Paper Title

A CRITICAL STUDY ON BIGDATA AND AI CONCEPTS IN NETWORKS

Abstract

The applications of network technology have exerted profound influence on the artificial intelligence .This big data contains enormous economic, social, industrial, scientific values and has become the focus of attention of all walks of life. Further Artificial intelligence (AI) improves the performance and effectiveness of computer network technology. Now the computer network technology has been upgraded constantly and the computer technology has been applied more and more extensively, which bring a lot of convenience to people\'s life. An attempt made in this article takes artificial intelligence in the background of big data concepts by exploring network technology applications, which provides some reference for the research. Therefore, artificial intelligence is in computer network technology plays a very important role with Big data.
KEYWORDS : big data, application; network management; artificial intelligence; computer network technology

Paper Title

ARTIFICIAL INTELLIGENCE (AI) STRATEGIES FOR THE EXPECTATION OF VARIOUS SORTS FOR LIVER ILLNESSES

Abstract

: The data mining and restoration management of the committee is not typical for the area of irreversible change in the way that existing data is affected and effectively, legally and socially helpful with self-help information. Most of these studies are rooted in in-depth analysis of the area of liver function around three types of features: type of deformity, set-up pattern and graphic modeling. In order to protect the liver from the active immune system, the mammary gland system (SSM) is often integrated into these systems. studies suggest a two-pronged approach for liver division. The necessary barriers were completed with a quick walk-in set, and then the rafters were repaired using a different level system. Different systems were analysed as necessary and integrate relevant features into local models , such as the addition of self-reinforcement forcing local boundaries for liver health systems. Incomplete photography of the whole world is associated with a level reserved for the liver region and the system involves the introduction of a map with follow-up analysis based on the setting for the liver area.
KEYWORDS : liver, data mining, web mining, artificial intelligence

Paper Title

A STUDY ON WIRELESS SENSOR NETWORKS AND CHALLENGES IN CLUSTERING ALGORITHMS

Abstract

This paper describes the concept of optimization techniques in Wireless Sensor Networks. Wireless Sensor Network consist of many sensor nodes in which each sensor node collects the data from sensing environment and transmit to the base station. Optimization techniques used in wireless sensor networks for minimizing energy consumption generally and for solve routing problems. For improving network lifetime and energy consumption various optimization techniques have been proposed. The paper gives overview of most successful .Wireless sensor networks (WSNs) are networks of autonomous nodes used for monitoring an environment. Developers of WSNs face challenges that arise from communication link failures, memory and computational constraints, and limited energy. Many issues in WSNs are formulated as multidimensional optimization problems, and approached through bio-inspired techniques. Particle swarm optimization (PSO) is a simple, effective and computationally efficient optimization algorithm. It has been applied to address WSN issues such as optimal deployment, node localization, clustering and data-aggregation. This paper outlines issues in WSNs and discusses its suitability for WSN applications.
KEYWORDS : WSN, protocols,

Paper Title

OPTIMIZATION OF POROSITY OCCURANCE IN PRESSSURE DIE CASTING BY TAGUCHI METHOD

Abstract

High-pressure die casting (HPDC) is particularly suitable for high production rates and it is applied in several industrial fields; actually, approximately half of the world production of light metal castings is obtained by this technology. An overview of the actual status of HPDC technology is described in the current work, where both critical aspects and potential advantages are evidenced. In the current study of die casting for Automobile starter motor casing, the following issues are focused: shot piston simulation, defect analysis, and, finally, the use of the Taguchi mutuality analytical method to find the optimal parameters and factors to increase the aluminium ADC10 die casting quality and efficiency. Experiments were conducted by varying molten alloy temperature, die temperature, plunger velocities in the first and second stage, and multiplied pressure in the third stage using L9 orthogonal array of Taguchi method. After conducting a series of initial experiments in a controlled environment, Response for Signal to Noise Ratios L9 Orthogonal array for developing a robust performance for pressure die casting processes. The appropriate multivariable linear model is a useful and efficient method to find the optimal process conditions in pressure die casting associated with the minimum shrinkage porosity percent.
KEYWORDS : High-pressure die casting, Signal to Noise Ratios, L9 Orthogonal array

Paper Title

A STUDY ON STRUCTURES WITH REFERENCE TO HSC IN COASTAL AREA

Abstract

The aim of this section is to provide an overview of the structural engineering properties and characteristics of HSC, in light of the recent experimental and theoretical research and published results. There are other non-structural benefits of using HSC, for example the improved durability of the material which is a result of reduced porosity and the use of high-quality materials. However, the topic of durability is not discussed here in detail. HSC with good binder and aggregates with footing taken in to consideration for mix design of the structural properties enhancement for water resisted structures. The work further makes a theoretical and computational response comparison at the end for better recommendations. A recommended difference of 2 to 3 % in all the cases found between numerical and computational.
KEYWORDS : Structural properties, HSC, Water resisted structures.

Paper Title

A STUDY ON CONTROL STRATEGIES FOR DIFFERENT SOLAR GRIDS

Abstract

Ever-rising concerns on climatic changes and accelerated depletion of fossil fuels raised by the world needs an immediate action to accelerate the clean energy generation with available renewable energy resources (RES). Hence the involvement of alternative energy sources is growing at a faster pace. There are many renewable sources like solar, wind, hydro, geothermal, etc but only a few pertain the adequate potential. Alternative from solar energy for daily needs is one such platform which has immense potential and is universally accessible with least environmental effects. Solar photovoltaic (PV) is a promising solution for extracting solar energy. Along with the growing dependence, there is a thriving need for the development and advancement of the technologies presently on the deck. This is a platform which needs the ultimate attention in the current scenario. This paper focuses on the analysis of the available trends in inverter technology for grid tied solar PV systems to make it fast and reliable thereby reducing losses and mitigating harmonics. Some of the inverter control strategies will be discussed here to improve the overall efficiency of the system by modifying synchronous reference frame (SRF) technique. The adaptive dc link technology is being focussed in all the topologies as it helps in reducing the switching losses in the system.
KEYWORDS : Solar PV, SRFT, Adaptive DC Link

Paper Title

FRAUD DETECTION IN MOBILE RANKING WITH MACHINE LEARNING TECHNIQUES

Abstract

Ranking fraud in the mobile App market refers to fraudulent or deceptive activities which have a purpose of bumping up the Apps in the popularity list. Indeed, it becomes more and more frequent for App develops to use shady means, such as inflating their Apps\' sales or posting phony App ratings, to commit ranking fraud. While the importance of preventing ranking fraud has been widely recognized, there is limited understanding and research in this area. To this end, in this paper, we provide a holistic view of ranking fraud and propose a ranking fraud detection system for mobile Apps. Specifically, we investigate two types of evidences, ranking based evidences and rating based evidences, by modeling Apps\' ranking and rating behaviors through statistical hypotheses tests. In addition, we propose an optimization based aggregation method to integrate all the evidences for fraud detection. The mobile industry is growing rapidly, subsequently the number of mobile apps coming in the market is also increasing. Google Play and Apple are app stores where apps can be downloaded by either paying or they can be downloaded free of cost. Rank of an app is important, as high ranked apps get noticed by customers more easily than those ranked low. In order to get a high rank some developers are resorting to fraudulent means in order to increase their app’s rank. Hence a ranking fraud detection system is required to detect rankings obtained through fraudulent means. We design and develop a ranking fraud detection system to detect fraud ranks.
KEYWORDS : Ranking fraud detection, Reviews, Ranking, Data mining, Mobile applications.

Paper Title

FACE RECOGNITION (FR) WITH HIGH DIMENSIONAL FEATURES ON HIGHER RESOLUTION IMAGES IN CONTEXT TO LESSER DATA LOSS

Abstract

The idea of using a feature with a large dimension for face recognition isn\'t an ideal idea as it can cause difficulties in subsequent training, computation and storage. This hinders further research into the potential use of a dimension feature. This paper will investigate how a highly dimensional feature. We first show empirically that high-dimensionality is crucial for high-performance. A feature with 100K dimensions, based on one type of Local Binary Pattern (LBP) descriptor, is able to achieve significant enhancements over its low-dimensional counterpart as well as the latest technology. The high-dimensional feature feasible. By using our projection technique known as rotated sparse regression models and computation storage can be reduced by more than 100 times without losing quality.
KEYWORDS : facial expression recognition, smile detection, high-dimensional, feature, Census transformation, deep learning.

Paper Title

EXPERIMENTAL STUDY ON EFFECT OF SALT HYDRANTS ON FLAX AND COIR FBRE DEGRADATION

Abstract

Due to environmental concern the natural fibres are gaining more importance because of their eco-friendly nature. Natural fibre is abundantly available in nature, the development of natural fibre composites will lead to the replacement of existing materials in various applications. This paper presents results from an experimental study of the mechanical behaviour of coir and flax fibre reinforced acrylic composites after immersion in seawater. First, in-plane design data are presented. Then, seawater diffusion kinetics are shown, the influence of seawater on design properties is quantified and flexural fatigue performance is described. Finally, the results are compared with those for glass reinforced composites. Seawater saturated specimens show a large drop in stiffness (>50%) due to fibre plasticization, but smaller drops in strength (<30%).
KEYWORDS : Natural Fibre, Coir, Flax, Salt hydrants, Mechanical Properties. Degradation