Search

Artificial intelligence techniques are excessively used in computing for training, forecasting and evaluation purposes. Among these techniques, artificial neural network (ANN) is widely used for developing prediction models. ANNs use various Meta-heuristic algorithms including approximation methods for training the neural networks. ANN plays a significant role in this area and can be helpful in determining the neural network input coefficient. The main goal of presented study is to train the neural network using meta-heuristic approaches and to enhance the perceptron neural network precision. In this article, we used an integrated algorithm to determine the neural network input coefficients. Later, the proposed algorithm was compared with other algorithms such as ant colony and invasive weed optimization for performance evaluation. The results reveal that the proposed algorithm results in more convergence with neural network coefficient as compared to existing algorithms. However the proposed method resulted in reduction of prediction error in the neural network.

Nowadays, wireless mesh networks are known as important parts of different commercial, scientific, and industrial processes. Their prevalence increases day-by-day and the future of the world is associated with such technologies for better communication. However, the issue of improving quality of service for dealing with more complex and intense flow of data has been always a remarkable research problem, as a result of improved wireless communication systems. In this sense, objective of this study is to provide a new algorithm for contributing to the associated literature. In the study, peer to peer wireless mesh networks and the concept of service quality were examined first and then an approach for improving service quality in such networks has been proposed accordingly. In detail, the proposed an approach allows profiting data transfer capability by data packet and using this information for routing and preventing overcrowd in network nodes and finally, distributing the load over it. When middle nodes overcrowd, they withhold to send control messages of route creating or do that by delay. The proposed approach has been evaluated and the findings revealed that at least 10% of undue delays through network can be prevented while permittivity does not reduce, thanks to the approach. Also energy consumption within network nodes partially increases due to adding table and the search which can be overlooked.

Stakeholder satisfaction is the main motive of the software industry. Consumer and producer satisfaction means achieving a software-quality product. There are so many techniques, methods, and models are present for the software-quality prediction. Computational intelligence is also playing a crucial role in the prediction of quality characteristics. This paper gives a new optimal mathematical model for the prediction of the degree of stakeholder satisfaction (Q). Optimal models validate the real data using the relationship impacts of various quality attributes. It uses the equations of constraints. The optimal model gives the maximum and minimum values for Q. Constraints constitutes of software quality characteristics. In the given case study example, the idle value of Q is 30 but using optimal model it gives the maximum optimal value of Q = 22.788020075 for xLAB IT consulting services on their project In-Reg Molecule Registration using the MATLAB. It means if there is any change in the value of any software quality characteristics, then it will decrease the value of Q. It proves that the given result is an optimal solution.

Limitations of the pinhole method and astigmatic defocus detection have difficulties in determining the direction of defocus and a restricted linear correction range. Here, a distance-measuring approach based on the laser triangulation principle is proposed with a corresponding mathematical model to overcome these problems and to satisfy the requirements of an industrial thin-film transistor liquid-crystal display (TFT-LCD) inspection microscope system in active auto-focus applications. The approach combines infrared light at a wavelength of 808 nm with visible light. The light reflected from the surface of the object reaches a CCD camera and forms a spot via a set of optical devices. To control a PZT to achieve real-time auto-focusing, a Gaussian curve fitting method is used to process the spot information with the presented mathematical model giving the relationship between the detection value and the defocus value focus error signal (FES). The preliminary experiments with a $50\times $ objective lens show that the measured values are consistent with the theoretical values, have good linearity and possess a focusing accuracy of 0.2 $\mu \text{m}$ within $\pm 30~\mu \text{m}$ of the focal plane. The analysis of the experimental results proves the feasibility of using this method in industrial applications. Compared with the traditional method of microscope focus correction, this method has the advantages of high accuracy, good linearity, and fast focus speed for the actual requirements of industrial inspection processes. This method has been applied to the circuit board component defect detection in our laboratory.

Recently, IoT has greatly influenced our daily lives through various applications. One of the most promising application is smart city that leverages IoT devices to manage cities without any human intervention. The high possibility of sensing and publishing sensitive data in this smart environment leads to three significant issues: (1) privacy-preserving (2) heterogeneity, and (3) real-time services. We observe that current studies are in lack of addressing these challenges. In this paper, we propose a new privacy-preserving architecture for IoT devices in the smart city by leveraging ontology, a data model, at the edge of the network. At first, we propose an ontology that consists of privacy information of devices. Then, we mount a real-time privacy-preserving method on top of it that is achieved by providing a dynamic environment from the privacy-preserving point of view. Based on the simulation results using Protege and Visual Studio on a synthetic dataset, we find that our solution provides privacy at real-time while addressing heterogeneity issue so that many IoT devices can afford it. Thus, our proposed solution can be widely used for smart cities.

The main purpose of this paper is the allocation of orders to suppliers in an agile and flexible manner suitable to the automobile industry. In this paper, parts supplied by a single source were eliminated from the set of parts. Using mathematical modeling and through the interval-valued fuzzy-rough numbers best worst method (IVFRN-BWM), we try to achieve the results that can meet the proposed model's needs and provide the ideal results by introducing new modes. This paper addressed some new aspects of the subject and achieved robust results by considering five objective functions. These five functions are as follows: minimization of production line disruptions due to the performance of suppliers, minimization of the complaints of production line about supplied parts, minimization of defective parts received from suppliers (PPM), maximization of on-time delivery services, and minimization of overall costs of supplied parts. Reviewing the literature, the originality of this study are as follows: 1) identifying the structure of a supply chain (SC) in general and particularly in an automobile industry SC; 2) investigating the modeling techniques of the existing SC models for coordinating all the members of a product SC; 3) building a hybrid model of IVFRN-BWM and a robust goal programming agile and flexible supply chain in an uncertain situation; and 4) identifying the suitable scenarios/cases for testing the proposed models to validate the models. This paper can help decision makers and managers to opt for the best suppliers and also allocate the right numbers of parts to those supplier(s) based on a real situation of each firm.

In this paper, Deep Neural Networks (DNN) with Bat Algorithms (BA) offer a dynamic form of traffic control in Vehicular Adhoc Networks (VANETs). The former is used to route vehicles across highly congested paths to enhance efficiency, with a lower average latency. The latter is combined with the Internet of Things (IoT) and it moves across the VANETs to analyze the traffic congestion status between the network nodes. The experimental analysis tests the effectiveness of DNN-IoT-BA in various machine or deep learning algorithms in VANETs. DNN-IoT-BA is validated through various network metrics, like packet delivery ratio, latency and packet error rate. The simulation results show that the proposed method provides lower energy consumption and latency than conventional methods to support real-time traffic conditions.

IoT devices generate data over time, which is going to be shared with other parties to provide high-level services. Smart City is one of its applications which aims to manage cities automatically. Because of the large number of devices, three critical challenges come up: heterogeneity, privacy-preserving of generated data, and providing high-level services. The existing solutions cannot even solve two of the mentioned challenges simultaneously. In this paper, we propose a three-module framework, named “Ontology-Based Privacy-Preserving” (OBPP) to address these issues. The first module includes an ontology, a data storage model, to address the heterogeneity issue while keeping the privacy information of IoT devices. The second one contains semantic reasoning rules to find abnormal patterns while addressing the quality of provided services. The third module provides a privacy rules manager to address the privacy-preserving challenges of IoT devices achieved by dynamically changing privacy behaviors of the devices. Extensive simulations on a synthetic smart city dataset demonstrate the superior performance of our approach compared to the existing solutions while providing affordability and robustness against information leakages. Thus, it can be widely applied to smart cities.

To improve the interpretability or perception of information in images for human viewers is the main goal of image enhancement. Aiming at the problem that image edges are difficult to determine due to artefacts, plaques, and vascular branches in cardiovascular ultrasound, an edge ultrasound imaging detection algorithm based on spatial-frequency-domain image enhancement is proposed to improve the clarity of ultrasound images. Firstly, this paper uses the space-frequency-domain enhancement algorithm to enhance the image. This algorithm overcomes the problem of low contrast of conventional algorithms. The enhanced data matrix is used as the cost matrix, and then, the heuristic image search method is used to search the image of the cost matrix. The results show that the use of spatial-frequency-domain image ultrasound imaging algorithm can improve the contrast and sharpness of ultrasound images of cardiovascular disease, which can make the middle edge of the image clearer, the detection accuracy rate is increased to 92.76%, and the ultrasound of cardiovascular disease is improved. The edge of the image gets accuracy. The paper confirms that the ultrasound imaging algorithm based on spatial-frequency-domain image enhancement is worthy of application in clinical ultrasound image processing. The performance of the proposed technique is 32.54%, 75.30%, 21.19%, 21.26%, and 11.10% better than the existing technique in terms of edge energy, detail energy, sharpness, contrast, and information entropy, respectively.

The Micro-Electro-Mechanical Systems (MEMS) and Wireless Sensor Networks (WSNs) developments have had a crucial effect on our daily lives. The usage of wireless sensor networks is increasing daily. They can be used in various fields such as incident management, war detection and exploration, border protection and, security monitoring. Also, they are used in unattended environments as a remote. The sensors in WSNs are fully automatic. One of the efficient ways to manage WSN effectively is clustering because it can support the scalability of nodes. One of the main challenges in Wireless Sensor Network is not only its implementation but also finding the best clustering algorithm. Besides, wireless sensor networks' features should be considered in their design as the primary keys. In this paper, we present some of the most well-known available clustering algorithms and compare them based on the features and complexity of the network. These features include the rate of node convergence, the stability, the overlapping of each cluster, supporting node movement.

This paper presents a system that can recognize handwritten words expressed using broken letters of the Persian alphabet. The proposed system can be used for most activities related to the gathering of public information. Statistical features of the separated/broken letters are employed in the system. Each letter is recognized using interconnected fuzzy neural network. The advantages of this method include high precision owing to the strength of the neural network algorithm and the possibility of extending dataset instance codes in a simple manner. At last, an evaluation for the proposed method is provided experimentally.

To supervise massive generated data by the Internet of Things (IoT) efficiently, we face two issues that should be addressed which are: (1) heterogeneity or satisfying diversity among IoT devices, and (2) privacy-preserving or preventing unintentional disclosure of sensitive data. Through observation, we found that existing solutions apply one common privacy-preserving rule for all devices while they address the heterogeneity issue separately that lead to unappealing performance. In this paper, we propose a framework for addressing the heterogeneity issue and privacy-preserving of IoT devices at the network edge using a novel proposed ontology data model. Besides, it leverages the proposed ontology to obtain a privacy-preserving method by frequently changing the privacy-preserving behaviors of IoT devices. Through simulation, we show that our solution overhead is less than 9 percent in the worst situation so that it is affordable to most IoT devices in one of its applications that is smart city.

IoT aim is connecting all objects around the world with each other through the Internet. There are a large number of devices in the IoT that each one produces data over time. We can not publish the original data, without any process, due to the possibility of sensitive data disclosure. A networking paradigm that provisions network management flexibility and easier manipulation of the network called "Software Defined Networking" (SDN) recently emerged. Through observations, we have found existing solutions are in lack of flexibility in management while preserving-privacy. In this paper, at first, we propose a platform for integration of IoT with SDN. Then, we propose a method for solving the data privacy issue on top of it. Instead of having one static rule for all IoT devices, in our solution, each device can apply six possible privacy-preserving rules. During the time, the privacy method that each device should apply changes. We show the striking flexibility of our architecture so that management of data would be more efficient along with we are able to preserve the privacy of produced data in an acceptable level, finding original data would be a tough task.

Internet of Things (IoT) era appeared to connect all the digital and non-digital devices around the globe through the Internet. Based on predictions, billions of devices will be connected with each other by 2050 with the aim of providing high-level and humanized services. One application of IoT is a smart city that means IT-enabled cities running by themselves without human interventions. These large number of devices, especially in a smart city environment, may sense sensitive and personal data which makes the system vulnerable. We have to protect private information so that unwanted parties would not be able to find original data, which is a part of privacy-preserving. Meanwhile, a new networking paradigm evolved called Software Defined Networking (SDN) that aimed to separate the Control Plane and the Data Plane of the network results in much more flexibility to manage the network. Most of the existing works are deficient in flexibility or very tedious. In this paper, we facilitated IoT-based smart city with SDN paradigm to leverage the benefits of SDN. Then, based on the environment, we propose IoT-SDN Privacy-Preserving, IoT-SDNPP, to keep private data safe. We have done extensive experiments, and the experimental results have demonstrated the effectiveness of our approach.

High-speed Internet becomes more widely accessible, the cost of connecting devices is reducing, more devices are being created with Wi-Fi abilities and sensors are built into those devices, technology costs are cost-effective. All of these things are creating a ``storm" for the Internet of Things (IoT) era. With the emergence of the Internet of Things, connect things through internet, there are many devices that are providing data. The more devices, the more data. If these devices want to share data with the aim of achieving abstract knowledge, they need to pass through the network. Some devices provide sensitive information that can be time. We should protect these sensitive data, from unwanted disclosure that is called privacy. In other words, privacy preserving of data is one of the main problems of IoT devices, protecting sensitive data against unauthorized users when we do analysis and even transferring data. To achieve this in this paper, we propose a new method based on modular arithmetic for privacy-preserving when IoT devices produce sensitive time label called MAPP. We applied Number Theory, Modular Arithmetic to achieve that aim. We used CupCarbon 3.0 for simulation and evaluating our proposed method. Performance evaluation shows that our proposed method has good performance from the energy consumption point of view.

Big Data means extremely huge large data sets that can be analyzed to find patterns, trends. One technique that can be used for data analysis so that able to help us find abstract patterns in Big Data is Deep Learning. If we apply Deep Learning to Big Data, we can find unknown and useful patterns that were impossible so far. With the help of Deep Learning, AI is getting smart. There is a hypothesis in this regard, the more data, the more abstract knowledge. So a handy survey of Big Data, Deep Learning and its application in Big Data is necessary. In this paper, we provide a comprehensive survey on what is Big Data, comparing methods, its research problems, and trends. Then a survey of Deep Learning, its methods, comparison of frameworks, and algorithms is presented. And at last, application of Deep Learning in Big Data, its challenges, open research problems and future trends are presented.

Smart City is an application of the Internet of Things (IoT) with the aim of managing cities without human intervention. Each IoT device that is producing data may sense a sensitive one that should not be disclosed unintentionally. Due to the existence of a large number of devices in the near future, the possibility of information leakage, privacy breach, is increasing. To prevent this, each device applies a privacy-preserving method. We discover that all of the existing solutions have three major drawbacks: (1) applying one static privacy-preserving method for the entire system, (2) sending whole data at once, and (3) not context-aware. These cause unacceptable privacy-preserving degree. To address them, in this paper, at first, we equip IoT-based smart city with Software Defined Networking paradigm (SDN). Then, we mount an efficient privacy-preserving method on top of it that manages flowing data packets of split IoT device’ data. We have done extensive simulation through MININET-WIFI to show the effectiveness of our approach. Evaluation results show that our method can be widely applied to the smart city application with a superior performance regarding accuracy, overhead, and penetration rate compared to existing privacy-preserving solutions.

The original version of this article unfortunately contained an error in one of the co-author’s name. The third author’s name should read as “Xiaobo Zhang” instead of “Xioabo Zhang”.

Sensor networks usually generate mass of data, which if not structured for future applications, will require much effort on analytical processing and interpretations. Thus, storing sensor data in an effective and structured format is a key issue in the area of sensor networks. In the meantime, even a little improvement on data storing structure may lead to a significant effect on the lifetime and performance of the sensor network. This paper describes a new method for sensor storage that combines semantic web concepts, a data aggregation method along with aligning sensors in hierarchical form. This solution is able to reduce the amount of data stored at the sink nodes significantly. At the same time, the method structures sensed data in a way that we can respond to semantic web-based queries with less consumption of energy compared to previous conventional methods. Results show that, in some situations especially when the diversity of query responses and life of network are vital, the efficiency of our new solution is much better.

Due to the high volume of information and electronic documents on the Web, it is almost impossible for a human to study, research and analyze this volume of text. Summarizing the main idea and the major concept of the context enables the humans to read the summary of a large volume of text quickly and decide whether to further dig into details. Most of the existing summarization approaches have applied probability and statistics based techniques. But these approaches cannot achieve high accuracy. We observe that attention to the concept and the meaning of the context could greatly improve summarization accuracy, and due to the uncertainty that exists in the summarization methods, we simulate human like methods by integrating fuzzy logic with traditional statistical approaches in this study. The results of this study indicate that our approach can deal with uncertainty and achieve better results when compared with existing methods.