http://210.212.227.212:8080/xmlui/handle/123456789/295 2026-05-27T20:51:08Z 2026-05-27T20:51:08Z Mayuri, M Jasmin, M R http://210.212.227.212:8080/xmlui/handle/123456789/358 2022-12-08T07:18:57Z 2022-07-01T00:00:00Z

Title: Contrastive Analysis Of Supervised And Unsupervised Learning Techniques For Voice Pathology Detection And Classification Authors: Mayuri, M; Jasmin, M R Abstract: The development of technology makes it possible to offer better solutions to the complicated issues that people encounter. The early identification, treatment, and ongoing monitoring provided by today's smart healthcare sectors are crucial in lowering hospital visits, travel expenses, and waiting times.A medical condition known as voice pathology affects the vocal chords and makes it difficult for the patient to speak. As a result of this, the patient may experience difficulty communicating. A study that was only recently presented found that vocal pathology detection systems are capable of accurately diagnosing voice pathologies at an early stage.These systems made use of machine learning strategies, which are regarded as particularly reliable instruments for identifying speech disorders. However, the majority of suggested algorithms for detecting voice disorders used small databases.The low accuracy rate continues to be one of the most difficult problems for these approaches. A technique for identifying voice pathology is described in this research paper.Utilizing the Mel-Frequency Cepstral Coefficient, the voice features are retrieved (MFCC). Vowel /a/ speech samples were equally obtained from the Saarbrücken voice database (SVD). As assessment indices, accuracy is used to compare the effectiveness of various machine learning classifiers. The voice signals in this work are classified as either healthy or disordered using a CNN architecture.

2022-07-01T00:00:00Z Hari Krishnan, S R Fousia M, Shamsudeen http://210.212.227.212:8080/xmlui/handle/123456789/357 2022-12-08T07:14:24Z 2022-07-01T00:00:00Z

Title: SECURE-VOTE: A VOTING DAPP ON THE METIS STARDUST BLOCKCHAIN Authors: Hari Krishnan, S R; Fousia M, Shamsudeen Abstract: ABSTRACT Large segments of society today no longer trust the traditional method of voting because they think it may be easily manipulated. Cryptographic techniques can be used to address several problems, assure the security of voting systems, and extend their widespread usage. Modern civilization is seeing a rise in the practice of electronic voting. It has a significant chance of lowering administrative expenses and raising participation rates. Moreover, the installation of polling stations and printing of ballot paper can be minimized. This voting technology allows voters to vote from the comfort of their own homes. A simple polling app is a great use case for blockchain technology. The voting process requires special attention to privacy, especially in the government area, but it will be public, auditable, tamper-proof, and unfiltered, and it can also provide a global voting process. A block chain polling system also makes it possible to build response incentive mechanisms for specific use cases. The creation of a voting system built on top of the Metis Stardust Test net blockchain is proposed in this work. Users can log in to vote in a particular poll, and each poll is confirmed using a transaction that can be viewed on the Stardust blockchain explorer.

2022-07-01T00:00:00Z Ganga Krishnan, G Fousia M, Shamsudeen http://210.212.227.212:8080/xmlui/handle/123456789/356 2022-12-08T07:11:19Z 2022-07-01T00:00:00Z

Title: AUTOMATIC LICENSE NUMBER PLATE RECOGNITION SYSTEM Authors: Ganga Krishnan, G; Fousia M, Shamsudeen Abstract: Numerous aspects of daily life are still being transformed by technologies and services that are geared toward intelligent transportation systems and smart automobiles. Automatic Number Plate Recognition has ingrained itself in our culture and is here to stay. The approach used to examine a vehicle's license plate in a photo or video collection is referred to as Automatic License Plate Recognition (ALPR) or Automatic Number Plate Recognition (ANPR). Intelligent Transportation Systems are made possible by ANPR technology, which also reduces the need for human interaction. This project aims to find out the best algorithm for license plate detection. The project uses four deep neural networks such as CNN, VGG16, VGG19, and YOLOV3 to detect the license number plate and evaluate the performance of the models in terms of accuracy and find out the best model.

2022-07-01T00:00:00Z Fathima, Novrin Nadera Beevi, S http://210.212.227.212:8080/xmlui/handle/123456789/355 2022-12-08T07:06:48Z 2022-07-01T00:00:00Z

Title: A Deep Learning Model for Classification of Gender and Age from Facial Images Authors: Fathima, Novrin; Nadera Beevi, S Abstract: Gender classification and Age identification play an important role in our social lives. Gender is central characteristics of personality, and it is essential in our life. Age is important for our identity. Security, biometric system, and treatment are part of gender classification and age prediction. Age prediction can help to authorize people from buying adult products or other kind of restricted goods. In this project, for classification of gender and prediction of age from pictures deep learning model is used. The objective of this study is to create a model for gender classification and an age estimation using convolutional neural networks and ResNet50. The image's feature extraction and categorization are included by CNN. Feature extraction gives the features corresponding to gender and age from the face pictures whereas the classification classify the image into correct age and gender.ResNet50 is the convolutional network that have 50 layers. Age prediction is the regression problem and prediction of gender is a binary classification problem. The model is evaluated using the UTKFace dataset, a sizable face dataset with a broad age range. Deep learning algorithm is used to obtain higher accuracy and lower MAE, also MAE of the both algorithm is compared to obtain which algorithm more efficient.

2022-07-01T00:00:00Z