International Journal of Intelligent Engineering and Systems

1

Authors: Tamilarasan Santhamurthy, Kumar Parasuramane

Today’s wireless communication systems required groundbreaking solution to meet scarcity of radio spectrum. Cognitive radio (CR) is an emerging technology which provides futuristic solution and improving the precious likely resources utilization. Cognitive radio network (CRN) is an intellectual wireless communication system as well as aware of its environment. In CRN, we have sensing problem by multiple nodes with changing computational power, spectrum allocation and range of sensing. The secondary user (SU) plays major role of primary channel sensing and appropriate unused channel selection for communication. In this paper we focused on optimum resource allocations and priority based scheduling for primary user (PU) and secondary user (SU) to exploit the performance of the entire network by reducing the interference at PU and also exploiting the throughput and decreasing the risk of overlying the coverage of CRNs. The effectiveness of dynamic resource allocation priority based scheduling (DRAPBS-CRN) algorithm is compared with dynamic resource allocation (DRA-CRN) algorithm and is found to be 26% more efficient using ns-2 simulation. This proposed DRAPBS-CRN algorithm also will avoid collisions and perform smart data transmission in CRN.

21

Authors: M.N.Shah Zainudin, Md Nasir Sulaiman, Norwati Mustapha, Thinagaran Perumal, Azree Shahrel Ahmad Nazri, Raihani Mohamed, Syaifulnizam Abd Manaf

In various classification areas, the curse of dimensionality becomes a major challenge among the researchers. Thus, feature selection plays an important role in overcoming dimensionality problem. Relief-f is one of the filter methods to rank the most significant features based on their relevance. Although relief-f proved to be a powerful technique in filter strategy, but this method only rank the features based on their significant level. Hence, feature selection is embedded to select the most meaningful features based on their rank. Differential evolution (DE) is one of the evolutionary algorithms that are widely used in various classification domains. Simple and powerful in implementation, we combined relief-f with DE in our proposed feature selection method to solving the optimization problem. In this work, population size and generation size were adaptively determined from the number of features from relief-f. The performance of proposed method is compared with several feature selection techniques in order to prove their superiority using ten datasets obtained from UCI machine learning repository.

40

Authors: Anitha Arumalla, Madhavi Latha Makkena

Reconfigurable architectures have provided a low cost, fast turnaround platform for the development and deployment of designs in communication and signal processing applications. The floating point operations are used in most of the signal processing applications that require high precision and good accuracy. In this paper, an effective implementation of Fused Floating-point Add-Subtract (FFAS) unit with a modification in dual path design is presented. To enhance the performance of FFAS unit for reconfigurable architectures, a dual path unit with a modification in close path design is proposed. The proposed design is targeted on a Xilinx Virtex-6 device and implemented on ML605 Evaluation board for single, double and double extended precision. When compared to discrete floating point adder design, the FFAS unit reduces area requirement and power dissipation as the later shares common logic. A Dual Path FFAS (DPFFAS) unit has reduced latency when compared with FFAS unit. The latency is further reduced with the proposed modified DPFFAS when compared with DPFFAS for reconfigurable architectures.

58

Authors: Ramani Selvanambi, Jaisankar Natarajan

In data mining, association rules are produced in view of solid relations and regularities existing among the variables in extensive exchanges. These association rules go for extricating connections, frequent patterns and associations among the item sets in exchanges. Association rules are connected for use in different zones, for example, media transmission, hazard administration and so forth. One such territory where the association rules are vital is the stock market. In stock marketing, picking the right stock relies on upon the genuine stock quality and the capacity to pick the stock is urgent as it impacts the profit of investors. In this work, the proposed technique develops a novel and effective way to deal with producing optimal stock rules to help in the stock market prediction by utilizing Enhanced Apriori algorithm and Artificial Bee Colony Optimization (ABC) algorithm. In the result profit of PP, EMA, ROC and RSI for min-support 3, 4, 5 and 6 individually in rule mining for HCL stock market dataset is appeared with correlation of GA-Apriori algorithm, AGA- Enhanced Apriori algorithm and ABC- Enhanced Apriori algorithm. From this Artificial Bee Colony (ABC) optimization algorithm is performed when contrasting and different strategies and grant that strong association rules to be produced.

78

Authors: Palamakula Ramesh Babu, Parimala Venkata Krishna

The MAC layer plays a major role in the enhancement of the performance of any network. Hence this paper proposes a modified virtual backoff algorithm which queues the packets based on the delay that application can tolerate and ant colony optimization technique is used to choose the best of all available forwarding nodes. Two counter referred as Naccess and Nattempt are maintained for each node which is used to calculate the success rate of each node based on which the node is given the channel access of all contending nodes. Sleep scheduling is incorporated in order to enhance the energy conservation and hence increase the lifetime of the network. The performance of the proposed algorithm is proved to be better when compared to the legacy systems like VBA, S-MAC and EACAODV. The parameters used for testing are packet delivery ratio, average energy consumption, delay and number of collisions.

96

Authors: Sunitha Badanahatti, Yelisetty Satya Sree Rama Murthy

Regression testing is a kind of software testing that authenticates that software previously developed and established still accomplishes correctly after it was altered or interfaced with other software. The aim of the investigation is to progress the software competence via cloud based regression testing. The projected technique has three chief stages such as, 1) test case generation, 2) clustering and 3) test case prioritization. Primarily the input implementation is send to the cloud for test case generation. For producing the test cases the projected method utilizes coverage metrics. Following the test case generation, the existing test cases are gathered with the help of kernel fuzzy c means clustering algorithm. Subsequently each group is fed to test case prioritization; in that grey wolf optimization algorithm is utilized for test case prioritization. Thus we will get operative prioritized test cases. Our method will be implemented on JAVA with Cloud Sim platform. The presentation will be assessed using execution time and memory use. From the solution the applied method precedes minimum implementation time associated with the available technique.

116

Authors: Nageswara Rao Sirisala, C. Shoba Bindu

Evaluation of node’s trust value is certainly advantage in mobile Adhoc networks (MANETs) where the applications run efficiently by involving trustable nodes only. The proposed method “A Novel QoS Trust computation in MANETs using Fuzzy Petri Nets-QTFPN”, evaluates node trust value based on its quality of service (QoS) parameters. Here the MANET is represented as Dynamic Adaptive Fuzzy Petri Nets (DAFPN) model with concurrent reasoning algorithm (CRA). In which delivery of each packet from node to node requires evaluation of certainty factor (μ) using fuzzy expert system. This fuzzy inference system uses QoS parameters as fuzzy input variables namely energy, bandwidth, node mobility and reliability. In the routing process the intermediate node’s trust values are evaluated based on certainty factor. The concurrent reasoning algorithm can strengthen the proposed method in selection of quality path to destination and reestablishment of path in case of path breaks. The proposed method performance is analyzed theoretically in terms of time and space complexities. The simulation results are taken against node velocity and network size, where the proposed method outperforms the existing protocols.

136

Authors: Anggun Fitrian Isnawati, Risanuri Hidayat, Selo Sulistyo, I Wayan Mustika

Dynamic user in mobile communication encourages the implementation of self-organized and non-cooperative distributed power control. To be implemented, the power control must meet the feasible and convergent conditions. Feasibility of power control must be qualified for non-negative power vectors and the limit of maximum power, whereas convergence is tested by the speed for achieving of convergent conditions on fixed point. If it is feasible, then the system will be convergent, but when it is infeasible then the power transmit of user will be negative and the system is never reach the convergence. While the semi feasible condition requires the implementation of a proposed method of HDCPC. When power transmit of user exceeded the maximum power, Pmax, HDCPC method choose the transmit power that equal with ½ Pmax compared to use Pmax that required on DCPC or to force the user turned off the power transmit on GDCPC. Results showed that it would be more efficient in power usage than DCPC and more implementable than GDCPC. Proposed HDCPC is done when there is no option of handover channel, while the results after user move to another channel is able to achieve the SINR target and spent less power. Related to the convergence analysis, it can be concluded that the larger the SINR target, the longer iterations required to achieve a convergent condition.

156

Authors: Harshita Patel, Ghanshyam Singh Thakur

Learning from imbalanced data is one of the burning issues of the era. Traditional classification methods exhibit degradation in their performances while dealing with imbalanced data sets due to skewed distribution of data into classes. Among various suggested solutions, instance based weighted approaches secured the space in such cases. In this paper, we are proposing a new fuzzy weighted nearest neighbor method that optimally handle the imbalance issue of data. Use of optimal weights improve the performance of fuzzy nearest neighbor algorithm for default balanced distribution of data, for the classification of imbalanced data concept of adaptive K is merged with it that apply large K, number of nearest neighbors for large class and small K for small class. We deploy this combination to classify imbalanced data with better accuracy for different evaluation measures. Experimental results affirm that our proposed method perform well than the traditional fuzzy nearest neighbor classification for these type of data sets.

173

Authors: Achyut Shankar1*, Natarajan Jaisankar

In this paper, we propose an (SAPSO) Self-Adaptive Particle Swarm Optimization algorithm to solve the base station positioning problem. This algorithm is used to minimize the distance between the base station and cluster head owing to maximizing the energy. Moreover, the proposed algorithm is compared with many other conventional algorithms such as Artificial Bee Colony-Dynamic Scout bee (ABC-DS) algorithm, Genetic algorithm (GA), Particle swarm optimization (PSO) and Firefly with Dual Update Process (FFDUP) algorithm. Also, empowering SAPSO helps to find the optimal location of the base station to conserve energy in a noteworthy manner to maximize the network lifetime and prolong network connectivity regarding minimizing distance, delay and maximizing the security, energy. Our simulation results demonstrate that the proposed SAPSO algorithm performs better than the other conventional algorithm.