International Journal of Intelligent Engineering and Systems

7

Authors: Prashanth Kumar Bolisetty, Prasanth Yalla

The Software architecture is generated by using the interfaces and structural components of the software systems in an organization. Software architecture, along with the structure and behavior, also concerned with functionality, performance, reuse, economic and technological constraints etc. In software its components are related to one another in large variety of ways. The main intension of our research is to build the component based software architecture with adaptive configurations using Particle Swarm Optimization and clustering techniques. Building architecture is an inspiring progression. In this paper, we will propose Hybrid Particle Swarm Optimization (PSO) – Cuckoo Search (CS) algorithm for developing an adaptive software architecture based on the Process control model. Initially, the components are selected based on testcases generated. After that, adaptive architecture will be built by using PSO - CS on the basis of clustering results. The architecture is built along with its functional requirements, responsibility and evaluation. The functional requirements are given as graphs of functional responsibilities where modifiability, efficiency and traceability are considered as the quality attributes. The proposed method produced solution with increased quality and better metric values.

7

Authors: Farzan Rashidi

To improve wide angle, bottom-interacting situation with complex boundaries in ocean acoustic wave propagation, in this paper the finite element method is used to discretize the continuous depth system of equations. Coupled linear Galerkin finite element method in association with parabolic equation model is applied for depth discretization of underwater wave equation. This discretization leads to equivalent system of ordinary differential equations (ODEs) that are applied over complex shapes covered by variable nature of surface and bottom boundaries. These ODEs are estimated by Crank-Nicolson approach. Simulation results show the capability of the proposed method in comparison with the physically behavior of underwater sound propagation and some numerical results of standard software. The obtained results demonstrate good agreement and efficiency of the proposed method.

9

Authors: Younes Khandouch, El Houcein Aassif, Said Agounad, Gérard Maze

A number of researches in different areas has been conducted on using the Principal Component Analysis PCA combined with Artificial Neural Networks ANN. In this current research, we use these two techniques to estimate the radius ratio b/a (a: outer radius, b: inner radius) of an elastic tube based on its form function. The PCA technique is used to estimate the component loadings corresponding to form function. Then, the component loadings it’s used in the ANN technique to estimate the radius ratio of the tube. To get the optimal network, several configurations are implemented and tested. The optimal configuration selected is a network with 16 inputs, 2 hidden layers composed of 4 and 1 neurons respectively, and trained by the back-propagation algorithm. This configuration is able to estimate the radius ratio

10

Authors: Anju Malik, Vinod Kumar Jain

Cloud providers offer several storage services for their users in efficient manner. Cloud users are allowed to store their data in cloud. The data leakage, lack of proper security control policy, and weakness in the data security are the main worries of the companies. We intended to propose a secure cloud storage system RSA-ABC algorithm for encryption and decryption process. Initially the user will login with the aid of private key and public key. Then send a request to the data base administrator for upload a file in a cloud. In this phase we will give one time password and keys. Then the DBA will verify that data and accept that file and encrypt that file and stored in to the cloud server. If the user want that file means they send a request to DBA continue the same process after they will decrypt the file and send to the user.

10

Authors: Vinu Sundararaj

Electrocardiographic (ECG) signal is significant to diagnose cardiac arrhythmia among various biological signals. The accurate analysis of noisy Electrocardiographic (ECG) signal is very motivating challenge. Prior to automated analysis, the noises present in ECG signal need to be eliminated for accurate diagnosis. Many researchers have been reported different methods for denoising the ECG signal in recent years. In this paper, an optimized threshold mechanism is proposed for wavelet based medical signal noise reduction. This scheme is based on a variable step size firefly algorithm (VSSFA) in dual tree complex wavelet scheme, in which the VSSFA is utilized for threshold optimization. This approach is evaluated on several normal and abnormal ECG signals of MIT/BIH arrhythmia database, by artificially adding white Gaussian noises with variation of 5dB and 10dB. Simulation result illustrate that the proposed system is well performance in various noise level, and obtains better visual quality compare with other methods.

10

Authors: Thiruppathy Kesavan Venkatasamy, Radhakrishnan Shanmugasundaram

In this paper, Cluster Based Dynamic Keying Technique for Authentication in Wireless Sensor Networks (WSN) is proposed. The CH enabled by Global Positioning System (GPS) determines a Combined Cost Value (CCV) for each sensor node based on nodes location, node degree and virtual battery power. Since the key to the encryption scheme changes dynamically when there is change in CCV, separate dynamic keys are generated in each cluster by each CH and using RC5 encryption mechanism the source CH forwarding the data along different clusters along the path to the sink are able to verify the authenticity. When the source CH needs to transmit the aggregated data packet to the sink, it splits the packet into shares by threshold secret sharing algorithm and forwards them to the sink using multi-path dispersal routing technique.

11

Authors: Kuruva Lakshmanna, Neelu Khare

In this paper, we propose a 3-step DNA sequence mining algorithm, called 3s-DNASM, incorporating prefix span, length and width constraints and group search optimization. The complete mining process is comprised into following vital steps: 1) applying prefix span algorithm, 2) length and width constraints, 3) Optimal mining via group search optimization (GSO). We first present the concept of prefix span, which detects the frequent DNA sequence. Based on this prefix tree, length and width constraints are applied to handle restrictions. Finally, we adopt the group search optimization (GSO) algorithm to completeness of the mining result. The experimentation is carried out using DNA sequence dataset, and the evaluation with DNA sequence dataset showed that the 3s-DNASM system is good for sequence mining. The simulation results illustrated that when min_support=4, the number of DNA sequence mined only 29 patterns by 3s-DNASM system, and in this case prefix span mined about 2168 patterns.

15

Authors: Vedururu Sireesha, Sandhya Rani Kasi Reddy

In the document, we are intending to present an innovative technique for the multimodal biometric authentication. Initially the input image is preprocessed then offered to feature extraction, where the modified local binary pattern is effectively utilized. Thereafter, the extracted features are furnished to the feature level and score level fusions. In feature level fusion, extracted features are offered to the GSO where the optimal features are shortlisted, and are furnished to the optimized neural network which effectively detects the iris and fingerprint image. In score level fusion, extracted features from the iris image are offered to the PSO and naive bayes classifier here one score value is achieved. After that, extracted features from the fingerprint image are applied to the AGFS and then one score value is attained. Finally, both the score values are combined. The evaluation tools utilized precision, FAR and FRR. The proposed method implemented in MATLAB platform.

6

Authors: Pawan Whig, Syed Naseem Ahmad

: The Spice Model for photo catalytic sensor (PCS) proposed by Whig and Ahmad overcome several drawbacks like complex designing, non-linearity and long computation time generally found in Flow Injection Analysis (FIA) technique by Yoon-Chang Kim et al for the determination of Chemical Oxygen Demand (COD). FIA technique involves the complete analysis including sampling and washing. Flow Injection Analysis is analytical method for the measurement of chemical oxygen demand using photochemical column. This method uses a bulky setup and takes 10-15 minutes to get the output result which is a tedious and time consuming job. If conventional method is continuously used for a long time than it is stable only for 15 days. The purpose of this paper is to propose a new Quasi Floating Gate Photo Catalytic Sensor (QFGPCS) approach which has low power consumption and compared the results with the conventional models. The proposed model operates under sub threshold conditions which are appreciated in large integrated system design. The results of simulation were found to be fairly in agreement with the theoretical predictions. The results are exhibited near linear variations of parameters of interest with appreciably reduced response time.

7

Authors: Chintan Bhatt, C. K. Bhensdadia

Data Mining techniques are broadly utilized crosswise over numerous orders to recognize hidden patents, rules or relationships among gigantic volumes of information. Induction Tree, for example, C4.5 is the most favored technique since it functions well under any dataset set being utilized. Exponential ascent in the utilization of the internet because of informal organizations began to get enormous volume of information crosswise over various areas in brief timeframe. These attributes by which the colossal measures of informal organization information are produced make them to order as Big Data. When adapting to huge information (Big Data), the greater part of the current discretization methodologies won't be very productive with respect to implementation. The most effective method to separate significant data from huge information has been a famous open issue. In this paper, we are proposing new algorithm of decision tree in big data. At last, we have shown some result using weka.

13

Authors: G. Balaji, R. Balamurugan, L. Lakshminarasimman

Generator Maintenance Scheduling (GMS) problem in a vertically integrated electric utility system is considered in this paper. The cost and reliability objectives are included in the problem formulation. The GMS is formulated as a non linear, heavily constrained multi-objective optimization problem and the non dominated solutions are obtained using multi objective hybrid integer coded differential evolution (MOHDE) algorithm. To attain the best compromise non dominated solution between cost and reliability, fuzzy based mechanism has been used in MOHDE. In this paper, fuzzy clustered multi objective hybrid differential evolution (FC-MOHDE) is proposed for solving thermal generator maintenance scheduling. To validate the performance of the proposed algorithm, two systems having 4 and 22 generating units are considered. The test results confirm the superiority of the algorithm in determining the best compromise solution for the multi objective GMS problem.

7

Authors: Minghua Niu, Jianmin Zhang, Gen Li

Lane recognition is a kind of technology which can reconstruct either continuous or discontinuous lanes in the driving region into the continuous curves from the images of the road containing the lane markings. It is the basis and prerequisite for the whole lane departure warning system and the key technology in intelligent traffic safety assistant driving now. Generally speaking, the road images which the camera captures are processed by three steps: image preprocessing, image threshold segment and lane recognition. This paper proposed an efficient system to detect the lanes and mainly made experimental research on the images simulation of the three kinds of algorithms of the threshold segment and used the principle of Hough Transform in the lane recognition. Finally, the relatively efficient and accurate lane recognition processing algorithm was obtained according to the experimental results. Undoubtedly, this would lay a theoretical foundation for putting lane detection algorithm into practical application.

13

Authors: Senthil Murugan Balakrishnan, Arun Kumar Sangaiah

Internet of Things refers to a paradigm consisting of a variety of uniquely identifiable day to day things communicating with one another to form a large scale dynamic network. The integration of these heterogeneous things in the constrained network is a challenging issue, for which service oriented and architecture based solutions are considered to be useful. The key element of any service oriented paradigm is service discovery which allows the client to get access to the right service at the right time to complete the requested tasks. This paper presented a comprehensive survey of major solutions for service and resource discovery detailing techniques and features used in existing systems. The survey presented the findings in tabular representation and outlined the proposed aspect oriented middleware framework for IoT highlighting context awareness and solving certain pitfalls in the existing service discovery approaches. The survey results might be helpful in deriving the limitations of the existing protocols in literature and identify future research opportunities in service discovery.

6

Authors: Dun Liu, Qian-Fu Cheng

This paper elaborates the basic operation principle of the Doherty power amplifier (DPA) and analyzes the method of improving the linearity of the DPA. A novel DPA with dual DC power supplies and a high linearity is designed and implemented at the operating frequency of 4 GHz. EM (Electro Magnetic)/Circuit Co-Simulation shows that under one tone test, the DPA can obtain the high performance of the 40.4 dBm saturated output power, about 63% maximum power added efficiency (PAE) and about 50% PAE at 6 dB output power back-off (OBO). Under two tones test, the third order inter-modulation distortion (IMD3) is less than -30 dBc when the input power is less than 27dBm. Moreover the DPA delivers the maximum PAE of 61% with the corresponding input power of 26.5 dBm and output power of 38.5 dBm respectively.