مجله کامپیوتر و روباتیک
سال:1393 | دوره: | شماره: |تعداد مقالات:8

One of the complex documents in the real world is city maps. In these kinds of maps, text labels overlap by graphics with having a variety of fonts and styles in different orientations. Usually, text and graphic colour is not predefined due to various map publishers. In most city maps, text and graphic lines form a single connected component. Moreover, the common regions of text and graphic lines have similar features; hence, the separation of text and graphic lines is a challenging task in document analysis. Generally, these text labels could not be recognized efficiently by current commercial OCR systems in city map processing. In this paper, we propose an image decomposition approach based on stroke width feature to extract text labels from city maps. In our approach, we assign to each pixel of image a local stroke width based on minimum distance from borders in four directional borders. This mapping generates a suitable representation to distinguish text and non-text pixels. The experimental results on several varieties of city maps are promising.

A complete procedure for the design of W-band low noise amplifier in MMIC technology is presented. The design is based on a simultaneously power and noise matched technique. For implementing the method, scalable bilateral transistor model parameters should be first extracted. The model is also used for transmission line utilized in the amplifier circuit. In the presented method, input/output matching networks and transistor gate width have been optimized for simultaneous maximum gain and minimum noise figure. It is easily shown that due to the low gain property of amplifier at high frequency, it is unconditionally stable; so, the common source topology has superior performance compared to other topologies. In addition, better noise figure, lower size and higher gain with the same power consumption can be achieved compared with those of the cascode topology. The simulation results show a gain of better than 18dB and noise figure of 7.4dB at 94GHz while input/output return losses are better than 20dB.

Titanium dioxide (TiO2) nanoparticles have been frequently employed in the environmental treatment and purification purposes as a cheap and highly efficient photocatalyst. A photocatalyst can facilitate the breakdown and removal of a variety of environmental pollutants at room temperature. TiO2 photocatalyst is the best candidate because of its strong oxidized ability, non-toxicity and long thermal photostability. The TiO2 is also important and need deep studies because it can be used as self-cleaning and anti-fogging glass in future. In this paper, TiO2 nanoparticles were synthesized by liquid phase method. The samples were characterized by x-ray diffraction (XRD) and transmission electron microscopy (TEM) analyses after heat treatments. The XRD results show the sharp picks after annealing process. The TEM results reveal that the size of nanoparticles is in the range of 20-40 nm in diameter. Raman scattering pattern of the TiO2 nanoparticles confirm the TEM analysis and indicate the anatase phase.

Noise removal operation is commonly applied as pre-processing step before subsequent image processing tasks due to the occurrence of noise during acquisition or transmission process. A common problem in imaging systems by using CMOS or CCD sensors is appearance of the salt and pepper noise. This paper presents Cellular Automata (CA) framework for noise removal of distorted image by the salt and pepper noise. In order to enhance the performance of the designed CA for noise removal, a parallel programming approach has been adopted and implemented on GPU. The results obtained show that the proposed CA models implemented on general purpose processor and GPU are able to suppress noise in high noise intensity up to 90 percents. The proposed CA implemented on GPU has successfully outperformed the method implemented on CPU by factor of 2 for gray scale image and factor of 10 for color images.

When emerging technologies such as Search Engine Marketing (SEM) face tasks that require human level intelligence, it is inevitable to use the knowledge repositories to endow the machine with the breadth of knowledge available to humans. Keyword suggestion for search engine advertising is an important problem for sponsored search and SEM that requires a goldmine repository of knowledge. A recent strategy in this area is bidding on non-obvious yet relevant keywords, which are economically more viable. In this paper, we exploited a modified relevance-based language model for keyword suggestion problem using Wikipedia as our knowledge base. Huge amounts of clean information in Wikipedia allowed us to uncover important relations between concepts and suggest excessive low volume, inexpensive keywords. Also, we will show the viability of our approach by comparing its results to recent proposed systems. Compared to previous researches, our proposed approach have many advantages, namely, being language independent, being well-grounded, containing expert keywords and being more computationally efficient.

In this article, a Multi-Objective Memetic Algorithm (MA) for rule learning is proposed. Prediction accuracy and interpretation are two measures that conflict with each other. In this approach, we consider accuracy and interpretation of rules sets. Additionally, individual classifiers face other problems such as huge sizes, high dimensionality and imbalance classes’ distribution data sets. This article proposed a way to handle imbalance classes’ distribution. We introduce Multi-Objective Memetic Rule Learning from Decision Tree (MMDT). This approach partially solves the problem of class imbalance. Moreover, a MA is proposed for refining rule extracted by decision tree. In this algorithm, a Particle Swarm Optimization (PSO) is used in MA. In refinement step, the aim is to increase the accuracy and ability to interpret. MMDT has been compared with PART, C4.5 and DTGA on numbers of data sets from UCI based on accuracy and interpretation measures. Results show MMDT offers improvement in many cases.

In this paper we introduce an improvement in the path planning algorithm for the humanoid soccer playing robot which uses Ferguson splines and PSO (Particle Swarm Optimization). The objective of the algorithm is to find a path through other playing robots to the ball, which should be as short as possible and also safe enough. Ferguson splines create preliminary paths using random generated parameters.The random parameters are then iteratively fed into the PSO for optimization and converging to optimal path. Our proposed method makes a balance between the path shortness and the safety which makes it more efficient for humanoid soccer playing robots and also for any other crowded environment with various moving obstacles. Experimental results show that our proposed algorithm converges in at most 60 iterations with the average accuracy of 92% and the maximum path length overhead of 14% for planning the shortest and yet safest path.

In electronic commerce markets, agents often should acquire multiple resources to fulfil a high-level task. In order to attain such resources they need to compete with each other. In multi-agent environments, in which competition is involved, negotiation would be an interaction between agents in order to reach an agreement on resource allocation and to be coordinated with each other. In recent years, negotiation has been employed to allocate resources in multi-agent systems. Yet, in most of the conventional methods, negotiation is done without considering past experiments. In this paper, in order to use experiments of agents, a hybrid method is used which employed case based reasoning and learning automata in negotiation. In the proposed method, the buyer agent would determine its seller and its offered price based on the passed experiments and then an offer would be made. Afterwards, the seller would choose one of the allowed actions using learning automata. Results of the experiments indicated that the proposed algorithm has caused an improvement in some performance measures such as success rate.