Haizhou Du, Ping Han, Wei Chen, Yi Wang, Chenlu Zhang
{"title":"Otterman: A Novel Approach of Spark Auto-tuning by a Hybrid Strategy","authors":"Haizhou Du, Ping Han, Wei Chen, Yi Wang, Chenlu Zhang","doi":"10.1109/ICSAI.2018.8599304","DOIUrl":"https://doi.org/10.1109/ICSAI.2018.8599304","url":null,"abstract":"Spark has become a very attractive platform for big data analytics in recent years due to its unique advantages such as parallelism, fault tolerance, and complexity associated with clusters setup. On the spark platform, users can adjust parameter configurations according to different job requirements and specific applications to optimize performance. This leads to a problem that we can’t ignore, Spark already has more than 180 parameters, and its huge combination of parameters means that we can’t rely on manual tuning to grasp the impact of all parameters on performance. In order to solve the problem of relying heavily on expert experience and manual operation, we propose Otterman, a parameters optimization approach based on the combination of Simulated Annealing algorithm and Least Squares method, which can help us dynamically adjust parameters according to job types to obtain optimal configuration to improve performance. Simulated Annealing can find the optimal solution, but has poor convergence. We make use of the Least Squares method to effectively improve the speed at which the former converges to the optimal solution. Otterman is simple and easy to perform, with no additional cost. The effectiveness of the approach is verified by experiments, the results show that Otterman’s average performance has increased by 30% compared to the default parameters configuration, with an accuracy of about 68%.","PeriodicalId":375852,"journal":{"name":"2018 5th International Conference on Systems and Informatics (ICSAI)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125150936","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":"Plasma Probe Measurement Control System Design","authors":"J. Wen","doi":"10.1109/ICSAI.2018.8599385","DOIUrl":"https://doi.org/10.1109/ICSAI.2018.8599385","url":null,"abstract":"This paper studies the design scheme for the plasma probe measurement control circuit system. MSP430 SCM is employed as the control chip. The design uses two-stage amplification of the voltage outputted by DA and collects segmented and precise scanning voltage at the PA94 output end of the high-voltage operational amplifier. Finally, the voltage and current at both ends of the probe are AD-collected. The collected voltage and current measurement data are amplified by the secondary operational amplifier respectively, and then transmitted to the computer through the serial port for recording, thereby realizing accurate and precise data measurement on the plasma. (This system has obtained the national utility model patent numbered ZL201721203384.2)","PeriodicalId":375852,"journal":{"name":"2018 5th International Conference on Systems and Informatics (ICSAI)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121773518","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":"Extraction Micro-Doppler Feature of Precession Targets in Orthogonal Frequence Division Multiplexing-Linear Frequence Modulation Multiple Input Multiple Output Radar","authors":"Lixun Han, Bo Tian, C. Feng, Xugusng Xu","doi":"10.1109/ICSAI.2018.8599377","DOIUrl":"https://doi.org/10.1109/ICSAI.2018.8599377","url":null,"abstract":"The micro-Doppler feature of ballistic targets is a hot spot in current research. The problem that the single-base radar can’t accurately obtain the target micro-motion parameters due to the shielding effects in radar observation angle. This paper puts forward a method to introduce Orthogonal Frequence Division Multiplexing-Linear Frequence Modulation(OFDMLFM) signal into Multiple Input Multiple Output(MIMO) radar. Firstly, the mathematical model of the cone-cylinder ballistic target’s precession in MIMO radar is constructed, and then the micro-Doppler effect of the target when the radar radiates OFDM-LFM signal is analyzed. On this basis, using Hough transform to extract the parameters of the time-frequency curve, by solving multiple nonlinear equations to obtain the estimated value of the target precession angle, micro-motion angle velocity, target height, and finally verify the effectiveness of the algorithm through simulation experiments.","PeriodicalId":375852,"journal":{"name":"2018 5th International Conference on Systems and Informatics (ICSAI)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131678084","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}
J. Sa, Yilun An, Feng Ye, Liu Shi, Jiahui Xu, Hang Li, Shaogang Wan
{"title":"Corrugated Pipe Defect Detection Based on Digital Image Processing","authors":"J. Sa, Yilun An, Feng Ye, Liu Shi, Jiahui Xu, Hang Li, Shaogang Wan","doi":"10.1109/ICSAI.2018.8599362","DOIUrl":"https://doi.org/10.1109/ICSAI.2018.8599362","url":null,"abstract":"With the increase of human cost and the shortcomings of human eye to detect the product quality, such as visual fatigue and judging standard, these factors greatly restrict the development of the quartz rod manufacturing industry. In this paper, a method of detecting quartz rod bubbles and grading their quality based on machine vision is proposed. The main research contents are as follows: 1)image preprocessing, which includes image denoising, threshold segmentation and image binarization; 2) The algorithm of the connected domain tagging based on traveling; 3)Shan bubble feature extraction, feature parameters are limited to the area, position, number of bubbles, and determine the quality grade of quartz rods according to the characteristic parameters. Shan According to the algorithm presented in this paper, 100 samples are tested, and the correct rate is 96%, The improved position adaptive threshold segmentation algorithm proposed in this paper is better than the Ostu algorithm for the whole two-dimensional image. Compared with the general connected area labeling method, the run-based connected area labeling algorithm proposed in this paper consumes less time and has higher accuracy.","PeriodicalId":375852,"journal":{"name":"2018 5th International Conference on Systems and Informatics (ICSAI)","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116616803","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 Non-central Point Sound Field Reconstruction Method by Three Loudspeakers","authors":"Song Wang, Cong Zhang, Heng Wang","doi":"10.1109/ICSAI.2018.8599502","DOIUrl":"https://doi.org/10.1109/ICSAI.2018.8599502","url":null,"abstract":"The development of 3D technology makes 3D audio and video technology become a research hotspot. Most of the existing 3D audio technologies reconstruct the original sound field at the center point, which makes the reconstruction effect at the center point is the best, but the reconstruction effect at the non- central point is poor. In order to solve this problem, a non-central pint 3D sound field reconstruction method is presented. The proposed method finds the location of virtual loudspeakers by constructing a virtual sphere. The signals of virtual loudspeakers are solved by traditional method. By keeping particle velocity at the non-central point constant, the signal of real loudspeaker can be obtained from the signal of virtual loudspeaker. Compared with traditional methods, the effect of the proposed method is proved by simulation experiments.","PeriodicalId":375852,"journal":{"name":"2018 5th International Conference on Systems and Informatics (ICSAI)","volume":"641 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116474385","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}
Shanchao Yang, Kangsheng Tian, Changfei Wu, Weiping Huang, Renzheng Liu
{"title":"Adaptive Cycle Based Sensor Management Method","authors":"Shanchao Yang, Kangsheng Tian, Changfei Wu, Weiping Huang, Renzheng Liu","doi":"10.1109/ICSAI.2018.8599417","DOIUrl":"https://doi.org/10.1109/ICSAI.2018.8599417","url":null,"abstract":"To solve the problems of frequent sensor switching and large calculation amount in traditional sensor management methods, a new sensor management method based on adaptive cycle is proposed. Firstly, the adaptive cycle setting method is researched from the aspects of target tracking accuracy and visible window for sensors and targets. Then, a multi-objective optimization model for sensor management based on the cycle is proposed, and the single-objective solution method is used to solve this model. The simulation results show that, comparing to the traditional sensor management method, this method can effectively reduce the sensor switching frequency and the calculation amount, also it can improve the efficiency of sensor management and avoid resource waste.","PeriodicalId":375852,"journal":{"name":"2018 5th International Conference on Systems and Informatics (ICSAI)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134099837","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":"Performance Analysis of Quadratic Permutation Polynomials Network Coding in Wireless Networks","authors":"Lang Pei, Fenglin Li, Ying Song, Baolin Sun","doi":"10.1109/ICSAI.2018.8599393","DOIUrl":"https://doi.org/10.1109/ICSAI.2018.8599393","url":null,"abstract":"Network coding (NC) is the combination of two or more data packets, which can improve packet transmission rate of wireless networks (WNs). Quadratic permutation polynomials (QPP) provide excellent coding performance and support specific conflict-free parallel access and control mechanisms. In this paper, we propose a Quadratic Permutation Polynomial Network Coding algorithm in WNs (QPP-NC). The performance of the QPP-NC algorithm was experimentally studied by using network simulation software NS2, and the network data throughput, data packet transmission rate, energy consumption and energy efficiency of packet transmission were evaluated. Simulation experimental results show that the proposed QPP-NC algorithm can significantly improve the performance of wireless network and achieve a higher data packet transmission mechanism.","PeriodicalId":375852,"journal":{"name":"2018 5th International Conference on Systems and Informatics (ICSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134404516","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 and Development of Chinese Question Bank Information System Based on Web","authors":"Beihai Tan, Linjiang Luo, Shuting Cai","doi":"10.1109/ICSAI.2018.8599459","DOIUrl":"https://doi.org/10.1109/ICSAI.2018.8599459","url":null,"abstract":"With the rapid development of Internet technology, more and more industries use advanced network information technology to manage information. With the in-depth promotion of network technology in the field of education, the traditional education model can’t fully meet the needs in the field of education. The concept of a new form of education that combines Internet technology and education, namely “Internet + education” is proposed. This paper studies the Web-based Chinese question bank information system and take one of the important basic courses, “Computer Culture Foundation” as an example, Furthermore, a set of question database information system is developed for this course. After each exam is submitted, the system can quickly give test scores, save test costs, and improve work efficiency. In addition, the system can also provide online teachers with online assignments, without the need for classroom teachers to review, the system can automatically score the students who complete the homework online, giving the usual grades. Finally, this paper also proposes a test paper construction algorithm and system security algorithm. So, it performed well through multiple test runs of the system.","PeriodicalId":375852,"journal":{"name":"2018 5th International Conference on Systems and Informatics (ICSAI)","volume":"64 36","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134195603","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":"An Improved Image Segmentation Method Based on Maximum Fuzzy Entropy and Quantum Genetic Algorithm","authors":"Chen Chen","doi":"10.1109/ICSAI.2018.8599387","DOIUrl":"https://doi.org/10.1109/ICSAI.2018.8599387","url":null,"abstract":"In order to improve the speed of image segmentation, this paper proposes a hybrid algorithm combined maximum fuzzy entropy and quantum genetic algorithm. Based on the fuzzy set theory, the pixels in the original image are divided into three fuzzy sets: dark, gray and bright, according to the gray value of the pixel. And the maximum fuzzy entropy criterion is used to find the optimal combination of fuzzy parameters and realize image segmentation. Due to the high computational complexity of the exhaustive method to determine the optimal parameters combination, the quantum genetic algorithm is used to determine the optimal threshold. The experimental result shows that the proposed algorithm runs faster than algorithm combined maximum fuzzy entropy and genetic algorithm.","PeriodicalId":375852,"journal":{"name":"2018 5th International Conference on Systems and Informatics (ICSAI)","volume":"152 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132573291","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 Improvement of Text Processing and Clustering Algorithms in Public Opinion Early Warning System","authors":"Kongyu Yang, Ruijie Miao","doi":"10.1109/ICSAI.2018.8599424","DOIUrl":"https://doi.org/10.1109/ICSAI.2018.8599424","url":null,"abstract":"In order to provide the necessary data for Public opinion monitoring and trend warning, this paper did some researches on text processing and clustering algorithms based on hot topics of the Weibo. Data that get from Weibo were classification data which contain two properties. To adapt this feature and meet the requirement of public opinion trends warning, hamming distance was used to do text similarity computing. By improving the traditional K-means algorithm, a new K-mode algorithm which is used to text clustering on hot topics was achieved. Simulation and results analysis indicated the text processing method was accurate and suitable to the microblog public opinion early warning.","PeriodicalId":375852,"journal":{"name":"2018 5th International Conference on Systems and Informatics (ICSAI)","volume":"12 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114025878","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}