L. Jenefas
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
L. Jenefas has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- DanielRaj Kingston
Dr. G.U. Pope College of Engineering, India
2 shared publications - A. Ananthakumari
Dr. G.U. Pope College of Engineering, India
1 shared publication - Benitlin Subha K.
Kings Enginerring College, India
1 shared publication G. Jeyasri Nandhini
Dr. G.U. Pope College of Engineering, India
1 shared publication- G. Ponseka
Dr. G.U. Pope College of Engineering, India
1 shared publication J. Japhynth
Dr. G.U. Pope College of Engineering, India
1 shared publication
Latest Publications
- 27 March 2026
- Published by IGI Global Scientific Publishing
- p. 369-414
Preprocessing and Feature Engineering for Deep Learning-Enhanced Hyperspectral Oncology
This chapter per the authors examines the essential role of preprocessing and feature engineering in enhancing deep learning performance for hyperspectral imaging in oncology. It outlines key challenges such as noise, spectral redundancy, high dimensionality, and inter-patient variability, all of which affect diagnostic reliability. The chapter highlights major preprocessing techniques, including normalization, denoising, calibration, and dimensionality reduction using PCA, t-SNE, and autoencoder-based methods. Spectral–spatial fusion strategies are also discussed to illustrate how biochemical and morphological cues can be integrated for improved cancer detection and tumor margin analysis. Case studies from brain, breast, skin, and gastrointestinal oncology demonstrate the clinical value of optimized preprocessing pipelines. Emerging trends such as self-supervised learning, physics-informed modeling, and edge-based processing further emphasize future directions for scalable and clinically deployable hyperspectral systems.
- 27 March 2026
- Published by IGI Global Scientific Publishing
- p. 369-414
Preprocessing and Feature Engineering for Deep Learning-Enhanced Hyperspectral Oncology
This chapter per the authors examines the essential role of preprocessing and feature engineering in enhancing deep learning performance for hyperspectral imaging in oncology. It outlines key challenges such as noise, spectral redundancy, high dimensionality, and inter-patient variability, all of which affect diagnostic reliability. The chapter highlights major preprocessing techniques, including normalization, denoising, calibration, and dimensionality reduction using PCA, t-SNE, and autoencoder-based methods. Spectral–spatial fusion strategies are also discussed to illustrate how biochemical and morphological cues can be integrated for improved cancer detection and tumor margin analysis. Case studies from brain, breast, skin, and gastrointestinal oncology demonstrate the clinical value of optimized preprocessing pipelines. Emerging trends such as self-supervised learning, physics-informed modeling, and edge-based processing further emphasize future directions for scalable and clinically deployable hyperspectral systems.
- 10 October 2025
- Published by IGI Global Scientific Publishing
- p. 43-74
The Role of Speech Processing in the Metaverse
The metaverse, blending AR, VR, and persistent digital spaces, is reshaping how people interact and communicate. Speech processing covering ASR, NLP, and TTS is vital in enabling intuitive, voice-driven experiences like real-time translation, smart agents, and personalized avatars. This chapter explores these technologies' impact on user experience while addressing critical ethical concerns such as voice data privacy, surveillance, bias, and synthetic voice misuse. It highlights challenges in digital identity and accessibility, especially for marginalized users. With real-world case studies, it advocates for transparent, inclusive, and ethical voice tech governance in virtual spaces.
- 10 October 2025
- Published by IGI Global Scientific Publishing
- p. 43-74
The Role of Speech Processing in the Metaverse
The metaverse, blending AR, VR, and persistent digital spaces, is reshaping how people interact and communicate. Speech processing covering ASR, NLP, and TTS is vital in enabling intuitive, voice-driven experiences like real-time translation, smart agents, and personalized avatars. This chapter explores these technologies' impact on user experience while addressing critical ethical concerns such as voice data privacy, surveillance, bias, and synthetic voice misuse. It highlights challenges in digital identity and accessibility, especially for marginalized users. With real-world case studies, it advocates for transparent, inclusive, and ethical voice tech governance in virtual spaces.