Search

In various pattern recognition applications, angle variation is always a main challenging factor for producing reliable recognition. To increase the endurance ability on angle variation, this paper adopts a Hierarchical Temporal Memory (HTM) algorithm which applies temporal information to organize time-sequence change of image features, and constructs invariant features so that the influence of angle variation can be effectively learnt and overcome. The proposed multi-angle HTM-based posture recognition method consists of two main modules of Hand Posture Image Pre-processing (HPIP) and Hand Posture Recognition (HPR). In HPIP, each input image is first processed individually by skin color detection, foreground segmentation and edge detection. Then, the three processed results are further combined linearly to locate a hand posture region. If a forearm exists in the located hand posture region, a forearm segmentation process will be executed to keep only the part of palm. In HPR, the normalized image is forwarded to a HTM model for learning and recognizing of different kinds of hand postures. Experiment results show that when using the same continuous unconstrained hand posture database, the proposed method can achieve an 89.1% high recognition rate for discriminating three kinds of hand postures, which are scissors, stone and paper, and outperforms both Adaboost (78.1%) and SVM (79.9%). [ABSTRACT FROM AUTHOR]

Recently, research on computer based music generation utilizing composition algorithm has drawn attention. The goal of this research is to produce new music, never heard before, using the algorithm developed and presented in this paper. The developed algorithm uses learning technique and probability and statistical analysis. The algorithm uses note sequences and other musical parameters such as note length, pitch, accidentals, modifications (intensity, speed), and note sequence repetition density for the preparation of a probability table that will generate new music. We used thematic music pieces (from same theme) as input music for analysis using learning followed by statistical analysis. We used MATLAB for analysis and MC Music editor for display. This research study is the first of its kind to create thematic music pieces effectively in a computer-based environment. The outcome of this research has a wide range of usage: waiting-music during automated phone-calls, background music in airports, airplanes, and restaurants, and so on. The work can be extended to include variations of frequency and the shape of the note sequences for analysis. [ABSTRACT FROM AUTHOR]

Motivated by ecological appeal and laws, the Nokia's Take-Back initiative collects used mobile phones disposed in bins spread around the world, a kind of solid waste collection. This paper presents a light weight image processing technique to detect bin level based solely on internal wall entropy perturbation, aiming to automate the discovery of the best moment to take back disposed mobile phones and accessories. A low cost mobile phone scrapped in the manufacture center is recycled and installed inside the bin in a proper support, taking photos to extract entropy features sent as very few data to a server who finishes the processing. Learning and non-learning strategies are compared when analyzing entropy perturbations, showing great performance of the multilayer perceptron (MLP), Logistic Model Tree (LMT) and k-NN classifiers. An interesting resulting behavior shows that most of errors are acceptable since they occur in the adjacency of levels, allowing even higher accuracy evaluations. Our simple level detection method is efficient and efficacious allowing mobile side processing, cost reduction on data transfer and prevention of unnecessary trucks visiting the collecting points, enabling the method to be safely used by monitoring systems, increasing the reverse logistics capacity by scaling the take back process. [ABSTRACT FROM AUTHOR]

This paper proposes a new marshaling method for assembling an outgoing train considering the layout of incoming freight cars. In the proposed method, each set of freight cars that have the same destination make a group, and the desirable group layout constitutes the best outgoing train. The incoming freight cars are classified into several "sub-tracks" searching better assignment in order to reduce the total processing time. Classifications and marshaling plans based on the processing time are obtained by a reinforcement learning system. In order to evaluate the processing time, the total transfer distance of a locomotive and the total movement counts of freight cars are simultaneously considered. Moreover, by grouping of freight cars, candidates of classification of incoming train and the desired arrangement of the outgoing train is extended. This feature is considered in the learning algorithm, so that the total processing time is reduced. Then, the classification of incoming cars, the order of movements of freight cars, the position for each removed car, the layout of groups in a train, the arrangement of cars in a group and the number of cars to be moved are simultaneously optimized to achieve minimization of the total processing time for obtaining the desired arrangement of freight cars for an outgoing train. Initially, freight cars are located in a freight yard by the random layout, and they are moved and lined into a main track in a certain desired order in order to assemble an outgoing train. Learning algorithm in the proposed method is based on the Q-Learning, and, after adequate autonomous learning, the optimum marshaling plan can be obtained by selecting a series of movements of freight cars each of which has the best evaluation. [ABSTRACT FROM AUTHOR]