CASE PRESENTATION: An assemblage of unidentified, incomplete, highly fragmented skeletal remains were found scattered on a bare area of land in a forest. There was evidence of an explosion given the pattern of scattered evidentiary material of explosive and ballistic nature. Laboratory analysis of white powder found within the explosive material confirmed the presence of high impact C4-explosive trace containing cyclotrimethylene trinitramin [Royal Demolition Explosive (RDX)] & pentaerythritol tetranitrate (PETN). It took meticulous multidisciplinary efforts to confirm the identity of the victim that was marred by the severe fragmentation and skeletalization of the remains. The initial radiologic interpretation focused more on identification of foreign bodies and supporting documentation of fragmentation. With the current availability of post computed tomography (PMCT) in our center, we reexamined the value and potential of PMXR and PMCT as an adjunctive tool for biological profiling.
CONCLUSION: This was the first case of C4-blast related death reported in Malaysia. The multidisciplinary approach in efforts to identify the victim may serve as a guide in managing, coordinating and maximizing the expertise of different forensic specialists, with emphasis on anthropologic and radiologic collaboration.
METHODS/RESULTS: 32 cases of which 12 females and 20 male and 18 out of 32 cases were aged below 40. All of the cases were examined macroscopically and microscopically. 30 out of 32 cases (93%) died due to rupture associated with the AD. Two unusual complications were proximal extension of AD into left coronary artery (CA) with intramural haematoma blocking the vessel and AD involving the ostium of the right CA resulting in avulsion of the right CA from the aorta. Mode of death in both these cases were myocardial ischemia. Sections of the aorta in all cases confirmed extensive cystic medial degeneration with disorganisation, fragmentation and disappearance of the elastin fibres with increased collagen and smooth muscle nuclear degeneration.
CONCLUSION: Pathologists should be thorough when examining the aorta, the aortic valve and root in AD. When a rupture site cannot be found it is important to look for unusual complications involving the CAs. Histology plays an important role to corroborate the cause of death.
METHODS: For experiments, the autopsy reports belonging to eight different causes of death were collected, preprocessed and converted into 43 master feature vectors using various schemes for feature extraction, representation, and reduction. The six different text classification techniques were applied on these 43 master feature vectors to construct a classification model that can predict the cause of death. Finally, classification model performance was evaluated using four performance measures i.e. overall accuracy, macro precision, macro-F-measure, and macro recall.
RESULTS: From experiments, it was found that that unigram features obtained the highest performance compared to bigram, trigram, and hybrid-gram features. Furthermore, in feature representation schemes, term frequency, and term frequency with inverse document frequency obtained similar and better results when compared with binary frequency, and normalized term frequency with inverse document frequency. Furthermore, the chi-square feature reduction approach outperformed Pearson correlation, and information gain approaches. Finally, in text classification algorithms, support vector machine classifier outperforms random forest, Naive Bayes, k-nearest neighbor, decision tree, and ensemble-voted classifier.
CONCLUSION: Our results and comparisons hold practical importance and serve as references for future works. Moreover, the comparison outputs will act as state-of-art techniques to compare future proposals with existing automated text classification techniques.