null,"abstract":"Skin cancer is a kind of cancer that is usually diagnosed by images from dermoscopy. In recent years, researchers have attempted to utilize deep learning technology, especially convolution neural networks (CNN), in the recognition of skin cancer images. Many CNN models have already performed great applicability, like DenseNet, Inception, and Xception. This paper carried a comparative experiment on ISIC 2019 challenge dataset which includes 25,331 skin cancer images of 8 different kinds. On the classification task on the ISIC 2019, it introduced 6 models, VGGNet19, ResNet50, ResNet152, DenseNet201, Inception-v3, and Xception, then conducted a comparative analysis of their performance involving 2 methods (data enhance and transfer learning) and 2 optimizers (Adam and SGD), aiming to explore the impact of different methods and structures on the accuracy, in order to find traits for potential models of higher accuracy. In the 24 groups of results, Xception with data enhance, transfer learning (pretraining) and Adam optimizer had the highest accuracy of 83.8%, while VGGNet19 without transfer learning had the lowest of 66.67%. The influence of transfer leaning is positive on all models, both on accuracy and training time; similar to Adam optimizer, except for a noticeable enhancement effect on Inception-v3 and Xception. The data enhance method applied in this paper had a weak, non-directed impact. Possible reasons for this phenomenon are discussed in depth in the study.","PeriodicalId":388444,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126383974","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

Improved Method of Multi-objective Particle Swarm Algorithm Learning Factor Based on Fitness Change 基于适应度变化的多目标粒子群算法学习因子的改进方法

2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE) Pub Date : 2021-11-01 DOI: 10.1109/ICAICE54393.2021.00020

Jingchen Xie, Guoxin Luo, Hanlin Yin, Chenyao Li, Jiayang Pu, Xueli Zhang, Suyu Wang

{"title":"Improved Method of Multi-objective Particle Swarm Algorithm Learning Factor Based on Fitness Change","authors":"Jingchen Xie, Guoxin Luo, Hanlin Yin, Chenyao Li, Jiayang Pu, Xueli Zhang, Suyu Wang","doi":"10.1109/ICAICE54393.2021.00020","DOIUrl":"https://doi.org/10.1109/ICAICE54393.2021.00020","url":null,"abstract":"Aiming at the problem that the inertial component of particles could not guide the particle to the right direction when the fitness became poor, a multi-objective particle swarm algorithm learning factor improvement method based on the fitness change was proposed. The large learning factor improved the multi-objective particle swarm algorithm. In the simulation experiment, the improved algorithm PSO-AIC1C2 and the PSO-S, PSO-AIC1 and PSO-AIC2 with c1and c2obtained by splitting this algorithm were fixed with c1and c2changed separately, and then compared with other PSO improvements. The algorithms MOPSO, SMPSO, and dMOPSO are compared. Experiments showed that increasing c1could improve the performance of the algorithm, and increasing c2would cause the convergence of the algorithm to deteriorate. In most test functions, PSO-AIC1C2 had obvious advantages in convergence and distribution indicators. The improved method proposed had certain guiding significance for the study of learning factors of particle swarm optimization in the future.","PeriodicalId":388444,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE)","volume":"13 8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114162787","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

Post Earthquake Path Planning Based on Improved Ant Colony Algorithm 基于改进蚁群算法的震后路径规划

2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE) Pub Date : 2021-11-01 DOI: 10.1109/icaice54393.2021.00062

Yalong Li, J. Zhang, Wei Wang, Jing-rong Sun, Jie Wan

引用次数: 0

Cross-Scene Relationship Mining with Learning Graph Net for Hyperspectral Image Classification 基于学习图网的高光谱图像分类跨场景关系挖掘

2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE) Pub Date : 2021-11-01 DOI: 10.1109/ICAICE54393.2021.00106

Junbin Chen, Minchao Ye, Huijuan Lu, Ling Lei

{"title":"Cross-Scene Relationship Mining with Learning Graph Net for Hyperspectral Image Classification","authors":"Junbin Chen, Minchao Ye, Huijuan Lu, Ling Lei","doi":"10.1109/ICAICE54393.2021.00106","DOIUrl":"https://doi.org/10.1109/ICAICE54393.2021.00106","url":null,"abstract":"The problem of hyperspectral image (HSI) classification is usually accompanied by the problem of high dimension and few samples, that is, the high-dimensional-small-sample-size problem. In recent years, transfer learning has been widely used to solve this problem. In the cross-scene HSI classification, we consider a scene with a rich number of samples (called source scene) and a scene with a small number of samples (called target scene). The idea of transfer learning is to transfer the knowledge contained in the rich samples of source scene to target scene. Many HSI classification methods assume that two scenes come from the same feature space. However, the facts are often unsatisfactory, and the two scenes are likely to come from different feature spaces. In this case, we proposed a heterogeneous transfer learning method named cross-domain variational autoencoder (CDVAE), which achieved good results. But the imperfection is that CDVAE cannot use unlabeled samples on target scene to help classification. Therefore, on this basis, we have proposed a learning graph net (LGnet) of using convolutional neural networks (CNN) and graph to learn the relationship between cross-scene samples, so as to use the potential information of unlabeled samples. Then, a new method cross-domain variational autoencoder with learned graph (CDVAE-LG) was proposed by combining LGnet with CDVAE. The experimental results show that CDVAE-LG can effectively learn the information between cross-scene samples and help classification.","PeriodicalId":388444,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115936514","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

Cross-Domain Hyperspectral Image Classification Based on Generative Adversarial Networks 基于生成对抗网络的跨域高光谱图像分类

2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE) Pub Date : 2021-11-01 DOI: 10.1109/ICAICE54393.2021.00128

Zhihao Meng, Minchao Ye, Huijuan Lu, Ling Lei

{"title":"Cross-Domain Hyperspectral Image Classification Based on Generative Adversarial Networks","authors":"Zhihao Meng, Minchao Ye, Huijuan Lu, Ling Lei","doi":"10.1109/ICAICE54393.2021.00128","DOIUrl":"https://doi.org/10.1109/ICAICE54393.2021.00128","url":null,"abstract":"When classifying hyperspectral images, the limited number of samples will make classifier training difficult. Cross-domain information can help solve the problem of insufficient training samples. Cross-domain classification problem is discussed in this paper. In the problem, one scene with sufficient labeled samples is called source scene, and the other with limited training samples is called target scene. However, due to the changes in the imaging condition, the source scene and the target scene usually contain different feature distributions. This paper proposes a heterogeneous transfer learning method for cross-domain hyperspectral image classification based on generative adversarial networks (GANs). The method consists of two submodules: classification submodule composed of convolutional neural networks (CNNs), and scene alignment submodule that helps in reducing the domain shift between different datasets with a generator and a discriminator. The experimental results on two cross-domain hyperspectral image datasets reveal the excellent competitiveness of the proposed method.","PeriodicalId":388444,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116577520","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

Research Progress of Automatic Driving Path Planning 自动驾驶路径规划研究进展

2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE) Pub Date : 2021-11-01 DOI: 10.1109/icaice54393.2021.00027

Yuxuan Huang, Dashan Chen

引用次数: 1

Thwart Physical and Digital Domain's Adversarial Attack Methods on Face Detection 挫败物理和数字领域的对抗性人脸检测方法

2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE) Pub Date : 2021-11-01 DOI: 10.1109/icaice54393.2021.00167

Guohua Zhang, Huiyun Jing, Xinzhe Wang, Chuan Zhou, Xin He, Duohe Ma

{"title":"Thwart Physical and Digital Domain's Adversarial Attack Methods on Face Detection","authors":"Guohua Zhang, Huiyun Jing, Xinzhe Wang, Chuan Zhou, Xin He, Duohe Ma","doi":"10.1109/icaice54393.2021.00167","DOIUrl":"https://doi.org/10.1109/icaice54393.2021.00167","url":null,"abstract":"Face detection is a classic problem widely focused on the field of computer vision. It has essential values in security monitoring, human-computer interaction, social interaction, and other fields. Face detection technology has been widely integrated into digital cameras, smartphones, and other end-to-end devices to realize the functions of finding out and focusing on faces. For example, beauty camera applications use face detection to identify faces in preparation for subsequent beauty functions. Face recognition relies on face detection to provide support and assurance. Unfortunately, face detection security problems are constantly emerging in the public's vision with the widespread use of face detection technology. Research on attacking and defending methods on face detection has become a hot research topic about artificial intelligence security. By studying the adversarial attack methods on face detection, we can better evaluate the face detection models' security, and at the same time, can give beneficial help to improve the security of face detection. Among these methods, the most popular attacking method is adversarial attacks. In this paper, we have rationalized and classified the methods of adversarial attacks on face detection according to the attacking principles, the attacking domain, and the attacker's understanding of the face detection models. According to the domain to make classification, it includes digital-domain attack, physical-domain attack; according to the attacker's understanding of the face detection models, it includes black-box attack, white-box attack, grey-box attack. Finally, according to the problems in its current development situation, we proposed the possible solutions and predicted its future development trend.","PeriodicalId":388444,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125159273","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

Dual-forwarding routing protocol for wireless body area network based on energy harvesting 基于能量收集的无线体域网络双转发路由协议

2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE) Pub Date : 2021-11-01 DOI: 10.1109/ICAICE54393.2021.00157

Chuan-Ren Wu, Jin Tan

引用次数: 0

SinGlow: Singing Voice Synthesis with Glow: Help Virtual Singers More Human-like SinGlow:唱歌的声音合成与发光:帮助虚拟歌手更人性化

2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE) Pub Date : 2021-11-01 DOI: 10.1109/icaice54393.2021.00030

Haobo Yang

{"title":"SinGlow: Singing Voice Synthesis with Glow: Help Virtual Singers More Human-like","authors":"Haobo Yang","doi":"10.1109/icaice54393.2021.00030","DOIUrl":"https://doi.org/10.1109/icaice54393.2021.00030","url":null,"abstract":"Singing voice synthesis (SVS) is a task using the computer to generate songs with lyrics. So far, researchers are focusing on tunning the pre-recorded sound pieces according to rigid rules. For example, in Vocaloid, one of the commercial SVS systems, there are 8 principal parameters modifiable by song creators. The system uses these parameters to synthesize sound pieces pre-recorded from professional voice actors. We notice a common difference between computer-generated songs and real singers' songs. This difference can be addressed to help the generated ones become more like the real-singer ones. In this paper, we propose SinGlow, as a solution to minimise this difference. SinGlow is one of the Normalizing Flow that directly uses the calculated Negative Log-Likelihood value to optimize the trainable parameters. This feature gives SinGlow the ability to perfectly encode inputs into feature vectors, which allows us to manipulate the feature space to minimize the difference we discussed before. To our best knowledge, we are the first to propose an application of Normalizing Flow in SVS fields. In our experiments, SinGlow shows the ability to make the input virtual-singer songs more human-like. The code of the SinGlow model is available at https://github.com/discover304/singlow.","PeriodicalId":388444,"journal":{"name":"2021 2nd International Conference on Artificial Intelligence and Computer Engineering (ICAICE)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133832911","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