7294 research outputs found
Sort by
Recognition of Off-line printed Arabic text Using Hidden Markov Models
Get PDFThis paper describes a technique for automatic recognition of off-line printed Arabic text using Hidden Markov Models. In this work different sizes of overlapping and non-overlapping hierarchical windows to generate 16 features from each vertical sliding strip are used. We experimented with all tested fonts (viz. Arial, Tahoma, Akhbar, Thuluth, Naskh, Simplified Arabic, Andalus, and Traditional Arabic). It was experimentally proven that different fonts have their highest recognition rates at different numbers of states (5 or 7) and codebook sizes (128 or 256). Arabic text is cursive, and each character may have up to 4 different shapes based in its location in a word. We decided to consider each shape as a different class hence resulting in a total of 126 classes. The achieved average recognition rates (using 126 classes and 16 features for each vertical strip of three pixels width) were between 98.08% for Thuluth and 99.89% for Arial. The main contributions of this work are the novel hierarchical sliding window technique, and using 16 features only for each sliding window. Each shape of the Arabic characters is considered as a separate class, bypassing the need for segmenting Arabic text, and is applicable to other languages
Circularly Polarized Microstrip Ferrite Phase-shifter with Uneven Excitation
Get PDFA low-cost and externally controlled planar microstrip ferrite phase shifter is designed, where the differential phase shift is considerably improved by introducing circularly polarized electromagnetic waves in the structure. Simulated phase response of the designed phase shifter is presented to demonstrate the improvement in the differential phase shift compared to an equivalent traditional microstrip ferrite phase shifter
WIRELESS FAIR QUEUING ALGORITHM FOR WINDOW-BASED LINK LEVEL RETRANSMISSION
Get PDFWireless networks have unreliable channels that experience bursty and location-dependent errors. Several fair queuing algorithms have been proposed in order to provide QoS in presence of errors in a fair manner. However, most of these algorithms are unpractical as they require perfect channel predication or do not work well with the Link Layer. Wireless Fair Queuing with Retransmission (WFQ-R) algorithm was recently suggested to address these problems by penalizing flows that use wireless resources without permission in the link layer. However, the WFQ-R algorithm is based on Stopand- Wait LLR scheme which also costs the network extensive delay and low utilization. In this paper, a new wireless fair queuing based on the WFQ-R algorithm is proposed to work with the window-based error control schemes in the link layer. The proposed algorithm has shown outstanding results compared with WFQ-R in terms of lower queuing delay, better throughput and fairly allocated resources
Simple Microwave Method for Detecting Water Holdup
Get PDFA microwave sensor is designed to measure the resonance behavior of the hydrocarbon mixture to determine the water holdup of a near horizontal oil carrying pipeline. This technique is particularly useful for detecting very small water holdup (<5%) as demonstrated by simulated and experimental results
ARTIFICIAL NEURAL NETWORK APPLICATION OF MODELLING FAILURE RATE FOR BOEING 737 TIRES
Get PDFThis paper presents an application of artificial neural network technique for predicting the failure rate of Boeing 737 tires. For this purpose, an artificial neural network model utilizing the feed-forward back-propagation algorithm as a learning rule is developed. The inputs to the neural network are the independent variables and the output is the failure rate of the tires. Two years of data is used for failure rate prediction model and validation. Model validation, which reflects the suitability of the model for future predictions, is performed by comparing the predictions of the model with that of Weibull regression model. The results show that the failure rate predicted by the artificial neural network is closer in agreement with the actual data than the failure rate predicted by the Weibull model. The present work also identifies some of the common tire failures and presents representative results based on the established model for the most frequently occurring tire failure