Computer Engineering and Information Technology

Recording of ground motions with high amplitudes of  acceleration and velocity play a key role for designing engineering projects.Here we try to represent a reasonable prediction of peak ground acceleration which may create more than 1g acceleration in different regions.

In this study, applying different structures of Neural Networks and using four key parameters , moment magnitude, rupture distance,  site class , style of faulting which an earthquake may cause serious effects on a site. We introduced a Radial Basis Function Network(RBF) with mean error of 14×10-3,as the best network for estimating the occurance probability of an earthquake with large value of PGA ?1g in a region. Also the result of applying Back propagation feed forward neural network(FFBP) for predicting high value of PGA, with Mean error of 17×10-3 , show a good coincidence with the result of the designed RBF Network.

Definitely, mechatronic applications have been widely utilized in factory automation, space exploration, military service and even in our daily life. Traditionally, various control methods have been used for this kind of application such as radio, microwave, computer networks etc. The Internet is a dominating medium of communication and the Internet-based teleoperation of mechatronic systems is coming of age. Wireless Sensor and Actuators Networks (WSANs) are performing myriad functions and presenting enormous utilities. Generally, this paper is wanted to identify the problems and issues related to the Internet-based mechatronic applications which were used WSANs. Key words:Telerobotics applications % Wireless sensor actuators networks % Internet-based control % Ad-hoc network % Time delay control Classification of Wireless Networks: Generally, non-cluster-head members communicate with each wireless networks can be broadly classified into other for information dissemination related to the actual Data-centric networks and Communication-centric phenomenon. networks. Wireless LAN and the Sensor network are two Definitely, the infrared technology is being typical examples of Data-centric networks. In this type primitively applied in large scale in wireless mechatronic of network efficient routing of data takes preference. communication mainly due to its low cost. Study shows The examples of Communication-centric network are the that there are drawbacks to this technology which include Cellular networks, Ad-hoc Robotic networks and also failure to pass through obstacles (e.g. wall), poor Mobile Ad-hoc Networks (MANETs). The realization of communication rate and quality. Radio Frequency (RF) the sensor network applications need wireless ad-hoc technology is found to be better for mobile robot networking techniques. The environment in which these communication. Robots are able to communicate in the sensor networks are deployed could be in remote system using RF point-to-point or broadcasting

the Line follower robot is a mobile machine that can detect and follow the line drawn on the floor. Generally, the path is predefined and can be either visible like a black line on a white surface with a high contrasted color or it can be invisible like a magnetic field. Therefore, this kind of Robot should sense the line with its Infrared Ray (IR) sensors that installed under the robot. After that, the data is transmitted to the processor by specific transition buses. Hence, the processor is going to decide the proper commands and then it sends them to the driver and thus the path will be followed by the line follower robot.

Achieving secure vehicles equipped with accident prevention systems is one of the greatest passions of researchers in automotive laboratories. This article provides a detail description on the state of the art techniques for road situation monitoring and driver's behavior analysis (human factors). The focus would be to gain a practical multifaceted approach in order to simultaneous analysis of driver's distraction, and potential road hazards to make an emergency intervention in case of dangerous driving situations. In this regard, a diversity of information via Iris/Pupil status monitoring and EEG spectrum has been gathered and then fused with out-vehicle sensors such as RADAR, LIDAR, Ultrasonic and Vision. In order to cope with computational complexities due to multiple sensors, a heuristic method of multi sensory data fusion and fuzzy solutions has been developed. All discussions are based on real sensors. The method could be applied on various driver assistance systems such as cruise control, overtaking and lane keeping systems.

Definitely, mechatronic applications have been widely utilized in factory automation, space exploration, military service and even in our daily life. Traditionally, various control methods have been used for this kind of application such as radio, microwave, computer networks etc. The Internet is a dominating medium of communication and the Internet-based teleoperation of mechatronic systems is coming of age. Wireless Sensor and Actuators Networks (WSANs) are performing myriad functions and presenting enormous utilities. Generally, this paper is wanted to identify the problems and issues related to the Internet-based mechatronic applications which were used WSANs. Key words:Telerobotics applications % Wireless sensor actuators networks % Internet-based control % Ad-hoc network % Time delay control Classification of Wireless Networks: Generally, non-cluster-head members communicate with each wireless networks can be broadly classified into other for information dissemination related to the actual Data-centric networks and Communication-centric phenomenon. networks. Wireless LAN and the Sensor network are two Definitely, the infrared technology is being typical examples of Data-centric networks. In this type primitively applied in large scale in wireless mechatronic of network efficient routing of data takes preference. communication mainly due to its low cost. Study shows The examples of Communication-centric network are the that there are drawbacks to this technology which include Cellular networks, Ad-hoc Robotic networks and also failure to pass through obstacles (e.g. wall), poor Mobile Ad-hoc Networks (MANETs). The realization of communication rate and quality. Radio Frequency (RF) the sensor network applications need wireless ad-hoc technology is found to be better for mobile robot networking techniques. The environment in which these communication. Robots are able to communicate in the sensor networks are deployed could be in remote system using RF point-to-point or broadcasting

Software development always faces unexpected events such as technology changes, environmental changes, changing user needs. These changes will increase the risk in software projects. We need to risk management to deal with software risks. Risk assessment is one of the most important factors in risk and pro ject management of software projects. In this paper, we use Wallace's work and five factors to present an efficient method to measure software risk using fuzzy logic. Team, Planning, Co mplexity, Requirements and User are factors that we use in this paper. Results of experiments shows that our framework is mo re efficient than other frameworks and approaches for risk assessment in software projects.

Link prediction is a new interdisciplinary research direction in social network analysis (SNA) which, existing links are analyzed and future links are predicted among millions of users of social network. There are various prediction models including k-nearest neighbor (kNN), fuzzy inference, SVMs, Bayesian model, Markov model and others. In this paper we use Bayesian model to predict future links in flickr social network dataset, it was includes more than 35,000 users. then we use population-based metaheuristics algorithms to enhance accuracy of Bayesian Network Classifiers in feature Selection. We use two standard metric such as AUC and MAP measures for quantifying the accuracy of prediction algorithms.
Keywords: Link prediction, Bayesian Network, Feature Selection, Social network

Link prediction is a new interdisciplinary research direction in social network analysis (SNA) which, existing links are analyzed and future links are predicted among millions of users of social network. There are various prediction models including k-nearest neighbor (kNN), fuzzy inference, SVMs, Bayesian model, Markov model and others. In this paper we use Bayesian model to predict future links in flickr social network dataset, it was includes more than 35,000 users. then we use population-based metaheuristics algorithms to enhance accuracy of Bayesian Network Classifiers in feature Selection. We use two standard metric such as AUC and MAP measures for quantifying the accuracy of prediction algorithms.

Knowledge and organizational knowledge are considered as a permanent asset and wealth on modern works. This is especially emphasized in organizations and modern organizations which are considered as virtual organizations in virtual spaces. One of the issuable subjects in cooperation networks and inter organizational coworkers is about virtual space. Integrating knowledge capability for coacting with virtual organization members is one of the important challenges in virtual organizations. So, incapability of organizations in using common knowledge can cause derangement in performing current process at that organization and finally it cause the aims of organizations to be inaccessible. In this paper we represented an efficient model based on ontology for sharing knowledge between virtual organizations. The purpose and function of the model are creating semantic coordination between organizational partners in virtual organization and detecting potential partners according to meaning despondency between partners' demands and their acceptability. This issue is considered one of the most important dimensions of knowledge management in all of the organizations especially in virtual organizations.

University Course Timetabling Problem (UCTP) is a wellknown Constraint Satisfaction Problem (CSP) problem that has exponential number of solutions based on course conflicts, teacher’s empty times and other parameters. This is a NP-Hard problem. Scheduling is a major debate on planning which can be used in trains scheduling, classroom scheduling, traffic even in schools and universities. The Scheduling leads to organizing tasks and removing tasks interference which is important. The goal of solving UCTP is setting times for courses and teachers in weekdays in order to reach minimum courses conflicts. It is also ideal for teachers to have joint days for teaching in the least weekdays. Of course, subject to the restrictions of classes and teachers program this scheduling is very difficult. Generally, Evolutionary Algorithms (EA) are efficient tools to solve this problem. The final timetabling must be optimum which means that there is no conflicts if possible and best scheduling generate for teachers. In this paper we solve this problem based on genetic algorithm and implement this algorithm with DEAP python based toolbox on random dataset. The implementation results show that genetic algorithm is efficient tools that can close to the global optimum point.

بسم الله الرحمن الرحيم
Abstract
»Thematic text mining of Holy Quran« is a new approach in processing semantic relations among Holy Quran’s verses employing »Data mining tools«.
Having used »the exegetical principles of Allameh Tabatabaei« in »thematic regard« and »objective-centered regard«, we have formed a »thematic corpus« of Quran’s verses. This corpus encompasses a »exegesis section« (in two phases i.e. »surah modeling« and »related verses modeling«) and a »recognizing section«.
Proposed subject matters in this thematic corpus are based on a Quran exegesis called »Tafsir Almizan« and a series Collection of »Allameh Tabatabaei’s treatises«;
thematic corpus includes »seven main themes« that contain all contents of quranic verses, which construct a »consistent and holistic semantic network« with a »unified order«.
The exegesis section of thematic corpus includes »semantic structure« taken from Tafsir Almizan by Allameh Tabatabaei which is used in assessing the discovered relations in data mining algorithm and interpretation of discovered models.
Besides, the recognizing section of thematic corpus includes various »thematic Datasets« which is used for importing Datasets to data mining algorithm and also for implementing computer processes. 
In the present study, to prove the significance of the thematic text mining plan in discovering semantic relations among Holy Quran’s verses, this plan was implemented on »Surah al-Hejr« (in surah modeling) and on exegetical verses concerning the »21st verse« of the same surah (in related verses modeling) as samples.
At the end we could satisfactorily discover semantic relations in 10 data mining tests (out of 29 conducted tests).
The titles of the results are as follows:
• Discovering semantic structure of Surah al-Hejr using »Classification« algorithm.
• Discovering phrasal relations in tabular Datasets of surah modeling and related verses modeling,using »Clustering« algorithm.
• Discovering »longest length of common thematic string« among relations of pair verses using »Long Common Substring algorithm« (LCS), that is a string mining method.
• Discovering »most identcal length of thematic string of verses« in comprison to the »final thematic string« in surah modeling and related verses modeling, using LCS string mining algorithm.
• And discovering »the relation within the themes themselves« in sequential Datasets of surah modeling and related verses modeling,using sequence mining algorithm.
Ultimately, utilizing the proved plan of »thematic text mining« in this study, the grounds for implementing the plan in the entire Holy Quran as an innovative plan of »holistic semantic network of quran’s verses« based on «Tafsir Al-mizan» has been laid.