{"title":"An Integrated System of Adaptive Echo Cancellation and Residual Echo Suppression","authors":"Bingxiao Fang","doi":"10.1145/3418994.3419006","DOIUrl":"https://doi.org/10.1145/3418994.3419006","url":null,"abstract":"In hand-free full-duplex communication system, adaptive echo cancellation (AEC) is an essential and challenging part to cancel the annoying acoustic echo, especially in the case of double talk. In this paper, a structure with adaptive echo cancellation (AEC) followed by residual echo cancellation (RES) is proposed. A new variable step-size adaptive echo cancellation (AEC) algorithm is presented in AEC module, which combined with a normalized correlation residual echo cancellation (RES) algorithm, achieves a good performance in terms of return loss enhancement (ERLE) and speech-to-speech-distortion power ratio (SSDR).","PeriodicalId":294374,"journal":{"name":"Proceedings of the 2020 International Conference on Computer Communication and Information Systems","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124414091","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}
{"title":"Application of Support Vector Machine Methods in Classification of Customer Communications Data","authors":"Huynh Tan Hoi, Le Vu Truong","doi":"10.1145/3418994.3419002","DOIUrl":"https://doi.org/10.1145/3418994.3419002","url":null,"abstract":"The paper used automatic information extraction technique, text classification by SVM (Support vector machine) method, combined with Vietnamese word separation technique and natural language processing. Application results of the research used in extracting information, collecting user feedback from e-commerce websites, social networking sites providing businesses with useful information from contributing users in order to build an effective business strategy. The main contributions of this paper are the following: • Apply the BiGAN, the ability of the model to learn mutually coherent inference and generation networks through the inspections of model samples and reconstructions and confirm the usefulness of the learned representations by obtaining a performance competitive with state-of-the-art on Motorbike Generator task. • Improves learning for BiGAN outperforming several state-of-the-art GAN methods training on motorbike dataset by a few techniques such as preprocessing data, data augmentation and hyperparameter tuning.","PeriodicalId":294374,"journal":{"name":"Proceedings of the 2020 International Conference on Computer Communication and Information Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128499495","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}
{"title":"Automatic Requirements Elicitation from Social Media (ARESM)","authors":"Natthaphon Kengphanphanit, P. Muenchaisri","doi":"10.1145/3418994.3419004","DOIUrl":"https://doi.org/10.1145/3418994.3419004","url":null,"abstract":"After software applications are installed and deployed, the software applications enter to maintenance phase. Changes during maintenance phase often occur due to software faults and user new requests. Both software faults and user new requests are user feedbacks that can be normally obtained by interviewing, distributing questionnaires, or setting up JAD meeting. Nowadays, some user feedbacks are scattered online on App Store, Play Store, and social media and normal elicitation methods are not suitable for collecting online user feedbacks. Although some online user feedback elicitation methods are used to collect App Store's reviews and Play Store's reviews, these methods are not designed for eliciting user feedbacks from some social media. Social media contains both positive and negative user feedbacks which are important for software improvement. Positive user feedbacks are tentative new software requirements. Negative user feedbacks are suggestions for fixing existing features. Lacking adequate methods on how to elicit these requirements may eventually result to inefficient software evolution. This paper proposes an approach to extract requirements automatically from user feedbacks on social media and classify user feedbacks to requirements and non-requirements using Naïve Bayes's Machine Learning. The approach is evaluated with an example. A preliminary result is present.","PeriodicalId":294374,"journal":{"name":"Proceedings of the 2020 International Conference on Computer Communication and Information Systems","volume":"2014 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133803275","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}
{"title":"Research on Data-driven Models of Teaching Quality Evaluation","authors":"Yang Zhu, Hongcheng Liu","doi":"10.1145/3418994.3419001","DOIUrl":"https://doi.org/10.1145/3418994.3419001","url":null,"abstract":"In order to realize the data-driven teaching quality evaluation activities and the construction of its system, we must deeply study the relevant models used to guide its algorithm selection, evaluation implementation and system integration. This paper focuses on the analysis model, process model and system model of data-driven teaching quality evaluation. The analysis model is used to form the reference model of how to deal with relevant data and provide reference for data processing. In this part, the cluster analysis, association analysis and prediction analysis are discussed in detail; the process model is used to form the teaching quality evaluation cycle of evaluation to promote learning, which provides reference for organizing evaluation activities, this part analyzes the teaching activities, evaluation activities, intervention activities and their interrelations in the process model. The system model is used to form a reference mode for guiding the design, construction and transformation of teaching quality evaluation big data system, which provides reference for system implementation, this part analyzes the functions of data acquisition layer, data management layer, data interface layer, data processing layer, business application layer and service interface layer.","PeriodicalId":294374,"journal":{"name":"Proceedings of the 2020 International Conference on Computer Communication and Information Systems","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114547597","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}
{"title":"Radar Spectral Maps Classification Based on Deep Learning","authors":"Tong Lin, Xin Chen, Xiaojie Tang, Ling He, Songsheng He, Qiao-lin Hu","doi":"10.1145/3418994.3419007","DOIUrl":"https://doi.org/10.1145/3418994.3419007","url":null,"abstract":"Radar is widely used in various fields because of its all-weather, round-the-clock nature. However, there are still many problems to achieving accurate target detection. The increasing complexity of the electromagnetic environment and the complex and varied echo characteristics of the target have greatly affected target discrimination. In recent years, deep learning techniques have developed rapidly and have achieved extremely high performance in the field of image recognition. This paper introduces deep learning theory into radar target classification and recognition and discusses the use of deep convolutional neural networks for radar Spectral images. In this paper, several aspects of the work are carried out: firstly, experiments are conducted to screen image data enhancement methods in the field of computer vision, several data enhancement methods suitable for radar spectral images were identified, using the suitable data enhancement methods for spectral map data pre-processing to get a larger training set. Second, using deep learning techniques, we explored a framework for classifying and identifying targets based on radar spectral map data. By using the data enhancement and the framework, We achieved an overall classification accuracy of 0.946 on the test set.","PeriodicalId":294374,"journal":{"name":"Proceedings of the 2020 International Conference on Computer Communication and Information Systems","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115453215","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}
{"title":"Usability Analysis of Adaptive Characteristics in Mobile Phones for Visually Impaired People","authors":"Hammad Hassan Qureshhi, D. Wong","doi":"10.1145/3418994.3419005","DOIUrl":"https://doi.org/10.1145/3418994.3419005","url":null,"abstract":"In this modern era, mobile phones have become the most useable and popular devices in this world. These mobile phones provide a large number of applications that fulfill the needs of Visually Impaired People (VIP). The navigational complexity, the persistence of layout, an inconvenient input method, cross-device interactions, and accessibility is a part of the usability problem with today's touchscreen mobile applications for VIP. In modern mobile phones, many adaptive features help the VIP to fulfill their tasks. The objective of this paper is to investigate efficiency, effectiveness, and satisfaction based on existing adaptive features in mobile phones. The adaptive features in iOS and Android platforms consist of voice commands, screen rotation, kid mode, and LED notification. The efficiency and effectiveness have measured the task completion in a specific time period and satisfaction is measured through the After-Scenario Questionnaire Technique. There are around 63 VIP took part in this experiment. The results show the different attractive patterns of usability. There is a lot of usability and accessibility problems using mobile applications. In order to conclude, there is a need for an adaptive user interface that is visual impairment friendly for performing basic activities on mobile phones.","PeriodicalId":294374,"journal":{"name":"Proceedings of the 2020 International Conference on Computer Communication and Information Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129932713","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}
{"title":"A^2DTEL: Attention-Aware based Deep Tree Ensemble Learning","authors":"Zihao Fan, Feng Liu, Youru Li, Jiantao Qu","doi":"10.1145/3418994.3419009","DOIUrl":"https://doi.org/10.1145/3418994.3419009","url":null,"abstract":"In recent years, random forest, as a classic ensemble learning method, has been widely used in many real scenarios benefited from its advantages such as superior performance and easy implementation. Random forest has high generalization ability and can achieve quantitative backtracking of the importance of decision feature parameters during the prediction processing, but it is fail to effectively learn the representation from the input like some deep learning based methods can do, which limits the prediction accuracy unavoidably. To address this issue, this paper proposes an attention-aware deep tree ensemble learning method. Specifically, it introduces the idea of deep learning into the random forest to design a multilayer stacking prediction model. In this way, the prediction result of the upper layer can be weighted to derive the attention parameter of the input sample at the current layer so that the layered importance sampling can be achieved. Compared with the traditional random forest model, the proposed method can learn representation from the input in a more effectively way. In experimental results, the proposed method can outperform other baselines in two real classification tasks significantly.","PeriodicalId":294374,"journal":{"name":"Proceedings of the 2020 International Conference on Computer Communication and Information Systems","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122676434","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}
{"title":"The Implementation of Simple Smart Contract Language and Its Compiler Based on Ethereum Platform","authors":"Han-Wen Yin, Yun Pan, Han Jiang","doi":"10.1145/3418994.3419010","DOIUrl":"https://doi.org/10.1145/3418994.3419010","url":null,"abstract":"Compiling technology is an important technology in computer science. It is of great practical significance to create a language and implement its compiler. At the same time, with the rise of blockchain technology in recent years, smart contracts reappear in people's vision, and the combination of the two has great potential. The typical smart Contract languages, such as Solidity and LLL, have complex syntax and are not easy for beginners to learn and use. This paper introduces the process of making a simple smart contract language that is easy for beginners to learn. The whole process includes from language design to intermediate code execution. The compiler uses Python as the programming language, and the target running platform is Ethereum virtual machine. At the end of this paper, a demonstration example is shown.","PeriodicalId":294374,"journal":{"name":"Proceedings of the 2020 International Conference on Computer Communication and Information Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116230592","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}
{"title":"Distributed Coding Based Multiple Descriptions for Robust Video Transmission over Error-Prone Networks","authors":"D. Duong","doi":"10.1145/3418994.3418999","DOIUrl":"https://doi.org/10.1145/3418994.3418999","url":null,"abstract":"In this paper, we propose a novel multiple description coding (MDC) method to enhance the robustness of video transmission over error-prone networks. The proposed MDC method provides benefits of both distributed video coding (DVC) and multiple description coding techniques, which can offer not only higher performance compared to the conventional MDC methods but also effective scheme for the error resilience. In the proposed MDC method, the input video sequence is split into odd and even group of pictures (GOPs) subsequences, which are independently encoded using the new H.265/High efficiency video coding (H.265/HEVC) based DVC technique. Though the codec itself is not the core novelty of this paper, our proposed codec is the first MDC codec in literature employing H.265/HEVC based DVC approaches, thus all results presented in this paper are new. Experimental results show that the proposed method can achieve a wide range of tradeoffs between coding efficiency and error resilience, and provide much better peak signal-to-noise ratio (PSNR) performance than other conventional MDC methods.","PeriodicalId":294374,"journal":{"name":"Proceedings of the 2020 International Conference on Computer Communication and Information Systems","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115887524","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}
{"title":"Efficient Data Transmission Method Considering Hierarchical Data Structure","authors":"SeoYoon Jang, Jihoon Kang","doi":"10.1145/3418994.3418996","DOIUrl":"https://doi.org/10.1145/3418994.3418996","url":null,"abstract":"In the recent IoT environment, efficient data exchange and combination of heterogeneous data is a necessary function to provide richer services to users. Proper determination of transmission order and estimation of communication cost is one of the main techniques for efficiently providing data exchange and combining. The combination of heterogeneous data mainly uses data having a hierarchical structure. The communication cost estimation of data having a hierarchical structure considers the connection characteristics of the connected parent and child. Previously, there was an estimation of communication cost reflecting the XML structure in a distributed environment. However, the previously proposed formulas are difficult to calculate costs due to their high complexity. In addition, when determining the communication order, conventional methods calculate all cases. Many computations are difficult to apply to IoT environments that need to respond quickly to user needs. We propose a modified cost estimating formula that reduces the complexity to solve existing problems. Next, a method of determining the transmission order by estimating the communication cost in advance is proposed.","PeriodicalId":294374,"journal":{"name":"Proceedings of the 2020 International Conference on Computer Communication and Information Systems","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115825666","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}