National Journals
Permanent URI for this collectionhttps://dspace.psgrkcw.com/handle/123456789/160
Browse
10 results
Search Results
Item RECURRRENT NEURAL NETWORK BASED MODEL FOR AUTISM SPECTRUM DISORDER PREDICTION USING CODON ENCODING(Journal of The Institution of Engineers (India): Series B, 2022-09) Sudha V, Pream; Vijaya, M SDeep learning methods are noteworthy tools that go together with traditional machine learning techniques to enable computers learn from data and create smarter applications. Deleterious gene classification is an important task in a standard computational framework for biomedical data analysis. As gene sequences are high dimensional and do not represent explicit attributes for computational modelling, extracting features from them becomes a complex task. Recently neural deep learning architectures automatically extract valuable features from input patterns. The principal idea of this work is to exploit the power of Recurrent Neural Networks (RNN) to learn sequential patterns through high-level information associated with observed signals which in turn can be used for classification. Classification of affected genes that cause disease like Autism-spectrum disorder (ASD) is a noteworthy challenge in biomedical research. Long Short Term Memory (LSTM) units go well with sequence-based tasks with long-term dependencies and hence this work examines a stacked LSTM architecture for classifying genes causing ASD. The model is trained and tested with two hand crafted datasets and a codon encoded dataset. Experiments revealed the superiority of these advanced recurrent units compared to the traditional Deep Neural Networks and Bi-directional RNNs distinctively with codon encoded datasetItem RIVER WATER QUALITY PREDICTION AND INDEX CLASSIFICATION USING MACHINE LEARNING(IOP Science, 2022) Jitha, P Nair; M S, VijayaVarious pollutants have had a substantial impact on the quality of water in recent years. The quality of water directly impacts human health and the environment. The water quality index (WQI) is an indicator of effective water management. Water quality modelling and prediction have become essential in the fight against water pollution. The research aims to build an efficient prediction model for river water quality and to categorize the index value according to the water quality standards. The data has been collected from eleven sampling stations located in various locations across the Bhavani River, which flows through Kerala and Tamilnadu. The water quality index is determined by 27different parameters affecting water quality like dissolved oxygen, temperature, pH, alkalinity, hardness, chloride, coliform, etc. Data normalization and feature selection are done to construct the dataset to develop machine learning models. Machine learning algorithms such as linear regression, MLP regressor, support vector regressor and random forest has been employed to build a water quality prediction model. Support vector machines (SVM), naïve bayes, decision trees, MLP classifiers, have been used to develop a classification model for classifying water quality index. The experimental results revealed that the MLP regressor efficiently predicts the water Quality index with root mean squared error as 2.432, MLP classifier classifies the water quality index with 81% accuracy. The developed models show promising output concerning water quality index prediction and classification.Item ACUTE CYSTITIS AND ACUTE NEPHRITIS PREDICTION USING MACHINE LEARNING TECHNIQUES(Global Journal of Computer Science and Technology, 2010-09) Kowsalya R; Sasikala G; Sangeetha Priya JUrinary System includes kidneys, bladder, ureters and urethra. This is the major system involves electrolyte balance of the body and filters the blood and excretes the waste products in the form urine. Even the small disturbance in the renal function will step in a disasters manifestation. Among them we are considering the two diseases that affect the system are acute cystitis and acute nephritis. This paper presents the implementation of three supervised learning algorithms, ZeroR, J48 and Naive Bayes in WEKA environment. The classification models were trained using the data collected from 120 patients. The trained models were then used for predicting the acute cystitis or acute nephritis of the patients. The prediction accuracy of the classifiers was evaluated using 10-fold cross validation and the results were compared.Item ANTI-DIABETIC POTENTIAL OF INDIAN MEDICINAL PLANTS WITH GARCINIA KOLA AND SYZYGIUM CUMINI(A & V Publications, 2021) K J, Sharmila; L, Kanimozhi; Priya, J Shanmuga; G V, Vidhya; Caroline, R Jeba; R, KowsalyaDiabetes mellitus is a group of metabolic disease in which a person experiences high blood glucose levels either because the body produces inadequate insulin in the body. Though there are several treatment options available there are limitations such as high costs and side effects, weight gain etc. For this reason, the use of medicinal plants has increased to be used as an anti-diabetic agent with less side-effect and more efficient. In this regard, this study analyzed the anti-diabetic potential of Garcinia kola and Syzygium cumini using alpha amylase inhibition assay and glucose uptake by yeast cells. It was observed that Ethanol extract of Garcinia kola increased anti-diabetic potential compared to Syzygium cumini.Item SECURE AND EFFICIENT FIRE-FLY DATA ROUTING ALGORITHM FOR WIRELESS SENSOR NETWORKS IN IOT MONITORING SYSTEMS(IOP Publishing, 2021) Kowsalya R; Rosiline Jeetha BIn the Electronics world the sensor is used in IoT applications. The sensed data need to be transfer to the appropriate devices as input for further processing. Clustering used to group the sensors which could form cluster and select the nodes head from the cluster. The head of each cluster receives the forwarded data through the cluster member and pass on to nearest permanent fixed station. Identifying cluster head and shortest route identification is a major challenge. This paper proposed a novelty on hybrid decision making algorithm with firefly routing algorithm (HDMFRA) for Cluster Head selection. This research work focusing of three main criteria which could save the energy and extend the life activation of the node, through the usage of energy, amount of nodes adjacent and energy consumption from permanent fixed station. To aggregate the data in optimized manner and to transfer the data in efficient manner Fire Fly routing algorithm was used. Simulation results show that proposed algorithm HDMFRA network in homogeneous environment is effective and prolonging the life time of the node by 25%.Item AN EFFICIENT ENHANCED ALGORITHM TO DIMINISH THE CYBER SECURITY THREATS IN MULTI-TENANCY CLOUD COMPUTING(Journal of Emerging Technologies and Innovative Research (JETIR), 2019-02) Sheela Rini A; Meena CCloud computing is considered as the hopeful standard for distributing IT facilities as computing benefits. Several industries like banking, healthcare and education are moving towards the cloud due to the effectiveness of services provided by the pay-per-use pattern based on the resources equivalent to process power used, transactions administered, bandwidth consumed, knowledge transferred, or storage space occupied etc. Cloud computing is totally in web dependent technology wherever client data is kept and maintained within the cloud provider’s data center like Google, Amazon, Microsoft, Akamai, etc. Inadequate control over the data may procure several security concerns and threats which include data leakage, insecure interface, sharing of resources, data availability and insider attacks, which leads to cybercrimes in cloud environment. On the off chance that the organizations and clients are given web get to, they can get to their own records specifically from any side of the world. This innovation supports fruitful computing by coordinating information storage, processing and transfer speed... In Cloud, security of information isn't ensured and even the information can likewise be gotten to by the third party. There is a need to consequently, we have planned a protected document stockpiling framework with effortlessness, legitimacy and security. Nearly it is connected in everything which required giving consent to just affirmed approvals Consequently, we have planned a protected document stockpiling framework with effortlessness, legitimacy and security. Nearly it is connected in everything which required giving consent to just affirmed approvals on averting information release, warning for security mischance and security occurrence reviews. Cloud security needs to be enriched with the conventional methods like firewalls, Virtual Private Networks (VPN) and Security policies to get a carefully designed ripe administration from it. In any case, Cloud computing brings new difficulties, issues and dangers to the business. From many research it is observed that security is the main problem of cloud adoption. The dread of losing control of corporate information and the danger of data breaches in the cloud can possibly disturb the adoption of cloud services. Security issues must be addressed and new technologies must be produced in order to open cloud computing benefits. For retrieving the data in the cloud, clients need more security for guarding their data. Encryption and Hashing technique is being used in the cloud environment by carrying a key exchange process done with key encryption key and data encryption key to provide security. Also SHA3 hashing function is used for accomplishing data integrity and security in the cloud. This Proposed method looks in to an attack model based on threat model to overcome the Multi-tenancy situation. Additionally, resource allotment method will accomplish the balance between both the advantages gained from Multi-Tenancy and Security. To minimize the security threats and preserve the privacy, reliability and authenticity of data which is stored in cloud, Encryption and hashing techniques will be used. Consequently, we have designed a protected file storage system with effortlessness, legitimacy and security. Nearly it is connected in everything which required giving permission to just certified authorizations. In the database, the password is stored as a message digest. This sort of storing password should be carefully designed. The encryption procedure makes the data secure and it prevents clarity by unauthorized persons and furthermore it sets up a system to remove imposture. This system has been designed in such a way, if the one-way hash function gets cracked, it will lead to get the encrypted data alone. The usage of hash function makes impossible for any overlooked changes on data. After the deployment of RSA and SHA3 (Keccak) before Storage, the data becomes impervious to access or changes by any third party and to the capacity framework. In this manner by creating a two factor security verification of data which is stored in cloud will be a protected environment for the multitenant users to protect their data from cybercrimes. This will help the clients information to be more secured in the cloud platform.Item AN ENERGY COMPACTION USING OPTIMIZED DSR AND BRANCH AND BOUND ALGORITHM IN MANET(The Mattingley Publishing Co.Inc, 2020-04) Sasikala S; Ponmuthuramalingam PMobile Ad-hoc Network (MANET) is used for wireless communication, in that mobile nodes forms a communication without infrastructure. In the wireless communication, Routing has been the most decisive area of research in ad hoc network. The prominent type of MANET protocol is DSR protocol. Dynamic Source Routing (DSR) is used for the effective route discovery. The DSR protocol is incorporated with Branch and Bound algorithm for the optimal route discovery. The proposed algorithm, Modify DSR with Modify Branch and Bound aims at increasing the energy utilizing level in Discover Routing, Packet forwardingand Collision avoidance. It helps to progress the efficiency of the energy level in MANET. One of the chief impact of this research work is to ensure Packet forwarding with efficient utilization of Energy attributes in MANET. Performance metrics like End to end Delay, Packet Delivery Ratio (PDR), Nodes Energy, Network Life time, Routing Overhead and Throughput has used for the evaluation of performance of the proposed algorithm.Item ACCELERATION ARTIFICIAL BEE COLONY OPTIMIZATION-IMPROVED TRANSDUCTIVE SUPPORT VECTOR MACHINE FOR EFFICIENT FEATURE SELECTION IN BIG DATA STREAM MINING.(Jour of Adv Research in Dynamical & Control Systems, 2017-04) S, Meera; B, Rosiline JeethaHigh dimensional data seen in a practical issue imposes a hurdle for large data analysis. Attribute reduction or feature selection aids the learning algorithm to work with efficiency by eliminating unnecessary and repetitive information in the big data. The existing system like Acceleration Particle Swarm Optimization–Support Vector Machine (APSO-SVM) is proposed in order to deal with the above challenge. But the already existing technique has issues in addition to the pre-processing technique and optimal feature selection for scalable dataset. Therefore the system’s overall performance is decreased significantly. With the aim of eliminating these problems, in the proposed system, Acceleration Artificial Bee Colony –Improved Transductive SVM (AABC-ITSVM) is introduced so as to improve the system performance in a more efficient manner. The proposed system comprises of three important modules like preprocessing, feature selection and classification. The preprocessing is carried out by making use of min-max normalization algorithm that assists in increasing the classification accuracy more. Thereafter the feature selection is carried out by employing AABC optimization algorithm that is utilized for selecting the significant and necessary features from the data that is preprocessed. The selected features are classified by employing ITSVM algorithm. The ITSVMs gets the labeling of the test features, which increases the margin conjoined on the training and the test data. It yields classification results with more accuracy for the datasets specified. The proposed system offers great performance with regard to superior accuracy, recall, sensitivity, specificity, precision, f-measure, gmean, and lesser selected features, time complexity by utilizing the AABCITSVM technique.Item ANALYSIS ON USERS TEXTUAL OPINION TO PREDICT THEIR ACTION(Journal of the Gujarat Research Society, 2019-11) G, Anitha; M, SownthariyaNowadays most of the E-Commerce websites are using opinion mining to understand the trends and problems with their products. Opinion mining is performed to analyze the natural language and to identify the emotions expressed by the users. It is useful in product recommendations. The idea behind the opinion mining uses text mining techniques such as NLP (Natural Language Processing) and the polarity of the reviews given for a particular product is predicted using a Lexicon-Based Dictionary approach. The achieved polarity will be used to predict whether the users will recommend the product or not to new users using Naïve Bayes classifier in machine learning.Item PERFORMANCE ANALYSIS OF CANCELABLE UNIMODAL AND MULTIPLE BIOMETRIC USING DISTORTION TRANSFORMATION ALGORITHM(Indian Journal of Innovations and Developments, 2014-10) Gomathy N; Radha NCancelable unimodal and multimodal biometric using distortion transformation algorithm solve the authentication problem of raucous data, non-universality and unacceptable error rate during authentication.