{"title":"Composite Feature Extraction for Speech Emotion Recognition","authors":"Yangzhi Fu, Xiaochen Yuan","doi":"10.1109/CSE50738.2020.00018","DOIUrl":"https://doi.org/10.1109/CSE50738.2020.00018","url":null,"abstract":"This paper proposes an approach for speech emotion recognition based on the composite feature extraction. The traditional paralinguistic and prosodic features and the neurogram features are extracted and concatenated together to be the composite feature. The neural feature is presented by a computational model which outputs a series of responses of a speech's particular characteristic frequency through auditory nerve fiber. The exported responses signals are visualized as the 2D neurogram and then extracted as neural feature. With the extracted composite feature, support vector machines is used to classify the emotion. The eNTERFACE database is used and the various metrics are calculated to evaluate the performance of the proposed approach. Experimental results show that the proposed approach achieves good performances under different conditions and performs better than the related work in terms of the various evaluation metrics.","PeriodicalId":196966,"journal":{"name":"2020 IEEE 23rd International Conference on Computational Science and Engineering (CSE)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124733801","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":"HypFDI: Fault Domain Isolation for Hosted Hypervisor in ARM","authors":"Min Zhu, Bibo Tu, Jia Liu, Letian Yi","doi":"10.1109/CSE50738.2020.00013","DOIUrl":"https://doi.org/10.1109/CSE50738.2020.00013","url":null,"abstract":"Hosted hypervisor which takes advantage of a vast amount of mature and stable abilities inside Linux Kernel has been widely adopted to manage virtual machines (VM) in cloud system. Due to rich virtualization capabilities, hosted hypervisor already has large code base (e.g. 33.6K SLOC for KVM) and frequently interacts with VMs. However, commodity hosted hypervisor and kernel in a single address space, which implies that a vulnerability in the hypervisor opens a way to jeopardize the host OS and further may take over VMs running in the same server. So current clouds have a a fragile adversary model with serious security issues. To improve that, previous approaches either suffer from suboptimal performance or required hardware support. In this paper, we present a system that aims to isolate, ‘deprivilege’ and constrain the hosted hypervisor inside kernel. By enforcing function access control on hypervisor, disabling writes to virtual memory control registers from hypervisor and developing a trusted switch gate, our system not only reduces the attack surface between hypervisor and the host kernel but also shield the host kernel. We have implemented our prototype on the open source KVM hypervisor. The evaluation suggests that our system achieves protection against attacks from malicious guest with moderate performance overheads.","PeriodicalId":196966,"journal":{"name":"2020 IEEE 23rd International Conference on Computational Science and Engineering (CSE)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126996902","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 Design and Implementation of a High-Performance Portfolio Optimization Platform","authors":"Yidong Chen, Zhonghua Lu, Xueying Yang","doi":"10.1109/CSE50738.2020.00008","DOIUrl":"https://doi.org/10.1109/CSE50738.2020.00008","url":null,"abstract":"Aiming at the high complexity of parameter optimization for portfolio models, this paper designs a distributed high-performance portfolio optimization platform(HPPO) based on parallel computing framework and event driven architecture. The platform consists of the data layer, the model layer, and the excursion layer, which is built in a component, pluggable, and loosely coupled way. The platform adopts parallelization acceleration for backtesting and optimizing parameters of portfolio models in a certain historical interval. The platform is able to docking portfolio model with real-time market. Based on the HPPO platform, a parallel program is designed to optimize the parameters of the value at risk(VAR) model. The performance of the platform are summarized by analyzing the experimental results and comparing with the open source framework Zipline and Rqalpha.","PeriodicalId":196966,"journal":{"name":"2020 IEEE 23rd International Conference on Computational Science and Engineering (CSE)","volume":"130 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115178560","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 of New Integrated Medical and Health Clouding System based on Configurable Microservice Architecture","authors":"Di Zheng, Xianfeng Zhang, Lin Chen","doi":"10.1109/CSE50738.2020.00019","DOIUrl":"https://doi.org/10.1109/CSE50738.2020.00019","url":null,"abstract":"The outbreak of a novel coronavirus in 2020 has brought great impact on the whole health system. Firstly, the existing medical system needs further integration and optimization to improve the abilities of supporting Internet of things and service-oriented cloud applications, thus optimize the overall system composition and operation, optimize the adjustment and application of various resources, and form a integrated disposal capacity, so as to prevent the medical system from being unable to deal with the extreme epidemic situation. On the other hand, with development of hierarchical diagnosis and collaborative medical system, higher requirements have been put forward for all levels of medical and health system, so that it can be effectively incorporated into the whole health system. At present, with help of service-oriented technology, combining service-oriented ideas and configuration methods, breaking through business barriers and integrating business functions is an important method to build multi-type application groups into cloud applications. Therefore, based on the application of configurable microservice system, this paper designs a new generation of smart medical and health system integrating various business functions, and provides corresponding solutions.","PeriodicalId":196966,"journal":{"name":"2020 IEEE 23rd International Conference on Computational Science and Engineering (CSE)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129319092","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}
Qian Li, Weiguo Wu, Dun Yuan, Kang Liu, Lei Jia, Jianhang Huang
{"title":"A Workload-Aware Load Balancing Algorithm for Cluster Rendering Platform","authors":"Qian Li, Weiguo Wu, Dun Yuan, Kang Liu, Lei Jia, Jianhang Huang","doi":"10.1109/CSE50738.2020.00015","DOIUrl":"https://doi.org/10.1109/CSE50738.2020.00015","url":null,"abstract":"Load balancing is essential for a render farm on a supercomputer platform, according to the architecture characteristics of Sunway Blue Light and rendering applications, the design of a rendering cell is presented to mitigate the I/O load of storage nodes. A workload-aware load balancing algorithm for a rendering cluster system is proposed to solve the problem in which the traditional interframe equipartition method, based on the assumption that multiple frames of the same scene are similar in terms of rendering time, cannot achieve optimization of the load balance and minimize the job completion time for real animation scenes. The algorithm characterizes the workload depending on the number of frames to be rendered and the user-specific computational resource demand. For heavy workloads, an interleaved task distribution method is proposed to take advantage of frame-to-frame coherence. For light workloads, benefiting from the fine-grained intraframe scheduling in the aspect of load balance, a load balancing method using flexible task granularity is introduced. By four scene models of different computational requirements, experimental results and detailed comparisons with the traditional interframe scheduling method and intraframe scheduling method show that the proposed strategy not only achieves near-optimal load balancing but also reduces the rendering time of a rendering job.","PeriodicalId":196966,"journal":{"name":"2020 IEEE 23rd International Conference on Computational Science and Engineering (CSE)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123182821","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}
Yapei Liu, Jianhong Ma, Yongcai Tao, Lei Shi, Lin Wei, Linna Li
{"title":"Text Classification Based on Hybrid Neural Network","authors":"Yapei Liu, Jianhong Ma, Yongcai Tao, Lei Shi, Lin Wei, Linna Li","doi":"10.1109/CSE50738.2020.00011","DOIUrl":"https://doi.org/10.1109/CSE50738.2020.00011","url":null,"abstract":"Aiming at the problems of insufficient feature extraction and low classification accuracy in the classification of Chinese news texts by the neural network, this paper proposes a hybrid neural network text classification model which integrates time series convolutional network-TGNet. The new model utilizes Temporal Convolutional Network to capture the relationship between hidden features on different time scale, and uses Gated Tanh-ReLU Units (GTRU) as the activation layer to improve the expression ability of neural network to the model. Meanwhile, the Gated Recurrent Unit networks (GRU) is used to learn the semantic features of context. Finally, the extracted features are fused and input into Softmax for classification. Experimental results show that the text classification model proposed in this paper has achieved better classification results in the published Chinese news data sets SougoCS and FuDan.","PeriodicalId":196966,"journal":{"name":"2020 IEEE 23rd International Conference on Computational Science and Engineering (CSE)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115387668","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":"Sentiment Analysis of Code-Mixed Roman Urdu-English Social Media Text using Deep Learning Approaches","authors":"Aqsa Younas, Raheela Nasim, Saqib Ali, Guojun Wang, Fang Qi","doi":"10.1109/CSE50738.2020.00017","DOIUrl":"https://doi.org/10.1109/CSE50738.2020.00017","url":null,"abstract":"Sentiment analysis is the computational study of attitudes, opinions, and sentiments towards certain issues, products, individuals, and organizations. Companies and customers are making decisions by seeking opinions from social media text. Sentiment analysis is getting intelligent with the advancement of artificial intelligence and natural language processing. With a stunning increase in the use of social media, a huge volume of text available on these platforms is in imperfect and informal languages like Roman Urdu mixed with the English language. Present sentiment analysis techniques do not perform precisely on these code-mixed imperfect, informal, and poorly resourced languages. A promising solution is the use of deep learning models on these code-mixed Roman Urdu and English text. Therefore, the objective of this paper is to perform a sentiment analysis of code-mixed Roman Urdu and English social media text using state-of-the-art deep learning models. Our work is independent of lexical normalization, language dictionary, and code transfer indication. We perform sentiment analysis using Multilingual BERT (mBERT) and XLM-RoBERTa (XLM-R) models. The results reveal that performance of XLM-R model with tuned hyperparameters for code-mixed Roman Urdu and English social media text is better than the mBERT model with F1 score of 71%.","PeriodicalId":196966,"journal":{"name":"2020 IEEE 23rd International Conference on Computational Science and Engineering (CSE)","volume":"310 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124771850","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}
Yapei Liu, Jianhong Ma, Yongcai Tao, Lei Shi, Lin Wei, Linna Li
{"title":"Hybrid Neural Network Text Classification Combining TCN and GRU","authors":"Yapei Liu, Jianhong Ma, Yongcai Tao, Lei Shi, Lin Wei, Linna Li","doi":"10.1109/CSE50738.2020.00012","DOIUrl":"https://doi.org/10.1109/CSE50738.2020.00012","url":null,"abstract":"Aiming at the problems of insufficient feature extraction and low classification accuracy in the classification of Chinese news texts by the neural network, this paper proposes a hybrid neural network text classification model which integrates time series convolutional network TGNet. The new model utilizes Temporal Convolutional Network to capture the relationship between hidden features on different time scale, and uses Gated Tanh-ReLU Units (GTRU) as the activation layer to improve the expression ability of neural network to the model. Meanwhile, the Gated Recurrent Unit networks (GRU) is used to learn the semantic features of context. Finally, the extracted features are fused and input into Softmax for classification. Experimental results show that the text classification model proposed in this paper has achieved better classification results in the published Chinese news data sets SougoCS and FuDan.","PeriodicalId":196966,"journal":{"name":"2020 IEEE 23rd International Conference on Computational Science and Engineering (CSE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128688962","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 Consistent Address Allocation Algorithm Mitigating Address Conflict for Large-Scale LoRa-Enabled IoT Networks","authors":"X. Fan, Xiao Liang, Qiang Liu, Kun Yang, Hui Chen","doi":"10.1109/CSE50738.2020.00009","DOIUrl":"https://doi.org/10.1109/CSE50738.2020.00009","url":null,"abstract":"LoRa is a strong enabling technology for outdoor IoT (Internet of Things) networking. With LoRa networks increasingly getting bigger to provide wider coverage and indeed internet working of multiple individual LoRa networks, LoRa terminal devices are prone to address conflict, namely, different terminal devices have the same device ID or address. On the other hand, when a LoRa node is reconnected to the LoRa network after temporary disconnection it might be allocated a different device ID rendering application-layer disruption. We call this address inconsistency. These two issues are less concerned in the research community but are critically important in practice. This paper proposes an address allocation algorithm for LoRa terminal devices to tackle the above two challenges. The proposed algorithm increases the randomness of the generated addresses by changing the way the seed is chosen and by introducing a new random number generator called xorshift. An address registry is also introduced to further check whether the generated address has been used on one hand and to make sure the same address is assigned to a reconnecting node. Both experimental and simulation results have shown the effectiveness and efficiency of the proposed algorithm.","PeriodicalId":196966,"journal":{"name":"2020 IEEE 23rd International Conference on Computational Science and Engineering (CSE)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126458339","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}
Hafiz Ubaid ur Rahman, Guihua Duan, Guojun Wang, Md Zakirul Alam Bhuiyan, Jianer Chen
{"title":"Trustworthy Data Acquisition and Faulty Sensor Detection using Gray Code in Cyber-Physical System","authors":"Hafiz Ubaid ur Rahman, Guihua Duan, Guojun Wang, Md Zakirul Alam Bhuiyan, Jianer Chen","doi":"10.1109/CSE50738.2020.00016","DOIUrl":"https://doi.org/10.1109/CSE50738.2020.00016","url":null,"abstract":"Due to environmental influence and technology limitation, a wireless sensor/sensors module can neither store or process all raw data locally nor reliably forward it to a destination in heterogeneous IoT environment. As a result, the data collected by the IoT's sensors are inherently noisy, unreliable, and may trigger many false alarms. These false or misleading data can lead to wrong decisions once the data reaches end entities. Therefore, it is highly recommended and desirable to acquire trustworthy data before data transmission, aggregation, and data storing at the end entities/cloud. In this paper, we propose an In-network Generalized Trustworthy Data Collection (IGTDC) framework for trustworthy data acquisition and faulty sensor detection in the IoT environment. The key idea of IGTDC is to allow a sensor's module to examine locally whether the raw data is trustworthy before transmitting towards upstream nodes. It further distinguishes whether the acquired data can be trusted or not before data aggregation at the sink/edge node. Besides, IGTDC helps to recognize a faulty or compromised sensor. For a reliable data collection, we use collaborative IoT technique, gate-level modeling, and programmable logic device (PLD) to ensure that the acquired data is reliable before transmitting towards upstream nodes/cloud. We use a hardware-based technique called “Gray Code” to detect a faulty sensor. Through simulations we reveal that the acquired data in IGTDC framework is reliable that can make a trustworthy data collection for event detection, and assist to distinguish a faulty sensor.","PeriodicalId":196966,"journal":{"name":"2020 IEEE 23rd International Conference on Computational Science and Engineering (CSE)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122991377","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}