{"title":"A multiplier-less GA optimized pulsed neural network for satellite image analysis using a FPGA","authors":"H. Zhuang, K. Low, W. Yau","doi":"10.1109/ICIEA.2008.4582529","DOIUrl":"https://doi.org/10.1109/ICIEA.2008.4582529","url":null,"abstract":"This paper presents a digital hardware oriented system that uses a genetic algorithm (GA) for optimizing a pattern classifier based on the pulsed neural network (PNN). The scheme avoids the usage of multipiers and dividers, which are the bottlenecks for digital hardware implementation of parallel computations like GA and neural networks. Utilizing the nature of RBF being inherent in the pulsed neural network, the scheme yields very compact computational circuits for implementation on a FPGA chip with massive parallelism that guarantees the speed of the neural and evolutionary computations. The on-chip GA-PNN system is developed for terrain classification of a multi-spectral satellite image. Experimental results show that the performance of the proposed system is comparable to a back propagation (BP) neural network while its training speed exceeds the BP network overwhelmingly.","PeriodicalId":309894,"journal":{"name":"2008 3rd IEEE Conference on Industrial Electronics and Applications","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131015138","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":"Present situation and future development of wind power in China","authors":"Yongjun Chen, Yong He, Y. Bao, Jiehui Shen","doi":"10.1109/ICIEA.2008.4582802","DOIUrl":"https://doi.org/10.1109/ICIEA.2008.4582802","url":null,"abstract":"The application of wind energy develops much more rapidly than the other renewable resources in the 21st century. It becomes the third core energy resources following oil and chemical fuels. China is rich in wind energy resources. Although there is still a lag between China and the developed countries on the usage of wind energy, the wind power industry in China is now in a new developing period. There are good prospects to develop the wind power generation in China in the future. The paper provided an overview of the current status and the future development of the wind power in China. It detailed the regional distribution of wind energy resources and wind power plants, the capacity of the wind power plants, the problems in the wind power generation development in China, and the possible solutions to the current problems.","PeriodicalId":309894,"journal":{"name":"2008 3rd IEEE Conference on Industrial Electronics and Applications","volume":"25 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133356025","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":"Intelligent citrus seed identification","authors":"Lau Bee Theng","doi":"10.1109/ICIEA.2008.4582484","DOIUrl":"https://doi.org/10.1109/ICIEA.2008.4582484","url":null,"abstract":"Feature extraction in image processing is a research domain that changes rapidly. [4] introduces a model for identifying seeds from citrus MRI imagery for fruit packaging industry. Hence this research proposed a model for identifying seeds from MRI imagery preprocessed with wavelet transformation and active region identification. The proposed approach segments a citrus imagery into circular layers and wedges to identify the area of interest for seeds. This reduces searching space (in number of pixels) to find out whether a fruit contain seeds. This paper presents the conceptual design and findings from the research on seed identification from citrus imagery segmentation. The improvement might be suitable for bio systems engineering to differentiate fruits with and without seeds.","PeriodicalId":309894,"journal":{"name":"2008 3rd IEEE Conference on Industrial Electronics and Applications","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133699310","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 flexible-resolution 3D laser scanning method based on DSP","authors":"Weiyang Song, Weihai Chen, Yabin Liu, Lihong Xu","doi":"10.1109/ICIEA.2008.4582727","DOIUrl":"https://doi.org/10.1109/ICIEA.2008.4582727","url":null,"abstract":"This paper is focused on a method about collecting data from 3D data collection system for mobile robot efficiently. The system consists of a 2D laser scanner LMS291 and a motor module, through planning the motorpsilas velocity profile, the scanner can get the objectpsilas three-dimensional information, aiming at the traditional scanning modepsilas fault in collecting efficiency, this paper presents a flexible-resolution 3D laser scanning method based on DSP, utilizing the high capacity of DSP, we divide the process of collecting and location to different steps, according to the information collected from the fore-step, DSP can plan the next steppsilas velocity profile, through planning velocity profile, the scanner can have a high scanning efficiency, compared with the traditional scanning approach, utilizing this method can get more useful information under the same condition.","PeriodicalId":309894,"journal":{"name":"2008 3rd IEEE Conference on Industrial Electronics and Applications","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128889096","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":"Multipath differentiated service in ad hoc networks","authors":"Liang Weidong, Wang Fang-jian","doi":"10.1109/ICIEA.2008.4582927","DOIUrl":"https://doi.org/10.1109/ICIEA.2008.4582927","url":null,"abstract":"To gain wide application, QoS should be provided in ad hoc networks. In this paper, we propose a multipath differentiated service model (MDS) in ad hoc networks. In contrast to the traditional methods which focus on the scheduling among different flows or packets at the routing layer, we utilize the path diversity between the source and destination nodes in ad hoc networks. It is observed that there are multiple paths between the source and destination and these paths have different qualities as throughput and end-to-end delay are considered. We take advantage of this quality difference to differentiate the service provided to different traffic. Moreover, differentiated admission control is applied to maintain the quality level of each path. We propose the basic framework of MDS and give an example to illustrate the functions of this model. The simulation results indicate that MDS can fulfill the goal of service differentiation well without introducing much modifications to the existing work.","PeriodicalId":309894,"journal":{"name":"2008 3rd IEEE Conference on Industrial Electronics and Applications","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115477159","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 liquefied petroleum gas gasification system utilizing solar thermal energy","authors":"GuoHua Shi, Youyin Jing, Yuefen Gao","doi":"10.1109/ICIEA.2008.4582803","DOIUrl":"https://doi.org/10.1109/ICIEA.2008.4582803","url":null,"abstract":"Liquefied petroleum gas (abbreviated as LPG) is still an important source of residential gas in China due to its advantages. LPG gasfier is the key equipment of the LPG center supplement system. Traditional LPG vaporizer mainly depends on electric heating as its heat source, which leads to high energy cost and can not meet the demand of energy conservation policy. A new LPG gasification system utilizing solar thermal energy has been designed in this paper. This system uses hot water produced by a solar water heating system as vaporization heat source and uses an electric heater as assisted heat source. In order to understand the running conditions and the thermodynamic performances of the whole system better, this paper presents several thermal-physical models. The paper chooses a community with 1000 households in Beijing as a subject, and selects one sunny day in November which has minimal average hours of sunshine to study the LPG gasification system using solar thermal energy. The result shows that the system is stable on the aspect of thermal performance and is efficient in electricity-saving. In addition, the economy efficiency of the LPG gasification system with solar energy is analyzed by using the cost-effective analysis. The result expresses that the new system is an efficient, reliable and environmentally friendly alternative to the traditional LPG vaporization system using electricity only.","PeriodicalId":309894,"journal":{"name":"2008 3rd IEEE Conference on Industrial Electronics and Applications","volume":"18 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115500139","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 distributed intelligent database system and its coordinated mechanism","authors":"Zhongchun Fang, Hairong Li","doi":"10.1109/ICIEA.2008.4582980","DOIUrl":"https://doi.org/10.1109/ICIEA.2008.4582980","url":null,"abstract":"Through deeply research and analysis of distributed database system (DDBS), Large System Cybernetics (LSC)[l-2] and distributed artificial intelligence (DAI), a new concept called DIDBS (distributed intelligent database system) is put forward, which is used for realizing man-man, man-computer, computer-computer coordinated operation in man-computer society. Then its conceptual model and systemic architecture are expatiated on. Based on this, this paper not only studies coordinated mechanism and its implementation model of DIDBS but also puts forward coordinated strategies.","PeriodicalId":309894,"journal":{"name":"2008 3rd IEEE Conference on Industrial Electronics and Applications","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115558250","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":"Array steering vector estimation with nonstationary noise exploiting calibrated noise subspace","authors":"Z. Yu, M. Er, W. Ser","doi":"10.1109/ICIEA.2008.4582958","DOIUrl":"https://doi.org/10.1109/ICIEA.2008.4582958","url":null,"abstract":"Most of the robust adaptive beamformers to resolve target signal cancellation caused by array steering vector (ASV) mismatch use prior information on ASV. However, in some practical applications, no prior information on ASV is available or the ASV is changing due to the movement of target source. In such case, the identification of ASV is essential. There are some methods proposed for ASV identification but few of them work with nonstationary noise. In this paper, a new method is proposed to identify ASV with nonstationary noise by exploiting the calibrated noise subspace. With the identified ASV, a robust beamformer can be formed. Experiments illustrate that the proposed method has high performance in adverse environment.","PeriodicalId":309894,"journal":{"name":"2008 3rd IEEE Conference on Industrial Electronics and Applications","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115668510","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}
Liu Zhen, Shi Jin-ming, Bai Zhongying, Zhao Jin-yan
{"title":"A fast motion estimation algorithm by using Immune Quantum Algorithm","authors":"Liu Zhen, Shi Jin-ming, Bai Zhongying, Zhao Jin-yan","doi":"10.1109/ICIEA.2008.4582567","DOIUrl":"https://doi.org/10.1109/ICIEA.2008.4582567","url":null,"abstract":"In this paper, a novel fast multi-mode motion estimation algorithm by using immune quantum algorithm is proposed. By the judgement of the motion style according to he correlation of the motion vector. the type of searching modes can be choosed adaptively. In the slow-motion mode, CDS method can be used directly. In the exquisite motion mode, a combined IQA/CDS search strategy is utilized. Firstly, the IQA method is used to search the appropriate best motion vector in the combined search strategy, which can synthesizes the character of block motion estimation and that of global search, no prone to premature and high convergence speed. Then the CDS method is used to search global best motion vector in the region around the appropriate motion vector. Experimental results show that the algorithm can speed up the process of motion estimation effectively.","PeriodicalId":309894,"journal":{"name":"2008 3rd IEEE Conference on Industrial Electronics and Applications","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115756785","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":"Price volatility analysis by Grey disaster theory","authors":"Li Xie, Hua Zheng, Guo-ying Fan","doi":"10.1109/ICIEA.2008.4582963","DOIUrl":"https://doi.org/10.1109/ICIEA.2008.4582963","url":null,"abstract":"Since the electricity market came into being, price volatility is along a difficult and unavoidable problem that makes the market participants face with great risks. But due to the short development of the deregulation, price and its relative data are insufficient, and then price researches have become a typical small-sampled problem. No doubt, such data condition have restricted the application and generalization ability of traditional methods. Then volatility analysis on the electricity price is along a focused and hot problem in the research fields of the electricity market. To solve the above problems, a novel model for price volatility analysis is proposed by grey disaster prediction, which aims at forecasting when the next price volatility will happen. After studying on the tendency when the price volatilities happen, this work builds a grey model to performing the price volatility prediction. Finally numerical experiments are applied to test the validity of the proposed model.","PeriodicalId":309894,"journal":{"name":"2008 3rd IEEE Conference on Industrial Electronics and Applications","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2008-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124171883","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}