发布求助
文献互助 智能选刊 最新文献

International Conference on Machine Learning and Soft Computing最新文献

筛选
英文 中文
Optimizing native analysis with android container 利用android容器优化原生分析
International Conference on Machine Learning and Soft Computing Pub Date : 2018-02-02 DOI: 10.1145/3184066.3184101
Ngoc-Tu Chau, Hojin Chun, Souhwan Jung
{"title":"Optimizing native analysis with android container","authors":"Ngoc-Tu Chau, Hojin Chun, Souhwan Jung","doi":"10.1145/3184066.3184101","DOIUrl":"https://doi.org/10.1145/3184066.3184101","url":null,"abstract":"Demystifying an Android shared library is always a challenging task. In order to inspect a native shared library, analyzers have to execute the application that will load the target library on runtime. Executing the whole application code for the purpose of debugging only a single native library is a waste of computing resource. To solve that problem, we consider deploying Java virtual machine only for hosting the target library a promising approach. Java virtual machine is designed to support both Dalvik and ART runtime. Other contribution is the design of a suitable environment for hosting Java virtual machine. Since the deployment of an Android environment, from either by using virtualized or real devices, is either too costly for virtualization approach or waste of resources in real device. For optimizing computing and hardware resources, the authors have proposed a lightweight environment that suitable for native analysis that based on container technology. Compare to virtualization technology, containerization has the performance advantage. Container technology also a better option than the use of real device since it could provide more than one Android containers at the same time with the same device. The implementation results have shown results from running native analysis on multiple runtime and in different Android version. Because a full Android environment is too heavy for a lightweight sandbox like Java virtual machine, we have stripped most of the components and provide only components that are related to analysis work. The result provided from our experiment shows that stripped Android container has a significant improvement in performance compared with other solutions.","PeriodicalId":109559,"journal":{"name":"International Conference on Machine Learning and Soft Computing","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132222505","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
Hybrid recommendation based on implicative rating measures 基于隐含评级措施的混合推荐
International Conference on Machine Learning and Soft Computing Pub Date : 2018-02-02 DOI: 10.1145/3184066.3184076
Lan Phuong Phan, H. Huynh, H. Huynh
{"title":"Hybrid recommendation based on implicative rating measures","authors":"Lan Phuong Phan, H. Huynh, H. Huynh","doi":"10.1145/3184066.3184076","DOIUrl":"https://doi.org/10.1145/3184066.3184076","url":null,"abstract":"This paper proposes the implicative rating measures and the hybrid recommendation model based on those measures to suggest a list of top N items to an active user. The proposed recommendation model is the combination of the user-based collaborative filtering approach and the association rule based approach. This hybrid model are compared to some existing models such as the popular model, the item based collaborative filtering using the Jaccard measure, the user based collaborative filtering using the Jaccard measure, the latent factor model, and the association rule based model using the Confidence measure on two datasets CourseRegistration and MSWeb. The experimental results show that the performance of the proposed model is better than that of the compared models.","PeriodicalId":109559,"journal":{"name":"International Conference on Machine Learning and Soft Computing","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114254175","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
Audio-based emotion recognition using GMM supervector an SVM linear kernel 基于GMM超向量和SVM线性核的音频情感识别
International Conference on Machine Learning and Soft Computing Pub Date : 2018-02-02 DOI: 10.1145/3184066.3184086
Dinh-Son Tran, Hyung-Jeong Yang, Soohyung Kim, Gueesang Lee, L. Do, Ngoc-Huynh Ho, Van Quan Nguyen
{"title":"Audio-based emotion recognition using GMM supervector an SVM linear kernel","authors":"Dinh-Son Tran, Hyung-Jeong Yang, Soohyung Kim, Gueesang Lee, L. Do, Ngoc-Huynh Ho, Van Quan Nguyen","doi":"10.1145/3184066.3184086","DOIUrl":"https://doi.org/10.1145/3184066.3184086","url":null,"abstract":"In this paper, we present an audio-based emotion recognition model by using OpenSmile, Gaussian mixture models (GMMs) Supervector and Support vector machines (SVM) with Linear kernel. Features are extracted from audio characteristics of emotional video through OpenSmile into Mel-frequency Cepstral Coefficient (MFCC) of 39 dimensions for each video. Furthermore, these features are normalized to the same size using GMM Supervector with 32 mixture components. Finally, data is classified using SVM with Linear Kernel. To evaluate the model, this paper using the AFEW2017 dataset and SAVEE dataset and show comparable the results on the state-of-the-art network. The experimental results perform with 37% on AFEW and 73.5% on SAVEE dataset. Our proposed achieves improved emotion recognition from audio as compared to several other models.","PeriodicalId":109559,"journal":{"name":"International Conference on Machine Learning and Soft Computing","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115491414","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
Developing a graph-based system for storing, exploiting and visualizing text stream 开发一个基于图形的文本流存储、开发和可视化系统
International Conference on Machine Learning and Soft Computing Pub Date : 2018-02-02 DOI: 10.1145/3184066.3184084
T. T. T. Hong, P. Do
{"title":"Developing a graph-based system for storing, exploiting and visualizing text stream","authors":"T. T. T. Hong, P. Do","doi":"10.1145/3184066.3184084","DOIUrl":"https://doi.org/10.1145/3184066.3184084","url":null,"abstract":"In an era of information explosion, collecting and exploiting information automatically is very essential so that many studies have proposed models for solving storage problems and supporting efficient data processing. In this paper, we propose a system based on graph that can store, exploit and visualize text streams. This model first gathers daily articles automatically from Vietnamese online journals. After articles are collected, keywords' frequency of existence is calculated to rank the importance of keywords, finding worthy topics and tracking the changes in pertinent topics. In addition, our system supports users to search and create statistical maps to visually display their data. We also perform the system testing and evaluation to show its performance, estimate its responding time and find out how to improve it in the future.","PeriodicalId":109559,"journal":{"name":"International Conference on Machine Learning and Soft Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129711477","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: 4
Improving the shortest path finding algorithm in apache spark graphX 改进了apache spark graphX中的最短路径查找算法
International Conference on Machine Learning and Soft Computing Pub Date : 2018-02-02 DOI: 10.1145/3184066.3184083
T. Phan, P. Do
{"title":"Improving the shortest path finding algorithm in apache spark graphX","authors":"T. Phan, P. Do","doi":"10.1145/3184066.3184083","DOIUrl":"https://doi.org/10.1145/3184066.3184083","url":null,"abstract":"The shortest path finding problem is one of the most important and common problems on graphs. It is also a basic problem applied to solve other problems such as the betweenness centrality problem, the closeness centrality problem... Therefore, in all graph processing platforms, there is a way to solve this problem. Apache Spark GraphX is also. However, the shortest path finding algorithm in GraphX has some drawbacks to discuss more. Therefore, in this paper we analyze some issues in finding the shortest path in GraphX, then we propose two new algorithms to improve for better performance, and finally we compare the performance between the shortest path finding algorithm in GraphX and proposed algorithms.","PeriodicalId":109559,"journal":{"name":"International Conference on Machine Learning and Soft Computing","volume":"463 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131579147","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
Automatic template feature extraction and the application to utterance in a dialogue system 模板特征自动提取及其在对话系统话语中的应用
International Conference on Machine Learning and Soft Computing Pub Date : 2018-02-02 DOI: 10.1145/3184066.3184069
Yoshitaka Mikami, M. Hagiwara
{"title":"Automatic template feature extraction and the application to utterance in a dialogue system","authors":"Yoshitaka Mikami, M. Hagiwara","doi":"10.1145/3184066.3184069","DOIUrl":"https://doi.org/10.1145/3184066.3184069","url":null,"abstract":"In this paper, we propose an automatic template features extraction method and apply it to utterance generation in a dialogue system. Template-based utterance generation has been widely used in many dialogue systems because of its robustness. Although variety of templates and the appropriate selection are crucial points in the method, they have not been paid attention so far. This paper focuses on the points; first, we propose the new neural network model utilizingLSTM (Long Short-Term Memory) to extract effective and unique features for templates, and then applied it to utterance generation in a dialogue system. To examine the effectiveness of the proposed method, we conduct two kinds of experiments; subjective evaluation and dialogue breakdown detection experiment. In both of the experiments, the proposed method has shown higher accuracy than the conventional methods.","PeriodicalId":109559,"journal":{"name":"International Conference on Machine Learning and Soft Computing","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131225667","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
Agraph convolution-based classification model for identifying anticancer metabolites from traditional vietnamese herbal medicine database 基于图像卷积的越南传统草药数据库抗癌代谢物分类模型
International Conference on Machine Learning and Soft Computing Pub Date : 2018-02-02 DOI: 10.1145/3184066.3184090
N. Vu, P. T. Duy, Leang Ly
{"title":"Agraph convolution-based classification model for identifying anticancer metabolites from traditional vietnamese herbal medicine database","authors":"N. Vu, P. T. Duy, Leang Ly","doi":"10.1145/3184066.3184090","DOIUrl":"https://doi.org/10.1145/3184066.3184090","url":null,"abstract":"Vietnam has been well known as a source of abundantly diverse herbal medicines for thousands of years, which serves a variety of purposes in drug development in attempts to address health issues, such as cancer. As claimed by a chemoinformatics-related principle that structurally similar chemical compounds will very likely have similar biological activity, this study employs molecular graph convolution, a machine learning architecture for extracting features from small molecules as undirected graphs, to predict anticancer ability of Vietnamese herbal medicines based on their metabolites' structures. In addition to molecular graph convolution, extended connectivity fingerprint (ECFP), a traditional featurizer for exploiting details of molecules, is also performed in order to make performance comparison. Finally, we successfully constructed a graph convolution-based neural network with high predictive accuracy on both training and validation set, suggesting that the model is reliable in detecting anticancer activity.","PeriodicalId":109559,"journal":{"name":"International Conference on Machine Learning and Soft Computing","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128296601","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
A new approach for supervised learning based influence value reinforcement learning 基于影响值强化学习的监督学习新方法
International Conference on Machine Learning and Soft Computing Pub Date : 2018-02-02 DOI: 10.1145/3184066.3184094
André Valdivia, Jose Herrera Quispe, D. Barrios-Aranibar
{"title":"A new approach for supervised learning based influence value reinforcement learning","authors":"André Valdivia, Jose Herrera Quispe, D. Barrios-Aranibar","doi":"10.1145/3184066.3184094","DOIUrl":"https://doi.org/10.1145/3184066.3184094","url":null,"abstract":"The neural self-organization, is an innate feature of the mammal's brains, and is necessary for its operation. The most known neuronal models that use this characteristic are the self-organized maps (SOM) and the adaptive resonance theory (ART), but those models, did not take the neuron as a processing unit, as the biological counterpart. On the other hand, the influence value learning paradigm [1], used in multi-agent environments, proof that agents can communicate with each other [2]; and they can self-organize to assign tasks; without any interference. Motivated by this missing feature in artificial networks, and with the influence value reinforcement learning algorithm; a new approach to supervised learning was modeled using the neuron as an agent learning by reinforcement.","PeriodicalId":109559,"journal":{"name":"International Conference on Machine Learning and Soft Computing","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128399255","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
Application of image processing and neural networks in determining the readiness of maize 图像处理和神经网络在确定玉米成熟状态中的应用
International Conference on Machine Learning and Soft Computing Pub Date : 2018-02-02 DOI: 10.1145/3184066.3184068
A. Peter, S. Abdulkadir
{"title":"Application of image processing and neural networks in determining the readiness of maize","authors":"A. Peter, S. Abdulkadir","doi":"10.1145/3184066.3184068","DOIUrl":"https://doi.org/10.1145/3184066.3184068","url":null,"abstract":"1. Amongst crops cultivated in Nigeria, maize tends to rank the highest due to its nutrient contents of carbohydrate, fat and protein. The entire maize plant is a good source of food for livestock. Nevertheless, the plant is left to attain biological maturity in Nigeria where the leaves have little or no nutritional content. Before biological maturity, the maize kernel is ready for harvest and the maize plant is still having its green coloration. Changes in the maize plant were studied before physiological maturity, at physiological maturity and before biological maturity. Images of the three stages mentioned were obtained using a charge coupled device (CCD) camera. Significant color features were extracted and used as inputs in determining the classification by neural network. The network achieved an accuracy of 100% based on the sample set.","PeriodicalId":109559,"journal":{"name":"International Conference on Machine Learning and Soft Computing","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114350764","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: 4
QR code based image steganography via variable step size firefly algorithm and lifting wavelet transform 基于变步长萤火虫算法和提升小波变换的二维码图像隐写
International Conference on Machine Learning and Soft Computing Pub Date : 2018-02-02 DOI: 10.1145/3184066.3184095
P. Raja, E. Baburaj
{"title":"QR code based image steganography via variable step size firefly algorithm and lifting wavelet transform","authors":"P. Raja, E. Baburaj","doi":"10.1145/3184066.3184095","DOIUrl":"https://doi.org/10.1145/3184066.3184095","url":null,"abstract":"The Image steganography is the art of hiding secret message onto the source image. A good approach to the steganography must provide for the high stego image quality. An efficient Steganographic method is proposed for embedding secrete message into the image. In this paper, a wavelet domain steganography is adopted for hiding a large amount of data with high security, good invisibility and no loss to the secret message. Here, the frequency domain steganography based information hiding technique using the lifting wavelet transform (LWT) with variation step size firefly algorithm (VSSFA) is envisaged. Our proposed work consists of three phases such as the optimal parameter selection, embedding phase and the extraction phase. In this method, the lifting wavelet coefficients of the Least Significant Bit (LSB) at high frequency sub bands are used to embed the QR coded secret message. The same process is repeated to the extraction process. The performance of the proposed steganography method is analyzed through various constraints such as the Mean Square Error (MSE), Tamper Assessment Factor (TAF), Normalize correlation (NC), bit error rate (BER) and the peak signal to noise ratio (PSNR). The proposed scheme maintains the stego-image quality with an average PSNR value of 63.76 dB and an embedding capacity of 5624 bits.","PeriodicalId":109559,"journal":{"name":"International Conference on Machine Learning and Soft Computing","volume":"469 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-02-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132055674","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
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信