Scientia Iranica
Volume:30 Issue: 5, Sep-Oct 2023

The financial time series data is a highly nonlinear signal and hence difficult to predict precisely. The prediction accuracy can be improved by linearizing the signal. In this paper the nonlinear data sample is linearized by decomposing it into several IMFs. A hybrid multi-layer decomposition technique is developed. The decomposition proposed in this paper is the combination of both EMD and VMD methods. As a new contribution to the previous literature in this study the VMD is used to further decompose the higher frequency signals obtained from the EMD based decomposed signal. In the result analysis it is observed that the double decomposition improves the prediction accuracy. This is a new introduction in the field of stock market prediction. The prediction accuracy of the proposed model is performed by applying it to three different stock markets for predicting the closing price. Historical data (closing price) is implemented to obtain 1 day ahead predicted closing price. Comparative analysis of different previously implemented methods like BPNN, SVM, ANN and ELM, along with the proposed method is performed. GA is implemented for optimizing the kernel factors. It is observed that the proposed hybrid model outperformed the other methods.

Traditional cross-media retrieval methods mainly focus on coarse-grained data that reflect global characteristics, while ignoring the fine-grained descriptions of local details. Meanwhile, traditional methods cannot accurately describe the correlations between the anchor and the irrelevant data. To solve the problems mentioned above, this paper proposes to fuse coarse-grained and fine-grained features and a multi-margin triplet loss on the basis of a dual-framework. 1) Framework I: a multi grained data fusion framework based on Deep Belief Network, and 2) Framework II: a multi-modality data fusion framework based on the multi-margin triplet loss function. In Framework I, the coarse grained and fine-grained features fused by the joint Restricted Boltzmann Machine are input into Framework II. In Framework II, we innovatively propose the multi-margin triplet loss. The data, which belong to different modalities and semantic categories, are stepped away from the anchor in a multi-margin way. Experimental results show that the proposed method achieves better cross-media retrieval performance than other methods with different datasets. Furthermore, the ablation experiments verify that our proposed multi-grained fusion strategy and the multi-margin triplet loss function are effective.

One of the most important, but tedious and costly tasks of the software testing process is test data generation. The challenge is finding approaches in which humans could generate test data through more attractive, faster, and cheaper ways. One approach is using Game with A Purpose in the process of test data generation. In our previous work, we introduced two games called Rings and Greenify, by which many inexpensive players, with no special technical abilities, become engaged in test data generation. Despite the promising results of Rings and Greenify, they have certain limitations and issues. In this paper, we present a new GWAP for test data generation, called QOTE, in order to improve the application of GWAP in test data generation for program units. QOTE provides a different game-play and has certain advantages compared to prior gamesc. Experimental results have shown that QOTE outperforms prior games from two aspects: game quality and capability of test data generation. We have conducted another experiment based on mutation analysis to further evaluate test data generation capabilities of QOTE compared to four automatic approaches and show that the test data generated by QOTE can reveal more failures compared to the mentioned automatic approaches.

The essential reduction of fossil fuels and environmental pollutants has caused Electric Vehicles (EVs) to be considered. EVs are able to participate as a manufacturer in the electricity market through Vehicle to Grid (V2G) technology. This greatly improves the reliability of distribution systems. Therefore, it is necessary to plan the charging and discharging process in the parking lot. This paper has firstly investigated the different strategies for planning the charging and discharging process of EVs considering the random and unpredictable nature of various parameters, and also the limitation of the power exchange between the distribution system and parking, to evaluate the impact of V2G-equipped parking spaces on reliability. An appropriate strategy is the strategy that will increase the owner's interest in the parking lot. The results show that the use of V2G and charge-discharge strategies improve reliability (SAIFI, SAIDI, ASAI and ENS indices) of the distribution system. By examining the results of each of the strategies, the proposed strategies are able to increase parking revenue by an average of 21.6% and improve reliability indices of the distribution network up to 8.8%.

A novel geometry of polarization and frequency reconfigurable antenna is proposed in this paper. Proposed antenna consists of an L shaped patch antenna, where arms are separated using PIN-diode. Two parasitic elements, shorted back element and edge tapered defected ground structure with slot are used for achieving wide impedance and axial ratio bandwidth. It acts as circular polarized antenna with 1.183 GHz axial ratio band width and 3.09 GHz impedance bandwidth in ON state of both diodes and act as linear polarized frequency reconfigurable antenna at remaining states of diodes. Proposed antenna can be used in C band wireless applications like RADAR, satellite communication etc.

Multiple networking layers existing in the IoT network involve heterogeneity that must be addressed to facilitate proper communication such that the performance of an IoT network does not suffers. The performance of the IoT networks depends on networking topologies used in different layers, clustering algorithms, protocols used for handling heterogeneity communication speeds, and data packet sizes. In this Research, the performance of IoT networks is improved by adding device clustering via a multi-Stage network and using an efficient SOJK clustering algorithm in the device layer, which minimizes power depletion and increases the quantity of data and data packets; transmitted at zero power. A mechanism to handle heterogeneity that exists due to Wi-Fi, CDMA, and USB communication protocols is also presented while optimizing the communication speeds and data transmission size. It has also been shown that the use of 170Mbps cellular speed and the data size of 468 bytes gives the optimum response time of an IoT network. The time taken to transport information from the device to the storage layer is reduced by 57% compared to the time taken to transport the data using the prototype network.

A deep learning-based convolutional artificial neural networks structured a new image classification method approach was implemented in the study. Sample application was carried out with Diabetic Retinopathy disease. Obtaining information about the blood vessels and any abnormal patterns from the rest of the phonoscopic image and assessing the degree of retinopathy is the problem itself. To solve this problem developed methodology and algorithmic structure of this new approach is presented in the study. An approach called care model was used in this study different from the classical CNN structure. The care approach is based on the idea that the best solution will be taken from the new data obtained by rescale the available data according to total number of pixels before the average data pool is created and then CNN processes will continue. In the care model approach, all data is multiplied by the number of elements by the number of epoch time eight tensors. The purposed care model include VGG19 image classification model and developed mathematical model presented. Pre-trained model and all image dataset taken from kaggle and keras for implementation of case study. The purposed model provide train accuracy 87%, test accuracy 88%, precision 93% and recall 83%.

This study describes an approach to identify multiple flicker sources at the point of common coupling (PCC). The voltage signals of different flicker sources such as the electrical arc furnace, the fixed-speed wind turbine, and the diesel-engine driven generator were recorded at the PCC. For this purpose, various aerodynamic and mechanical faults of a wind turbine such as wind shear and tower shadow, gearbox tooth-breaking, blade crash, pitch angle error and various mechanical faults of diesel-engine driven generator such as misfiring, exciter, and governor error, are considered. After acquiring voltage signals of various faults, the empirical mode decomposition (EMD) as a robust signal processing technique for extracting useful features was used. Then, for reducing required memory space and computational burden, the minimal-redundancy-maximal-relevance (MRMR) and the symmetric uncertainty (SU) as the feature selection methods were applied. Also, for increasing the efficiency of feature selection methods, the cooperative game-theoretic method was utilized. Afterward, two classifiers based on the Naive-Bayes and the support vector machine (SVM) are used to detect the faults. Simulation results are presented to validate the effectiveness of the proposed method.

This paper presents a new method to investigate the effects of demand response programs on the life expectancy of distribution transformers. The proposed method has been applied on a realistic distribution network, and the results are evaluated under various models of the demand response program and different levels of tariffs. According to the results, distribution transformers’ life extension under various scenarios of applying demand response programs, in spite of differences among them, brings a great economic benefit. The results show a significant life extension in the interval of about 9 to 33 years. Also, this life extension brings a considerable benefit between 624.91$ to 821.669$, per year. However, the amount of obtained benefit considerably depends on the model of the demand response program and the level of tariffs. Besides, an economic analysis from both utility’s and customer’s perspectives is carried out in order to determine the optimal demand response model. To do this, an economic index is presented, and the best solution is determined by an Analytical Hierarchy Process so that it can satisfy both utilities and customers. As revealed by the results, the total annual benefits of the utility and customers are increased by 762.64$ and 73.85$.