A Hybrid Model using Artificial Neural Network and Genetic Algorithm for Degree of Injury Determination
Mohd Hadyan Wardhana1, Abd Samad Hasan Basari2, Abdul Syukor Mohd Jaya3, Dedi Afandi4, Nur Rachman Dzakiyullah5
1Mohd Hadyan Wardhana*, BC.s, MC.s, Center for Advanced Computing Technology (C-ACT), Fakulti Teknologi Maklumat dan Komunikasi, Universiti Teknikal Malaysia Melaka (UTeM), Melaka, Malaysia.
2Prof. Dr. Abd Samad Hasan Basari, Center for Advanced Computing Technology (C-ACT), Fakulti Teknologi Maklumat dan Komunikasi, Universiti Teknikal Malaysia Melaka (UTeM), Melaka, Malaysia.
3Dr. Abdul Syukor Mohd Jaya, Center for Advanced Computing Technology (C-ACT), Fakulti Teknologi Maklumat dan Komunikasi, Universiti Teknikal Malaysia Melaka (UTeM), Melaka, Malaysia.
4Prof. Dr. dr. Dedi Afandi, D.F.M., Sp.F.M.(K), Department of Forensic Medicine and Medicolegal Study, University of Riau, Pekanbaru, Indonesia.
5Nur Rachman Dzakiyullah, Fakulti Teknologi Maklumat dan Komunikasi, Universiti Teknikal Malaysia Melaka (UTeM), Melaka, Malaysia, Faculty of Science and Technology, Department of Information Technology, Universitas „Aisyiyah Yogyakarta (UNISA), Indonesia.
Manuscript received on November 14, 2019. | Revised Manuscript received on 23 November, 2019. | Manuscript published on December 10, 2019. | PP: 1357-1365 | Volume-9 Issue-2, December 2019. | Retrieval Number: B6169129219/2019©BEIESP | DOI: 10.35940/ijitee.B6169.129219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Essentially, determination degree of injury is crucial for to support the law enforcement process. The existing models are deemed difficult in identifying the critical features for degree of injury classification. Some of which are considerable irrelevant and cause the inconsistency decision on process to determine degree of injury among the practitioners. If the Visum et Repertum (VeR) report is not well interpreted, the victim will get injustice decision. The purpose of this study is to develop a hybrid model for determining degree of injury. Based on Visum et Repertum (VeR) data. The model can classify the output of either having a minor, moderate, or serious injury which inclusively stated in Indonesian Penal Code. A hybrid model is developed from literature and case studies are conducted in three hospitals in Pekanbaru, Indonesia. Analysis is performed to discover the suitable component of the model-due to lack of comparison and analysis on the combination of critical features analysis and optimize the classification algorithm. Development and testing of the model are utilized VeR Dataset as private dataset (289 patients’ data). In validating model, three case studies are investigated based on Subject Matter Expert (SME) groups to identify the agreement level. The questionnaires consist of a component, implementation, and viability of model that involved. Hybrid model components are validated by the SMEs, whereby the group determined highest rank of accuracy performance. Result from the questionnaire reveal that the average agreement level of SMEs. In conclusion, the finding shows hybrid model is generated 99.23% accuracy. The model components are implementable as a model and acceptable by the Practitioners as contribution for determining degree of injury.
Keywords: Data Mining, Neural Network, Forensic Medicolegal, Artificial Intelligence.
Scope of the Article: Data Mining