Drug recognition expert evaluations made using limited data.
نویسندگان
چکیده
The Drug Evaluation Classification (DEC) Program is used by Drug Recognition Expert (DRE) officers to determine whether a suspect is under the influence of a drug or drugs at the time of arrest, and, if so, what category of drug(s). The goal of this project was to investigate the relative importance of face-to-face interactions with the suspect, physical evidence (drugs or paraphernalia found), and confessions/statements made by the suspect (or others) in making these determinations. Seventy records of DRE evaluations were selected from a database containing information from all evaluations conducted in Oregon between 1996 and 1998. Each of the 70 records represented a suspect who had either taken a drug from one of four categories (CNS depressant, CNS stimulant, narcotic analgesic, or cannabis) or who had not taken a drug. To be included, the original DRE evaluation and the subsequent toxicology analysis had to agree that the suspect was under the influence of a drug from one of the four categories or not under the influence of a drug. Records from the 70 cases were submitted in written form to 18 Oregon DREs with statements made by suspects or arresting officers, confessions, toxicology results, and descriptions of drugs or paraphernalia found on the suspect omitted. Based only on the written reports of direct observations, and with physiological and psychophysical test results, the DREs attempted to determine whether each of the 70 suspects was under the influence of a drug or drugs, and, if so, what category of drug(s). If the officers determined that a suspect was under the influence of a drug, their accuracy in specifying the drug category was 81% for cannabis, 94% for narcotic analgesics, 78% for CNS stimulants, and 69% for CNS depressants. Overall accuracy in recognizing drug intoxication was 95%. These percentages indicate that although face-to-face interactions, physical evidence, and confessions/statements can be useful adjuncts to DRE decision-making, the majority of drug category decisions can be made solely on the basis of recorded suspect observations and DRE evaluation results.
منابع مشابه
Off-line Arabic Handwritten Recognition Using a Novel Hybrid HMM-DNN Model
In order to facilitate the entry of data into the computer and its digitalization, automatic recognition of printed texts and manuscripts is one of the considerable aid to many applications. Research on automatic document recognition started decades ago with the recognition of isolated digits and letters, and today, due to advancements in machine learning methods, efforts are being made to iden...
متن کاملNeural Network Based Fuzzy Membership Function Estimation . Application to Uncertain Time - Varying Systems Supervision
Within the framework of fuzzy logic for pattern recognition, we propose a neural network based membership function procedure. The estimate is obtained as the output of a multilayer network trained to minimize a fuzziness measure of the concept to be learnt. This method is shown to be able to deal with probabilistic, resolutional and fuzzy uncertainty. Fuzziness estimation is also made possible ...
متن کاملExtraction of Drug Crime Patterns and Identifying People at Risk Using Data Mining Techniques
Introduction: In recent years, technology advancement and the growth of information technology in organizations have provided a huge source of data stored in the field of drug-related offenses. Analyzing these data and discovering hidden patterns in it can help detect and prevent the occurrence of crimes in this area. This paper aimed to identify the susceptible people to drug trafficking in Si...
متن کاملExtraction of Drug Crime Patterns and Identifying People at Risk Using Data Mining Techniques
Introduction: In recent years, technology advancement and the growth of information technology in organizations have provided a huge source of data stored in the field of drug-related offenses. Analyzing these data and discovering hidden patterns in it can help detect and prevent the occurrence of crimes in this area. This paper aimed to identify the susceptible people to drug trafficking in Si...
متن کاملMonte-Carlo Tree Search
representation of the game. It was programmed in LISP. Further use of abstraction was also studied by Friedenbach (1980). The combination of search, heuristics, and expert systems led to the best programs in the eighties. At the end of the eighties a new type of Go programs emerged. These programs made an intensive use of pattern recognition. This approach was discussed in detail by Boon (1990)...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Forensic science international
دوره 130 2-3 شماره
صفحات -
تاریخ انتشار 2002