Transaction Search Form: please type in any of the fields below.
Date: April 29, 2024 Mon
Time: 8:17 pm
Time: 8:17 pm
Results for forensic sciences
2 results foundAuthor: Hayeslip, David Title: Evaluation of the Forensic DNA Unit Efficiency Improvement Program Summary: This evaluation examined the implementation and outcomes of a 2008 National Institute of Justice program designed to increase the volume of DNA evidence processing through innovative methods designed to increase efficiency instead of expanding laboratory capacities. Four crime labs funded by this program participated in the evaluation. The key implementation findings were that there were significant implementation delays, largely the result of external demands and administrative constraints; and, project management varied across the sites with a laboratory-wide collaborative approach appearing to be most successful. DNA evidence processing productivity and efficiency also varied across sites. Nonetheless, outcome findings did provide support for the hypothesis that DNA processing can be improved in novel and innovative ways besides simply increasing capacity. Details: Washington, DC: Urban Institute, Justice Policy Center, 2012. 190p. Source: Internet Resource: Accessed June 26, 2012 at: http://www.urban.org/UploadedPDF/412575-evaluation-of-the-forensic.pdf Year: 2012 Country: United States URL: http://www.urban.org/UploadedPDF/412575-evaluation-of-the-forensic.pdf Shelf Number: 125406 Keywords: Criminal EvidenceDNA TypingForensic SciencesForensics (U.S.) |
Author: Kuperus, Jasper Title: Catching Criminals by Chance: A Probabilistic Approach to Named Entity Recognition using Targeted Feedback Summary: In forensics, large amounts of unstructured data have to be analyzed in order to nd evidence or to detect risks. For example, the contents of a personal computer or USB data carriers belonging to a suspect. Automatic processing of these large amounts of unstructured data, using techniques like Information Extraction, is inevitable. Named Entity Recognition (NER) is an important rst step in Information Extraction and still a dicult task. A main challenge in NER is the ambiguity among the extracted named entities. Most approaches take a hard decision on which named entities belong to which class or which boundary ts an entity. However, often there is a signi - cant amount of ambiguity when making this choice, resulting in errors by making these hard decisions. Instead of making such a choice, all possible alternatives can be preserved with a corresponding con dence of the probability that it is the correct choice. Extracting and handling entities in such a probabilistic way is called Probabilistic Named Entity Recognition (PNER). Combining the elds of Probabilistic Databases and Information Extraction results in a new eld of research. This research project explores the problem of Probabilistic NER. Although Probabilistic NER does not make hard decisions when ambiguity is involved, it also does not yet resolve ambiguity. A way of resolving this ambiguity is by using user feedback to let the probabilities converge to the real world situation, called Targeted Feedback. The main goal in this project is to improve NER results by using PNER, preventing ambiguity related extraction errors and using Targeted Feedback to reduce ambiguity. This research project shows that Recall values of the PNER results are significantly higher than for regular NER, adding up to improvements over 29%. Using Targeted Feedback, both Precision and Recall approach 100% after full user feedback. For Targeted Feedback, both the order in which questions are posed and whether a strategy attempts to learn from the answers of the user provide performance gains. Although PNER shows to have potential, this research project provides insucient evidence whether PNER is better than regular NER. Details: Enschede, The Netherlands: University of Twente, 2012. 116p. Source: Master's Thesis: Internet Resource: Accessed August 1, 2012 at http://essay.utwente.nl/61639/1/MSc_J_Kuperus_DB_CTIT.pdf Year: 2012 Country: Netherlands URL: http://essay.utwente.nl/61639/1/MSc_J_Kuperus_DB_CTIT.pdf Shelf Number: 125827 Keywords: Computer CrimeForensic SciencesForensics |