Efficiency Analysis of Genetic Algorithm and Genetic Programming in Data Mining and Image Processing

Today, in the age of artificial intelligence and machine learning, Data mining and Image processing are two important platforms. GA and GP are value based and program based randomized searching tools respectively and these two are very much useful in the fields' data mining and image processing for handling different issues. In this chapter, a review is made on ability of GA and GP in some applications of these two fields. Here, the selected subfields of data mining are market analysis, fraud detection, risk management, sports analysis, protein interaction, classification of data, drug discovery and feature construction. The similar in image processing are enhancement and segmentation of images, face recognition, photo mosaic generation, data embedding, image pattern classification, object detection and Graphics Processor Unit (GPU) development. The efficiencies of GA and GP in these particular applications are analyzed with corresponding parameters, comparing with other non-GA and non-GP approaches of the corresponding subfields.

Process Optimization in Non-Conventional Processes

Conventional machining becomes non-efficient and non-effective in case of intricate shape and also while working with hard metals and alloys due to excessive tool wear. In such situations non-conventional machining, in contrast becomes more appropriate due to non-contact between tool and work-piece. In the present study, EN31 steel was machined using Plasma Arc Cutting with pre-defined process parameters. Material Removal Rate and Surface roughness were considered as responses for the study. The responses were optimized both as single and multi-response. Considering the complexities of this present problem, experimental data were generated and the results were analyzed by using Taguchi, Grey Relational Analysis and Artificial Bee Colony (ABC) Algorithm. Responses variances with the variation of process parameters were thoroughly studied and analyzed and ‘best optimal values' were identified. The result were verified by the morphological study. It was observed that there was an improvement in responses from mean to optimal values of process parameters.

Modelling and Optimization of End Milling Process Using TLBO and TOPSIS Algorithm

To assure desire quality of machined products at minimum machining costs and maximum material removal rate, it is very important to select optimum parameters when metal cutting machine tool are used. Minimum Surface Roughness (Ra) is commonly desirable for the component; however Material Removal Rate (MRR) should be maximized. This chapter presents an approach for determination of the best cutting parameters precede to minimum Ra and maximum MRR simultaneously by integrating Response Surface Methodology with Multi-Objective Technique for Order Preference by Similarity to Ideal Solution and Teaching and learning based optimization algorithm in face milling of Al-6061 alloy. 30 experiments have been conducted based on RSM with 4 parameters, namely Speed, Feed, Depth of Cut and Coolant Speed and three levels each. ANOVA is performed to find the most influential input parameters for both MRR and Ra. Later the multi-objective attribution selection method TOPSIS and multi objective optimization method TLBO is used to optimize the responses.

Prediction of Water Quality Indices by Using Artificial Neural Network Models

Conventionally, fixed techniques are used for prediction of future time-series data. Subsequently adaptive techniques are used to forecast improved future data. The adaptive techniques are essentially based on ANN and fuzzy logic techniques. It is observed that these techniques also perform poorly when the input data set available is less and when there is abrupt change in the input data set. In this paper the proposed hybrid technique is based on data farming for intermediate data generation and the ANN model for better learning and forecasting. The performance of the proposed model has been tested with actual pertaining to water quality indices of various water samples collected from different sources.

Development of Hybrid Cellulose Bio Nanocomposite From Banana and Jute Fiber

In the era of globalization and industrialization the concern is limited only in development, without taking the environment into consideration this leads to global warming and big ecological changes in recent year. The material like Synthetic materials used in many applications due to ease of fabrication and higher strength, but the major disadvantage with it is, its neither recyclable nor bio-degradable. Therefore, the researchers develop a new material and technique for the sustainable development. A lot of researches were carried out in the reinforcing potential in the polymer matrix composite, reinforcing can be of two kinds synthetic and natural fiber. Natural fiber is gaining importance in the last decade due to its ecofriendly nature and does not leave carbon foot print, for better utilization of banana and jute fiber for making value added products. Hence, in this work the objective is to develop a new class of hybrid nano-materials from natural fiber such as banana and jute fiber. This chapter sees an opportunity of enhancement of interface property.

Prediction of Hardness Distribution in Plasma Arc Surface Hardening Using Neural Network

In this chapter, an attempt has been made to develop neural network models to predict the hardness distribution of hardened zone in plasma arc surface hardening process. The back propagation method with the Levenberg-Marquardt algorithm was used to train the neural network models. Hardness distributions were collected by the experimental setup in the laboratory and the associated data were used to train the neural network models. Furthermore, the prediction of neural network models were compared with those obtained from a statistical regression models. It is confirmed experimentally that the hardness distribution can be accurately predicted by the trained neural network models. The accuracy of hardness distribution prediction using neural network is superior to that using other statistical regression models.

Modeling of Polypropylene Modified Bitumen Mix Design Results Using Regression Analysis

This study investigates the effects of mixing Polypropylene waste plastics in the bituminous mix for the design of Flexible Pavement. Since, obtaining Marshall Test results from the bituminous mix is time-consuming, so if the practitioners measure the values of stability and flow by mechanical testing, other computations can be done by applying simple mathematical calculations. So, this study carried out stability and flow tests on different specimens made with varying bitumen and polypropylene plastic content. From the initial test results, the optimum bitumen and plastic contents are found. Further, the test results obtained from Marshall Test are modelled by identifying various input variables, which are various physical properties of the mix such as plastic content, bitumen content, air voids and unit weight. The regression modeling framework is adopted in this study to predict the Marshall stability and flow value. Since the developed models have yielded good results, these can be effectively used in parameter estimation, and thus aids the future researchers.

Optimizing the Electrical Discharge Drilling Process for High Aspect Micro Hole Drilling in Die Steel

Electric discharge drilling (EDD) is a thermo erosion process used to produce holes in high strength materials for various applications such as fuel injector, medical devices, turbine blades cooling channels etc. In this chapter, high aspect micro holes are drilled in die steel (of thickness 15 mm) using tubular electrodes of diameter 500µm. Using Taguchi' design of experiment method, four process parameters namely electrode material, discharge current (Ip), pulse on time (Ton) and pulse-off time (Toff) are investigated and optimized for two performance characteristics namely drilling rate (DR) and electrode wear rate (EWR). DR and EWR are opposite in nature, i.e. DR is higher the better type of characteristics while EWR is lower the better type of characteristics. Using Grey relational analysis (GRA) along with Taguchi method, both the characteristics are optimized simultaneously. Through GRA, grey relational grade has been computed as a performance index for predicting the optimal parameters setting for multi machining characteristics.

Modeling and Simulation of Surface Texture for End-Milling Process

Analysis and simulation of manufacturing process require extensive and complicated computations. Nowadays, computer resources and computational algorithms reach to the state that can model and simulate the problem efficiently. One of the important processes in manufacturing is machining. In this research end-milling process which is one of the complex and wide-spread processes in machining is chosen. Most important parameters in end-milling are surface roughness and surface location errors. A comprehensive simulation software is developed to model end-milling process in order to anticipate finishing parameter such as surface roughness and errors. The proposed algorithm takes into account cutting conditions, such as feed, doc, woc, tool run out, etc. In addition, dynamic simulation module of the software can accurately model flexible end-mill tool, the milling cutting forces and regeneration of waviness effects. The software can accurately determine the most commonly used index of surface roughness parameters such as Ra, P.T.V. and surface errors.

Artificial Intelligence

This chapter explains the Artificial Intelligence (AI) techniques in terms of Artificial Neural Networks (ANNs), fuzzy logic, expert systems, machine learning, Genetic Programming (GP), Evolutionary Polynomial Regression (EPR), and Support Vector Machine (SVM); the AI applications in modern education; the AI applications in software engineering development; the AI applications in Content-Based Image Retrieval (CBIR); and the multifaceted applications of AI in the digital age. AI is a branch of science which deals with helping machines find the suitable solutions to complex problems in a more human-like manner. AI technologies bring more complex data-analysis features to the existing applications in various industries and greatly contribute to management's organization, planning, and controlling operations, and will continue to do so with more frequency as programs are refined.