{"title":"Acquisition of state transitions in neural network","authors":"N. Ishii, Chiyuki Kondo, A. Furukawa, K. Yamauchi","doi":"10.1109/IJSIS.1996.565051","DOIUrl":"https://doi.org/10.1109/IJSIS.1996.565051","url":null,"abstract":"In the artificial intelligence, the breadth-first search is optimal with uniform cost. But it takes long time to obtain the solution. Neural networks process states transitions in parallel with learning ability. We developed a search procedure of states transition doing the the breadth-first, in the neural network. First, the input pattern states are self-organized in the neural network, which consists of the Kohonen layer followed by the state planning layer. The state planning layer makes lateral connections between cells of transitions. Then, the initial and the target states are given as a problem. The network shows an optimal state transition pathway in the neuron firings. Next, the state transition procedure is developed for the formation of the concept of action planning. Here, as the action planning, an integration between the symbols and the action pattern is carried out in the extended neural network.","PeriodicalId":437491,"journal":{"name":"Proceedings IEEE International Joint Symposia on Intelligence and Systems","volume":"109 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127208709","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":"Transforming system formulations in robotics for efficient perception and planning","authors":"D. Benjamin","doi":"10.1109/IJSIS.1996.565064","DOIUrl":"https://doi.org/10.1109/IJSIS.1996.565064","url":null,"abstract":"For efficient perception and planning, it is necessary for an autonomous robot to find a formulation with good computational properties. An especially important computational property is decomposability. The perspective of this work is to view a system's state space as though it were physical space, and the system's behavior as though it were physical motion. Following the analogy with physics, a formulation is an abstract coordinate system whose axes specify a decomposition, and formulations are transformed by changing coordinates. The mathematical basis for this analogy is given. Continuous and discrete formulations for a robot vehicle are transformed to yield decompositions, which shed light on the relationship between the continuous and discrete formulations.","PeriodicalId":437491,"journal":{"name":"Proceedings IEEE International Joint Symposia on Intelligence and Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130402330","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 methodology of separating images from text using an OCR approach","authors":"N. Bourbakis","doi":"10.1109/IJSIS.1996.565084","DOIUrl":"https://doi.org/10.1109/IJSIS.1996.565084","url":null,"abstract":"This paper presents a document processing methodology based on an OCR approach. The document methodology separates text from images by keeping their relationships for a possible reconstruction of the original page. The text separation and extraction is based on a hierarchical framing process. The process starts with the framing a single character, after its recognition, continues with the framing of a word, and ends with the framing of all text lines.","PeriodicalId":437491,"journal":{"name":"Proceedings IEEE International Joint Symposia on Intelligence and Systems","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114200394","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 application of wavelet-based vector quantization in target recognition","authors":"L. Chan, N. Nasrabadi","doi":"10.1109/IJSIS.1996.565079","DOIUrl":"https://doi.org/10.1109/IJSIS.1996.565079","url":null,"abstract":"An automatic target recognition (ATR) classifier is constructed that uses a set of dedicated vector quantizers (VQs). The background pixels in each input image are properly clipped out by a set of aspect windows. The extracted target area for each aspect window is then enlarged to a fixed size, after which a wavelet decomposition splits the enlarged extraction into several subbands. A dedicated VQ codebook is generated for each subband of a particular target class at a specific range of aspects. Thus, each codebook consists of a set of feature templates that are iteratively adapted to represent a particular subband of a given target class at a specific range of aspects. These templates are then further trained by a modified learning vector quantization algorithm that enhances their discriminatory characteristics.","PeriodicalId":437491,"journal":{"name":"Proceedings IEEE International Joint Symposia on Intelligence and Systems","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124016049","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":"Modeling pathological patterns of spoken natural language by using SPNs","authors":"B. Roy, D. Kavraki, N. Bourbakis","doi":"10.1109/IJSIS.1996.565050","DOIUrl":"https://doi.org/10.1109/IJSIS.1996.565050","url":null,"abstract":"This paper deals with the modeling of spoken natural language (NL) to detect schizophrenic patterns. The modeling and analysis of the spoken NL is based on its formal representation by using stochastic Petri nets (SPNs) and the synthesis of the SPN forms for the appropriate interpretations and the detection of schizophrenic patterns, if any.","PeriodicalId":437491,"journal":{"name":"Proceedings IEEE International Joint Symposia on Intelligence and Systems","volume":"442 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125779800","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":"Neuralware engineering: develop verifiable ANN-based systems","authors":"Wu Wen, J. Callahan","doi":"10.1109/IJSIS.1996.565052","DOIUrl":"https://doi.org/10.1109/IJSIS.1996.565052","url":null,"abstract":"Artificial neural networks (ANN) play an important part in developing intelligent robotic and autonomous systems; it relies on training to formulate the control mechanisms. When such ANN-based components are embedded in a larger system, their interactions become harder to analyze and model. Formal testing of such system for safety properties is extremely hard due to the lack of a complete system model. In this paper we propose the neuralware engineering framework to address the above issues. This framework is based on our experience with verifying and testing complex software systems. It is based on an iterative approach on specification, model checking, and testing. After the ANN-based system is designed and trained using an initial partial system model, a rule extraction algorithm is used to discover what has been learned. The discrepancies between the learned rules and the model is compared to modify the system model. This process is repeated until the behavior of the real system is validated against the model and specification.","PeriodicalId":437491,"journal":{"name":"Proceedings IEEE International Joint Symposia on Intelligence and Systems","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129782984","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":"Transmission scheduling for fieldbus: a strategy to schedule data and messages on the bus with end-to-end constraints","authors":"L. Franco","doi":"10.1109/IJSIS.1996.565063","DOIUrl":"https://doi.org/10.1109/IJSIS.1996.565063","url":null,"abstract":"The transmission scheduling for fieldbus has been addressed until now to minimize the number of data. It does not take into account the temporal dependency of data. Usually, the approaches of transmission scheduling for fieldbus let to the application processes to decide whether to use old values or not. The objective of this paper is to show how to adapt Gerber's methodology to generate a scheduling table of a set of periodic and aperiodic data from application processes to be transmitted through a fieldbus, guaranteeing their end-to-end constraints; and how this can be done in according to IEC 1158. This strategy obviates the transmission of old and useless data to application, thus optimizing the fieldbus scheduling.","PeriodicalId":437491,"journal":{"name":"Proceedings IEEE International Joint Symposia on Intelligence and Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123741614","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 description of a universal assembler","authors":"Forrest F. Bishop","doi":"10.1109/IJSIS.1996.565060","DOIUrl":"https://doi.org/10.1109/IJSIS.1996.565060","url":null,"abstract":"An \"active cell aggregate\", or \"shape shifter\", is an aggregation of similar, space-filling polyhedral machines, preferably built by molecular nanotechnology methods. \"Active\" means each machine, or \"active cell\", has the capacity to exchange power and signals with other similar machines, and to interact with the external environment. A robot constructed in this manner can have a very large and detailed envelope of motion. By incorporating simple manipulators onto the various faces of the polyhedron, a universal assembler, or \"overtool\", may be possible, for molecular, mesoscopic, and macroscopic assembly.","PeriodicalId":437491,"journal":{"name":"Proceedings IEEE International Joint Symposia on Intelligence and Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133749372","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 model-based gaze tracking system","authors":"R. Stiefelhagen, Jie Yang, A. Waibel","doi":"10.1109/IJSIS.1996.565083","DOIUrl":"https://doi.org/10.1109/IJSIS.1996.565083","url":null,"abstract":"In this paper we present a non-intrusive model-based gaze tracking system. The system estimates the 3D pose of a user's head by tracking as few as six facial feature points. The system locates a human face using a statistical color model without any mark on the face and then traces the facial features, such as eyes, nostrils and lip corners. A full perspective model is employed to map these feature points onto the 3D pose. Several techniques have been developed to track the features points and recover from failure. We currently achieve a frame rate of 15+ frames per second using an HP 9000 workstation with a frame grabber and a Canon VC-C1 camera. The application of the system has been demonstrated by a gaze-driven panorama image viewer. The potential applications of the system include multimodal interfaces, virtual reality and video-teleconferencing.","PeriodicalId":437491,"journal":{"name":"Proceedings IEEE International Joint Symposia on Intelligence and Systems","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123592923","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":"Construction and operation of a snake-like robot","authors":"R. Worst, R. Linnemann","doi":"10.1109/IJSIS.1996.565065","DOIUrl":"https://doi.org/10.1109/IJSIS.1996.565065","url":null,"abstract":"Our robot, called the GMD-Snake, uses its body instead of wheels, legs, or arms for locomotion as well as for handling items. It may be used for inspection and manipulation in areas where motion is restricted. We describe the hardware and software of the GMD-Snake and some locomotion experiments. The GMD-Snake is assembled of some uniform sections, each one consisting of two rubber joints. The joints can be bent in arbitrary directions, thus making the robot's body very flexible. To imitate closely a real snake and to study different ways of movement, an appropriate control software is necessary, which manages the harmonious motion of all the sections. Therefore, the individual sections are connected to an external processor via a special type of field bus, called CAN bus. Currently, the snake can do its locomotion according to predefined commands. In future, the robot shall be able to use its sensors for flexible interactions with objects of its environment.","PeriodicalId":437491,"journal":{"name":"Proceedings IEEE International Joint Symposia on Intelligence and Systems","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122781850","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}