Journal of Advanced Computing, Communication and Technologies
Journal of Advanced Computing, CommunicatiOn &
Volume 4 - Issue 1
- Analysis and Differentiation of Music for Predominant Instrument Recognition using Neural Network
Deepa. N and Sulthan Ibrahim.M
ABSTRACT: Music retrieval becomes dominant in Jukeboxes and sound systems. As the interest of listeners is varying time to time and based on other factors like environment, psychology, etc. Identifying the type of music category helps the sound provider and listener to make their interest of choice. This paper presents a software methodology based on spectrum analysis and neural network which classifies the category of music based on known features. Several audio classifications are presented and the results are obtained on audio framing, spectrum analysis, feature extraction and classification on machine learning approach.
- Asynchronous and Asymmetric Neighbor Discovery Method based on Distributed Topology Control Algorithm for Energy Efficient Low-Power IoT Communication Networks
Gomathi. P and Baby Deepa.V
ABSTRACT: Topology control is one of the unique method which deals with traditional wireless networks. It ensures that the connectivity of nodes be present in a network. The wireless nodes are provided with limited energy like battery. To ensure this, an algorithm is been proposed in this paper, which discover the neighboring nodes. The proposed algorithm consists of distributed topology control algorithm by merging the combinatorial block design from a design theory with the multiples of 2. This technique discovers specifically asynchronous and asymmetric neighbors. To analyze energy consumption of proposed design, the energy consumed by worst case discovery latency is compared with each discovery latency at given duty cycle. The proposed technique find neighbors quickly with minimum battery power compared with other protocols for distributed topology control. For future scope, should concentrate on some other parameter with multiple of certain number.
- A Hybrid Signal Analysis Methodology for BSN Healthcare Based Secure IoT Communication
Arul Vyiya.K.G and Kumar.S.R
ABSTRACT: Electrocardiogram (ECG) is noninvasive technique used in most of Heart Arrhythmia. The ECG signal provides required information about the electrophysiology condition of the heart. It detects the disease and ischemic changes in the heart. This helps the physician to make correct interpretation of the disease. They calculate parameters to determine whether the ECG shows signs of cardiac disease or not. The data can be through internet and stored in a cloud. Analyzing historical data is often the first step in understanding data intend to use in real time. Performing few statistics on ECG data to find anomalies, and may also need to clean up data by removing bad data points or filtering out noise. In this paper a method to perform filtering and re-sampling data, applying basic statistics on data, and machine learning techniques to perform classification, regression and clustering analyses which are common tasks in IoT is presented. The proposed method is based on support vectors which classifies the signal into normal and abnormal signal.
- A Novel Method for the extraction and classification of Tumor features in MRI Imaging
Indhumathi.R and Ravikumar Gurusamy
ABSTRACT: A new method for the extraction and Tumor detection on MRI images is presented in this paper. An MRI images helps the physician to study and diagnose the disease present in the brain. The MRI image acquired from the machine is subjected to analysis in the work. The real time data is used for the analysis. Basic preprocessing is performed using median filter followed by a Rician Noise removal. The de-noised image is segmented and the feature extractions are performed. The features are extracted using coiflet wavelet which is suitable for MRI images. The features are given to the classifier which uses Binary tree SVM classification.
- Embedded Based Safety Management and Dynamic Driving Control System for Automated Vehicles
Kalpana.A and Baby Deepa. V
ABSTRACT: The proposed design proposes an embedded based safety management and dynamic driving control system for modern vehicles in urban scenarios. The proposed method consists of an input sensing unit, controlling unit and displaying unit. The ultrasonic sensor, IR sensor and vibration sensor are used to monitor and control the road condition. The system also sense the opposite vehicle movement. The current status of the vehicle movement and obstacle detection is displayed in the LCD unit which is connected in the automobile system. The ATmega16 microcontroller forms the controlling unit in the proposed method. The AVR Studio is used to develop the system. The proposed method helps the drivers to drive their vehicle with safety.
- Comparative survey on Association Rule Mining Algorithms
ABSTRACT: Association Rule Mining (ARM) has been the area of interest for many researchers for a long time and continues to be the same. It is one of the important tasks of data mining. It aims at discovering relationships among various items in the database. Association rule mining has become particularly popular among marketers. In fact, an example of association rule mining is known as market basket analysis. The task is to find which items are frequently purchased together. This knowledge can be used by professionals to plan layouts and to place items that are frequently bought together in close proximity to each other, thus helping to improve the sales. Association rule mining finds out item sets which have minimum support and are represented in a relatively high number of transactions. These transactions are simply known as frequent item sets. The algorithms that use association rules are divided into two stages, the first is to find the frequent sets and the second is to use these frequent sets to generate the association rule. In this paper the application in the ARM, advantages, disadvantages of these algorithms have been studied. The objective of this paper is to present a review on the basic concepts of ARM technique along with the recent related work that has been done in this field.
- Energy Efficient Partitioning Scheduling Approach for Scientific Workflow in the Cloud
Nandhini.C and Mohana Priya.M
ABSTRACT: Cloud computing is a growing technique that has reconstruct services offered by Information Technology. This technique has modified the method storing and handling of data for scalable, real time, Internet based applications and resources satisfying end user’s requirement. In past two decades power consumption is the important parameter to be considered for computing resources. In proposed design all possible areas which cause energy consumption are investigated and less power consuming method is addressed. The proposed method is designed for less power utilization without compromising Quality of Service (QoS) and overall performance.
- Algorithms Comparative Survey on Classification Algorithms
SriMaha Saranya saravanan.S and Banumathi.A
ABSTRACT: Data Mining or Knowledge Discovery is the latest emerging trend in the information technology. It is the process of analyzing data from different perspectives and summarizing it into useful information. One of the function of data mining is classification, is a process of generalizing data sets based on different instances. There are various classification techniques which help as to group the data sets. Several major kinds of classification algorithms including C4.5, ID3, Naive Bayes, SVM, k-nearest neighbor, Decision Tree, ANN are used for classification. This paper provides a Comparative study of different classification algorithms and their advantages and disadvantages.
- An Efficient Water Usage Drip Irrigation System for Multiple Crop Cultivation based on IoT
Sathiyapriya. K and Banumathi. A
ABSTRACT: Agriculture is a backbone of Indian Economy. Nowadays, many modern agricultural systems are developed. Internet plays a vital role in the agricultural world. The proposed design presents a combination of autonomous agricultural control system with Internet which makes the agriculture process through Internet of Things (IoT). An IoT based drip irrigation system is proposed for multiple crop cultivation. The proposed design uses a Raspberry Pi IoT module to control the unit. Soil moisture sensor, Temperature sensor and Light sensor monitor the moisture content, temperature and illumination status respectively. The current status of the sensing and controlling unit will be updated to the user via TCP Tool. Python 2.7.9 is used as front end design.
- Simulators for Vehicular Adhoc Network (VANET) Development
Unnamalai. L and Mohana Priya.M
ABSTRACT: The rapid growths of on-road vehicles are the key factor of accidents. In that most of accidents are caused by human mistakes. To reduce this, a method is proposed based on vehicular adhoc networks (VANET). Networking and mobility are the important parameters while designing a VANET. In proposed design mobility Components are focused and discussed. MATLAB and simulation of urban mobility (SUMO) are further used for VANET simulation. On other hand TraC14 MATLAB (Application programming interface) developed in MATLAB which provides communication between all application written in MATLAB and SUMO.