مجله رایانش نرم و فناوری اطلاعات
سال هفتم شماره 2 (پاییز و زمستان 1397)

Abstract- Spatial experience is the ability of comprehending relation between real world’s objects, spaces and areas and can be acquired after several years of learning and experience by the expert persons. This experience leads to generating spatial knowledge and can be helpful in making high accuracy, realistic and in accordance with reality decisions. Therefore, using some methods for storing and reusing this experiment and preventing the exit of experiences from organizations is necessary. In this research, different experience modeling methods such as semantic networks, rules, logic and ontology are investigated and due to the advantages of ontology method in comparison with other methods, this modeling method is chosen for proposing an algorithm for storing spatial experiences in urban route finding. In this regard, first, an ontology model is created with the taxi routes in Tehran city. Then, this ontology model is used for route finding and its results compared with Dikjestra’s algorithm at peak traffic times. The results show that although the route lengths of ontology based route finding algorithm are longer than route lengths of Dikjestra’s algorithm but its travel times are lower and in some routes the difference between travel times reaches to 10 minutes.

Particle filter is one of the most important filters for estimating nonlinear/non-Gussian systems that is used in many applications. In a standard particle filter, since the common state density function of the state is approximated by recursive importance sampling, the dimension of the joint posterior grows with each time step. This causes the algorithm to be rapidly degenerated. Therefore, the use of a resampling strategy is required for guaranteeing a logical approximation of the density function on the entire path. However, in practice, resampling step is performed on marginal space. Since the system may not exhibit an exponential forgetting behavior from its past errors, it will produce an incomplete estimate with a small number of finite sampling processes on the marginal space. To solve this problem, an improved particle filter based soft computing is proposed in this paper. Unlike a particle filter, this filter is applied to the marginal distribution, and the sampling dimensions do not increase with time. In addition, sampling has been improved using an evolutionary differential algorithm. The proposed method is evaluated using computer simulations. The results show that the proposed method has a better performance than standard particle filter.

Hyperspectral images as a source of information can be used for diverse applications in various fields, including target identification, classification, change detection and anomaly detection in urban and non-urban areas. Noise is an inevitable part of a signal which limits the use of hyperspectral images in some applications. Noise removal is one of the most important pre-processing stages in hyperspectral images. In order to remove the noise in hyperspectral images, the data needs to be preprocessed to reduce noise impact on the images. The process and analysis of hyperspectral images is rather complicated because of the high dimensionality of hyperspectral images compared to multispectral remote sensing images. Hyperspectral image cube consist of three dimensions which the first and second dimensions related to the spatial domain and the third one related to the spectral domain which includes more than hundred bands. Most of the methods operate in the spectral domain for noise reduction while in this proposed method, a novel algorithm for reducing noise in hyperspectral images is implemented. The proposed method uses two different algorithms which are applied in two different hyperspectral images in both spatial and spectral domains. These images are Hyperion satellite image and AVIRIS airborne image. In order to reduce noise in the spatial domain, Total Variation (TV) algorithm and in the spectral domain, Wavelet algorithm is used. After the implementation of these methods, the results are fused at the pixel level. For the evaluation of the proposed method, the results were compared with other methods, both qualitatively and quantitatively. Various indices are used to assess the quantitative results which demonstrate the high accuracy of this method.CEI index for Hyperion image is 1.421 and for AVIRIS image is 0.0022. Another index is PSNR which the value for Hyperion image is 33.519 and for AVIRIS image is 22.371.

In this paper, a new method is proposed for offline handwritten Persian words recognition. The proposed method introduces the Centroid Sequence Freeman Chain Code (CSFCC) as a new and powerful feature along with the use of morphological features and an optimize support vector machine (SVM) classifier. A conbination of particle swarm optimization (PSO) and gravitational search algorithm (GSA), abbreviated to PSOGSA, has been employed to optimaze the SVM classifier. In the proposed method, all the connected components of a word are detected and combined with each other. For this purpose, a pictorial dictionary of asymptomatic subwords has been made. In addition, a database has been created to include the positions of asymptomatic subwords in order to narrow down the search space and increase the speed and improve the recognition accuracy. Based on the position of a subword in a word, it is more likely to make the right decision and detect the subword, accurately. The proposed method was implemented on the Iranshahr Database, containing nearly 17000 images of handwritten names of 503 cities of Iran. The resultant recognition accuracy is 89% in the expriments, which shows the capability of the proposed method and improving the results, compared to the other well-known methods.

Science progress has introduced new issues into the world requiring optimization algorithm with fast adaptation with uncertain environment changing with time. In these issues, location and optimized value change over time, so optimization algorithm should be capable of fast adaptation with variable conditions. This study has proposed a new algorithm based on particle optimization algorithm called Adaptive Increasing/Decreasing PSO. This algorithm, adaptively with an increase and decrease in the number of algorithm particles and effective search limit, is capable of searching and finding optimized number changed with time in non-linear and dynamic environments with undetectable changes. Also, a new definition, focused search zone, is provided for signalizing hopeful areas in order to accelerate local search process and prevent premature convergence, and success index as an indicator of the behavior of centralized search area in relation to environmental conditions. Results of the proposed algorithm on the moving peaks benchmark were assessed and compared with the results of some other studies. Results show positive effects of adaptive mechanisms such as a decrease and an increase in the particles and search limit on the duration of searching and finding optimization in comparison with other multi-population based optimization algorithms.

One of the main challenges of wireless sensor networks (WSNs), is unequal energy consumption of the nodes and early dead of the forwarder nodes around the base station because of the high load on these nodes. This matter causes a hole around the base station, thus, the communications between the alive nodes of the network and the base station are disrupted. In this paper, balancing the load and then energy consumption of the network nodes are followed. The aim is prolongation of the lifetime of all the nodes, particularly, the nodes around the base station to keep the communications between the network nodes and the base station until the end of lifetime of the nodes without any hole. To this purpose, a method for zoning the area of sensor networks is proposed. The distance of data transfer hop of each forwarder node is adjusted based on the amount of data to be transmitted by the forwarder. Hence, energy consumption of forwarders and thus their lifetimes are balanced. The proposed approach presents a solution for the challenge of short life of forwarders around the base station. Moreover, the dimensions of zones are calculated in such way that the communications between the sensors and the forwarder in each zone are performed in single hop manner. The approach balances the density of sensors of the created zones to uniform the coverage ratio in all the network area. The performance evaluations of the proposed scheme indicate that the scheme prolongs the lifetime of both forwarders and sensor nodes compared with the related works.

Recommender systems analyze the user’s preference patterns and provide personalized recommendations of items that will suit a user’s taste. An essential challenge in these systems is that user preferences are not static and users are likely to change their preferences over time. The adaptability of recommender systems to capture the evolving user′s preferences which are constantly changing, improves the accuracy of recommender systems. In this paper, we develop a model to capture the users’ preference dynamics in a personalized manner. We introduce an individual time decay factor for each user according to the rate of his preference dynamics to weight the past user preferences and decrease gradually the importance of them. We exploit the users’ demographics as well as the extracted similarities between users over time, in addition to the past weighted user preferences, in a developed coupled tensor-matrix factorization technique to provide the personalized recommendations. Our evaluation results on the two real-world datasets indicate that our proposed model is better and more robust than the competitive methods in term of recommendation accuracy and is more capable to cope with cold-start problem.