Nanda Kumar Tharu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Nanda Kumar Tharu has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
- Arsanchai Sukkuea
School of Engineering and Technology, Walailak University, Nakhon Si Thammarat 80160, Thailand
3 shared publications - Pensiri Akkajit
Faculty of Technology and Environment, Prince of Songkla University, Phuket Campus, Phuket 83120, Thailand
3 shared publications - Anuja Rijal
National Potato Research Program, Nepal Agricultural Research Council (NARC), Lalitpur, Nepal
1 shared publication - Jarina Joshi
Central Department of Biotechnology, Tribhuvan University, Kirtipur, Kathmandu, Nepal
1 shared publication - Kunjan Mishra
Central Department of Biotechnology, Tribhuvan University, Kathmandu, Nepal
1 shared publication - Nat Wannawas
School of Engineering and Technology, Walailak University, 222 Thaiburi, Thasala, Nakhon Si Thammarat 80160, Thailand
1 shared publication
Latest Publications
- Open Access
- 6 November 2026
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8 (11) , 366
Deep Learning Stock Index Forecasting Against Tuned Learners and Naive Baselines Under a Leakage-Free Protocol
Deep learning forecasters of stock index direction often report high accuracy, but results are rarely checked under leakage-free protocols, against naive baselines, or across markets. We compared compact deep networks, classical learners, and naive rules for next-day direction over 3910 out-of-sample sessions (2022–2025), with SET100, the S&P 500, and CSI 300 as confirmatory markets and SET50, whose test years an earlier single-market version of this work had used, as exploratory. All models shared one point-in-time contract with expanding windows, purged boundaries, and train-only scaling; tuned and extended arms (GRU, TCN, DLinear, PatchTST-style, and MLP networks) selected settings on validation windows only, and the comparison was repeated with stationary features. No network showed a significant advantage over logistic regression or persistence in any confirmatory market, with original or stationary features, and equivalence within ±2 points was not established, so small advantages can be neither confirmed nor excluded. Cross-entropy networks mostly collapsed to all-up forecasts (AUC 0.43–0.55). A tuned random forest on CSI 300 (55.0% balanced accuracy) outperformed an independence benchmark in the Pesaran–Timmermann test after joint adjustment but showed no significant paired improvement over the competing baselines and lost significance with stationary features; it remains a candidate for prospective testing, not evidence of dependable skill. The study evaluates directional forecasting, not trading profitability. Single protocol errors raised the raw accuracy to 80%, and reporting 100 minus the mean absolute percentage error gave 99%. Code and predictions are openly available.
- 6 November 2026
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8 (11) , 366
Open AccessDeep Learning Stock Index Forecasting Against Tuned Learners and Naive Baselines Under a Leakage-Free Protocol
Deep learning forecasters of stock index direction often report high accuracy, but results are rarely checked under leakage-free protocols, against naive baselines, or across markets. We compared compact deep networks, classical learners, and naive rules for next-day direction over 3910 out-of-sample sessions (2022–2025), with SET100, the S&P 500, and CSI 300 as confirmatory markets and SET50, whose test years an earlier single-market version of this work had used, as exploratory. All models shared one point-in-time contract with expanding windows, purged boundaries, and train-only scaling; tuned and extended arms (GRU, TCN, DLinear, PatchTST-style, and MLP networks) selected settings on validation windows only, and the comparison was repeated with stationary features. No network showed a significant advantage over logistic regression or persistence in any confirmatory market, with original or stationary features, and equivalence within ±2 points was not established, so small advantages can be neither confirmed nor excluded. Cross-entropy networks mostly collapsed to all-up forecasts (AUC 0.43–0.55). A tuned random forest on CSI 300 (55.0% balanced accuracy) outperformed an independence benchmark in the Pesaran–Timmermann test after joint adjustment but showed no significant paired improvement over the competing baselines and lost significance with stationary features; it remains a candidate for prospective testing, not evidence of dependable skill. The study evaluates directional forecasting, not trading profitability. Single protocol errors raised the raw accuracy to 80%, and reporting 100 minus the mean absolute percentage error gave 99%. Code and predictions are openly available.
- Open Access
- 1 November 2026
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8 (11) , 360
ByteScope: Detection-Aware Learning for Robust Visual Malware Recognition Under Leakage-Audited, Open-World Evaluation
Visual malware recognition classifies byte-plot images of executables and reports near-perfect accuracy, yet it is rarely evaluated the way a deployed detector would be. We present ByteScope, a framework that adds a cosine-margin family classifier, a supervised contrastive embedding for rejecting unknown families, and a class-balanced malware detection head calibrated at a fixed false-positive rate to an image backbone, together with a leakage-audited, open-world evaluation protocol, and we evaluate it on MaleVis against nine convolutional neural network (CNN), Vision Transformer and hybrid backbones with three seeds. A perceptual-hash audit, confirmed by pixel-level, embedding-based and visual inspection, shows that 50.6% of the test images and 70.0% of the malware have a same-class near-duplicate in the training split. On Swin-T, ByteScope reaches the highest mean 26-class accuracy (89.3%) and de-duplicated accuracy (78.4%), matches the best baseline in unknown-family detection (area under the receiver operating characteristic curve, AUROC, 0.925 against 0.922), and halves the evasion rate of its backbone under image-domain benign padding at a validation-calibrated threshold (15.2% against 36.0%) by making the operating point more stable, an effect that we trace to the normalized cosine classifier; at matched test false-positive rates, robustness is similar. At a 1% false-positive rate, neither ByteScope nor any of the nine baselines detects more than 3% of malware on average, whereas several variants of our hybrid CNN–Transformer architecture exceed this level (6.8 to 48.1%, with a large variance across seeds), and roughly 52 benign validation images cannot certify any rate below 5.6%. We release the code, the near-duplicate list and the splits.
- 1 November 2026
- Published by MDPI AG in Machine Learning and Knowledge Extraction
- Vol. 8 (11) , 360
Open AccessByteScope: Detection-Aware Learning for Robust Visual Malware Recognition Under Leakage-Audited, Open-World Evaluation
Visual malware recognition classifies byte-plot images of executables and reports near-perfect accuracy, yet it is rarely evaluated the way a deployed detector would be. We present ByteScope, a framework that adds a cosine-margin family classifier, a supervised contrastive embedding for rejecting unknown families, and a class-balanced malware detection head calibrated at a fixed false-positive rate to an image backbone, together with a leakage-audited, open-world evaluation protocol, and we evaluate it on MaleVis against nine convolutional neural network (CNN), Vision Transformer and hybrid backbones with three seeds. A perceptual-hash audit, confirmed by pixel-level, embedding-based and visual inspection, shows that 50.6% of the test images and 70.0% of the malware have a same-class near-duplicate in the training split. On Swin-T, ByteScope reaches the highest mean 26-class accuracy (89.3%) and de-duplicated accuracy (78.4%), matches the best baseline in unknown-family detection (area under the receiver operating characteristic curve, AUROC, 0.925 against 0.922), and halves the evasion rate of its backbone under image-domain benign padding at a validation-calibrated threshold (15.2% against 36.0%) by making the operating point more stable, an effect that we trace to the normalized cosine classifier; at matched test false-positive rates, robustness is similar. At a 1% false-positive rate, neither ByteScope nor any of the nine baselines detects more than 3% of malware on average, whereas several variants of our hybrid CNN–Transformer architecture exceed this level (6.8 to 48.1%, with a large variance across seeds), and roughly 52 benign validation images cannot certify any rate below 5.6%. We release the code, the near-duplicate list and the splits.
- Open Access
- 13 October 2026
- Published by Elsevier in Results in Engineering
- Vol. 32
Modeling the impact of climatic variables on cereal crop production in the Terai region of Nepal
- 13 October 2026
- Published by Elsevier in Results in Engineering
- Vol. 32
Open AccessModeling the impact of climatic variables on cereal crop production in the Terai region of Nepal
- 5 May 2025
- Published by Springer Nature in Potato Research
- Vol. 68 (3) , 3147-3160
Meristem Culture, Callus Induction, and Regeneration Optimization of Cultivated and Unreleased Potatoes of Nepal
- 5 May 2025
- Published by Springer Nature in Potato Research
- Vol. 68 (3) , 3147-3160
Meristem Culture, Callus Induction, and Regeneration Optimization of Cultivated and Unreleased Potatoes of Nepal