Showing papers in "International journal of engineering research and technology in 2015"

Comparative Study of Chronic Kidney Disease Prediction using KNN and SVM

Abstract: Chronic kidney disease (CKD), also known as chronic renal disease. Chronic kidney disease involves conditions that damage your kidneys and decrease their ability to keep you healthy. You may develop complications like high blood pressure, anemia (low blood count), weak bones, poor nutritional health and nerve damage. . Early detection and treatment can often keep chronic kidney disease from getting worse. Data Mining is the term used for knowledge discovery from large databases. The task of data mining is to make use of historical data, to discover regular patterns and improve future decisions, follows from the convergence of several recent trends: the lessening cost of large data storage devices and the everincreasing ease of collecting data over networks; the expansion of robust and efficient machine learning algorithms to process this data; and the lessening cost of computational power, enabling use of computationally intensive methods for data analysis. Machine learning, has already created practical applications in such areas as analyzing medical science outcomes, detecting fraud, detecting fake users etc. Various data mining classification approaches and machine learning algorithms are applied for prediction of chronic diseases. The objective of this research work is to introduce a new decision support system to predict chronic kidney disease. The aim of this work is to compare the performance of Support vector machine (SVM) and K-Nearest Neighbour (KNN) classifier on the basis of its accuracy, precision and execution time for CKD prediction. From the experimental results it is observed that the performance of KNN classifier is better than SVM. Keywords—Data Mining, Machine learning, Chronic kidney disease, Classification, K-Nearest Neighbour, Support vector machine.

Dimensional Accuracy and Surface Finish Optimization of Fused Deposition Modelling Parts using Desirability Function Analysis

Abstract: Fused deposition modelling (FDM) machines are increasingly being used to manufacture parts for functional use. The need to ensure that the parts have good surface finish and dimensional accuracy thus exist. The work described in this paper aim to determine the optimum process parameters that can be used to produce parts with both good surface finish and dimensional accuracy. Test parts were fabricated on FDM machine with different factor levels of layer thickness, speed of deposition and fill density. Factorial design of experiment (DOE) and desirability function were used to investigate the optimum factor levels for fabricating parts. The optimum factor levels for dimensional accuracy was observed to be different from that of surface roughness. Optimum process factors levels for minimization of both surface roughness and dimensional accuracy were then determined in this research work. The experimental results was validated by producing parts with the obtained optimum process parameters. Keywords— Fused filament fabrication, desirabiliy function, Polylactic acid, dimensional accuracy, surface roughness

Student Performance Prediction using Machine Learning

Abstract: In this paper, a model is proposed to predict the performance of students in an academic organization. The algorithm employed is a machine learning technique called Neural Networks. Further, the importance of several different attributes, or \"features\" is considered, in order to determine which of these are correlated with student performance. Finally, the results of an experiment follow, showcasing the power of machine learning in such an application. Keywords— Artificial intelligence, machine learning, student performance, neural networks

Smart Garbage Management System

Abstract: With increase in population, the scenario of cleanliness with respect to garbage management is degrading tremendously. The overflow of garbage in public areas creates the unhygienic condition in the nearby surrounding. It may provoke several serious diseases amongst the nearby people. It also degrades the valuation of the area. To avoid this and to enhance the cleaning, ‘smart garbage management system’ is proposed in this paper. In the proposed system, the level of garbage in the dustbins is detected with the help of Sensor systems, and communicated to the authorized control room through GSM system. Microcontroller is used to interface the sensor system with GSM system. A GUI is also developed to monitor the desired information related to the garbage for different selected locations. This will help to manage the garbage collection efficiently. Keywords—IR Sensor; Microcontroller; GSM; GUI

Power Efficient Gathering in Sensor Information Systems based on Ant Colony Optimization (ACO) in WSN

Abstract: Abstract: Wireless Sensor Network has the major constraint of energy resources while they are encountered in the real time applications. Numerous routing techniques have been developed to achieve the maximum network lifetime. Data collection has always been the concerning in terms of the routes being followed for sending data to the Base Station. PEGASIS (Power Efficient Gathering in Sensor Information Systems) is one of the impactful chain based protocol which follows the chain topology to collect data and forwarding it to the next node till it reaches to the Base Station. This protocol proves its significance in the small area network. Leader node selection is one of the areas where PEGASIS finds its scope for improving the network lifetime. Various optimization techniques which are naturally inspired helps in finding out the optimized path to reduce the energy consumption. Here in this paper, Ant Colony Optimization Technique (ACO) has been used. ACO helps in finding out the optimized routes for data transmission. Simulation results show that with used of ACO optimized technique, FND (First Node Dead) is found to be increased by 15% and LND (Last Node Dead) is enhanced by 6 %

A Comparative Study on Egg Shell Concrete with Partial Replacement of Cement by Fly Ash

Abstract: The carbon dioxide produced by cement industries causes environmental pollution and global warming. In 1000Kg of cement manufacturing processes approximately 900Kg of CO2 is emitted. In order to reduce the impact of cement production on atmosphere, waste by products is used as admixture in this study, so that environmental pollution and natural resources consumption is reduced. 75million tones of fly ash which are rich in silica are disposed to landfill as a waste annually in India. Egg shell powders which are rich in calcium are thrown away as a waste. In the present study, these two wastes are used as a partial replacement of cement and various properties like workability, compressive strength, split tensile strength and flexural strength were determined. Egg shell powder are varied upto 12.5% ( 0%, 2.5%, 5%, 7.5%, 10% and 12.5%) and fly ash is added to optimum egg shell powder content cement concrete from 0% to 30% (0%, 5%, 10%, 15%, 20%, 25% and 30%)

Application of Artificial Neural Network in Hydrology- A Review

Abstract: In this research paper exhaustive review is conducted on artificial neural network (ANN) which is employed in the field of hydrological related problems, whereas the conventional approaches are cumbersome and complex in view of computational analysis. Artificial intelligence operation can be well exemplified through application in rainfall-runoff modelling, modelling streamflow, water quality modelling, and application in ground water. A good physical understanding of the hydrologic process being modelled can help in selecting the input vector and designing a more efficient network. This review provides examples for ANN model that provides reasonable accuracy for hydrological problems, and a more effective tool for engineering applications. KeywordsArtificial Neural Network (ANN), Feed Forward, Hydrology, Precipitation, Rainfall-Runoff, Stream-flow.

Impact of Employee Turnover in Small and Medium Construction Firms: A Literature Review

Abstract: The issue of employee turnover has raised quite a number of concerns in the construction industries as a result of its effect on productivity. It is a known fact that employees are important stakeholders in the firm, but unfortunately after limited resources have been used in recruiting, training and developing the employees, they leave for other organizations. Employee's turnover has drained limited resources of small and medium sized construction firms as the services of the lost employees are no longer available to be utilized by the firm. Hence, this research is aimed at assessing the impact of employee's turnover rate in small and medium construction firms in Nigeria. The study adopts a literature review approach to review existing journals in related field so as to arrive at recent findings. However, many of the researches done in this area emphasized on big firms with complex operating structures and strong research and development background. Not much research has examined this concept in the perspective of small and medium sized construction firms. The findings from this study will add to existing body of knowledge in the domain of managing employees in small and medium sized construction firms, thereby increasing job performance and productivity in the sector.

Particle Size and Shape Analysis using Imagej with Customized Tools for Segmentation of Particles

Abstract: Image Processing is becoming important area of study in many industries including food processing, medical science, particle technology, cement industries, powder industries, etc., given the easy of measuring different dimension of particles including size, shape, color (RGB) analysis. Based on the computer algorithms to perform image processing on digital images, it not only allows for accurately measurement of the different physical properties of the object but gives various like size, size distribution, shape factors, color composition of the object very fast and real time analysis is possible. The efficacy of this technique depends on the factors such asimage quality, better noise reduction technique, and good filtration and segmentation techniques. Platforms like Matlab, ImageJ, Olympus, PAXit, etc., are available for the image processing. This work uses the platform ImageJ and a plugin will be developed for the segmentation of the overlapping and touching particles which are difficult to separate through in-built software are works fairly well for the circular particle. In the end, after incorporating this plugin, we will measure the size and shape factors of the different particles Keywords— Digital Images Processing, ImageJ, Binary, Watershed segmentation, etc.

Statistical Analysis and Predicting Kidney Diseases using Machine Learning Algorithms

Abstract: Data mining techniques has been used as a recent trend for achieving diagnostics results, in medical fields such as kidney dialysis. Data mining concepts are used to examine a rich collection of data from different perspectives and deriving useful information. This project intends to diagnosis and prediction system based on predictive mining. This paper covers the essential problems associated with the data mining method and its usage within the medical field. The data has been collected from Visakhapatnam district during 2014 and 2015 with 690 instances and 49 attributes. This has been done in cases of kidney diseases. It was proved that the data mining is applicable within the medical sector and can improve the various medical applications .The K-Means(KM) algorithm is a major role in determine the number of clusters k for large datasets The data mining classification techniques are done based on namely ADT trees, Naïve Bayes , J48 are analyzed on kidney disease data set.

Braking Systems in Railway Vehicles

Abstract: Brake is an essential feature in order to retard and stop the railway vehicle within minimum possible time. This paper presents a discussion about the different braking systems used in railway vehicles. This paper also considers electrodynamic and electromagnetic braking of trains, which is of particular importance in high-speed trains. The calculation for stopping distance for railway vehicle is provided in this study.

Enhancement of Google Earth Positional Accuracy

Abstract: Google Earth is one of many online mapping applications that offer users interactive mapping capabilities It is often being used by academic users as a source for reference or base maps It provides an open source, easy access and cost free image data that support map interest community This contemporary high resolution archive of the Earth's landmass represents a significant, rapidly expanding and largely unexploited resource for scientific inquiry Therefore, many individuals and researchers still use Google Earth as a reliable and accurate data source for mapping applications This issue raises questions about the expected positional accuracy of Google Earth, which is the main interest of the current research In this context, the positional accuracy assessment was not carried out directly on the Google Earth imagery, but on a selected scene for a certain study area that resulted in a corresponding non georeferenced image Then, it is georeferenced with the aid of some control points in order to be compared with a base ground surveying map, on which the accuracy assessment will depend on the coordinates' discrepancies of some selected well-defined check points The results show a significant improvement on the horizontal accuracy, related to all previous similar researches, that finally yields to sub-meters accuracy in the horizontal positions However, this finding can be valid in the place of study, besides coordinates extracted from Google Earth imagery should be used with care caution

Big Data, CEP and IoT : Redefining Holistic Healthcare Information Systems and Analytics

Abstract: Healthcare industry has been a significant area for innovative application of various technologies over decades. Being an area of social relevance governmental spending on healthcare have always been on the rise over the years. Event Processing (CEP) has been in use for many years for situational awareness and response generation. Computing technologies have played an important role in improvising several aspects of healthcare. Recently emergent technology paradigms of Big Data, Internet of Things (IoT) and Complex Event Processing (CEP) have the potential not only to deal with pain areas of healthcare domain but also to redefine healthcare offerings. This paper aims to lay the groundwork for a healthcare system which builds upon integration of Big Data, CEP and IoT. Keywords—Big Data; Internet of Thing; Complex Event Processing; CEP; IoT; Body Sensor Networks; Healthcare

GSM Based Home Automation, Safety and Security System Using Android Mobile Phone

Abstract: In this paper, we will deliberate how to control home appliances, safety and security system using GSM technology by using android application through android mobile phone. We will also show that we can control the appliances even in the absence of an android phone by sending a normal SMS. The advantage of using GSM technology is that we can control the home appliances from remote places anywhere in the world. This system allows the owner to control the appliances and to receive a feedback status of the home appliances by sending instructions in form of SMS as well as through an android application. For the home security system we are using an antitheft reporting system which will report the owner by ringing an alarm and by sending an SMS. Also for the safety system in case of fire or gas leakage it will report the owner by sending a SMS and also by ringing an alarm. Thus by using GSM technology, it provides the wireless access to the devices to be controlled.

Sensor Based Automated Irrigation System

Abstract: In a country like India, the agriculture plays the important role in the economy and development of the country. In the field of agriculture, use of proper method of irrigation is important and it is well known that irrigation by drip is very economical and efficient. At the present era, the farmers have been using irrigation technique in India through the manual control in which the farmers irrigate the land at the regular intervals. This process sometimes consumes more water or sometimes the water reaches late due to which the crops get dried. Over-irrigation can increase energy consumption and water cost as well as leaching of fertilizers below the root zone, erosion, and transport of soil and chemical particles to the drainage ditches. Irrigators who monitor soil moisture levels in the field greatly increase their ability to conserve water and energy, optimize crop yields, and avoid soil erosion and water pollution. The objective of this paper is to develop sensor based automated irrigation system to reduce water requirement and increase the productivity of orange orchard in Vidarbha region. This system is best suited for places where water is scarce and has to be used in limited quantity. Also, third world countries can afford this simple and low cost solution for irrigation and obtain good yield on crops. Keywords— Irrigation, Sensors, Soil moisture

Assessing Ground Water Quality using GIS

Abstract: Groundwater is an important component of our nation’s fresh water resources. It plays a key role in meeting the water needs of various user-sectors in the nation. The natural resource cannot be optimally used and sustained unless the quality of water is assessed. In the present study, the impact of mining activities on groundwater quality around the Korba coalfields covering an area of 530 sq.km which lies between latitudes 22°15′ and 22°30′N and longitudes 82°15′E and 82°15′E in the state of Chhattisgarh, India was carried out. For the study, data collection includes maps, toposheets, water quality data, well locations, mining lease areas, village locations etc. The above said data has been collected from various government departments of Chhattisgarh. After the data collection, base map has been prepared using ArcMap 9.3. The water quality database is analyzed and then used as attribute database for the preparation of thematic maps showing distribution of various water quality parameters. Water Quality Index has been calculated for various parameters such as pH, Turbidity, Total hardness(TH), Chloride, Total dissolved solids(TDS), Calcium, Nitrate, Iron, and Fluoride. Water Quality Index map is also developed. The results obtained are presented in the form of maps, used for better understanding of present water quality scenario of the study area. Analysis reveals that the groundwater of the region needs field specific treatment before put to use.

SQL to SPARQL Mapping for RDF querying based on a new Efficient Schema Conversion Technique

Abstract: In this paper we give an algorithm for querying RDF data using SQL without conversion of RDF instances. This algorithm translates an SQL query into an equivalent SPARQL query that is to be directly executed on the RDF data and allows it for SQL users to efficiently and easily query the RDF data. The SQL queries are formulated based on the converted relational database schema that the algorithm builds from the RDF one. In this algorithm not only simple SQL queries are considered but also complex ones such as those with UNION, INTERSECT or EXCEPT expressions. Keywords— RDB, RDF, SQL, SPARQL, Query translation

Arduino Based Smart RFID Security and Attendance System with Audio Acknowledgement

Abstract: there has been emerging demand for secure system that must be reliable and fast responded for the industries and company. RFID (Radio Frequency Identification) is one of the reliable and fast means of identifying any material object. Their significant advantage are that they can read wirelessly, contain more information than barcode and more robust in nature and based on non-line-of-sight technology. RFID tags can read in any environmental challenging conditions where other read technology likes barcode or optical card reader useless. In this paper we purposed a secure system that provides information about authorized and unauthorized persons. In this system when card brought near to the RFID module it reads the card information and it compare with the data in the program memory and displays authorized or unauthorized entry. The door opens for authorized entry and marked the attendance corresponding to that code id and save in excel sheet format in SD card and after that display it’s all information on the LCD like name and employee code number that link with authorize entry and welcome message with audio greetings by taking their name which is already saved into SD card and for unmatched entry the gate remain closed and alerts the security person through SPEAKERS by playing the separate audio file saying entry is unauthorized. Keywords— Automatic Identification and Data Capture technologies (AIDC), Liquid Crystal Display(LCD), RFID Reader, RFID Tag, Proximity Integrated Circuit Card(PICC).

Loan Credibility Prediction System Based on Decision Tree Algorithm

Abstract: Data mining techniques are becoming very popular nowadays because of the wide availability of huge quantity of data and the need for transforming such data into knowledge. Techniques of data mining are implemented in various domains such as retail industry, telecommunication industry, biological data analysis, intrusion detection and other scientific applications. Data mining techniques can also be used in the banking industry which help them compete in the market well equipped. In this paper we introduce an effective prediction model for the bankers that help them predict the credible customers who have applied for loan. Decision Tree Induction Data Mining Algorithm is applied to predict the attributes relevant for credibility. A prototype of the model is described in this paper which can be used by the organizations in making the right decision to approve or reject the loan request of the customers. Keywords— Decision Tree; Credit Risk Assessment; Classification; Prediction; Attribute Selection

Comparison of ACO-OFDM and DCO-OFDM in IM/DD Systems

Abstract: In this paper the two Optical Wireless orthogonal frequency division multiplexing (OFDM) techniques in intensity modulated/direct detection (IM/DD) optical systems are compared. These are asymmetrically clipped optical OFDM (ACO-OFDM) and DC biased optical OFDM (DCO-OFDM). The comparison is done by the analysis of BER versus SNR of ACO-OFDM and DCO-OFDM for intensity-modulated directdetection systems. DCO-OFDM is less efficient in terms of optical power than ACO-OFDM for lower SNR value. But for higher SNR values it is power efficient. This is because the DC bias used in DCO-OFDM is inefficient in terms of optical power, while the use of only half of the subcarriers to carry data in ACO-OFDM is inefficient in terms of bandwidth. Keywords—ACO-OFDM, DCO-OFDM, IM/DD, optical systems.

Heat Transfer and Friction Characteristics of Solar Air Heater Duct Roughened by Broken Arc Shaped Ribs Combined with Staggered Rib Piece

Abstract: Thermal performance of solar air heater has been found to be substantially improved by the application of artificial roughness provided on underside of absorber surface. The present investigation was taken up to study the effect of broken V-rib roughness combined with staggered ribs on heat transfer and friction in a flow through artificially roughened solar air heater duct. This work covered a range of Reynolds number (Re) 3000–17 000, relative staggered rib pitch (p′/p) 0.2–0.8, relative staggered rib size (r/e) 1–2.5, relative gap position (s′/s) 0.2–0.8 for the fixed values of relative roughness pitch (p/e) of 10, relative roughness height (e/Dh) of 0.043, relative gap size (g/e) of 1, and angle of attack (α) of 60°. Experimental data pertinent to heat transfer and friction was generated and thermohydraulic performance was determined for different sets of roughness and flow parameters.

Analysis of Crack Detection of A Cantilever Beam using Finite Element Analysis

Abstract: This paper describes finite elemental analysis of a cracked cantilever beam and analyzes the relation between the modal natural frequencies with crack depth, modal natural frequency with crack location. Also the relation among the crack depth, crack location and natural frequency has been analyzed. Only single crack at different depth and at different location are evaluated and the analysis revels relationship between crack depth and modal natural frequency. As we know when a structure suffers from damage its dynamic property can change and it was observed that crack caused a stiffness reduction with an inherent reduction in modal natural frequencies. Consequently it leads to change in dynamic response of the beam. The analysis was performed using ANSYS software. The material of the beam is taken as aluminum. The proposed technique represents actually a modal analysis having great benefits for health monitoring of structures. For this 3D model of cantilever beam with single crack is created in ANSYS. Total 49 model of crack cantilever beam has been analyzed. Thus result obtained from ANSYS software we can draw the graph of modal natural frequency Vs crack depth for constant crack location and modal natural frequency Vs crack location keeping crack depth constant. And finally the value obtained from ANSYS is checked with result obtained from analytical method.

Modelling and Control of Coupled Tank Liquid Level System using Backstepping Method

Abstract: The level and flow control in tanks are the heart of all chemical engineering system. The control of liquid level in tanks and flow between tanks is a basic problem in the process industries. Many times the liquids will be processed by chemical or mixing treatment in the tanks, but always the level of fluid in the tanks must be controlled and the flow between tanks must be regulated in presence of non-linearity, disturbance and time varying system parameters. This work introduce the approach of modelling and compute a level backstepping control strategy with pure feedback form for non-linear modelled coupled tanks system.The goal of the control algorithm is to track the desired level of liquid in second tank by using flow rate of liquid into first tank as the manipulated variable. The designed non-linear controller is capable of tracking the desired water level for all set points with high degree of accuracy, maximally fast and without significant overshoot. Keywords---Backstepping, Coupled tank, Non-linear model, Process control

Lean Manufacturing: An Approach for Waste Elimination

Abstract: Lean Manufacturing (LM), a manufacturing system and philosophy, was originally developed by Toyota, Japan and is now widely practiced by many manufacturers throughout the world. Lean manufacturing is a systematic approach to identifying and reducing waste (non value-added activities) through continuous improvement by flowing the product at the pull of the customer in pursuit of perfection. LM is important, primarily because of waste reduction and reduction in lead time. The objective of this paper is to identify Lean manufacturing practices in small scale industries. For this purpose some case studies were chosen and critical observations are identified. Some of these annotations are improper utilization of resources, quality tools for improvements and improper plan for location and layout. This paper includes one case study with the initiatives, observations, results and conclusions of the study carried out in a small scale industry.

Land Cover Classification using Support Vector Machine

Abstract: In modern changing world, it is very important to track the current status of Earth surface for geological and ecological point of view. It can be performed by collecting information about various surface types using high definition satellite sensors and airborne SAR (Synthetic Aperture Radar) sensors. In this aspect, Hyperspectral imaging plays an important role for the classification of different land cover types due to it’s rich information content. In this paper, we have extracted spatial and spectral features from Samson hyperspectral image and designed a model that can perform classification task. Initially, we performed unsupervised learning which provides a good understanding about the dataset. We prepared training data under supervised learning and testing is done to verify the accuracy of the proposed model. Support Vector Machine (SVM) is employed for automatic classification of various land cover types and overall accuracy is found to be more than 90 % almost in all cases. Keywords—Hyperspectral data, Remote sensing, Support Vector Machine

A Study on Outrigger System in a Tall R.C Structure with Steel Bracing

Abstract: Tall building development has been rapidly increasing worldwide introducing new challenges that need to meet through engineering judgment. As the height of the building increases the stiffness of the building reduces. Therefore to improve the performance of the building under seismic loading, outrigger system is proposed in the present study of work. In the present work, contains a comparative study on regular building with and without outrigger and irregular building with and without outrigger with centrally rigid shear wall and steel bracings as outrigger. The modeling of the structure is done using “ETABS” program. The analysis of the model is carried out by equivalent static method and response spectrum method. The stiffness and efficiency characteristics of the structure is measured in terms of lateral displacement, drift, base shear and fundamental natural period for different types of buildings to provide stiffness against static and dynamic loads. The parameters should be minimized to prevent damage to the buildings. Keywords—Tall building; regular and irregular building; lateral displacement; base shear; fundamental natural period