List of Articles
-
Open Access Article
1 - Resource Management in Multimedia Networks Using Software-Defined Network Technology
Ahmadreza MontazerolghaemNowadays, multimedia networks on the Internet have become a low-cost and efficient alternative to PSTN. Multimedia transfer applications on the Internet are becoming more and more popular. This connection consists of two phases: signaling and media. The signaling phase MoreNowadays, multimedia networks on the Internet have become a low-cost and efficient alternative to PSTN. Multimedia transfer applications on the Internet are becoming more and more popular. This connection consists of two phases: signaling and media. The signaling phase is performed by SIP proxies and the media phase by network switches. One of the most important challenges in multimedia networks is the overload of SIP proxies and network switches in the signaling and media phases. The existence of this challenge causes a wide range of network users to face a sharp decline in the quality of service. In this article, we model the routing problem in multimedia networks to deal with the overload. In this regard, we present a technology-based method of software-based networks and a mathematical programming model in multimedia networks. The proposed method is simulated under various scenarios and topologies. The results investigate that the throughput and resource consumption has improved. Manuscript profile -
Open Access Article
2 - Improving Register File Access Latency Tolerance in GPUs by Value Reproduction
Rahil Barati Mohammad Sadrosadati حمید سربازی آزادLarge register files reduce the performance and energy overhead of memory accesses by improving the thread-level parallelism and reducing the number of data movements from the off-chip memory. Recently, the latency-tolerant register file (LTRF) is proposed to enable hig MoreLarge register files reduce the performance and energy overhead of memory accesses by improving the thread-level parallelism and reducing the number of data movements from the off-chip memory. Recently, the latency-tolerant register file (LTRF) is proposed to enable high-capacity register files with low power and area cost. LTRF is a two-level register file in which the first level is a small fast register cache, and the second level is a large slow main register file. LTRF uses a near-perfect register prefetching mechanism that warp registers are prefetched from the main register file to the register file cache before scheduling the warp and hiding the register prefetching latency by the execution of other active warps. LTRF specifies the working set of the warps by partitioning the control flow graph into several prefetch subgraphs, called register-interval. LTRF imposes some performance overhead due to warp stall during the register prefetching. Reducing the number of register-intervals can greatly mitigate this overhead, and improve the effectiveness of LTRF. A register-interval is a subgraph of the control flow graph (CFG) where it has to be a single-entry subgraph with a limited number of registers. We observe that the second constrain contributes more in reducing the size of register-intervals. Increasing the number of registers inside the register-interval cannot address this problem as it imposes huge performance and power overhead during the register prefetching process. In this paper, we propose a register-interval-aware re-production mechanism at compile-time to increase register-interval size without increasing the number of registers inside it. Our experimental results show that our proposal improves the effectiveness of LTRF by 29%, and LTRF’s performance by about 18% (about 30% improvement over baseline GPU architecture). Moreover, our proposal reduces GPU energy and power consumption by respectively 38% and 15%, on average. Manuscript profile -
Open Access Article
3 - An Intelligent Vision System for Automatic Forest Fire Surveillance
Mohammad Sadegh Kayhanpanah Behrooz KoohestaniFighting forest fires to avoid their potential dangers as well as protect natural resources is a challenge for researchers. The goal of this research is to identify the features of fire and smoke from the unmanned aerial vehicle (UAV) visual images for classification, o MoreFighting forest fires to avoid their potential dangers as well as protect natural resources is a challenge for researchers. The goal of this research is to identify the features of fire and smoke from the unmanned aerial vehicle (UAV) visual images for classification, object detection, and image segmentation. Because forests are highly complex and nonstructured environments, the use of the vision system is still having problems such as the analogues of flame characteristics to sunlight, plants, and animals, or the smoke blocking the images of the fire, which causes false alarms. The proposed method in this research is the use of convolutional neural networks (CNNs) as a deep learning method that can automatically extract or generate features in different layers. First, we collect data and increase them according to data augmentation methods, and then, the use of a 12-layer network for classification as well as transfer learning method for segmentation of images is proposed. The results show that the data augmentation method used due to resizing and processing the input images to the network to prevent the drastic reduction of the features in the original images and also the CNNs used can extract the fire and smoke features in the images well and finally detect and localize them. Manuscript profile -
Open Access Article
4 - A Patient Identification and Authentication Protocol to Increase Security
Afsaneh Sharafi Sepideh Adabi Ali Movaghar Salah Al-MajedToday, with the ever-expanding IoT, information technology has led the physical world to interact more with stimuli, sensors, and devices. The result of this interaction is communication "anytime, anywhere" in the real world. A research gap that can be felt in addition MoreToday, with the ever-expanding IoT, information technology has led the physical world to interact more with stimuli, sensors, and devices. The result of this interaction is communication "anytime, anywhere" in the real world. A research gap that can be felt in addition to providing a multi-layered and highly secure protocol (a protocol that simultaneously performs authentication) and at the same time has a low computational burden. Therefore, in the field of health and treatment and for the purpose of remote monitoring of patients with physical and mental disabilities (such as patients with cerebral palsy and spinal cord amputation) there is an urgent need for a very safe protocol. The protocol we propose in this study is a two-layer protocol called "Identification-Authentication" which is based on EEG and fingerprint. Also, our authentication step is the modified Diffie-Hellman algorithm. This algorithm needs to be modified due to a security problem (the presence of a third person) that the proposed method is able to authenticate the patient with very high accuracy and high speed by receiving the patient's fingerprint and EEG signal. The proposed protocol was evaluated using data from 40 patients with spinal cord injury. The implementation results show more security of this protocol, Validity of the proposed protocol is checked and the processing time of authentication stage is decrease to 0.0215 seconds. Manuscript profile -
Open Access Article
5 - Provide an Energy-aware Markov Based Model for Dynamic Placement of Virtual Machines in Cloud Data Centers
mehdi rajabzadeh Abolfazl Toroghi Haghighat Amir Masoud RahmaniThe use of energy-conscious solutions is one of the important research topics in the field of cloud computing. By effectively using virtual machine placement and aggregation algorithms, cloud suppliers will be able to reduce energy consumption. In this paper, a new mode MoreThe use of energy-conscious solutions is one of the important research topics in the field of cloud computing. By effectively using virtual machine placement and aggregation algorithms, cloud suppliers will be able to reduce energy consumption. In this paper, a new model is presented that seeks to achieve the desired results by improving the algorithms and providing appropriate methods. Periodic monitoring of resource status, proper analysis of the data obtained, and prediction of the critical state of the servers using the proposed Markov model have reduced the number of unnecessary migrations as much as possible. The combination of genetic algorithm and simulated annealing in the replacement section along with the definition of the adsorbent Markov chain has resulted in better and faster performance of the proposed algorithm. Simulations performed in different scenarios in CloudSim show that compared to the best algorithm compared, at low, medium and high load, energy consumption has decreased significantly. Violations of service level agreements also fell by an average of 17 percent. Manuscript profile -
Open Access Article
6 - Anomaly Detection in the Car Trajectories Using Sparse Reconstruction
Reyhane Taghizade Abbas Ebrahimi moghadam M. KhademiIn traffic control and vehicle registration systems a big challenge is achieving a system that automatically detects abnormal driving behavior. In this paper a system for detection of vehicle anomalies proposed, which at first extracts spatio-temporal features form clus MoreIn traffic control and vehicle registration systems a big challenge is achieving a system that automatically detects abnormal driving behavior. In this paper a system for detection of vehicle anomalies proposed, which at first extracts spatio-temporal features form clusters then creates dictionary from these features. This classification stage consists of processes such as, optimized clustering with the bee mating algorithm and sparse processing on spatiotemporal features derived from the training data. Finally the trained classifier is applied to the test data for anomaly detection. The distinction of this study from previous research is using new method of pre-processing to create a dictionary matrix and anomaly detection based on evaluation of matrix that related to each class dependency, which leads to higher accuracy of the proposed method compared to other leading methods. To evaluate the proposed method, UCSD database and video sequences recorded from vehicle traffic on Vakilabad Boulevard at the north side of Ferdowsi University of Mashhad are used and the performance of the proposed method is compare to other competing methods in this field. By analyzing the evaluation standards, we find that the proposed method performance is better than other methods. Manuscript profile -
Open Access Article
7 - Deep Extreme Learning Machine: A Combined Incremental Learning Approach for Data Stream Classification
Javad Hamidzadeh Mona MoradiStreaming data refers to data that is continuously generated in the form of fast streams with high volumes. This kind of data often runs into evolving environments where a change may affect the data distribution. Because of a wide range of real-world applications of dat MoreStreaming data refers to data that is continuously generated in the form of fast streams with high volumes. This kind of data often runs into evolving environments where a change may affect the data distribution. Because of a wide range of real-world applications of data streams, performance improvement of streaming analytics has become a hot topic for researchers. The proposed method integrates online ensemble learning into extreme machine learning to improve the data stream classification performance. The proposed incremental method does not need to access the samples of previous blocks. Also, regarding the AdaBoost approach, it can react to concept drift by the component weighting mechanism and component update mechanism. The proposed method can adapt to the changes, and its performance is leveraged to retain high-accurate classifiers. The experiments have been done on benchmark datasets. The proposed method can achieve 0.90% average specificity, 0.69% average sensitivity, and 0.87% average accuracy, indicating its superiority compared to two competing methods. Manuscript profile -
Open Access Article
8 - A New Heuristic for Deadlock Detection in Safety Analysis of Software Systems
عین الله پیراThe safety analysis of software systems, especially safety-critical ones, should be performed exactly because even a minor failure in these systems may result in disaster consequences. Also, such analysis must be done before implementation, i.e. the design step and in t MoreThe safety analysis of software systems, especially safety-critical ones, should be performed exactly because even a minor failure in these systems may result in disaster consequences. Also, such analysis must be done before implementation, i.e. the design step and in the model level. Model checking is an exact and mathematical-based way that gets a model of a system and analyzes it through exploring all reachable states of the model. Due to the complexity of some systems and their models, this way may face the state space explosion problem, i.e. it cannot explore all available states. A solution to solve this problem in these systems is that model checking tries to refute them, instead of verifying them, by finding errors such as deadlock (if available).Although, a heuristic has been previously proposed to find a deadlock in the model's state space and it has been applied in several simple heuristic search and evolutionary algorithms, its detection speed has been low. In this paper, we propose a novel heuristic to detect a deadlock in the model's state space, and test and compare its detection speed by applying it in several simple heuristic search algorithms such as iterative deepening A*, beam search, and evolutionary algorithms such as genetic, particle swarm optimization, and Bayesian optimization. Comparison results confirm that the new heuristic can detect a deadlock in less time than the previous heuristic. Manuscript profile