{"title":"The biological inspired somatic neuron design and its application in robot nervous system","authors":"Zhongcheng Wu, Enliang Song, Fei Shen, Dezhang Xu, Bing Fang","doi":"10.1109/ICIA.2005.1635139","DOIUrl":"https://doi.org/10.1109/ICIA.2005.1635139","url":null,"abstract":"The nervous system is the major controlling, regulatory, and communicating system in human body. One of the basic functions of the nervous system is the sensory, by which one monitors the external and internal environments. Sensory pathways to the cortex usually consist of three sensory neurons termed 1st order, 2nd order, and 3rd order neurons. In this paper, a standard biological inspired neuron was presented, which can be acted as the basis node of robot perceptual systems. The hardware and software has been designed and implemented for modeling, testing and employing sensor networks composing of many identical neuron nodes. Each node considers ease-of-use and power considerations. Some requirements, such as 'plug-and-play' capability, system integration and dynamic reconfiguration, were described, which is achieved through an 'transducer electronic data sheet' (TEDS) in our networked transducer neuron node. The TEDS contains fields that fully describe the type, operation, and attributes of one or more transducers and its data formats are defined. The paper also specifies a digital interface for connecting neuron to access the TEDS data sheets for reading sensor data and setting actuators. Each neuron can connect more than 8 channel analog signals by 12 bit resolution, two digital channel for SPI and I/sup 2/C interface sensor, and more than 20 channel I/O for switch signal, it can also offer two channel analog output for controlling purpose. A set of designed neurons can be connected together by different structure to form robot nervous system, not only for sensing, but for controlling too. Example application on robot perception system and future in progress work are discussed in the end.","PeriodicalId":136611,"journal":{"name":"2005 IEEE International Conference on Information Acquisition","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124849170","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 the frequency calibration of high shock accelerometer using Hopkinson bar","authors":"Ping Song, Kejie Li, Husheng Zhang, Zhiqiang Pan","doi":"10.1109/ICIA.2005.1635105","DOIUrl":"https://doi.org/10.1109/ICIA.2005.1635105","url":null,"abstract":"A method about the shock comparison frequency calibration is brought forward in this paper to calibrate a high shock accelerometer using the Hopkinson bar as the pulse exciter. The output of the standard accelerometer is used as the input of the test accelerometer, the output of the test accelerometer is used as the output of test accelerometer, the transfer function can be obtained by the characteristic of the input and the output of the test accelerometer, then the frequency characteristic of the test accelerometer is known.","PeriodicalId":136611,"journal":{"name":"2005 IEEE International Conference on Information Acquisition","volume":"54 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125058960","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}
Tae Sung Kim, K. Park, Chi-Hyo Kim, Ji Hoon Park, M. K. Lee
{"title":"Development of a parallel typed robot with a sensorless observer for harbor construction","authors":"Tae Sung Kim, K. Park, Chi-Hyo Kim, Ji Hoon Park, M. K. Lee","doi":"10.1109/ICIA.2005.1635079","DOIUrl":"https://doi.org/10.1109/ICIA.2005.1635079","url":null,"abstract":"This paper presents an underwater robot developed for harbor construction, which requires the robot to carry a heavy load with large workspace and high dexterity. The requirement can't be attained by a conventional serial typed robot but by a parallel typed robot. For underwater work, it is necessary to waterproof the robot and its sensors. Especially, a sensor waterproof is a main drawback to build the underwater robot. This leads us to develop a sensorless observer which gives the position information without any position sensor. We design a neural network to identify the displacement change of the hydraulic cylinder according to the voltage exerting at servo valve. This paper introduces the design strategy for the parallel typed robot and the development with hydraulic control and wireless communication. The robot is attached to the end of an excavator or a crane to carry a large stone to build a bank. This paper shows the experimental results and explains the performance of the robot.","PeriodicalId":136611,"journal":{"name":"2005 IEEE International Conference on Information Acquisition","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125423677","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":"Automated on-line inspection for glass fiber forming","authors":"P. P. Lin, Q. Guo","doi":"10.1109/ICIA.2005.1635113","DOIUrl":"https://doi.org/10.1109/ICIA.2005.1635113","url":null,"abstract":"Glass fiber forming is a complicated process in which many factors could affect the measuring accuracy of fiber diameters. In the forming machine there are many tubes close to each other, which results in improper lighting and unwanted video signals. This paper presents the employment of a new filter called anti-causal zero-phase was to remove noise without distortion. In this work, the unwanted video signals constantly moved from one place to another, which created a major problem in image analysis. This paper presents a technique to identify the unwanted signals by developing a model for an object, and training the modeled experimental data using a neural network to classify patterns. Only the patterns that met the expectation were used for fiber diameter measurement. The entire inspection process was automated with the aid of a PLC (programmable logic controller). The results for noise removal and pattern classification are included.","PeriodicalId":136611,"journal":{"name":"2005 IEEE International Conference on Information Acquisition","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121996876","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 novel two stage image recognition method","authors":"Zhuofu Liu, Zhenpeng Liao, E. Sang","doi":"10.1109/ICIA.2005.1635131","DOIUrl":"https://doi.org/10.1109/ICIA.2005.1635131","url":null,"abstract":"In this paper, a novel algorithm for image recognition, consisting of two stages: coarse recognition and fine recognition, is presented. For coarse recognition, a new gray-spatial histogram is proposed, which incorporates spatial information with gray-scale compositions without sacrificing the robustness of traditional gray histograms. For fine recognition, a new wavelet set, called directional wavelets, is obtained from the exponential wavelet family. And then an approach to directional wavelet transform-based recognition using feature weighting is proposed. The weighted directional wavelet coefficients represent the directionality and multi-scale characteristics of images. The combination of coarse and fine recognition steps reduces the computational cost without degrading the classifying accuracy. In the end, the recognition experiment of underwater acoustic images has been done and the result is satisfactory, which verifies the effect of this method.","PeriodicalId":136611,"journal":{"name":"2005 IEEE International Conference on Information Acquisition","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125709101","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":"Textile defect classification using discriminative wavelet frames","authors":"Xuezhi Yang, Jun Gao, G. Pang, N. Yung","doi":"10.1109/ICIA.2005.1635053","DOIUrl":"https://doi.org/10.1109/ICIA.2005.1635053","url":null,"abstract":"The classification of defects is highly demanded for automated inspection of textile products. In this paper, a new method for textile defect classification is proposed by using discriminative wavelet frames. Multiscale texture properties of textile image are characterized by its wavelet frames representation. For a better description of the latent structure of textile image, wavelet frames adapted to textile are generated rather than using standard ones. Based on discriminative feature extraction (DFE) method, the wavelet frames and the back-end classifier are simultaneously designed with the common objective of minimizing classification errors. The proposed method has been evaluated on the classification of 466 defect samples containing eight classes of textile defects, and 434 nondefect samples. In comparison with standard wavelet frames, the designed discriminative wavelet frames has been shown to largely improve the classification performance, where 95.8% classification accuracy was achieved.","PeriodicalId":136611,"journal":{"name":"2005 IEEE International Conference on Information Acquisition","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133478996","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":"Physiological system modeling applied to an intelligent wheel chair","authors":"Liting Yao","doi":"10.1109/ICIA.2005.1635118","DOIUrl":"https://doi.org/10.1109/ICIA.2005.1635118","url":null,"abstract":"As the number of interactions between robotic machines and humans increases so does the need for the development of better means of integrating machines and humans. In order that user commands might become better understood, a human physiological model should first be developed. Such a system incorporates specialized sensors and actuators to obtain data from the user and control the actions of the machine. For the system as a whole to operate effectively, the various sensors and actuators must interact harmoniously with each other. This paper outlines a design for an intelligent wheel chair and elaborates on the basic features of human physiological modeling and sensor-actuator systems.","PeriodicalId":136611,"journal":{"name":"2005 IEEE International Conference on Information Acquisition","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114183700","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 overview of pen computing","authors":"Kang Le, Wei Mingxu, Wu Zhong-cheng","doi":"10.1109/ICIA.2005.1635154","DOIUrl":"https://doi.org/10.1109/ICIA.2005.1635154","url":null,"abstract":"Pen computing broadly refers to an interdisciplinary matter and attracts many researchers recent years. In this paper we review four aspects of pen computing, say, pen-computing devices, pen interfaces, online handwriting recognition systems and pen computer applications. On the one hand we present a contour of pen computing, on the other hand, by virtual of reviewing the state of the art of pen computing, we also find many dissatisfaction in pen computing and hence consider that to further promote the development of pen computing, firstly researchers need to improve the hardware performance of pen computers and secondly to develop pen-base operating systems and more friendly pen interfaces and lastly to propose more better recognition algorithms.","PeriodicalId":136611,"journal":{"name":"2005 IEEE International Conference on Information Acquisition","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114242029","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 novel distributed CMLWLC CFAR detector","authors":"Jin-song Jiang, Hong Sun, Jun Yang, Shouyong Wang","doi":"10.1109/ICIA.2005.1635128","DOIUrl":"https://doi.org/10.1109/ICIA.2005.1635128","url":null,"abstract":"In the past applications, the centralized CFAR, which used in the multi-sensor information fusion system, brings an overload communication burden, therefore the distributed CFAR detector becomes a developing and important field. In current distributed CFAR detectors, most of them assume that every sensor in the detector have same signal to noise ratio (SNR). In this paper, we study the case that every sensor in the detector have different SNR. Corresponding to this case, a novel distributed adaptive CFAR detector termed as CMLWLC is presented. In the scheme, a local test statistic, which is the ratio of its test sample level and a designated censored mean level (CML) of its reference samples, is calculated by distributed sensors, and then each sensor transmits its local test statistic to the fusion center. At the fusion center, the global decision is made based on weighted linear combining (WLC). Since the weights are adjusted according to different SNR, adaptively, the proposed detector can available in the case that the target echo and noise/clutter have different level for every sensor. Meanwhile, for a Swerling II fluctuating target in Gaussian noise of unknown level, its closed-form expressions of false alarm probability and detection probability are derived. Comparison numerical results show that the CMLWLC detector has good detection performance in both homogeneous and multi-target backgrounds.","PeriodicalId":136611,"journal":{"name":"2005 IEEE International Conference on Information Acquisition","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123462208","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 policy gradient estimation of continuous-time hidden Markov decision processes","authors":"Liao Yanjie, Yin Bao-qun, Xi Hongsheng","doi":"10.1109/ICIA.2005.1635101","DOIUrl":"https://doi.org/10.1109/ICIA.2005.1635101","url":null,"abstract":"Recently, gradient based methods have received much attention to optimize some dynamic systems with hidden information, such as routing problems of robotic systems. In this paper, we presented a process - continuous time hidden Markov decision process (CTHMDP), which can be used to model the robotic systems. For this process, the problem of policy gradient estimation is studied. Firstly, an approximation formula to the gradient is presented, then by using the uniformization method, we introduce an algorithm, which can be considered as an extension of gradient of partially observable Markov decision process (GPOMDP) algorithm to the continue time model. Finally, the convergence and error bound of the algorithm are considered.","PeriodicalId":136611,"journal":{"name":"2005 IEEE International Conference on Information Acquisition","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129740564","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}