International Journals
Permanent URI for this collectionhttps://dspace.psgrkcw.com/handle/123456789/157
Browse
65 results
Search Results
Item ANDROID APPLICATIONS FOR LUNG NODULES CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORK(IGI Global, 2023) Karthikeyan, M P; Banupriya, C V; Kowsalya, R; Jayalakshmi, ADigital image processing is currently used in various fields of research. One of them is in the field of medicine. In fact, experienced radiologists have difficulty distinguishing the cancerous portions of the blood vessels in the lung or detecting fine nodules that suggest lung cancer on X-ray images. Previous studies have shown that doctors and radiologists fail to detect cancerous patches in 30% of positive cases. Implementation of CAD system to classify and detect parts of cancer has been developed, but the results obtained from this implementation are that there are still many errors in the classification results. Therefore, this study will develop android app image technique to perform the classification process of lung cancer. With this research, it is hoped that the developed algorithm can help doctors and radiologists to detect cancer in a short time with more accuracy. Finally, after 20 iterations, a percentage of 90.65% was attained for the test results' performance in classifying 10 X-ray pictures.Item A NOVEL HYBRID APPROACH ON SECURE DATA TRANSMISSION IN WIRELESS SENSOR NETWORKS(International Journal of Future Generation Communication and Networking, 2020) R, Kowsalya; B, Rosiline Jeethan recent year wireless sensor network plays an important role in day to day life, to achieve the security, cryptography techniques are used. As wireless sensor has the limited memory space and energy consumption to provide security is vital problem. The main aim of this research work is to analysing different cryptographic techniques such as symmetric key cryptography and asymmetric key cryptography and comparing AES, DES, 3DES, RC5 and IDEA encryption techniques. In this paper, a new security symmetric algorithm was proposed to provide high security. It provides cryptographic primary key integrity, confidentiality and authentication. The results show that the proposed hybrid algorithm HSR19 gives efficient performance for communication devices with the parameters in computation time with different file sizes, encryption and decryption speed and energyItem EFFICIENT AUTHENTICATION SCHEME TO DETECT THE SPOOFER LOCATION USING PASSIVE IP TRACEBACK TECHNIQUES(International Journal of Innovative Computer Science & Engineering, 2017-06) A, Sheela RiniInternet plays a vital role in the modern world. As the internet grows day by day the security problem also arises. Intruders spoof the packets by using their spoofed IP addresses. Nowadays installing Intrusion Detection Systems (IDS) coupled with firewalls, and monitoring networks enables us to quickly detect and react to unauthorized access. However, even if these tools can detect illegitimate activities, their sources cannot be identified. Denial of service and Distributed denial-of-service (DDoS) attacks present an Internet-wide threat. In Denial of service attacks huge amount of un-wanted packets are sent by the attacker to the IP address which they want to attack. The same attack is take place in DDos also but in a distributed manner. The reason is that denial of service (DoS) attacks, which have recently increased in number, can easily hide their sources and forge their IP addressesItem A SURVEY ON MANET ENERGY CONSUMPTION CHALLENGES(International Journal of Advances in Science Engineering and Technology, 2016-05) Sasikala S; Suganyadevi SIn mobile ad hoc network progressive approach and circulated methodology are more functional when contrasted with the level construction modeling. Energy preserving in mobile ad hoc network is critical. Comparative the circling free way is likewise vital. In spite of the fact that setting up right and proficient courses is an imperative configuration issue in mobile ad hoc networks (MANETs), an all the more difficult objective is to give energy efficiency, since mobile hubs' operation time is the most basic restricting factor. Keeping in mind the end goal to increase the lifetime of ad hoc networks movement ought to be sent by means of a course that can maintain a strategic distance from hubs with low consumption of energy while minimizing the aggregate transmission power. In a MANET, the energy exhaustion of a hub does not influence the hub itself just but rather the general network lifetimeItem AN ADAPTION OF CONGESTION AWARE ROUTING IN MANET USING MODIFIED BRANCH AND BOUND WITH DSR PROTOCOL(International Journal of Advanced Science and Technology, 2020) Sasikala S; Ponmuthuramalingam PMobile adhoc network is a decentralized wireless system that does not rely on a pre-existing infrastructure. In adhoc the system can be setup at anytime and anywhere. Each node in a MANET act as a router and communicate packets with each other from source to destination. Mobile Adhoc network is a self configured network and nodes move randomly when the network changes frequently due to its infrastructure less network. Routing plays a vital role to select paths in a network. The routing decides the packets route between devices in a MANET. The proposed methodology Modify DSR with Modify Branch and Bound i.e., MDSR with MBB with congestion aware routing focus in rising the energy utilize level, forwarding the packet, Route discovery and avoiding collision when sending packets from an origin to end. The efficiency of the energy level is improved in MANET with the proposed methodology (MDSR with MBB). The metrics were used to calculate the efficiency in a network system such as Lifetime of a network, Energy utilization of a node, End to end delay of packet , Delivery ratio of Packet in a network ,Throughput and Routing overhead.Item EXPLORING THE NUANCES OF INTERNET OF THINGS IN HEALTH CARE ASSISTING SYSTEM(International Research Journal of Engineering and Technology (IRJET), 2019-02) S, LakshmipriyaInternet of Things (IoT) is one of the influential technology which is widely used. This technology associated in a wide variety of network products, systems and sensors, which yield benefits of advancements in computing power, electronics miniaturization, and network interconnection to deliver new capabilities not previously possible. The growth of these associated ‘smart’ technologies distribute different chances for renewing teaching and learning, as well as real-time, on-demand data, for evoking immediate changes. The fields of computer science and electronics have combined to consequence into one of the most notable technological advances in the procedure of realization of the Internet of Things (IoT).Item ANALYSIS OF MACHINE LEARNING CLASSIFIERS TO DETECT MALICIOUS NODE IN VEHICULAR CLOUD COMPUTING(2022-04-30) Sheela Rini A; Meena CVANET or Vehicular networks are created using the principles of MANETS and are used by intelligent transport systems to offer efficient communication between the domains of vehicles. Increasing the number of vehicles requires communication between vehicles to be fast and secure, where cloud computing with VANET is more prominent. To provide a secure VANET communication environment, this paper proposes a malicious or hacked vehicle identification system. Malicious vehicles are identified using four steps. The first step uses a clustering algorithm for similar group vehicles. In the Second step, cluster heads are identified and elected. In the next step, Multiple Point Relays are selected. Finally, classifiers are used to identify hacked vehicles. However, the existing system performance degrades as soon as the number of vehicles increases, resulting in increased cost during Cluster head election, inability to produce stable clusters, and the need for accurate and fast classification in high traffic scenarios. This work improves clustering algorithms and examines several classification algorithms to solve these issues. The classifiers analyzed are Decision Tree (DT), Support Vector Machine (SVM), K-Nearest Neighbour (KNN) and Naïve-Bayes (NB). A Hybrid classifier that combines SVM and KNN classifiers is also analyzed for its effectiveness to detect malicious vehicles. From the experimental results, it could be observed that the detection accuracy is high while using the hybrid classifier.Item GATED RECURRENT NEURAL NETWORK FOR AUTISM SPECTRUM DISORDER GENE PREDICTION(Research Trend , International Journal on Emerging Technologies, 2020) Pream Sudha V; Vijaya M.SAutism Spectrum Disorder (ASD) is the fastest-growing complex disorder and the genetic ground of this comprehensive developmental disability is very difficult to research. Autism diagnosis for an average child is not done till the age of four, though it can be given at the age of 18 months to two years. Hence a computational model that enables the early diagnosis and personalized treatment is the need of the hour. In this research work, a deep learning based approach is proposed for Autism Spectrum Disorder (ASD) gene prediction. There are various contributors for Autism including genes, mutations, chromosomal settings influence of the environment, prenatal influences, family factors and problems during birth. Recurrent Neural Network (RNN) based Gated Recurrent Units (GRU) are implemented to develop a model that predicts ASD genes, mutations and gene susceptibility. GRUs with their internal memory capability are valuable to store and filter information using the update and reset gates. Also GRU offers a powerful tool to handle sequence data. The model is trained using three simulated datasets with features representing genes, mutations and gene susceptibility to ASD. Besides, the proposed approach is compared to original RNN and Long Short Term Memory Units (LSTM) for ASD prediction. The experimental results confirm that the proposed approach is promising with 82.5% accuracy and hence GRU RNN is found to be effective for ASD gene predictionItem PREDICTION OF GENE SUSCEPTIBILITY TO AUTISM SPECTRUM DISORDER USING DEEP ARCHITECTURES(International Journal of Scientific and Technology Research, 2020) Pream Sudha V; Vijaya M.SA genetic predisposition or susceptibility to Autism Spectrum Disorder (ASD) is an increased likelihood of developing it based on the genetic makeup of a person. The multiple variants found in each gene have their own probability of associated risk and so the major problem lies in the systematic evaluation of their functional significance to ASD. Hence it is essential to develop methods for quantitative evaluation of ASD candidate genes with co-occurring mutations which will provide a clear understanding of their relevance to ASD. This research work deals with the development of a discriminative model for prioritization of candidate genes considering mutations in them and to classify them based on their predisposition to the disorder. The model for gene susceptibility prediction is built by integrating the combined potential of substantiation for each ASD linked gene and the related mutations. In this research work gene susceptibility prediction is modelled as a pattern classification problem and deep learning techniques are employed to build the models. The performance evaluation of these models proves that Long Short Term Memory (LSTM) based gene susceptibility prediction model has shown better performance.Item RECURRENT NEURAL NETWORK BASE MODEL TO PREDICT AUTISM SPECTRUM DISORDER CAUSATIVE GENES(Science and Engineering Research Support Society(SERSC) International journal of Advanced science and technology, 2019) Pream Sudha V; Vijaya M SRecognizing genes causing Autism Spectrum Disorder (ASD) is still a complex task. The role played by domain experts is crucial in identifying relevant contributive features and as recognizing hand-crafted attributes occupies a great deal of time, a varying successful solution is necessary. The swift advancements in the design of deep architecture models have shown substantial accomplishment in sequential data processing tasks. Deep learning models examine the data to discover associations among the features and enable faster learning without being explicitly programmed to do so. Hence the principal goal of this work is to categorize the ASD genes by applying deep learning based models without feature engineering. One hot encoding method is used to encode the gene sequences as vector of numerical values and to further simplify the input representation to aid the prediction of ASD gene sequences. Recurrent Neural Network (RNN) models like Bidirectional Recurrent Neural Network (BRNN), Long Short Term Memory (LSTM) and Gated Recurrent Units (GRU) are employed to build the prediction models using user defined and self learned features. The performances of the models evaluated using cross validation with various metrics like precision, recall, accuracy and F-measure confirm that GRU model shows promising results using one hot encoding technique.