http://210.212.227.212:8080/xmlui/handle/123456789/163 Wed, 27 May 2026 20:57:58 GMT 2026-05-27T20:57:58Z http://localhost:8080/jspui/retrieve/dd2320bc-7ed6-47ba-b090-6d5ef3a2017b/close-up-handwritten-whiteboard-year-168763957.jpg http://210.212.227.212:8080/xmlui/handle/123456789/163 http://210.212.227.212:8080/xmlui/handle/123456789/250 Title: DETECTION AND CLASSIFICATION OF FLOODING ATTACKS IN WIRELESS ADHOC NETWORKS USING MACHINE LEARNING Authors: Shanifa, E; Nishanth, N Abstract: In developing wireless adhoc networks, several sorts of attacks represent serious security problems.Various forms of attacks are currently being carried out against various services and resources, with the goal of compromising their availability, confi dentiality, and integrity. Flooding based Denial of Service attacks has a serious impact on Wireless Local Area Networks. It may result in clients being denied service. This is a severe problem since it compromises one of the services offered by cyber security such as availability. In ad-hoc networks, it is crucial to detect and block such attacks in a timely manner. The objective of this thesis is to accurately detect and categorise flooding attacks such as TCP, UDP, or ICMP. This thesis additionally categorises ad ditional assaults, such as U2R, R2L, and probe .The suggested method utilises various supervised machine learning algorithms, including SVM, KNN, Naive Baye’s, Deci sion Tree, and Random Forest. Classification is performed using the NSL KDD data set. The outcome demonstrated that RF classifier provides the highest performance accuracy Fri, 01 Jul 2022 00:00:00 GMT http://210.212.227.212:8080/xmlui/handle/123456789/250 2022-07-01T00:00:00Z http://210.212.227.212:8080/xmlui/handle/123456789/249 Title: Design of novel Sigma Shifted Matrix code family with adaptive transmitter-receiver architecture in OCDMA Authors: Sherin Susan, Thomas; Afra, Basheer Abstract: Multiple Access Techniques are unavoidable part in a communication system.Among that optical code division multiple access (OCDMA) technique’s support for asyn chronous communication with comparatively high secrecy and Quality of service has made it an attractive technology for multiple-access optical networks. In OCDMA,the coding scheme that acts as the foundation for the system’s operation is the main ap proach to satisfy user expectations. Each code in the OCDMA system is specifically created to prevent interference from multiple access. Sigma Shifted Matrix code is a novel spectral amplitude coding (SAC) technique that is developed.For the SSM coding scheme design, two methods are suggested. The identity and upper shift ma trices are combined in the first method to create the SSM1 coding matrix. The second method implements the composition of an additional SSM matrix termed SSMs by assembling a single entry, lower, and upper shift matrix. To further improve the per formance of the suggested setup, Then we are creating another code sequence which is called Modified Sigma shifted Matrix (MSSM) by bit wise ANDing of SSMI and SSM2. Combining these matrices results in variable SSM code families,which, de pending on the number of users and the code weights chosen,and can offer additional flexibility. A concept for an optical control module(encoder) is described to make the system as adaptable as possible. To switch between SSM families, this control module chooses the desired encoding-decoding method based on the intended application. In comparison to the formerly used SAC-OCDMA codes, simulation findings show that the optical code division multiple access system based on the proposed SSM code fam ily has better transmission rates, lower bit error rates (BER), Good Quality factor and longer travel distances without any signal quality loss Fri, 01 Jul 2022 00:00:00 GMT http://210.212.227.212:8080/xmlui/handle/123456789/249 2022-07-01T00:00:00Z http://210.212.227.212:8080/xmlui/handle/123456789/248 Title: DIABETIC RETINOPATHY CLASSIFICATION USING MACHINE LEARNING AND DEEP LEARNING MODELS Authors: Afra, K; Ajitha, S. S Abstract: The majority of people worldwide have the risk of getting the eye disease called Diabetic Retinopathy (DR). This is a major problem that could impair vision for most of diabetic patients. High glucose levels in retinal blood vessels are the main reason for this. Color fundus images are used to diagnose DR from databases like IDRiD, KAGGLE, MESSIDOR and DIARETDB1 etc. The traditional method re quires trained doctors to determine the presence of lesions in the image, that may be utilised to effectively detect the illness, making it a time-consuming process. The effective classification of the disease relies heavily on feature extraction. Due to the superior image grading efficiency of deep learning approach, computer diagnosis of DR has developed into a viable tool for rapid detection and evaluation of the severity of DR. In this work, different types of CNN architectures are used to extract the features. The CNN output features are used as input for different types of machine learning methods (Support Vector Machines, Decision Tree, Random Forest, Naive Bayes Classifier and K-Nearest Neighbour). Deep learning techniques like (ResNet 50, VGG-16, MobileNet, EfficientNet-B3, Inception-v3, and Self-designed models) are also implemented for classification. Here performed a performance comparison of dif ferent techniques using different datasets. The models are evaluated using various evaluation metrices such as accuracy, precision, recall and auc etc. The model having highest value for evaluation metrices is selected as the best model. Fri, 01 Jul 2022 00:00:00 GMT http://210.212.227.212:8080/xmlui/handle/123456789/248 2022-07-01T00:00:00Z http://210.212.227.212:8080/xmlui/handle/123456789/247 Title: A long-haul 100 Gbps hybrid PDM/CO-OFDM hybrid FSO transmission system:Impact of climate conditions and atmospheric turbulence Authors: Akshaya, S R; Amina, N Abstract: Free space optics system(FSO) is significantly degraded by attenuation under dif ferent climatic conditions. An FSO transmission system with high-speed transmission capability is proposed by hybridization of PDM with CO-OFDM .The m-ary modu lation scheme like 4-QAM analysis were obtaining. The impact of different climatic condition on system performance is investigated. Though simulations briefly explains the 100Gbps 4-QAM information transmission at 0.5km.The proposed system reduces channel fading,improves information rate,maximum transmission distance. This work is considered as future FSO system in adverse climatic conditions. Sat, 01 Jan 2022 00:00:00 GMT http://210.212.227.212:8080/xmlui/handle/123456789/247 2022-01-01T00:00:00Z