AI SearchLeveraging phonological clustering for word-level Bangla Sign language recognition (Record no. 69324)
[ view plain ]
| 000 -LEADER | |
|---|---|
| fixed length control field | 03476nas a2200337 a 4500 |
| 005 - DATE AND TIME OF LATEST TRANSACTION | |
| control field | 20260818145444.0 |
| 008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION | |
| fixed length control field | 260219s20259999th u ms t 000 eng d |
| 035 ## - SYSTEM CONTROL NUMBER | |
| System control number | .b12478039 |
| 099 #9 - LOCAL FREE-TEXT CALL NUMBER (OCLC) | |
| Classification number | AIT Thesis no.CS-25-01 |
| 100 1# - MAIN ENTRY--PERSONAL NAME | |
| Personal name | Nayeem, Jannatun |
| 245 10 - TITLE STATEMENT | |
| Title | Leveraging phonological clustering for word-level Bangla Sign language recognition |
| 260 ## - PUBLICATION, DISTRIBUTION, ETC. | |
| Place of publication, distribution, etc. | Pathum Thani, Thailand : |
| Name of publisher, distributor, etc. | Asian Institute of Technology, |
| Date of publication, distribution, etc. | 2025 |
| 300 ## - PHYSICAL DESCRIPTION | |
| Extent | 63 leaves : |
| Other physical details | ill.+ |
| Accompanying material | 1 online resource |
| 490 1# - SERIES STATEMENT | |
| Series statement | Thesis ; |
| Volume/sequential designation | no.CS-25-01 |
| 500 ## - GENERAL NOTE | |
| General note | A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in Computer Science |
| 502 ## - DISSERTATION NOTE | |
| Dissertation note | Thesis (M. Sc.) - Asian Institute of Technology, 2025 |
| 520 ## - SUMMARY, ETC. | |
| Summary, etc. | Bangla Sign Language (BdSL) recognition presents multifaceted challenges due to signer diversity and spatiotemporal variability. While flat classification pipelines are widely used, they often overlook the underlying phonological relationships among signs that can inform more structured and accurate recognition. To address this gap, we propose a hierarchical recognition framework that integrates phonological clustering into a Bidirectional Long Short-Term Memory (Bi-LSTM)-based sequence modeling pipeline. First, baseline classification{u2014}referring to a flat, non-clustered recognition approach{u2014}is performed us ing five Bi-LSTM configurations of increasing complexity to assess the trade-off between accuracy and model size. The resulting confusion matrices are analyzed to identify sign pairs with high misclassification rates, revealing underlying phonological similarities. Based on this analysis, a confusion-matrix driven clustering strategy is employed to group visually and phonologically similar signs. Cluster-specific feature engineering is then applied, and the same Bi-LSTM architecture is retrained separately within each cluster. Experiments are conducted on a curated 50-class subset of the SignBD-Word dataset. In the baseline setting, the most complex model (Bi-LSTM-1) achieves 91.10% accuracy with 2.6 million parameters. With the proposed confusion-matrix driven clustering architecture, four out of six clusters employing the lightweight Bi-LSTM classifiers outperform the baseline model, reaching up to 94.58% accuracy. Remarkably, the lightweight Bi-LSTM-4 model{u2014}with only 373K parameters (14.4% of Bi LSTM-1){u2014}achieves a weighted average accuracy of 92.60% on cluster-level classification, surpassing the baseline by1.5percentagepoints. Thisreflectsan85.6%reduction in a number of parameters, demonstrating that efficient cluster-specific feature engineering, which allows each model to capture nuanced patterns within each cluster can improve overall predictive accuracy. |
| 650 #0 - SUBJECT ADDED ENTRY--TOPICAL TERM | |
| Topical term or geographic name entry element | Sign language |
| General subdivision | Data processing |
| 700 0# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Chantri Polprasert, |
| Relator term | Chairperson |
| 700 0# - ADDED ENTRY--PERSONAL NAME | |
| Personal name | Mongkol Ekpanyapong, |
| Relator term | Examination Committee |
| 710 2# - ADDED ENTRY--CORPORATE NAME | |
| Corporate name or jurisdiction name as entry element | ADB-Japan Scholarship Program (ADB-JSP), |
| Relator term | Scholarship Donor |
| 810 2# - SERIES ADDED ENTRY--CORPORATE NAME | |
| Corporate name or jurisdiction name as entry element | Asian Institute of Technology. |
| Title of a work | Thesis : |
| Volume/sequential designation | no.CS-25-01 |
| 856 40 - ELECTRONIC LOCATION AND ACCESS | |
| Materials specified | Full-Text |
| Uniform Resource Identifier | <a href="http://203.159.5.9/ait-thesis/Viewer/viewer.php?id=B23610">http://203.159.5.9/ait-thesis/Viewer/viewer.php?id=B23610</a> |
| 907 ## - LOCAL DATA ELEMENT G, LDG (RLIN) | |
| a | .b12478039 |
| b | mnarc |
| c | a |
| 902 ## - LOCAL DATA ELEMENT B, LDB (RLIN) | |
| a | 260227 |
| 998 ## - LOCAL CONTROL INFORMATION (RLIN) | |
| Operator's initials, OID (RLIN) | 0 |
| Cataloger's initials, CIN (RLIN) | 260226 |
| First date, FD (RLIN) | m |
| -- | h |
| -- | a |
| -- | 0 |
| 945 ## - LOCAL PROCESSING INFORMATION (OCLC) | |
| l | mnarc |
| 942 ## - ADDED ENTRY ELEMENTS (KOHA) | |
| Koha item type | 67-Electronic Resource |
| 909 ## - LOCAL ITEMS USED | |
| Barcode | Barcode : - |
| CREATED | CREATED : 2026-02-19 |
| RECORD Id | RECORD # : i13574966 |
| LPATRON | LPATRON : 0 |
| LCHKIN | LCHKIN : - |
| RENEWALS | # RENEWALS : 0 |
| -- | # OVERDUE : 0 |
| -- | IUSE3 : 0 |
| -- | TOT CHKOUT : 0 |
| -- | TOT RENEW : 0 |
| Withdrawn status | Lost status | Damaged status | Not for loan | Home library | Current library | Shelving location | Date acquired | Total checkouts | Full call number | Date last seen | Copy number | Price effective from | Koha item type |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Available for Loans | Asian Institute of Technology Library | Asian Institute of Technology Library | Archives | 18/08/2026 | AIT Thesis no.CS-25-01 | 18/08/2026 | 1 | 18/08/2026 | 67-Electronic Resource |