Search

Keyword extraction is one of the most important aspects of text mining. Keywords help in identifying the document context. Many researchers have contributed their work to keyword extraction. They proposed approaches based on the frequency of occurrence, the position of words or the similarity between two terms. However, these approaches have shown shortcomings. In this paper, we propose a method that tries to overcome some of these shortcomings and present a new algorithm whose efficiency has been evaluated against widely used benchmarks. It is found from the analysis of standard datasets that the position of word in the document plays an important role in the identification of keywords. In this paper, a fuzzy logic-based automatic keyword extraction (FLAKE) method is proposed. FLAKE assigns weights to the keywords by considering the relative position of each word in the entire document as well as in the sentence coupled with the total occurrences of that word in the document. Based on the above data, candidate keywords are selected. Using WordNet, a fuzzy graph is constructed whose nodes represent candidate keywords. At this point, the most important nodes (based on fuzzy graph centrality measures) are identified. Those important nodes are selected as final keywords. The experiments conducted on various datasets show that proposed approach outperforms other keyword extraction methodologies by enhancing precision and recall. [ABSTRACT FROM AUTHOR]

Wireless sensor network (WSN) is a group of interconnected sensor nodes that work wirelessly to capture the information of surroundings. The routing of the network is a challenging task. The routing of WSN is classified as proactive, reactive, and hybrid. Adhoc on-demand distance vector (AODV) routing is an example of reactive routing based on the demand route formations among different nodes in the network. The research article emphasizes the design and simulation of the AODV routing hardware chip using very-high-speed integrated circuit hardware description language (VHDL) programming in Xilinx integrated synthesis environment (ISE) 14.7 software. The performance of the chip is studied based on the field-programmable gate array (FPGA) hardware parameters such as slices, lookup table (LUTs), input/output block (IOB), flipflops, and memory for the different configurations of the network (N = 10, 20 ....100). The delay and frequency are also estimated on the Virtex-5 FPGA. The performance of the WSN with AODV routing is also analyzed based on the packet delivery ratio, throughput, delay, and control overhead. The simulation test cases verified the 8-bit, 64-bit, and 128-bit data communication within the nodes. [ABSTRACT FROM AUTHOR]

A hybrid of supervised (artificial neural network), unsupervised (clustering) machine learning, and soft computing (interval type 2 fuzzy logic system)-based load balancing algorithm, i.e., clustering-based multiple objective dynamic load balancing technique (CMODLB), is introduced to balance the cloud load in the present work. Initially, our previously introduced artificial neural network-based dynamic load balancing (ANN-LB) technique is implemented to cluster the virtual machines (VMs) into underloaded and overloaded VMs using Bayesian optimization-based enhanced K-means (BOEK-means) algorithm. In the second stage, the user tasks are scheduled for underloading VMs to improve load balance and resource utilization. Scheduling of tasks is supported by multi-objective-based technique of order preference by similarity to ideal solution with particle swarm optimization (TOPSIS-PSO) algorithm using different cloud criteria. To realize load balancing among PMs, the VM manager makes decisions for VM migration. VM migration decision is done based on the suitable conditions, if a PM is overloaded, and if another PM is minimum loaded. The former condition balances load, while the latter condition minimizes energy consumption in PMs. VM migration is achieved through interval type 2 fuzzy logic system (IT2FS) whose decisions are based on multiple significant parameters. Experimental results show that the CMODLB method takes 31.067% and 71.6% less completion time than TaPRA and BSO, respectively. It has maintained 65.54% and 68.26% less MakeSpan than MaxMin and R.R algorithms, respectively. The proposed method has achieved around 75% of resource utilization, which is highest compared to DHCI and CESCC. The use of novel and innovative hybridization of machine learning, multi-objective, and soft computing methods in the proposed algorithm offers optimum scheduling and migration processes to balance PMs and VMs. [ABSTRACT FROM AUTHOR]

Wireless Sensor Network (WSN) is a self-organized network, contains sensor nodes deployed in particular regions to gather the environmental parameters and communicate the information to the base station directly through intermediate nodes. In recent times, WSN has gained attention from wireless device manufacturers, researchers, and users for remotely accessing and monitoring the information in diverse environments. The scalability and routing are the major concerns of the network. Apart from that, the performance of WSN depends on network simulation parameters such as delay, throughput, packet delivery ratio (PDR), and control overhead. The research paper focused on the DSDV and OLSR routing protocol realization on the new hardware platform. The hardware chip of these protocols is designed in Xilinx ISE 14.7 software using VHDL, targeted on Virtex-5 FPGA. The node communication is verified on Modelsim 10.0 simulation software. The FPGA hardware and timing parameters are analyzed for different node clusters (N = 10, 20 ...150) configuration. The OLSR routing protocol network performance parameters are used to build the machine learning prediction model using cluster tree regression, random forest regression, multiple regression, and K-means clustering. The K-means clustering predicted 99.12% and 98.50% accuracy in terms of the packet delivery ratio and throughput respectively. [ABSTRACT FROM AUTHOR]

Cloud computing is an emerging paradigm that offers various services for both users and enterprisers. Scheduling of user tasks among data centers, host and virtual machines (VMs) becomes challenging issues in cloud due to involvement of vast number of users. To address such issues, a new multi-criteria approach i.e., technique of order precedence by similarity to ideal solution (TOPSIS) algorithm is introduced to perform task scheduling in cloud systems. The task scheduling is performed in two phases. In first phase, TOPSIS algorithm is applied to obtain the relative closeness of tasks with respect to selected scheduling criteria (i.e., execution time, transmission time and cost). In second phase the particle swarm optimization (PSO) begins with computing relative closeness of the given three criteria for all tasks in all VMs. A weighted sum of execution time, transmission time and cost used as an objective function by TOPSIS to solve the problem of multi-objective task scheduling in cloud environment. The simulation work has been done in CloudSim. The performance of proposed work has been compared with PSO, dynamic PSO (DPSO), ABC, IABC and FUGE algorithms on the basis of MakeSpan, transmission time, cost and resource utilization. Experimental results show approximate 75% improvement on average utilization of resources than PSO. Processing cost of TOPSIS–PSO reduced at approximate 23.93% and 55.49% than IABC and ABC respectively. The analysis also shows that TOPSIS–PSO algorithm reduces 3.1, 29.1 and 14.4% MakeSpan than FUGE, ant colony optimization (ACO) and multiple ACO respectively. Plotted graphs and calculated values show that the proposed work is very innovative and effective for task scheduling. This TOPSIS method to calculate relative closeness for PSO has been remarkable. [ABSTRACT FROM AUTHOR]

Yager [1] introduced the concept of q-rung orthopair fuzzy sets (q-ROFSs) in which the sum of the qth exponent of the support for membership and the qth exponent of the support against membership is bounded by one. Thus, the q-ROFSs are an important way to express uncertain information in broader space, and they are superior to the intuitionistic fuzzy sets (IFSs) and the Pythagorean fuzzy sets (PFSs). However, in dealing with many real life situations, it is not appropriate for experts to precisely quantify their judgements with a crisp number due to insufficiency in available information. In such situation it is advisable for decision makers to provide their judgements by the subset of the closed interval [0, 1]. The notion of interval-valued q-rung orthopair fuzzy sets (IVq-ROFSs) is presented in this paper, which allows decision makers to provide their satisfying degrees and non-satisfying degrees to a given set of alternatives by an interval value. Some of its important operations such as: negation, union and intersection are also given. Based on these operations, the aggregation of IVq-ROFSs is also studied. [ABSTRACT FROM AUTHOR]

In this paper, policy iteration (PI) based adaptive critic approach has been utilized to design a controller for AGC scheme. PI approach consists policy evaluation and improvement steps to determine optimal control. Optimal controller based on linear quadratic regulator (LQR) design requires complete knowledge of the system dynamics, whereas PI technique provides optimal control of system without knowing the internal dynamics. PI based optimal controller has been tested on a power system having two area deregulated. The results are used to show the effective performance of the designed controller. A comparative study has also been given in between the performance of the PI based optimal controller and LQR. [ABSTRACT FROM AUTHOR]