Article Per Year (5 Year)
p-Index From 2021 - 2026
0.562
P-Index
This Author published in this journals
All Journal Journal of Technology Informatics and Engineering International Journal of Graphic Design
Lumeng Han
International Agricultural Development, University of California, Davis, CA, USA
Arts Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Domain-Shift-Aware Climate-Smart Crop Portfolio Advisory for Nepal with Self-Supervised Tabular Learning and Conformal Shortlists Lumeng Han; Derek Zhou
Journal of Technology Informatics and Engineering Vol. 4 No. 2 (2025): AUGUST | JTIE : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v4i2.592

Abstract

Crop advisory models can perform well on balanced benchmarks while failing under unfamiliar environmental or household conditions. This study evaluates two separate research tracks: crop-label classification using 2,200 agronomic benchmark records and observed crop-portfolio prediction using 43,753 village-census households and 981 TAFSSA households in Nepal. Eight crop classifiers were compared within a training pool, with independent temperature-calibration, conformal-calibration, and test subsets. Household models were evaluated under random and geographic holdouts, including 30 paired community-level ablations. An external explanation-consistency experiment used 900 held-out, human-annotated RAGTruth responses. Random forest attained the highest cross-validated macro-F1 (0.992), while LightGBM had the lowest conventional-model log loss (0.059). Temperature scaling produced negligible change in held-out log loss. At 90% nominal coverage, adaptive prediction sets included the benchmark label in 438 of 440 cases, with a mean of 1.09 crops. Environmental-cluster holdouts reduced macro-F1 to 0.000–0.656, partly because some test crops were absent from training. Village-census logistic-regression macro average precision declined from 0.680 under random partitioning to 0.578 under district holdout for the same test households. TAFSSA cross-district values were 0.332 and 0.445. A fixed-split contextual gain did not persist across community holdouts: full context reduced macro average precision by 0.037 relative to farm-only predictors. On RAGTruth, numeric checks detected 132 of 579 erroneous responses; a source-linked lexical screen detected 432 but also rejected 102 of 321 valid responses. The findings support cautious interpretation of benchmark shortlists and household associations. The components remain a research prototype without end-to-end or field validation of agricultural decisions in Nepal.
Lightweight Image–Text Triage for Rice Leaf Diseases with Clarify-or-Abstain Decisions and Nepal-Context Advisory Support Lumeng Han; Derek Zhou
Journal of Technology Informatics and Engineering Vol. 4 No. 1 (2025): APRIL | JTIE : Journal of Technology Informatics and Engineering
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/jtie.v4i1.593

Abstract

Image-based rice disease screening requires assessment of unfamiliar conditions, degraded photographs, and the evidence used for advice. This study evaluates a modular image–text workflow with separately trained visual and retrieval components. A rotation- and reflection-aware audit of 5,932 rice leaf images identified 343 similarity groups for leakage-reduced training, validation, and testing. Seven lightweight classifiers and a 24,724-parameter CNN were evaluated alongside open-set rejection, image-quality triage, simulated recapture, and external testing on 10,333 exact-unique Paddy Doctor images. Color-texture logistic regression achieved 78.41% grouped-test accuracy and the CNN achieved 81.03%; their accuracies on 4,232 external images from the four known classes fell to 13.33% and 12.55%, respectively. External unknown-detection AUROCs were 0.512 for Mahalanobis scoring and 0.486 for CNN nonconfidence. Across 7,745 scoped CROP records, reranked retrieval recovered the paired answer within five candidates for 934/1,168 test queries (79.97%). Evidence-assisted benchmark accuracy was 65.21% on 365 questions and 41.34% on 179 without an exact question match in the retrieval collection. Four advisory gates enforced disease, location, treatment, and numeric-rate rules, with a trade-off between answer delivery and reference-answer retention. Nepal-context retrieval remained preliminary: the reranker succeeded on 7/8 queries (87.50%; Wilson 95% CI, 52.91–97.76%). Classification, triage, and advisory retrieval provide separate levels of evidence. The findings support further investigation of the workflow, while the external failures preclude claims of reliable field deployment.
From Field Geometry to Jewelry Interfaces: Multimodal AI-Assisted Shape Translation and Evidence-Grounded Agricultural Storytelling Evelyn Liu; Lumeng Han
International Journal of Graphic Design Vol. 3 No. 1 (2025): May | IJGD: International Journal of Graphic Design
Publisher : University of Science and Computer Technology

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51903/ijgd.v3i1.4276

Abstract

This study develops a field-to-ornament framework connecting agricultural field geometry, computational jewelry design, and evidence-grounded interface storytelling. The main design pipeline uses 350 Fields2Benchmark polygons from the Netherlands, Lithuania, and Estonia as authoritative sources for contour translation. Five abstraction levels are evaluated through geometric similarities and a Geometry Preservation Score (GPS). The Balanced setting retains mean GPS 93.46, compared with 95.06 for Subtle and 88.06 for Abstract. The non-Trace ranking persists across 15,000 sampled weight–scale combinations, although orientation-only weighting reverses Subtle and Balanced. Balanced remains a heuristic demonstration choice without evidence of aesthetic preference. Optional image-recovery experiments assess the limitations of deriving contours when vector geometry is unavailable. On 53 overlay-suppressed annotated map plates, Random Forest achieves mean IoU 0.5417, boundary F1 0.2119, and absolute area error 53.56%. A separate 350-tile AI4Boundaries subset yields modest labelled-extent recovery on 70 aerial test tiles; contour smoothing does not correct prediction errors. Four provenance-card designs are instantiated for 30 fields, producing 120 deterministic audits. Balanced disclosure scores 20.00 and the unsupported minimal claim 100.00 under the proposed overclaim rubric. Sensitivity and controlled content–layout comparisons characterize the rubric's behavior, without measuring comprehension or trust. The framework documents how field geometry can inform two-dimensional ornament concepts while distinguishing design provenance from claims about crop identity, ownership, farming practice, material origin, or environmental benefit.
Co-Authors Derek Zhou Evelyn Liu