clustering

The purpose of this study is to design and analyze a model for exit strategies from recession in companies operating in the automotive parts manufacturing industry. This study is of a developmental-applied nature and follows a mixed-methods approach (qualitative and quantitative). The qualitative section is based on a multi-grounded theory approach to develop a qualitative model of dimensions, combining empirical exploratory findings (interviews) and theoretical exploratory findings (meta-synthesis of scientific documents). Quantitative analyses were conducted using the fuzzy cognitive map approach and clustering of companies based on k-means partitioning. The validity of the qualitative findings was confirmed using content validity for constructs and the opinions of external experts. The quantitative research population consisted of two groups: an expert panel of 18 individuals and managers and directors of automotive parts manufacturing companies located in northwest Iran. The expert panel was selected through purposive sampling, while the sample of companies, comprising 360 firms, was selected using stratified random sampling based on provincial distribution. The qualitative findings identified a model of exit strategies from recession for automotive parts manufacturers within a framework of 63 key concepts, 11 subcategories, and 3 major categories. The quantitative findings resulted in the development of a relational model comprising one sender node, two receiver nodes, and eight central nodes. Company clustering identified three major clusters of firms in response to recession exit strategies. The overall analysis of corporate exit strategies from recession indicated that automotive parts manufacturers should adopt a long-term plan focused primarily on transformation-oriented strategies to achieve a suitable level of competitiveness and competitive advantage in the business environment.

Clustering is a common method for prolonging a wireless sensor network lifetime. We can achieve higher energy efficiency by implementing multi-hop communication. Because of the induced load on the middle clusters, they die faster in comparison to the clusters on the borders. There is an efficient protocol for Rotating Energy-Efficient Clustering (REECHD). In this article, we introduced a load-balancing technique for the REECHD protocol to solve the energy hole issue. Initially, the base station calculates a maximum and minimum cluster range based on node density. We calculate the cluster range for each layer. The final values for these cluster ranges are then used as inputs in the REECHD protocol. The energy efficiency of this technique is compared with the REECHD protocol. The results show that our proposed technique enhances the REECHD in the matter of the first node dies (FND) and half node dies (HND) measure criteria (respectively 15% and 11.5% for 250 node) and also it prolongs the network lifespan by balancing the load on inter-cluster communications.
 

Due to the increasing use of VANET networks and the use of smart systems in these types of networks, their challenges have been the focus of researchers. One of the important challenges of such networks is the security issues that threaten this category of networks. In this article, the Sybil attack, which is one of the security challenges in VANET networks, has been investigated and identified. In a Sybil attack, a node threatens VANET networks by stealing the identity of other nodes or creating a virtual identity, by making incorrect decisions and sending false information. In this article, the clustering method is used to avoid the overhead of identification nodes in centralized methods and avoid delay in distributed methods. RSU determines the cluster head with the help of fuzzy logic. The cluster head creates moving clusters by placing similar nodes in terms of direction, speed, and distance in separate clusters while moving. The cluster head performs malicious node detection using a directional antenna and a fuzzy system. The first fuzzy system places the cluster head in the best possible place of the cluster. The cluster head identifies the malicious nodes in each cluster locally, while the second fuzzy system interferes in determining the validity of the cluster members. In the proposed plan, in addition to optimizing the sending and receiving of messages, The simulation results show that the proposed method has improved by 1.2% in detecting the malicious node, 0.4% in the number of a false positive detection, 0.6% in the lost packet, and 0.1% in the delay compared to the previous methods.

  Clustering is one of the most popular techniques in unsupervised learning in which data is divided into different groups without any prior knowledge, and for this reason, clustering is used in various applications today. One of the most popular algorithms in the field of clustering is the k-means clustering algorithm. The most critical weakness of k-means clustering is that it is sensitive to initial values for parameterization and may stop at local minima. Despite its many advantages, such as high speed and ease of implementation due to its dependence on the initial parameters, this algorithm is in the optimal local configuration and does not always produce the optimal answer for clustering. Therefore, this paper proposes a new model using the Bald Eagle Search (BES) Algorithm with the Sine Cosine Algorithm (SCA) for clustering. The evaluation of the proposed model is based on the number of iterations, convergence, number of generations, and execution time on 8 UCI datasets. The proposed model is compared with Flower Pollination Algorithm (FPA), Crow Search Algorithm (CSA), Particle Swarm Optimization (PSO), and Sine-Cosine Algorithm (SCA). The results show that the proposed model has a better fit compared to other algorithms. According to the analysis, it can be claimed that the proposed model is about 10.26% superior to other algorithms and also has an extraordinary advantage over k-means.

Vehicular Ad-Hoc Networks (VANET) models are derived from Mobile Ad-Hoc Networks that possess an impressive role in the intelligent transportation system today and also in the future. So scientists are always looking for the best theories in hope of grasping the fastest and safest connections between vehicles, to provide traffic and accident news in real time. The high number of nodes is one of the significant features of this network that results in an increase of the number of transmitted packets in the network. Distributed system and high mobility of the nodes are the other most important attributes of Vehicular Ad-Hoc networks. In this paper, we aim to review the studies and improvements of vehicular Ad-Hoc network in the fields of safety and traffic management. In addition, we introduce the most common challenges of this network and gather latest methods for resolving those problems. Multi agent systems will be one of the newest and suitable tools in this system. The main purpose is arranging safe connection between agents. Fixing agreements and removing the disputes are not detachable from functional system. It is like group associations and societies which require human collaborations and cooperation. Development of science resulted in utilization of these systems in various aspects like VANET. Nowadays scientists and researchers are interested to make use of these methods for improving the role of vehicle networks in the field of traffic management, safety and entertainment, we will review them in the following paragraphs.

Machine learning is one of the most practical branches of artificial intelligence that tries to provide algorithms by which the system can analyze a set of data in different formats. Machine learning algorithms are widely used in biomedicine, bioinformatics and neuroscience. The main goal of this paper is to propose the latest applications of machine learning in bioinformatics and neural imaging and to introduce new branches of research. In this article, the application of four indicators of machine learning techniques in the field of bioinformatics is examined. The four categories of techniques studied include clustering, classification, dimensionality, and deep learning. In this paper, we also show that machine learning techniques can be successfully used to address common bioinformatics challenges such as gene expression, DNA methylation identification, mRNA expression, patient classification, brain network analysis, protein chain identification, clustering, and biomarker identification. In each section, some efficient articles with technical details are discussed separately. The results of some papers are also reported in terms of accuracy, database and techniques used.

Energy is an important parameter in establishing various communications types in the sensor-based IoT. Sensors usually possess low-energy and non-rechargeable batteries since these sensors are often applied in places and applications that cannot be recharged. The most important objective of the present study is to minimize the energy consumption of sensors and increase the IoT network's lifetime by applying multi-objective optimization algorithms when selecting cluster heads and routing between cluster heads for transferring data to the base station. In the present article, after distributing the sensor nodes in the network, the type-2 fuzzy algorithm has been employed to select the cluster heads and also the genetic algorithm has been used to create a tree between the cluster heads and base station. After selecting the cluster heads, the normal nodes become cluster members and send their data to the cluster head. After collecting and aggregating the data by the cluster heads, the data is transferred to the base station from the path specified by the genetic algorithm. The proposed algorithm was implemented with MATLAB simulator and compared with LEACH, MB-CBCCP, and DCABGA protocols, the simulation results indicate the better performance of the proposed algorithm in different environments compared to the mentioned protocols. Due to the limited energy in the sensor-based IoT and the fact that they cannot be recharged in most applications, the use of multi-objective optimization algorithms in the design and implementation of routing and clustering algorithms has a significant impact on the increase in the lifetime of these networks.

The Internet of Things (IOT) has advanced in parallel with the wireless sensor network (WSN) and the WSN is an IOT empowerment. The IOT, through the internet provides the connection between the defined objects in apprehending and supervising the environment. In some applications, the IOT is converted into WSN with the same descriptions and limitations. Working with WSN is limited to energy, memory and computational ability of the sensor nodes. This makes the energy consumption to be wise if protection of network reliability is sought. The newly developed and effective hierarchical and clustering techniques are to overcome these limitations. The method proposed in this article, regarding energy consumption reduction is tree-based hierarchical technique, used clustering based on dynamic structure. In this method, the location-based and time-based properties of the sensor nodes are applied leading to provision of a greedy method as to form the subtree leaves. The rest of the tree structure up to the root, would be formed by applying the centrality concept in the network theory by the base station. The simulation reveals that the scalability and fairness parameter in energy consumption compare to the similar method has improved, thus, prolonged network lifetime and reliability.

Batch scheduling is among the important problems in industrial engineering and has been widely attendant in practical applications. Clustering is the set of observation assignment into some subsets so that the observations in the same cluster are similar in some sense and the similarity of generated clusters is very low. Clustering is considered as one of the approaches in unsupervised learning and a common technique for statistical data analysis which has been applied in many fields, including machine learning, data mining and etc. This paper studies a case study in Iran Puya company (as a home appliance maker company in Iran). In the production line of refrigerator of the current company, a cutting machine is identified as a bottleneck that can process several iron plates simultaneously. In this regard a good scheduling on this cutting machine improves the effectiveness of production line in terms of cost and time. The objective is to minimize the total tardiness and maximizing the job values when the deteriorated jobs are delivered to each customer in various size batches. Based on these assumptions a mathematical model is proposed and two hybrid algorithms based on simulation annealing and clustering methods are offered for solving it and the results are compared with the global optimum values generated by Lingo 10 software. Based on the effective factors of the problem, a number of sensitivity analyses are also implemented including number of jobs and rate of deterioration. Accordingly, the running time grows exponentially when the number of jobs increases. However the rate of deterioration could not affect the running time. Computational study demonstrates that using clustering methods leads an specified improvements in total costs of company between 15 to 41 percent.