[email protected]
Academic Editor
Contributions by role
Editor 2
ORCID
0000-0003-4257-0688
Aditya Kumar Sahu
Amrita School of Computing, Amrita Vishwa Vidyapeetham, India
Summary
ADITYA KUMAR SAHU is an Associate Professor at Amrita School of Computing, Amaravati, Andhra Pradesh, India. Dr. Sahu completed his Ph.D. in Digital mage Steganography and Steganalysis in 2020. He has 17 years of teaching and research experience. Dr. Sahu was listed in the World’s Top 2% Scientists list there times, in 2024, 2023 and 2021, respectively, by Elsevier and Stanford University. Currently, he is working in the research areas of Multimedia Forensics, Digital Image Watermarking, Image Tamper Detection and Localization, Image Steganography, Reversible Data Hiding, and Convolution Neural Network based Data hiding. He has more than 60 publications on his credit and published one book titled ‘Multimedia Watermarking: Latest Developments and Trends’. He also has two patents (1 published and one granted). Dr. Sahu is also an Associate/editorial board member for ten international journals. Further, he is also a reviewer for more than 50 SCI journals. He has been the main guest editor for three special issues in reputed publishers.
Edited Journals
IECE Transactions on Emerging Topics in Artificial Intelligence
IECE Contributions
Articles
0
Edited
2
Free Access | Research Article | 15 March 2025
Scaling AI with Limited Labeled Data: A Self-Supervised Learning Approach
by
Praveen Kumar Myakala
IECE Transactions on Emerging Topics in Artificial Intelligence | Volume 2, Issue 1: 26-35, 2025 | DOI:10.62762/TETAI.2025.607708
Abstract
The scalability of modern AI is fundamentally limited by the availability of labeled data. While supervised learning achieves remarkable performance, it relies on large annotated datasets, which are expensive and time-consuming to acquire. This work explores self-supervised learning (SSL) as a promising solution to this challenge, enabling AI to scale effectively in data-scarce scenarios. This study demonstrates the effectiveness of the proposed SSL framework using the EuroSAT dataset, a benchmark for land cover classification where labeled data is limited and costly. The proposed approach integrates contrastive learning with multi-spectral augmentations, such as spectral jittering and band... More >
Graphical Abstract
Scaling AI with Limited Labeled Data: A Self-Supervised Learning Approach
Free Access | Research Article | 16 February 2025
Short and Long-Term Renewable Electricity Demand Forecasting Based on CNN-Bi-GRU Model
by
Shuchen Zhao
,
Zhongjin Xu
,
Zhefan Zhu
,
Xiaoxiang Liang
,
Zecheng Zhang
,
Ruxue Jiang
IECE Transactions on Emerging Topics in Artificial Intelligence | Volume 2, Issue 1: 1-15, 2025 | DOI:10.62762/TETAI.2024.532253
Abstract
With the increasing global focus on renewable energy and the growing proportion of renewable power in the energy mix, accurate forecasting of renewable power demand has become crucial. This study addresses this challenge by proposing a multimodal information fusion approach that integrates time series data and textual data to leverage complementary information from heterogeneous sources. We develop a hybrid predictive model combining CNN and Bi-GRU architectures. First, time series data (e.g., historical power generation) and textual data (e.g., policy documents) are preprocessed through normalization and tokenization. Next, CNNs extract spatial features from both data modalities, which are... More >
Graphical Abstract
Short and Long-Term Renewable Electricity Demand Forecasting Based on CNN-Bi-GRU Model