International Journal of Information Acquisition

In this paper, we would focus on submitting a new decision fusion method based on multiple sensors' behaviors applying to target detection and identification in a network of distributed sensors. Each sensor has its own reliability, error rate and output data. Hence, in a processing and decision-making center in which target data are received from different sensors and sources, correctness and speed of final decision-making depend on data fusion method. The extraction, modeling and weighing of long-time and temporary behavior functions of each data source and using precise and fast decision making/fusion method are the main purpose of this article. After the introduction, we try to consider the data fusion method in decision level, such as voting schemes, rank based method and Bayesian inference. Hence, in a distributed target detection and identification system, we explain the specific and the functional features model of each source using long-time and temporary behavior functions. So we introduce the behavior based method as a new decision fusion method based on long-time and temporary behaviors of local decision makers. Therefore, we will observe that the behavior based method results, which pointed both to the temporal and the long time behaviors of the input decision makings, are very much nearer to reality and its correctness in target identification is much higher than the other methods. Examples are given corresponding to the target detection and identification systems to compare the new method with the other methods are shown that the behavior based method has its own exclusive capability in target detection, identification and producing final decision without ambiguity.

A rigorous preselection of identified compounds by in vitro cellular screening is necessary prior to using the drug candidates for the further time consuming and parallel monitoring stage. In this paper we introduced an integrated cell based chip which can detect changes of electrophysiological parameters by using microelectronic chips such as Light-Addressable Potentiometric Sensors (LAPS), Micro-electrodes Array Sensors (MEAS) and Interdigitated Array Sensor (IDA) etc. to record the extracellular metabolism chemical and biological substances, action potential and living characteristics of cells representing the different response. In this research we presented novel ideas including an integrating multifunctional cell sensors chip, obtaining the living cells as the source of cell sensors with cardiac myocytes. The characteristic curve and primary electrophysiological measurement of each part were tested. Further developments will be done by culturing living olfactory and taste cells on surface of the devices. Now, we have completed the fabrication of the sensor and obtained some promising experiments results in different sensor units. This research will be interesting and useful for parallel extracellular monitoring.

This work describes a method to allow objects for autonomous robot navigation on outdoor environment. The proposition of the method segments and recognizes the object from an image taken by moving robot on outdoor environment. We classify the object natural and artificial. We classify trees as natural objects and buildings as artificial objects. Then we define their characteristics individually. In the process, we segment objects included by preprocessing using multiple cues and show the method of segmentation based on low-level features using multiple cues. Multiple cues are color, line segment, context information, HCM (Hue Co-occurrence Matrix), PCs (Principal Components), vanishing point. Objects can be recognized when we combine predefined multiple cues. The correct object recognition of proposed system is over 92% among our test database which consist of about 1200 images. We accomplish the result of image segmentation using multiple cues and object recognition through experiments.

This paper presents a method for modeling abnormal human gait using hidden Markov model under the framework of a shoe-integrated system. The intelligent system focuses on modeling the following patterns: normal gait, toe in abnormality, and toe out abnormality. In the developed prototype, an inertial measurement unit (IMU) consisting of three-dimensional gyroscopes and accelerometers is employed to measure the angular velocities and accelerations of the foot. Four force sensing resistors (FSRs) and one bend sensor are arranged on the insole of each foot for force and flexion information acquisition. The proposed method is mainly based on supervised Principal Component Analysis (SPCA) for feature generation and hidden Markov model (HMM) for multi-pattern modeling. The "similarity distance measure" criterion is introduced to do model-to-model evaluation. Experimental results demonstrate the proposed approach is robust and efficient in detecting abnormal gait patterns. Our goal is to provide a cost-effective system for detecting gait abnormalities in order to assist persons with abnormal gaits in developing a normal walking pattern in their daily life.

A background is a part that does not vary too much or change frequently in an image sequence. Using this assumption, an algorithm of reconstructing remained background and detecting moving objects for static and also moving camera is presented. For generating background, we detect regions that have high correlation coefficient compared within prior pyramid images from the current image. These detected regions are used for two process. First, we calculate the temporal displacement vector of each detected regions and classify clusters of pixel intensity based on camera movement. Second, we calculate temporally principal displacement vector using histogram of displacement vectors. Temporally principal displacement vector indicates camera movement. Finally we eliminate clusters which have lower weight than threshold, and combine remained clusters for each pixel to generate multiple background clusters. Experimental results show that remained background model and detected moving object under camera moving.

This paper presents a vision based motion control and trajectory tracking strategies for microassembly robots including a self-optimizing visual servoing depth motion control method and a novel trajectory snake tracking strategy. To measure micromanipulator depth motion, a normalized gray-variance focus measure operator is developed using depth from focus techniques. The extracted defocus features are theoretically distributed with one peak point which can be applied to locate the microscopic focal depth via self-optimizing control. Tracking differentiators are developed to suppress noises and track the features and their differential values without oscillation. Based on the differential defocus signals a coarse-to-fine self-optimizing controller is presented for micromanipulator to precisely locate focus depth. As well as a novel trajectory snake energy function of robotic motion is defined involving kinematic energy, curve potential and image potential energy. The motion trajectory can be located through searching the converged energy distribution of the snake function. Energy weights in the function are real-time adjusted to avoid local minima during convergence. To improve snake searching efficiency, quadratic-trajectory least square estimator is employed to predict manipulator motion position before tracking. Experimental results in a microassembly robotic system demonstrate that the proposed strategies are successful and effective.

Due to a few great advantages such as viewing the entire small intestine with almost non-invasiveness and no sedation over traditional endoscopies and other imaging techniques for gastrointestinal tract diseases, the wireless capsule endoscopy invented by Given Imaging has found its gradually wide applications in hospitals. However, one major issue concerning this new technology is that too many images to be examined by naked eyes cause a huge burden to physicians, so it is very necessary to ease the physician if we can do diseases detection using computerized methods. In this paper, we develop a new method by making use of color feature, also a very important clue for diagnosis by physicians, to discriminate between normal region and abnormal region. Exploiting the color histogram of the image, we can get the distribution of the color in the image. Then we use the minimum distance classifier to judge the status of the regions. Experimental results on our present data prove promising performance of the proposed scheme in detecting bleeding and ulcers.

There are many schemes to increase energy efficiency in wireless sensor network as energy is a precious resource. We focus on improving energy efficiency in sensing module while most of the previous works focus on the energy saving in communication module. When a sensor network continuously senses wide area, energy consumption is needed largely in the sensing module. We consider a change rate of sensed data and adjust sensing period to reduce energy consumption while minimizing average delay between change of field and detection. Additionally, cooperation among neighbor nodes is essential to reduce energy consumption and the delay. Our dynamic sensing algorithm reduces the energy consumption and delay between change of field and detection. Our scheme controls sensing cycle based on change of sensing data and information of neighbor nodes such as sensing cycle and number of cooperative nodes. It improves energy efficiency up to 90% comparing with the static sensing method, and reduces the delay up to 84% comparing to the previous works.

A secure mechanism is needed to use sensor nodes in real world, since we cannot anticipate attack types. Yu and Guan proposed the dynamic en-route filtering scheme (DEF) to detect and drop false reports as soon as possible in wireless sensor networks. In this scheme, the choice of a threshold value to diffuse keys is important since it represents a trade-off between detection power and overhead. A large threshold value can increase the probability of detecting false reports but it consumes too much energy during the key dissemination phase. Thus, we should choose a threshold value to optimize between the detection power and energy consumption. In this paper we propose a key dissemination limiting method to diffuse keys efficiently. The threshold value in the proposed method is determined by a fuzzy rule-based system by considering the energy level of the network, the number of secret keys in a cluster, and the distance from the base station (BS) to a cluster head. The simulation results show that the proposed method can conserve energy, while it provides sufficient detection power.