فهرست مطالب ali asghar pourhaji kazem

The proliferation of e-commerce has led to an overwhelming volume of customer reviews, posing challenges for consumers who seek reliable product evaluations and for businesses concerned with the integrity of their online reputation. This study addresses the critical problem of detecting fake reviews by developing a comprehensive framework that integrates Natural Language Processing (NLP) and machine learning techniques. Our methodology centers on sentiment analysis to discern the emotional valence of reviews, coupled with Part-of-Speech (PoS) tagging to analyze linguistic patterns that may signal deception. We meticulously extract a rich set of textual and statistical features, providing a robust basis for our predictive models. To enhance classification performance, we strategically employ both traditional machine learning algorithms and powerful ensemble techniques. Experimental results underscore the efficacy of our approach in detecting fraudulent reviews. We achieved a notable F1-Score of 82.9% and an accuracy of 82.6%, demonstrating the potential to safeguard consumers from misleading information and protect businesses from unfair practices.

The Internet of Things (IoT) now connects over nine billion devices. This number is predicted to approach 20 billion in the near future, and the number of things is rapidly expanding, implying that a large amount of data will be created. To handle the connected things, an infrastructure must be built. Cloud computing (CC) has become necessary in the analysis and data storage for IoT. A cloud broker, which is an intermediate in the infrastructure that controls connected things in cloud computing, is discussed in this study. An optimization problem is examined for maximizing the broker's profit and system availability while minimizing request response time and energy consumption. For this purpose, an objective function is proposed and solved using the Black Widow Optimization (BWO) algorithm. Subsequently, the obtained results are compared with the particle swarm optimization (PSO) algorithms. The results indicate that the BWO algorithm could outperform the PSO algorithm, and it can provide much better results considering different scenarios.

Nowadays, service-oriented systems according to possibility of using in heterogeneous distributed environments and being independent of the specific technology, also with the existence of large-scale dynamic system with changeable requirements, are highly regarded. Cloud services are one of the implementation methods of service-oriented concepts. Increasing the tendency of users to use cloud computing, encourages service vendors to provide services with different non-functionality features. Mostly single services couldn’t satisfy users’ requirements, so it’s necessary to compose some services to achieve the demand service. With the increasing of service providers, also services in the internet service pools, selecting the optimal service from a set of functionality equivalent candidates which are differ in QoS, becomes an important NP-Hard research problem. Therefore increasing the quality of composite services is a vital challenge and since the quality of cloud composite services derived from previous approaches can still be increased, in this research, we have tried to increase the quality of cloud composite services using the Symbiotic Organism Search Algorithm. Simulations are conducted in Matlab environment and the results are compared to three famous algorithms including GA, ACO and PSO. The comparisons demonstrate the remarkable superiority of SOS in result's quality, stability and scalability, also 13% improvement.

Computational Grids have developed as a new approach to solve large scale problems in scientific، engineering and business areas. Open Grid services architecture is an adaptation of the service-oriented architecture which presents the Grid operation a set of service-oriented softwares. Grid services composition provides the possibility for users to submit their complex requirements as a single request. QoS-aware Grid service composition algorithms try to construct a composite Grid service which satisfies the user-defined constraints as well as to optimize the QoS parameters. All of the presented service composition approaches in the literature discard using the Grid services with unknown QoS values in the composition process. However، estimation of unknown QoS values of Grid services provides an opportunity for them to be selected as component Grid services in the constructed composite service. In this paper، a probabilistic QoS model is presented for estimating the unknown QoS values using Bayesian network. Experimental results indicate that estimating the unknown QoS values has high accuracy and leads to more efficient composite Grid services.