Research

Multimodal Aesthetic Biometric System

Can a deep fusion method be established for biometric identification?

  • Human aesthetics play a crucial role in various domains of research focusing on human-computer interactions. These domains include video game development, emotional-aware robot design, online recommender systems, digital human creation, a nd emerging research areas such as social network user recognition based on aesthetic preferences. I developed a novel deep learning architecture for multi-modal audio-visual person identification, which combines audio and visual aesthetic features. This approach utilizes a pre-trained ResNet architecture to extract high-level features from user-preferred audio and image samples. To effectively merge the audio and visual features, a novel deep learning-based fusion technique called Residual-Aided Intermediate Fusion (RAIF) is introduced. The proposed architecture and fusion technique can be applied in various applications where multi-modal data analysis and person identification based on aesthetic preferences are required.
Fig 1. Architecture of the proposed multi-modal aesthetic system. Fig 2. Proposed DNN-based Residual Aided Intermediate Fusion (RAIF).

Unimodal Aesthetic Biometric System

Can a deep learning-based aesthetic system can identify users with the highest precision and lower inference time

  • A novel three-stage framework based on deep learning and classical machine learning is proposed for identifying individuals from their audio aesthetic. To extract audio features, mel-spectrograms are used instead of generic spectrograms. As a result, the extracted feature set becomes more discriminating for person identification. A novel hybrid meta-heuristic algorithm Cuckoo Search based Whale Optimization Algorithm (CSWOA) is proposed that retrieves the most optimal feature subset from the high-level features.
Fig 3. Architecture of the proposed audio aesthetic system. Fig 4. Proposed Hybrid meta-heuristic feature selection algorithm (CSWOA) along with transfer learning-based feature extraction method.

Online Judging Platform Utilizing Dynamic Plagiarism Detection Facilities

What approaches can be implemented to develop an efficient plagiarism detection system for programming problems in an online judging platform, considering the challenges faced by teachers in identifying source code plagiarism and the prevalence of plagiarism among students?

  • Designed an online judging framework designed specifically for programming labs, addressing the limitations of traditional online judging platforms. The proposed system incorporates automatic scoring of codes with efficient detection of plagiarized content, utilizing program fingerprints generated by the Rabin-Karp Algorithm. By selecting fingerprints through winnowing among k-gram hash values, the system improves time efficiency, correctness, and feature availability compared to existing online judging platforms. The evaluation of the system with large datasets and comparison of runtime with the widely used MOSS plagiarism detection technique further demonstrates its superiority.

Fig 5. Flowchart of the proposed Online Judging System. Fig 6. Architecture of the proposed pliagiarism detection system.

Human Activity Recognition

Can the integration of transfer learning with a two-stream neural network architecture, utilizing 3D dense optical flow, result in a significantly improved Human Activity Recognition (HAR) system?

  • In this work a novel human activity recognition technique is developed that combines action recognition and 3D dense optical flow from video sequences, leveraging the efficiency of optical flow as a feature for accurate recognition. and 3D dense optical flow from video sequences, leveraging the efficiency of optical flow as a feature for accurate recognition. The proposed method utilizes transfer learning with a two-stream neural network architecture, incorporating the pre-trained ResNet152 architecture, to extract fine-grained features from the dense optical flow. The proposed approach was evaluated on the UCF-101 dataset, highlighting its potential for advancing human activity recognition in various computer vision applications.

Fig 4. Architecture of the proposed Human Activity Recognition(HAR) system.

Cervical Cancer Prediction

Can machine learning algorithms along with Adaptive Synthetic Sampling(ADASYN) and Linear Discriminant Analysis (LDA) identify patterns or interactions among risk factors that may enhance the prediction of cervical cancer, and how do these findings align with existing knowledge in the field?

  • In this study, a significant contributions were made in developing a cervical cancer prediction system. Missing value imputation led to higher precision, highlighting the importance of addressing missing data in cervical cancer datasets. Additionally, Linear Discriminant Analysis (LDA) is implemented for dimensionality reduction and the Adaptive Synthetic Sampling approach (ADASYN) is adopted to balance the dataset, resulting in improved outcomes. Moreover, the Isolation Forest algorithm is used, to identify and removed outliers in the cervical cancer datasets, enhancing the quality of the data. Lastly, an effective classifier model using various machine learning techniques is developed and evaluated their performence using different evaluation approaches, resulting in higher performance efficacy for cervical cancer prediction.

Fig 5. Architecture of the proposed Cervical Cancer Prediction system.