A Systematic Methodology to Evaluate Prediction Models for Driving Style Classification.

Identifying driving styles using classification models with in-vehicle data can provide automated feedback to drivers on their driving behavior, particularly if they are driving safely. Although several classification models have been developed for this purpose, there is no consensus on which classifier performs better at identifying driving styles. Therefore, more research is needed to evaluate classification models by comparing performance metrics. In this paper, a data-driven machine-learning methodology for classifying driving styles is introduced. This methodology is grounded in well-established machine-learning (ML) methods and literature related to driving-styles research. The methodology is illustrated through a study involving data collected from 50 drivers from two different cities in a naturalistic setting. Five features were extracted from the raw data. Fifteen experts were involved in the data labeling to derive the ground truth of the dataset. The dataset fed five different models (Support Vector Machines (SVM), Artificial Neural Networks (ANN), fuzzy logic, k-Nearest Neighbor (kNN), and Random Forests (RF)). These models were evaluated in terms of a set of performance metrics and statistical tests. The experimental results from performance metrics showed that SVM outperformed the other four models, achieving an average accuracy of 0.96, F1-Score of 0.9595, Area Under the Curve (AUC) of 0.9730, and Kappa of 0.9375. In addition, Wilcoxon tests indicated that ANN predicts differently to the other four models. These promising results demonstrate that the proposed methodology may support researchers in making informed decisions about which ML model performs better for driving-styles classification.

mlCAF: Multi-Level Cross-Domain Semantic Context Fusioning for Behavior Identification.

The emerging research on automatic identification of user's contexts from the cross-domain environment in ubiquitous and pervasive computing systems has proved to be successful. Monitoring the diversified user's contexts and behaviors can help in controlling lifestyle associated to chronic diseases using context-aware applications. However, availability of cross-domain heterogeneous contexts provides a challenging opportunity for their fusion to obtain abstract information for further analysis. This work demonstrates extension of our previous work from a single domain (i.e., physical activity) to multiple domains (physical activity, nutrition and clinical) for context-awareness. We propose multi-level Context-aware Framework (mlCAF), which fuses the multi-level cross-domain contexts in order to arbitrate richer behavioral contexts. This work explicitly focuses on key challenges linked to multi-level context modeling, reasoning and fusioning based on the mlCAF open-source ontology. More specifically, it addresses the interpretation of contexts from three different domains, their fusioning conforming to richer contextual information. This paper contributes in terms of ontology evolution with additional domains, context definitions, rules and inclusion of semantic queries. For the framework evaluation, multi-level cross-domain contexts collected from 20 users were used to ascertain abstract contexts, which served as basis for behavior modeling and lifestyle identification. The experimental results indicate a context recognition average accuracy of around 92.65% for the collected cross-domain contexts.

IRT Analysis of the Frontal Systems Behavior Scale: Identifying the Best Items for Use with Geriatric Patients in Primary Care.

OBJECTIVE: The Frontal Systems Behavior Scale (FrSBe) (Grace & Malloy, 2001) assesses behavioral dysfunction associated with frontal-subcortical damage; it is often used to measure these indicators of executive dysfunction in older adults with possible dementia. Although prior research supports the FrSBe's clinical utility and factorial validity, little attempt has been made to examine which items are most useful for geriatric cases. The goal of the present study is to identify these items. METHOD: Data from 304 older patients referred for neuropsychological assessment were used to examine the FrSBe's three subscales: Apathy (A; 14 items), Executive Dysfunction (E; 17 items), and Disinhibition (D; 15 items). Item properties were investigated using the Graded Response Model, a two-parameter polytomous item response theory model. RESULTS: Difficulty parameters, discrimination parameters, and information curves identified 18 items that effectively discriminate (a ≥ 1.70) between levels of behavioral dysfunction and measure a range of dysfunction (bA: -1.23 - 2.22; bD: -.29 - 2.14; bE: -1.81 - 1.77). CONCLUSIONS: Most FrSBe items were effective at discriminating various levels of behavioral dysfunction, though weaker items were identified. CLINICAL IMPLICATIONS: The findings suggest the FrSBe is a useful clinical tool when working with a geriatric population, though some items provide more information than others.

The emergence of psychiatric semiology during the Age of Revolution: evolving concepts of 'normal' and 'pathological'.

This article addresses some important questions in psychiatric semiology. The concept of a sign is crucial in psychiatry. How do signs emerge, and what gives them validity and legitimacy? What are the boundaries of 'normal' and 'pathological' behaviour and mental experiences? To address these issues, we analyse the characteristics and rules that govern semiological signs and clinical elements. We examine 'normality' from the perspective of Georges Canguilehm and compare the differences of 'normal' in physiology and psychiatry. We then examine the history and the philosophical, linguistic and medical-psychiatric origins of semiology during the eighteenth and nineteenth centuries (the Age of Revolution). The field of rhetoric and oratory has emphasized the importance of passions, emotions and language as applied to signs of madness. Another perspective on semiology, provided by Michel Foucault, lays stress on the concept of 'instinct' and the axis of voluntary-involuntary behaviour. Finally, we analyse how statistics and eugenics have played an important role in our current conceptualization of the norm and therefore the scientific discourse behind the established clinical signs.

Traffic Behavior Recognition Using the Pachinko Allocation Model.

CCTV-based behavior recognition systems have gained considerable attention in recent years in the transportation surveillance domain for identifying unusual patterns, such as traffic jams, accidents, dangerous driving and other abnormal behaviors. In this paper, a novel approach for traffic behavior modeling is presented for video-based road surveillance. The proposed system combines the pachinko allocation model (PAM) and support vector machine (SVM) for a hierarchical representation and identification of traffic behavior. A background subtraction technique using Gaussian mixture models (GMMs) and an object tracking mechanism based on Kalman filters are utilized to firstly construct the object trajectories. Then, the sparse features comprising the locations and directions of the moving objects are modeled by PAMinto traffic topics, namely activities and behaviors. As a key innovation, PAM captures not only the correlation among the activities, but also among the behaviors based on the arbitrary directed acyclic graph (DAG). The SVM classifier is then utilized on top to train and recognize the traffic activity and behavior. The proposed model shows more flexibility and greater expressive power than the commonly-used latent Dirichlet allocation (LDA) approach, leading to a higher recognition accuracy in the behavior classification.

Using wearable cameras to categorise type and context of accelerometer-identified episodes of physical activity.

BACKGROUND: Accelerometers can identify certain physical activity behaviours, but not the context in which they take place. This study investigates the feasibility of wearable cameras to objectively categorise the behaviour type and context of participants' accelerometer-identified episodes of activity. METHODS: Adults were given an Actical hip-mounted accelerometer and a SenseCam wearable camera (worn via lanyard). The onboard clocks on both devices were time-synchronised. Participants engaged in free-living activities for 3 days. Actical data were cleaned and episodes of sedentary, lifestyle-light, lifestyle-moderate, and moderate-to-vigorous physical activity (MVPA) were identified. Actical episodes were categorised according to their social and environmental context and Physical Activity (PA) compendium category as identified from time-matched SenseCam images. RESULTS: There were 212 days considered from 49 participants from whom SenseCam images and associated Actical data were captured. Using SenseCam images, behaviour type and context attributes were annotated for 386 (out of 3017) randomly selected episodes (such as walking/transportation, social/not-social, domestic/leisure). Across the episodes, 12 categories that aligned with the PA Compendium were identified, and 114 subcategory types were identified. Nineteen percent of episodes could not have their behaviour type and context categorized; 59% were outdoors versus 39% indoors; 33% of episodes were recorded as leisure time activities, with 33% transport, 18% domestic, and 15% occupational. 33% of the randomly selected episodes contained direct social interaction and 22% were in social situations where the participant wasn't involved in direct engagement. CONCLUSION: Wearable camera images offer an objective method to capture a spectrum of activity behaviour types and context across 81% of accelerometer-identified episodes of activity. Wearable cameras represent the best objective method currently available to categorise the social and environmental context of accelerometer-defined episodes of activity in free-living conditions.

Principles underlying the use of multiple informants' reports.

Researchers use multiple informants' reports to assess and examine behavior. However, informants' reports commonly disagree. Informants' reports often disagree in their perceived levels of a behavior ("low" versus "elevated" mood), and examining multiple reports in a single study often results in inconsistent findings. Although researchers often espouse taking a multi-informant assessment approach, they frequently address informant discrepancies using techniques that treat discrepancies as measurement error. Yet, recent work indicates that researchers in a variety of fields often may be unable to justify treating informant discrepancies as measurement error. In this review, the authors advance a framework (Operations Triad Model) outlining general principles for using and interpreting informants' reports. Using the framework, researchers can test whether or not they can extract meaningful information about behavior from discrepancies among multiple informants' reports. The authors provide supportive evidence for this framework and discuss its implications for hypothesis testing, study design, and quantitative review.

[Interpreting change scores of the Behavioural Rating Scale for Geriatric Inpatients (GIP)]. / Wat is een reëel verschil bij herhaalde metingen met de Gedragsobservatieschaal voor de Intramurale Psychogeriatrie (GIP)? : Onderzoek bij deelnemers aan psychogeriatrische dagbehandeling.

The Behavioural Rating Scale for Geriatric Inpatients (GIP) consists of fourteen, Rasch modelled subscales, each measuring different aspects of behavioural, cognitive and affective disturbances in elderly patients. Four additional measures are derived from the GIP: care dependency, apathy, cognition and affect. The objective of the study was to determine the reproducibility of the 18 measures. A convenience sample of 56 patients in psychogeriatric day care was assessed twice by the same observer (a professional caregiver). The median time interval between rating occasions was 45 days (interquartile range 34-58 days). Reproducibility was determined by calculating intraclass correlation coefficients (ICC agreement) for test-retest reliability. The minimal detectable difference (MDD) was calculated based on the standard error of measurement (SEM agreement). Test-retest reliability expressed by the ICCs varied from 0.57 (incoherent behaviour) to 0.93 (anxious behaviour). Standard errors of measurement varied from 0.28 (anxious behaviour) to 1.63 (care dependency). The results show how the GIP can be applied when interpreting individual change in psychogeriatric day care participants.

[Behavioral types in relation to burnout, mobbing, personality, and adaptation of self-conduct in health care workers]. / Tipologías comportamentales en relación con el burnout, mobbing, personalidad, autoconcepto y adaptación de conducta en trabajadores sanitarios.

OBJECTIVE: To define the different patterns of behavior among workers in health care in Ceuta. DESIGN: Cross-sectional and descriptive. SITES AND PARTICIPANTS: 200 randomly selected workers in the Ceuta Health Care Area using a stratified sampling of workplace, job and sex. MEASUREMENTS: The instruments used were the MBI, the LIPT by Leymann, a reduced version of the Pinillos CEP, Musitu self concept and adaptation behavior, all adapted in the context of occupational health examinations. RESULTS: Principal components analysis allowed us to define 5 components, one strictly related to the scale of mobbing with 85% of weight; another for burnout with 70% weight; a third to adaptation and family satisfaction with a weight of 64%; a fourth with adaptation, control, emotional self, professional achievement and occupational self-weight of 52%; and a fifth component defined by social evaluations in the levels of extraversion and social adjustment with 73%. CONCLUSIONS: Highlights five different behavioral characteristics peculiar interest for clinical work are highlighted: burnout, mobbing, family work satisfaction; individual occupational and sociable satisfaction.

Communication ability in persons with trisomy 18 and trisomy 13.

The purpose of this study was to assess communication abilities among a sample of 10 individuals with Trisomy 18 and Trisomy 13. These 10 individuals were diagnosed with Trisomy 18 (n = 8) or Trisomy 13 (n = 2) and had a mean age of 15.96 years. The sample consisted of one male and nine females. Caregivers completed a case history and reported on words and gestures understood and/or produced. Participants were also videotaped during communication temptation tasks. Auditory comprehension was reported to be higher than expressive language. No participant produced intelligible words or word approximations, yet most produced hand gestures. The process and results of these 10 cases point to a potentially promising approach for assessing communication abilities in individuals with Trisomy 18 and Trisomy 13.

Recommended measures for the assessment of behavioral disturbances associated with dementia.

OBJECTIVE: The study reviewed all the published instruments used for the assessment, diagnosis, screening, and outcomes monitoring/evaluation of behavioral disturbances associated with dementia (BDAD) to recommend a set of psychometrically valid measures for clinicians and researchers to use, across a range of different practice settings. METHODS: The study involved a broad scoping search, followed by a series of in-depth literature reviews on 29 instruments using scientific literature databases (MEDLINE, PsycINFO, CINAHL, and the Cochrane Library) and various national, international government, and government agency websites and professional organization websites. External consultations from measurement, clinical and research experts in dementia care, consumer representatives, and policy/decision makers, were sought in selecting the best instruments and in making the final recommendations. FINDINGS: Key attributes and psychometric properties of a short list of five instruments were measured against prespecified criteria. The Neuropsychiatry Inventory (NPI) and the Behavioral Pathology in Alzheimer's Disease Rating Scale (BEHAVE-AD) were rated as the best measures for assessment of behavioral disturbances, followed by the Consortium to Establish a Registry for Alzheimer's Disease-Behavior Rating Scale for Dementia (CERAD-BRSD), the Dementia Behavior Disturbance Scale, and the Neurobehavioral Rating Scale. CONCLUSION: The use of valid and standardized outcome measures for the assessment of BDAD is critical for epidemiological studies, prevention, early intervention and treatment of dementia conditions, and funding for relevant healthcare services. The review recommends the NPI and BEHAVE-AD as the most appropriate measures for both clinical and research, whereas the CERAD-BRSD is suited better for research. The review was designed for the Australian context; however, the findings are applicable in other developed countries.

A comparison of the behavioral observation system (BOS) with clinician ratings of psychosis and mania.

This study investigated the relationship of the behavioral observation system (BOS; LePage & Mogge, 2001) and clinician ratings of psychosis and mania. Fifty interviews with psychiatric inpatients using the Scale for the Assessment of Positive Symptoms, the Scale for the Assessment of Negative Symptoms, and the Young Mania Rating scale were completed. Paraprofessionals completed a BOS on the patient during the same day of the clinician's interview. The results of the study demonstrate the convergent validity of the BOS scales and support the use of the BOS by paraprofessionals to assess behaviors associated with psychosis and mania.

Six clarifications for behaviour systems.

The precursors of contemporary behaviour systems theory were hotly debated, and yet a similar critical fervour has not followed the second generation of behaviour systems research. I raise six items of potential or extant misunderstanding concerning behaviour systems perspectives, and attempt to set straight some of the assumptions and what motivated them, with attention to historical and theoretical context. The six challenges in focus are: 1) variety of conceptualisation of consummation; 2) potential misapprehensions about the role of general search; 3) ambiguity of predictions concerning response form; 4) ambiguity concerning what aspects are modelled as hierarchical; 5) assumptions of directedness; and 6) the relevance of spontaneous activity. For each of these six issues, some clarification is offered.

LDA Ensembles for Interactive Exploration and Categorization of Behaviors.

We define behavior as a set of actions performed by some actor during a period of time. We consider the problem of analyzing a large collection of behaviors by multiple actors, more specifically, identifying typical behaviors and spotting anomalous behaviors. We propose an approach leveraging topic modeling techniques - LDA (Latent Dirichlet Allocation) Ensembles - to represent categories of typical behaviors by topics that are obtained through topic modeling a behavior collection. When such methods are applied to text in natural languages, the quality of the extracted topics are usually judged based on the semantic relatedness of the terms pertinent to the topics. This criterion, however, is not necessarily applicable to topics extracted from non-textual data, such as action sets, since relationships between actions may not be obvious. We have developed a suite of visual and interactive techniques supporting the construction of an appropriate combination of topics based on other criteria, such as distinctiveness and coverage of the behavior set. Two case studies on analyzing operation behaviors in the security management system and visiting behaviors in an amusement park, and the expert evaluation of the first case study demonstrate the effectiveness of our approach.

An atlas of personality, emotion and behaviour.

A novel two-dimensional matrix taxonomy, or atlas, of personality, emotion and behaviour is presented. The two dimensions of the atlas, affiliation and dominance, are demonstrated to have theoretical foundations in neurobiology and social psychology. Both dimensions are divided into five ordinal categories, creating a square matrix of 25 cells. A new catalogue of 20,669 English words descriptive of personality, emotion, behaviour, and power is also presented. The catalogue is more comprehensive than previous catalogues, and is novel in its inclusion of intrapersonal, group, and societal behaviours. All words in the catalogue were scored according to the atlas, facilitating visualisation in two dimensions. This enabled a contiguous and novel comparison of existing psychological taxonomies, as well as broader societal concepts such as leadership, ethics, and crime. Using the atlas, a novel psychological test is developed with improved sensitivity and specificity.

Understanding Multimodal User Gesture and Speech Behavior for Object Manipulation in Augmented Reality Using Elicitation.

The primary objective of this research is to understand how users manipulate virtual objects in augmented reality using multimodal interaction (gesture and speech) and unimodal interaction (gesture). Through this understanding, natural-feeling interactions can be designed for this technology. These findings are derived from an elicitation study employing Wizard of Oz design aimed at developing user-defined multimodal interaction sets for building tasks in 3D environments using optical see-through augmented reality headsets. The modalities tested are gesture and speech combined, gesture only, and speech only. The study was conducted with 24 participants. The canonical referents for translation, rotation, and scale were used along with some abstract referents (create, destroy, and select). A consensus set of gestures for interactions is provided. Findings include the types of gestures performed, the timing between co-occurring gestures and speech (130 milliseconds), perceived workload by modality (using NASA TLX), and design guidelines arising from this study. Multimodal interaction, in particular gesture and speech interactions for augmented reality headsets, are essential as this technology becomes the future of interactive computing. It is possible that in the near future, augmented reality glasses will become pervasive.

An exploratory analysis of the use of cognitive, adaptive and behavioural indices for cluster analysis of ASD subgroups.

BACKGROUND: Autism spectrum disorder (ASD) includes symptoms that vary in severity and frequency between children. Consequently, multiple psychometric assessment procedures are recommended to detect an ASD, including scales which asses the presence and nature of ASD-related behaviour. However, to date, few studies have examined the relative and specific contribution which such behaviourally oriented scales can make to the diagnosis of individual children with ASD. METHOD: Cluster analysis was used to explore the common characteristics of a group of 53 preschool and elementary school children with an ASD, based upon scores on tests of cognitive ability, adaptive behaviour and behavioural checklists designed to measure the presence of typical ASD. RESULTS: Data confirmed the expected variability in intelligence test scores. In addition, measures of adaptive behaviour and data from a behaviourally based rating scale suggested that children with Asperger's Disorder and autism might be reclassified into subgroups according to the presence of particular ASD-specific behaviours. CONCLUSIONS: As well as confirming that children with ASD vary in their adaptive behaviour and cognitive levels, these data emphasise the limited contribution such assessment procedures make to an understanding of the child's day-to-day behaviour and functioning, thus arguing for the inclusion of behaviourally based rating scales to develop ideographic intervention plans.

Towards improved measurement of cognitive and behavioural work demands.

Determination of the cognitive and behavioural demands of work is an important part of holistic workplace intervention. Attention to these factors is especially important when developing return-to-work programs for persons with reduced cognitive, behavioural or psycho-emotional capacity, and when designing risk management programs in organizations. Occupational therapists have the background knowledge and skills to assess these components of work, but often lack valid and reliable measurement tools. This paper reports on three field studies that assessed the reliability and validity of ratings made by novice users of the City of Toronto Job Demands Analysis, which includes a measure of cognitive and behavioural work demands. Numerous challenges to accuracy and reliability that are common to empirical measurement were disclosed, including the necessity for clear and strong definitions, and the importance of thorough rater training. Implications for therapist training and mentorship are discussed.

Driving behavior recognition using EEG data from a simulated car-following experiment.

Driving behavior recognition is the foundation of driver assistance systems, with potential applications in automated driving systems. Most prevailing studies have used subjective questionnaire data and objective driving data to classify driving behaviors, while few studies have used physiological signals such as electroencephalography (EEG) to gather data. To bridge this gap, this paper proposes a two-layer learning method for driving behavior recognition using EEG data. A simulated car-following driving experiment was designed and conducted to simultaneously collect data on the driving behaviors and EEG data of drivers. The proposed learning method consists of two layers. In Layer I, two-dimensional driving behavior features representing driving style and stability were selected and extracted from raw driving behavior data using K-means and support vector machine recursive feature elimination. Five groups of driving behaviors were classified based on these two-dimensional driving behavior features. In Layer II, the classification results from Layer I were utilized as inputs to generate a k-Nearest-Neighbor classifier identifying driving behavior groups using EEG data. Using independent component analysis, a fast Fourier transformation, and linear discriminant analysis sequentially, the raw EEG signals were processed to extract two core EEG features. Classifier performance was enhanced using the adaptive synthetic sampling approach. A leave-one-subject-out cross validation was conducted. The results showed that the average classification accuracy for all tested traffic states was 69.5% and the highest accuracy reached 83.5%, suggesting a significant correlation between EEG patterns and car-following behavior.

Toward a taxonomy of the unintentional discharge of firearms in law enforcement.

An unintentional discharge (UD) is an activation of the trigger mechanism that results in an unplanned discharge that is outside of the firearm's prescribed use. UDs can result in injury or death, yet have been understudied in scientific literature. Pre-existing (1974-2015) UD reports (N = 137) from seven law enforcement agencies in the United States of America were analyzed by context, officer behavior, type of firearm, and injuries. Over 50% of UDs occurred in contexts with low threat potential while engaged in routine firearm tasks. The remaining UDs occurred in contexts with elevated to high threat potential during muscle co-activation, unfamiliar firearm tasks, contact with inanimate objects, and a medical condition. An antecedent-behavior-consequence (A-B-C) taxonomy as well as a standardized reporting form, based on the current findings and the existing literature, are offered as tools for identifying the conditions under which UDs may be likely to occur.