International Journals

Permanent URI for this collectionhttps://dspace.psgrkcw.com/handle/123456789/164

Browse

Filters

2012 - 201921

Settings

Author: search.filters.author.Arunpriya CHas files: Yes

Search Results

Now showing 1 - 10 of 21
  • No Thumbnail Available
    Item
    ASSESSING FOOD VOLUME AND NUTRITIOUS VALUES FROM FOOD IMAGES USING DECISION TREE APPROACH
    (International Research Journal of Engineering and Technology, 2019-12) Gopiga T; Arunpriya C
    Obesity and being overweight have become growing concerns due to their association with many diseases, such as type II diabetes, several types of cancer and heart disease. Thus, obesity treatments have been the focus of a large number of recent studies. Because of these studies, researchers have found that the treatment of obesity and being overweight requires constant monitoring of the patient’s diet. One of the important steps in the success of healthy diet is measuring food intake each day. One of the challenges in obesity management studies is measuring daily food consumption for obese patients. Countless recent studies have suggested that using technology like smart phones may enhance the under-reporting issue in dietary intake consumption. In this thesis, we propose a Food Recognition System (FRS) for calories and nutrient values assumption. The user employs the built-in camera of the smart phone to take a picture of any food before and after eating. The system then processes and classifies the photographs to discover the kind of food, portion size and then uses the knowledge to estimate the quantity of calories within the food using decision tree. An essential step in the system as it is used to estimate and calculate the food volume and amount of calories in the image
  • No Thumbnail Available
    Item
    CLOUD COMPUTING HYBRID SECURITY FROM SINGLE TO MULTI CLOUD SERVERS
    (Iconic Research and Engineering Journals, 2019-12) Deepika K; Deepika M; Arunpriya C
    Nowadays, storing and accessing data in multi-cloud infrastructure is a common solution adopted by large organizations. In this paper it presents two components mainly Administration Management and User Management. It contains the list of branches available for the bank in different countries and tree view which shows the country names under each country created. End User has manifested by administrator with the ability to identify and control the state of users logged into the account. The saving/current account holders can check person’s own account balance; list of transactions done by the user, account personal information can be edited efficiently by giving request to the admin. The account holder can view that information only with the unique user id and password provided by the bank. After those process completed successfully a message will be displayed to the user about the transaction. If the account holder provides the wrong user ID or Password it will provide an error. If the intruder deletes the database, the database will be backed up by checking the nearest server, traffic and available storage of the multi-server. The encrypted key will be received immediately by the admin through mail to restore the deleted database. Data security for such a cloud service encompasses several aspects including secure channels, access controls, and encryption. And, when it considers the security of data in a cloud, it also must consider the security triad such as: confidentiality, integrity, and availability. In the cloud storage model, data is stored on multiple virtualized servers.
  • No Thumbnail Available
    Item
    BREAST CANCER DETECTION USING BPN CLASSIFIER AND GREY LEVEL CO-OCCURRENCE MATRIX
    (International Journal for Science and Advance Research In Technology, 2019-12) Gayathri J; Arunpriya C
    This paper describes a computer-aided detection and diagnosis system for breast cancer, the most common form of cancer among women, using mammography. The system relies on the Multiple-Instance Learning (MIL) paradigm, which has been proven useful for medical decision support in previous works. In the proposed framework, the initial step is Partitioning; breasts are first partitioned adaptively into regions. The Grey level cooccurrence Matrix (GLCM) Features are extracted from wavelet sub bands. Then, features derived from the appearance of textural features as well as detection of lesions (masses and micro calcifications) are extracted from each region and combined in order to classify it into examinations of mammography as “normal” or “abnormal”. Whenever an abnormal examination record is detected, the regions that induced the automated diagnosis can be highlighted. There arise two strategies to define this anomaly detector. In a first scenario, manual segmentations of lesions are used to train an NN that assigns an anomaly index to each region; local anomaly indices are then combined into a global anomaly index.
  • No Thumbnail Available
    Item
    WEB DATA CLASSIFICATION USING SUPPORT VECTOR MACHINE BACK PROPAGATION NEURAL NETWORK
    (International Journal of Recent Technology and Engineering, 2019-09) Arunpriya C
    These days, the development of World Wide Web has surpassed a lot with extra desires. Extraordinary arrangement of content reports, transmission records and pictures were reachable inside the web it's as yet expanding in its structures. Information handling is that the style of removing information's realistic inside the web. Web mining could be a piece of information preparing that identifies with differed examination networks like data recovery, bearing frameworks and artificial insight. The data's in these structures are very much organized from the beginning. This web mining receives a great deal of the date mining procedures to discover most likely supportive data from web substance. The ideas of web mining with its classifications were examined. The paper chiefly focused on the web Content mining undertakings along the edge of its procedures and calculations. In this paper we proposed AI calculation based order .SVM_BPM calculation grouped the web content information and thought about existing calculations our proposed arrangement calculation is high effective and less time calculation.
  • No Thumbnail Available
    Item
    OPTIMAL PLACEMENT OF PICOCELLS TO ENHANCE THE PERFORMANCE OF ENERGY AWARE TRAFFIC OFFLOADING FOR GREEN HETEROGENEOUS NETWORKS
    (International Journal of Advanced Research in Computer Science, 2018) Devi Gayathri N; Arunpriya C
    Traditional macro-cell networks are experienced an increase of data traffic and small-cells are deployed help to offload the traffic from macro-cells. The Energy Aware Traffic Offloading for Green Heterogeneous Networks (EATOG) approach is analyzed on grid power saving by offloading traffic for green heterogeneous networks to increase the efficient utilization of harvested energy for on-grid power saving while satisfying the Quality of Service (QoS) requirement. The EATOG is mainly intends to of energy-aware traffic offloading for HCN with multiple Small cell Base Station (SBS) powered by diverse energy sources which reduces the on-grid network power consumption while satisfying the QoS requirement in terms of rate outage probability. The performance of energy consumption is degraded due to the Overlapped Small Cell Based Stations. An optimal deploying low power node within macrocell coverage area is proposed in this paper to improve the system utility while minimizing the installation cost. The proposed Optimized Energy Aware Traffic Offloading for Green Heterogeneous Networks (OEATOG) approach is considers the inter-cell interference and the configuration of Almost Blank Sub-frames (ABS) when maximizing the system utility. The proposed paper deals with the placement of Pico Base Station within the macro cell in LTE (Long Term Evolution) heterogeneous networks. A Pico Cell is a small cellular Base Station (BS) which supports low power nodes and offers greater capacity and coverage areas. Furthermore the heuristic algorithm is introduced too efficiently solve the formulated problem and obtain the optimal picocell placement. The simulation results indicate that the proposed algorithm is to improve the utility of the network, especially in regions with high traffic density, while maintaining the installation cost at a reasonable level.
  • No Thumbnail Available
    Item
    STUDY AND ANALYSIS OF ENERGY UTILIZATION GREEN HETEROGENEOUS NETWORKS
    (International journal of Modern Trends in Engineering and Science, 2017-11) Devi Gayathri N; Arunpriya C
    The most promising approach for International Mobile Telecommunication (IMT) Advanced is the Heterogeneous Networks (HetNets). It is an advanced network topology that cooperates between multiple tiers of base stations such as macro, micro, pico, femto and relay base stations. By intelligent interference management, HetNets exploits frequency reuse to its maximum, and provides high data rate coverage everywhere. However, existing research on HetNets has focused mostly on the high data rate aspects, but rarely on the energy efficiency aspects. In this paper analysed both energy and power consumption in green heterogeneous networks. Energy-efficiency is one of the major design goals in Green Heterogeneous Networks (Green-HetNets), has received much attention lately, due to increased awareness of environmental and economic issues for network operators. This paper is analyzed various green HetNets techniques such as two level dynamic schemes, multi objective optimization problem (MOP), Green energy aware and latency aware (GALA), area green efficiency (AGE), area spectral efficiency (ASE), centralized and distributed heuristic algorithm and two stage energy aware traffic off loading (TEATO) to achieve the required energy consumption while providing the required data rate increased based on their merits, demerits and metrics.
  • No Thumbnail Available
    Item
    FORECASTING VEGETABLE PRICE USING TIME SERIES DATA
    (International Journal of Advanced Research, 2016-05) Subhasree M; Arunpriya C
    Predicting the vegetable price is essential in agriculture sector for effective decision making. This forecasting task is quite difficult. Neural network is self-adapt and has excellent learning capability and used to solve variety of tasks that are intricate. This model is used to predict the next day price of vegetable using the previous price of time series data. The three machine learning algorithms are incorporated in this work namely Radial basis function, back propagation neural network and genetic based neural network are compared. The models are assessed and it is concluded from the derived accuracy that the performance of genetic based neural network is better than back propagation neural network and radial basis function and improves the accuracy percentage of vegetable price prediction.
  • No Thumbnail Available
    Item
    VEGETABLE PRICE PREDICTION BASED ON TIME SERIES ANALYSIS
    (International Journal of Computer Science and Information Technology & Security, 2015-12) Subhasree M; Arunpriya C
    Predicting the price vegetable is vegetable is essential in agriculture sector for effective decision making. This forecasting task is quite difficult. Neural network is self adapt and has excellent learning capability and used to solve variety of tasks that are intricate. The two machine learning algorithms namely back propagation neural network and genetic based neural network are compared in this work. The models are assessed and it is concluded from the derived accuracy that the performance of genetic based neural network is better than back propagation neural network percentage of prediction is derived.
  • No Thumbnail Available
    Item
    FUZZY INFERENCE SYSTEM ALGORITHM OF PLANT CLASSIFICATION FOR TEA LEAF RECOGNITION
    (Indian Journal of Science and Technology, 2015) Arunpriya C; Antony Selvadoss Thanamani
    Background/Objectives: Biologists found that the morphological, physiological, bio-chemical and molecular methods of plant identification are found to be laborious and require great amount of technical knowledge. This research paper concentrates on the identification of varieties of tea using leaf images. It aims to identify the species in an easy and an accurate manner. Methods/Statistical analysis: The phases involved in this work are image pre processing, feature extraction and classification. Three classification algorithms such as Fuzzy Inference system, Radial basis function network and K-nearest neighbour were used and optimized to achieve a better accuracy and execution time. Results/Findings: The classification algorithm K-nearest neighbor, Radial basis function neural network and Fuzzy Inference System are trained with 40 samples and tested using 20 samples. Conclusions: Fuzz
  • No Thumbnail Available
    Item
    A NEW FRAMEWORK FOR TEA PLANT RECOGNITION USING EXTREME LEARNING MACHINE WITH VERY FEW FEATURES
    (International Journal of Applied Engineering Research, 2015) Arunpriya C; Antony Selvadoss Thanamani
    Due to more and more tea varieties in the current tea market, rapid and accurate identification of tea varieties is crucial for tea quality control. Tea quality mainly depends on the variety of leaf, growing environment, manufacturing conditions, size of ground tea leaves and infusion preparation. In the past few years, tea cultivar has been assessed by morphological assessment coupled with pattern recognition. This paper uses an efficient machine learning approach called Extreme Learning Machine (ELM) for the classification purpose. The proposed approach consists of four phases which are as preprocessing, feature extraction, feature clustering and classification. Additionally, this work proposes an iterative algorithm for feature clustering and applies it to leaf recognition. Feature clustering is a powerful tool to reduce the dimensionality of the selected feature. For improving the accuracy and performance of tea leaf recognition, ELM is implemented. The classifier is tested with 20 leaves from each variety and compared with k-NN and RBF approach. The proposed ELM classification produces effective results.