List of Articles دسته‌بندی

• Open Access Article
  • Abstract Page
  • Full-Text
  
  1 - Classifying Two Class data using Hyper Rectangle Parallel to the Coordinate Axes
  zahra moslehi palhang palhang
  One of the machine learning tasks is supervised learning. In supervised learning we infer a function from labeled training data. The goal of supervised learning algorithms is learning a good hypothesis that minimizes the sum of the errors. A wide range of supervised alg More

  One of the machine learning tasks is supervised learning. In supervised learning we infer a function from labeled training data. The goal of supervised learning algorithms is learning a good hypothesis that minimizes the sum of the errors. A wide range of supervised algorithms is available such as decision tress, SVM, and KNN methods. In this paper we focus on decision tree algorithms. When we use the decision tree algorithms, the data is partitioned by axis- aligned hyper planes. The geometric concept of decision tree algorithms is relative to separability problems in computational geometry. One of the famous problems in separability concept is computing the maximum bichromatic discrepancy problem. There exists an -time algorithm to compute the maximum bichromatic discrepancy in d dimensions. This problem is closely relative to decision trees in machine learning. We implement this problem in 1, 2, 3 and d dimension. Also, we implement the C4.5 algorithm. The experiments showed that results of this algorithm and C4.5 algorithm are comparable. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  2 - Classification of two-level data with hyperrectangles parallel to the coordinate axes
  zahra moslehi palhang palhang
  One of the learning methods in machine learning and pattern recognition is supervised learning. In supervised learning and in two-category problems, the available educational data labels include positive and negative categories. The goal of the supervised learning algor More

  One of the learning methods in machine learning and pattern recognition is supervised learning. In supervised learning and in two-category problems, the available educational data labels include positive and negative categories. The goal of the supervised learning algorithm is to calculate a hypothesis that can separate positive and negative data with the least amount of error. In this article, among all supervised learning algorithms, we focus on the performance of decision trees. The geometric view of the decision tree brings us closer to the concept of separability in computational geometry. Among all the available resolution algorithms related to the decision tree, we raise the problem of calculating the rectangle with the maximum difference of two colors and implement the algorithm in one, two, three and m dimensions, where m represents the number of data features. The implementation result shows that this algorithm is competitive with the well-known C4.5 algorithm. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  3 - Improving performance of probe-based rate control mechanisms using classification: evaluation on an experimental testbed for High Throughput WLANs
  ghalibaf ali Mohammad Nassiri mohammadhassan daei mahdi sakhaei
  MIMO technology offers a wide range of transmission rates for modern wireless LANs. In order to improve the performance of the rate control module, statistical information on the history of state and usage of each transmission rate is maintained at the MAC layer to help More

  MIMO technology offers a wide range of transmission rates for modern wireless LANs. In order to improve the performance of the rate control module, statistical information on the history of state and usage of each transmission rate is maintained at the MAC layer to help determine the rate at which future packets are sent. However, the great diversity of transmission rates in the 802.11n and 802.11ac standards imposes an overhead for updating this information. In this article, to reduce the state space of transmission rates while keeping statistics approximately up to date for each rate, a method for clustering rates is presented so that when sending a packet over a transmission rate, statistical information relating to all the rates belonging to the same cluster is updated. As a result, statistics for a greater number of rates can be updated even when sending a fewer number of packets. We implemented our proposed mechanism in the Linux kernel environment and evaluated its performance under different conditions on an experimental testbed deployed in our research laboratory. The results show that the proposed method outperforms the de-facto Minstrel-HT rate control mechanism in terms of throughput and number of successful transmissions. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  4 - Identify and Clustering Challenges of knowledge-based Enterprises using ANN and BPMS Approaches; Case study: Yazd KBEs
  Mojtaba GholiPour Mohammad Ali Vahdat Zad Mohammad Saleh Oliua Hasan Khademi Zareu
  10.7508/jstpi.2015.04.006
  Knowledge always is a powerful tool in stabilizing position of individual/community service to the public and excellence approach in current autonomous communities. Value of knowledge has been more necessary if it capable for transfer to the High-Tec and needed Technolo More

  Knowledge always is a powerful tool in stabilizing position of individual/community service to the public and excellence approach in current autonomous communities. Value of knowledge has been more necessary if it capable for transfer to the High-Tec and needed Technologies of humanity societies. Knowledge Based Enterprise (KBE) is a real-law enterprise such as factory that transfer Knowledge to production/services. However KBEs are causing for sustainable knowledge economy and development native knowledge in more countries, but these enterprises havnt optimize occasion in view of quantity, production quality and service extensive according to the 20 years growth view of Iran. Purpose of this study is to identifying encounter challenges of KBEs that located on Yazds Science and Technology Park (STP) and clustering these challenges with ANN method exactly. The Samples contains 137 person such as manager and top employees of these enterprises. Number of reached challenges have been 59 that were attained from literature and experts guidelines were designed and distributed between samples suddenly. According to the PB artificial neural network, reliabilities of samples were confirmed with MSE=2.0332 and priority done with Multilayer Perceptron (MLP) artificial neural network and with inspiration of Business Process Management System (BPMS) approach. According to the BPMS approach and MLP method, Result show that challenges did cluster in three factions known as: management activities, operational activities and support activities. Thus, number of management, operational and support activities in order were 27, 15 and 17 items exactly. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  5 - Propose a Proper Algorithm for Incremental Learning Based on Fuzzy Least Square Twin Support Vector Machines
  Javad Salimi Sartakhti Salman Goli
  Support Vector machine is one of the most popular and efficient algorithms in machine learning. There are several versions of this algorithm, the latest of which is the fuzzy least squares twin support vector machines. On the other hand, in many machine learning applica More

  Support Vector machine is one of the most popular and efficient algorithms in machine learning. There are several versions of this algorithm, the latest of which is the fuzzy least squares twin support vector machines. On the other hand, in many machine learning applications input data is continuously generated, which has made many traditional algorithms inefficient to deal with them. In this paper, for the first time, an incremental version of the fuzzy least squares twin support vector algorithm is presented. The proposed algorithmis represented in both online and quasi-online modes. To evaluate the accuracy and precision of the proposed algorithmfirst we run our algorithm on 6 datasets of the UCI repository. Results showthe proposed algorithm is more efficient than other algorithms (even non-incremental versions). In the second phase in the experiments, we consider an application of Internet of Things, and in particular in data related to daily activities which inherently are incremental. According to experimental results, the proposed algorithm has the best performance compared to other incremental algorithms. Manuscript profile
• Open Access Article
  • Abstract Page
  • Full-Text
  
  6 - Iranian Dastgah Music Recognition Based on Notes Sequence Extraction and Use of LSTM Networks
  سینا غضنفری پور M. Khademi Abbas Ebrahimi moghadam
  Iranian "Dastgah" music classification by computer is a very interesting yet complex and challenging topic for those who are interested in Iranian Dastgah music. The aforementioned problem is important, firstly, due to its many applications in different areas such as co More

  Iranian "Dastgah" music classification by computer is a very interesting yet complex and challenging topic for those who are interested in Iranian Dastgah music. The aforementioned problem is important, firstly, due to its many applications in different areas such as composing and teaching music, and secondly, because of the needs of ordinary people to computer to detect the Dastgah. This paper presents a method for recognition of the genre (Dastgah) and subgenre (sub-Dastgah) of Iranian music based on sequential note extraction, hierarchical classification, and the use of LSTM networks. In the proposed method, the music track is first classified into one of the three general categories. The first category includes only "Mahour" Dastgah, the second category includes "Shour" and "Nava", and the third category includes "Homayoun", "Segah" and "Chahargah". Then, for each category, depending on its type, a different number of classifiers are applied until one of the 6 Dastgah and 11 sub-Dastgah of Iranian music are recognized. This research is not limited to any particular style of playing or instruments, it is also not affected by neither the speed nor the techniques of player. The labeled tracks in the "Arg" database, which is created for this research, are solo. However, some of them are also played by percussion instruments (such as the Tombak) along with melodic instruments. The results show that recognition of 6 main Dastgah and 11 sub-Dastgah have been approved by an average accuracy of 74.5% and 66.35%, respectively, which is more promising compared to other few similar studies. Manuscript profile