Visual Instruction Tuning for Drone Accident Forensics
The increasing use of drones in both commercial and personal use has led to a growing demand for effective forensic analysis following drone-related accidents. This research focuses on improving forensic analysis through the development of LLaVAFor, a fine-tuned version of the Large Language and Vis...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Ital Publication
2024-12-01
|
| Series: | HighTech and Innovation Journal |
| Subjects: | |
| Online Access: | https://hightechjournal.org/index.php/HIJ/article/view/778 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846100211904020480 |
|---|---|
| author | Arda Surya Editya Tohari Ahmad Hudan Studiawan |
| author_facet | Arda Surya Editya Tohari Ahmad Hudan Studiawan |
| author_sort | Arda Surya Editya |
| collection | DOAJ |
| description | The increasing use of drones in both commercial and personal use has led to a growing demand for effective forensic analysis following drone-related accidents. This research focuses on improving forensic analysis through the development of LLaVAFor, a fine-tuned version of the Large Language and Vision Assistant (LLaVA) model. The objective of this study is to enhance the interpretability of visual instruction tuning for drone accident forensics. LLaVAFor was developed by fine-tuning LLaVA via a specialized dataset of drone accident scenarios. The model's performance was evaluated via the BLEU score, a metric commonly used to assess machine translation and natural language processing models. The results demonstrated that LLaVAFor achieved superior BLEU scores compared with baseline models such as LLaVA, Google Gemini, and ChatGPT. It demonstrates its ability to provide more accurate and contextually relevant analyses. The key innovation in LLaVAFor is its ability to explain forensic findings in the context of drone accidents, making it a valuable tool for investigators. The results show that the model's fine-tuning process on drone-specific datasets enables it to offer detailed, domain-specific insights, improving the accuracy and reliability of forensic analyses in this field. Through these advancements, LLaVAFor represents a step forward in the integration of AI into drone accident investigations.
Doi: 10.28991/HIJ-2024-05-04-01
Full Text: PDF |
| format | Article |
| id | doaj-art-ed9b2df705474c6b964e272c266c0dac |
| institution | Kabale University |
| issn | 2723-9535 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | Ital Publication |
| record_format | Article |
| series | HighTech and Innovation Journal |
| spelling | doaj-art-ed9b2df705474c6b964e272c266c0dac2024-12-30T12:24:56ZengItal PublicationHighTech and Innovation Journal2723-95352024-12-015487088410.28991/HIJ-2024-05-04-01217Visual Instruction Tuning for Drone Accident ForensicsArda Surya Editya0Tohari Ahmad1Hudan Studiawan2Department of Informatics, Institut Teknologi Sepuluh Nopember, Surabaya, East Java,Department of Informatics, Institut Teknologi Sepuluh Nopember, Surabaya, East Java,Department of Informatics, Institut Teknologi Sepuluh Nopember, Surabaya, East Java,The increasing use of drones in both commercial and personal use has led to a growing demand for effective forensic analysis following drone-related accidents. This research focuses on improving forensic analysis through the development of LLaVAFor, a fine-tuned version of the Large Language and Vision Assistant (LLaVA) model. The objective of this study is to enhance the interpretability of visual instruction tuning for drone accident forensics. LLaVAFor was developed by fine-tuning LLaVA via a specialized dataset of drone accident scenarios. The model's performance was evaluated via the BLEU score, a metric commonly used to assess machine translation and natural language processing models. The results demonstrated that LLaVAFor achieved superior BLEU scores compared with baseline models such as LLaVA, Google Gemini, and ChatGPT. It demonstrates its ability to provide more accurate and contextually relevant analyses. The key innovation in LLaVAFor is its ability to explain forensic findings in the context of drone accidents, making it a valuable tool for investigators. The results show that the model's fine-tuning process on drone-specific datasets enables it to offer detailed, domain-specific insights, improving the accuracy and reliability of forensic analyses in this field. Through these advancements, LLaVAFor represents a step forward in the integration of AI into drone accident investigations. Doi: 10.28991/HIJ-2024-05-04-01 Full Text: PDFhttps://hightechjournal.org/index.php/HIJ/article/view/778forensic analysisdrone forensicsllavadrone accident. |
| spellingShingle | Arda Surya Editya Tohari Ahmad Hudan Studiawan Visual Instruction Tuning for Drone Accident Forensics HighTech and Innovation Journal forensic analysis drone forensics llava drone accident. |
| title | Visual Instruction Tuning for Drone Accident Forensics |
| title_full | Visual Instruction Tuning for Drone Accident Forensics |
| title_fullStr | Visual Instruction Tuning for Drone Accident Forensics |
| title_full_unstemmed | Visual Instruction Tuning for Drone Accident Forensics |
| title_short | Visual Instruction Tuning for Drone Accident Forensics |
| title_sort | visual instruction tuning for drone accident forensics |
| topic | forensic analysis drone forensics llava drone accident. |
| url | https://hightechjournal.org/index.php/HIJ/article/view/778 |
| work_keys_str_mv | AT ardasuryaeditya visualinstructiontuningfordroneaccidentforensics AT tohariahmad visualinstructiontuningfordroneaccidentforensics AT hudanstudiawan visualinstructiontuningfordroneaccidentforensics |