Dataset Information

An automatic behavior recognition system classifies animal behaviors using movements and their temporal context.

ABSTRACT: Animals can perform complex and purposeful behaviors by executing simpler movements in flexible sequences. It is particularly challenging to analyze behavior sequences when they are highly variable, as is the case in language production, certain types of birdsong and, as in our experiments, flies grooming. High sequence variability necessitates rigorous quantification of large amounts of data to identify organizational principles and temporal structure of such behavior. To cope with large amounts of data, and minimize human effort and subjective bias, researchers often use automatic behavior recognition software. Our standard grooming assay involves coating flies in dust and videotaping them as they groom to remove it. The flies move freely and so perform the same movements in various orientations. As the dust is removed, their appearance changes. These conditions make it difficult to rely on precise body alignment and anatomical landmarks such as eyes or legs and thus present challenges to existing behavior classification software. Human observers use speed, location, and shape of the movements as the diagnostic features of particular grooming actions. We applied this intuition to design a new automatic behavior recognition system (ABRS) based on spatiotemporal features in the video data, heavily weighted for temporal dynamics and invariant to the animal's position and orientation in the scene. We use these spatiotemporal features in two steps of supervised classification that reflect two time-scales at which the behavior is structured. As a proof of principle, we show results from quantification and analysis of a large data set of stimulus-induced fly grooming behaviors that would have been difficult to assess in a smaller dataset of human-annotated ethograms. While we developed and validated this approach to analyze fly grooming behavior, we propose that the strategy of combining alignment-invariant features and multi-timescale analysis may be generally useful for movement-based classification of behavior from video data.

SUBMITTER: Ravbar P

PROVIDER: S-EPMC6779137 | biostudies-literature | 2019 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

An automatic behavior recognition system classifies animal behaviors using movements and their temporal context.

Ravbar Primoz P Branson Kristin K Simpson Julie H JH

Journal of neuroscience methods 20190812

Animals can perform complex and purposeful behaviors by executing simpler movements in flexible sequences. It is particularly challenging to analyze behavior sequences when they are highly variable, as is the case in language production, certain types of birdsong and, as in our experiments, flies grooming. High sequence variability necessitates rigorous quantification of large amounts of data to identify organizational principles and temporal structure of such behavior. To cope with large amount ...[more]

PMID: 31415845

Similar Datasets

Project description:BackgroundTaiwan has insufficient nursing resources due to the high turnover rate of health care providers. Therefore, reducing the heavy workload of these employees is essential. Herein, speech transcription, which has various potential clinical applications, was employed for the documentation of nursing records. The requirement of including only one speaker per transcription facilitated data collection and system development. Moreover, authorization from patients was unnecessary.ObjectiveThe aim of this study was to construct a speech recognition system for nursing records such that health care providers can complete nursing records without typing or with only a few edits.MethodsNursing records in Taiwan are mainly written in Mandarin, with technical terms and abbreviations presented in both Mandarin and English. Therefore, the training set consisted of English code-switching information. Next, transfer learning (TL) and meta-TL (MTL) methods, which perform favorably in code-switching scenarios, were applied.ResultsAs of September 2021, the China Medical University Hospital Artificial Intelligence Speech (CMaiSpeech) data set was established by manually annotating approximately 100 hours of recordings from 525 speakers. The word error rate (WER) of the benchmark model of syllable-based TL was 29.54% in code-switching. The WER of the proposed model of syllable-based MTL was 22.20% in code-switching. The test set comprised 17,247 words. Moreover, in a clinical case, the proposed model of syllable-based MTL yielded a WER of 31.06% in code-switching. The clinical test set contained 1159 words.ConclusionsThis paper has two main contributions. First, the CMaiSpeech data set-a Mandarin-English corpus-has been established. Health care providers in Taiwan are often compelled to use a mixture of Mandarin and English in nursing records. Second, an automatic speech recognition system for nursing record document conversion was proposed. The proposed system can shorten the work handover time and further reduce the workload of health care providers.

Project description:PROBLEM/CONDITION:In 2017, a total of 70,237 persons in the United States died from a drug overdose, and 67.8% of these deaths involved an opioid. Historically, the opioid overdose epidemic in the United States has been closely associated with a parallel increase in opioid prescribing and with widespread misuse of these medications. National and state policy makers have introduced multiple measures to attempt to assess and control the opioid overdose epidemic since 2010, including improvements in surveillance systems. PERIOD COVERED:2010-2016 DESCRIPTION OF SYSTEM: The Prescription Behavior Surveillance System (PBSS) was created in 2011. Its goal was to track rates of prescribing of controlled substances and possible misuse of such drugs using data from selected state prescription drug monitoring programs (PDMP). PBSS data measure prescribing behaviors for prescription opioids using multiple measures calculated from PDMP data including 1) opioid prescribing, 2) average daily opioid dosage, 3) proportion of patients with daily opioid dosages ?90 morphine milligram equivalents, 4) overlapping opioid prescriptions, 5) overlapping opioid and benzodiazepine prescriptions, and 6) multiple-provider episodes. For this analysis, PBSS data were available for 2010-2016 from 11 states representing approximately 38.0% of the U.S. POPULATION:Average quarterly percent changes (AQPC) in the rates of opioid prescribing and possible opioid misuse measures were calculated for each state. RESULTS AND INTERPRETATION:Opioid prescribing rates declined in all 11 states during 2010-2016 (range: 14.9% to 33.0%). Daily dosage declined least (AQPC: -0.4%) in Idaho and Maine, and most (AQPC: -1.6%) in Florida. The percentage of patients with high daily dosage had AQPCs ranging from -0.4% in Idaho to -2.3% in Louisiana. Multiple-provider episode rates declined by at least 62% in the seven states with available data. Variations in trends across the 11 states might reflect differences in state policies and possible differential effects of similar policies. PUBLIC HEALTH ACTIONS:Use of PDMP data from individual states enables a more detailed examination of trends in opioid prescribing behaviors and indicators of possible misuse than is feasible with national commercially available prescription data. Comparison of opioid prescribing trends among states can be used to monitor the temporal association of national or state policy interventions and might help public health policymakers recognize changes in the use or possible misuse of controlled prescription drugs over time and allow for prompt intervention through amended or new opioid-related policies.

Dataset Information

An automatic behavior recognition system classifies animal behaviors using movements and their temporal context.

Publications

An automatic behavior recognition system classifies animal behaviors using movements and their temporal context.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets