Denise Joanitah Birabwa

Denise Joanitah Birabwa

Auto-generated profile, based on publicly available information

Denise Joanitah Birabwa

School of Computing, SASTRA Deemed University, Thanjavur, India

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
28 September 2022 in IEEE Access
Verified
Journal Article
Open access
BNB. Natarajan
B. Natarajan
ERE. Rajalakshmi
E. Rajalakshmi
ERElakkiya Rajasekar
Elakkiya Rajasekar
Ketan KotechaKetan Kotecha
Ketan Kotecha
Ajith AbrahamAjith Abraham
Ajith Abraham
VSV. Subramaniyaswamy
V. Subramaniyaswamy
The recent developments in deep learning techniques evolved to new heights in various domains and applications. The recognition, translation, and video generation of Sign Language (SL) still face huge challenges from the development perspective. Although numerous advancements have been made in earlier approaches, the model performance still lacks recognition accuracy and visual quality. In this paper, we introduce novel approaches for developing the complete framework for handling SL recognition, translation, and production tasks in real-time cases. To achieve higher recognition accuracy, we use the MediaPipe library and a hybrid Convolutional Neural Network + Bi-directional Long Short Term Memory (CNN + Bi-LSTM) model for pose details extraction and text generation. On the other hand, the production of sign gesture videos for given spoken sentences is implemented using a hybrid Neural Machine Translation (NMT) + MediaPipe + Dynamic Generative Adversarial Network (GAN) model. The proposed model addresses the various complexities present in the existing approaches and achieves above 95% classification accuracy. In addition to that, the model performance is tested in various phases of development, and the evaluation metrics show noticeable improvements in our model. The model has been experimented with using different multilingual benchmark sign corpus and produces greater results in terms of recognition accuracy and visual quality. The proposed model has secured a 38.06 average Bilingual Evaluation Understudy (BLEU) score, remarkable human evaluation scores, 3.46 average Fréchet Inception Distance to videos (FID2vid) score, 0.921 average Structural Similarity Index Measure (SSIM) values, 8.4 average Inception Score, 29.73 average Peak Signal-to-Noise Ratio (PSNR) score, 14.06 average Fréchet Inception Distance (FID) score, and an average 0.715 Temporal Consistency Metric (TCM) Score which is evidence of the proposed work.

27 September 2022 in IEEE Access
Verified
Journal Article
Open access
DBDenise Joanitah Birabwa
Denise Joanitah Birabwa
DRDaniel Ramotsoela
Daniel Ramotsoela
NVNeco Ventura
Neco Ventura
In 6G networks and beyond, multiple radio access networks (RANs), including; the satellite, high altitude platforms, low altitude platforms, and the terrestrial network, will co-exist. These networks are characterized by different capabilities and limitations in meeting the envisioned 6G contrasting user requirements. Therefore, associating users with the appropriate radio access network (RAN) in such an integrated network is rigorous and complex. In this work, the user association and resource allocation problem is formulated as a multi-objective optimization problem (MOOP), aiming to maximize data rate while minimizing mobility-induced handoff in the integrated network. Moreover, the problem is formulated in such a way as to prioritize the service provisioning of mission-critical users. The weighted sum method is adopted to simplify and transform the MOOP into a single-objective optimization problem (SOOP). In order to solve the formulated NP-hard SOOP, a genetic algorithm (GA) whose fitness value is based on the user’s service group is proposed. The performance of the proposed algorithm is evaluated by comparing it to the optimal solution, the greedy signal-to-interference-plus-noise ratio (SINR) based association, and the random user association algorithms. Simulation results show that as the number of access nodes in the network increases, the GA’s spectrum efficiency (SE) remains within 0.4% of the optimal solution. Moreover, the GA outperforms all three schemes in user acceptance ratio (AR) and handoff probability.

20 May 2023 in Computer Networks
Verified
Journal Article
Open access
DBDenise Joanitah Birabwa
Denise Joanitah Birabwa
DRDaniel Ramotsoela
Daniel Ramotsoela
NVNeco Ventura
Neco Ventura