Automatic visual detection of human behavior: a review from 2000 to 2014

Due to advances in information technology (e.g., digital video cameras, ubiquitous sensors), the automatic detection of human behaviors from video is a very recent research topic. In this paper, we perform a systematic and recent literature review on this topic, from 2000 to 2014, covering a selection of 193 papers that were searched from six major scientific publishers. The selected papers were classified into three main subjects: detection techniques, datasets and applications. The detection techniques were divided into four categories (initialization, tracking, pose estimation and recognition). The list of datasets includes eight examples (e.g., Hollywood action). Finally, several application areas were identified, including human detection, abnormal activity detection, action recognition, player modeling and pedestrian detection. Our analysis provides a road map to guide future research for designing automatic visual human behavior detection systems.

Detection of dangerous situations using a smart internet of things system

The Internet of Things (IoT) is a concept that can foster the emergence of innovative applications. In order to minimize parents’s concerns about their children’s safety, this paper presents the design of a smart Internet of Things system for identifying dangerous situations. The system will be based on real time collection and analysis of physiological signals monitored by non-invasive and non-intrusive sensors, Frequency IDentification (RFID) tags and a Global Positioning System (GPS) to determine when a child is in danger. The assumption of a state of danger is made taking into account the validation of a certain number of biometric reactions to some specific situations and according to a self-learning algorithm developed for this architecture. The results of the analysis of data collected and the location of the child will be able in real time to child’s care holders in a web application.

Gd2O3: Eu Nanoparticle-Based Poly(vinylidene fluoride) Composites for Indirect X-ray Detection

Polymer based scintillator composites have been fabricated by combining poly(vinylidene fluoride) (PVDF) and Gd2O3:Eu nanoparticles (50nm). PVDF has been used since it is a flexible and stable binder matrix and highly resistance to thermal and light deterioration. Gd2O3:Eu has been selected as scintillator material due to its wide band gap, high density and suitable visible light yield. The structural, mechanical, thermal and electrical characteristics of the composites were studied as a function of filler content, together with their performance as scintillator material. The introduction of Gd2O3:Eu nanoparticles into the PVDF matrix does not influence the morphology of the polymer or the degree of crystallinity. On the other hand, an increase of the Young´s modulus with respect to PVDF matrix is observed for filler contents of 0.1-0.75 wt.%. The introduction of Gd2O3:Eu into the PVDF matrix increases dielectric constant and DC electrical conductivity as well as the visible light yield in the nanocomposite, being this increase dependent upon Gd2O3:Eu content and X-ray input power. In this way, Gd2O3:Eu/PVDF composites shows suitable characteristics to be used as X-ray radiation transducers, in particular for large area applications.

Abstract computation in schizophrenia detection through artificial neural network based systems

Schizophrenia stands for a long-lasting state of mental uncertainty that may bring to an end the relation among behavior, thought, and emotion; that is, it may lead to unreliable perception, not suitable actions and feelings, and a sense of mental fragmentation. Indeed, its diagnosis is done over a large period of time; continuos signs of the disturbance persist for at least 6 (six) months. Once detected, the psychiatrist diagnosis is made through the clinical interview and a series of psychic tests, addressed mainly to avoid the diagnosis of other mental states or diseases. Undeniably, the main problem with identifying schizophrenia is the difficulty to distinguish its symptoms from those associated to different untidiness or roles. Therefore, this work will focus on the development of a diagnostic support system, in terms of its knowledge representation and reasoning procedures, based on a blended of Logic Programming and Artificial Neural Networks approaches to computing, taking advantage of a novel approach to knowledge representation and reasoning, which aims to solve the problems associated in the handling (i.e., to stand for and reason) of defective information.

Logic programming and artificial neural networks in breast cancer detection

About 90% of breast cancers do not cause or are capable of producing death if detected at an early stage and treated properly. Indeed, it is still not known a specific cause for the illness. It may be not only a beginning, but also a set of associations that will determine the onset of the disease. Undeniably, there are some factors that seem to be associated with the boosted risk of the malady. Pondering the present study, different breast cancer risk assessment models where considered. It is our intention to develop a hybrid decision support system under a formal framework based on Logic Programming for knowledge representation and reasoning, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate the risk of developing breast cancer and the respective Degree-of-Confidence that one has on such a happening.

On line pre-concentration for simultaneous determination of low molecular weight organic acids and inorganic anions in Amazonian river water samples employing ion chromatography with conductivity detection

An ion chromatography procedure, employing an IonPac AC15 concentrator column was used to investigate on line preconcentration for the simultaneous determination of inorganic anions and organic acids in river water. Twelve organic acids and nine inorganic anions were separated without any interference from other compounds and carry-over problems between samples. The injection loop was replaced by a Dionex AC15 concentrator column. The proposed procedure employed an auto-sampler that injected 1.5 ml of sample into a KOH mobile phase, generated by an Eluent Generator, at 1.5 mL min-1, which carried the sample to the chromatographic columns (one guard column, model AG-15, and one analytical column, model AS15, with 250 x 4mm i.d.). The gradient elution concentrations consisted of a 10.0 mmol l-1 KOH solution from 0 to 6.5 min, gradually increased to 45.0 mmol l-1 KOH at 21 min., and immediatelly returned and maintained at the initial concentrations until 24 min. of total run. The compounds were eluted and transported to an electro-conductivity detection cell that was attached to an electrochemical detector. The advantage of using concentrator column was the capability of performing routine simultaneous determinations for ions from 0.01 to 1.0 mg l-1 organic acids (acetate, propionic acid, formic acid, butyric acid, glycolic acid, pyruvate, tartaric acid, phthalic acid, methanesulfonic acid, valeric acid, maleic acid, oxalic acid, chlorate and citric acid) and 0.01 to 5.0 mg l-1 inorganic anions (fluoride, chloride, nitrite, nitrate, bromide, sulfate and phosphate), without extensive sample pretreatment and with an analysis time of only 24 minutes.

Concurrency detection on finish-to-start activity precedence networks

We explore the finish-to-start precedence relations of project activities used in scheduling problems. From these relations, we devise a method to identify groups of activities that could execute concurrently, i.e. activities in the same group can all execute in parallel. The method derives a new set of relations to describe the concurrency. Then, it is represented by an undirected graph and the maximal cliques problem identifies the groups. We provide a running example with a project from our previous studies in resource constrained project cost minimization together with an example application on the concurrency detection method: the evaluation of the resource stress.

Widespread environmental contamination with Mycobacterium tuberculosis complex revealed by a molecular detection protocol

Environmental contamination with Mycobacterium tuberculosis complex (MTC) has been considered crucial for bovine tuberculosis persistence in multi-host-pathogen systems. However, MTC contamination has been difficult to detect due to methodological issues. In an attempt to overcome this limitation we developed an improved protocol for the detection of MTC DNA. MTC DNA concentration was estimated by the Most Probable Number (MPN) method. Making use of this protocol we showed that MTC contamination is widespread in different types of environmental samples from the Iberian Peninsula, which supports indirect transmission as a contributing mechanism for the maintenance of bovine tuberculosis in this multi-host-pathogen system. The proportion of MTC DNA positive samples was higher in the bovine tuberculosis-infected than in presumed negative area (0.32 and 0.18, respectively). Detection varied with the type of environmental sample and was more frequent in sediment from dams and less frequent in water also from dams (0.22 and 0.05, respectively). The proportion of MTC-positive samples was significantly higher in spring (p<0.001), but MTC DNA concentration per sample was higher in autumn and lower in summer. The average MTC DNA concentration in positive samples was 0.82 MPN/g (CI95 0.70-0.98 MPN/g). We were further able to amplify a DNA sequence specific of Mycobacterium bovis/caprae in 4 environmental samples from the bTB-infected area.

Automatic eye blink detection using consumer web cameras

This research aims to advance blinking detection in the context of work activity. Rather than patients having to attend a clinic, blinking videos can be acquired in a work environment, and further automatically analyzed. Therefore, this paper presents a methodology to perform the automatic detection of eye blink using consumer videos acquired with low-cost web cameras. This methodology includes the detection of the face and eyes of the recorded person, and then it analyzes the low-level features of the eye region to create a quantitative vector. Finally, this vector is classified into one of the two categories considered —open and closed eyes— by using machine learning algorithms. The effectiveness of the proposed methodology was demonstrated since it provides unbiased results with classification errors under 5%

Estratégias desenvolvidas por usuários de crack para lidar com os riscos decorrentes do consumo da droga

OBJETIVOS: O objetivo deste estudo foi identificar, sob a ótica de usuários de crack, quais são as estratégias que eles utilizam para minimizar ou evitar os riscos decorrentes do consumo de crack. MÉTODO: Utilizou-se método qualitativo de pesquisa, desenvolvido mediante entrevistas semiestruturadas em profundidade. Foi entrevistada uma amostra intencional por critérios, composta por 30 usuários de crack, selecionados por meio de informantes-chave e distribuídos em oito diferentes cadeias. As entrevistas foram transcritas literalmente, inseridas e analisadas no software NVivo 8, com exploração dos dados mediante a técnica de análise de conteúdo. RESULTADOS: Os entrevistados acreditam que os maiores riscos decorrentes da dependência do crack sejam os relacionados aos efeitos psíquicos da droga, como fissura, sintomas paranoides transitórios e sintomas depressivos, assim como os decorrentes da ilegalidade dela, como a polícia e as questões referentes ao tráfico. Entretanto, os riscos de complicações físicas do consumo quase não foram apontados. As estratégias se concentraram no controle dos efeitos psíquicos, principalmente pelo consumo de álcool e maconha. Para lidar com as consequências da ilegalidade da droga, mostraram se preocupar com a postura que adotam perante o traficante e a polícia. CONCLUSÕES: As estratégias desenvolvidas pelos usuários focam na tentativa de se autoprotegerem principalmente dos episódios de violência e no alívio de sintomas desagradáveis causados pela droga - principalmente fissura e sintomas paranoides transitórios. Essas estratégias podem parecer efetivas a curto prazo, porém apresentaram riscos de longo prazo, tais como dependência de álcool e maconha.

Relação entre o craving por tabaco e o craving por crack em pacientes internados para desintoxicação

OBJETIVO: Verificar se há relação entre aumento do craving por crack e aumento do craving por tabaco em pacientes internados para desintoxicação. MÉTODO: Ensaio clínico tipo quase-experimental de análise quantitativa. Amostra composta por 32 homens dependentes de cocaína (crack) e tabaco, em duas a três semanas de abstinência. Realizou-se intervenção em grupo, no qual, inicialmente, foram aplicados: CCQB (Cocaine Craving Questionnaire-Brief ), QSUB (Questionnaire of Smoking Urges-Brief ) e BAI (Inventário Beck de Ansiedade). Em seguida, foram aplicadas imagens relacionadas ao crack e reaplicados CCQB, QSUB e BAI. Após, foi realizada entrevista individual em que se aplicaram FSD (Ficha com Dados Sociodemográficos) e FTND (Fagerström Test for Nicotine Dependence). RESULTADOS: A partir da exposição de imagens relativas ao crack, houve aumento significativo do craving por crack, do craving por tabaco e dos sintomas de ansiedade, estando essas medidas correlacionadas positivamente entre si. CONCLUSÃO: Os resultados indicam uma associação significativa entre craving por crack e craving por tabaco, sugerindo que a abstinência de tabaco pode ajudar na eficácia do tratamento para dependência de crack.

A bio-inspired computational model for motion detection

Tese de Doutoramento (Programa Doutoral em Engenharia Biomédica)

Associação entre fissura e perfil antropométrico em dependentes de crack

OBJETIVO: Verificar a variação da fissura de dependentes de crack no decorrer da internação e a associação com perfil antropométrico. MÉTODOS: Trata-se de uma pesquisa quantitativa com delineamento transversal (n = 30). Avaliaram-se o perfil de consumo de substâncias psicoativas; dados sociodemográficos; variáveis antropométricas (peso, estatura, índice de massa corporal, relação cintura-quadril, perímetros, dobras cutâneas e diâmetro ósseo); e fissura avaliada por meio do Cocaine Craving Questionnaire Brief. As coletas de dados ocorreram nas 24 horas iniciais e finais do tratamento. RESULTADOS: Observou-se aumento significativo do percentual de gordura e diminuição significativa da fissura. Não se evidenciou associação entre variáveis antropométricas e fissura, tanto no início como ao final da internação. CONCLUSÃO: Houve significativa diminuição na fissura e modificação na composição corporal, entretanto não houve correlação entre essas variáveis.

Validação psicométrica do Cocaine Craving Questionnaire-Brief - Versão Brasileira Adaptada para o Crack para dependentes hospitalizados

Introdução: O craving (ou fissura) é um fator muito importante no tratamento da dependência de substâncias psicotrópicas. Objetivo: Validar o Cocaine Craving Questionnaire-Brief - Versão Brasileira Adaptada para o Crack. Método: O delineamento foi experimental e seus participantes foram randomizados, em grupos: experimental, para o qual foi apresentada uma imagem de um indivíduo consumindo crack (G1), e controle (G2), para o qual não foi apresentada nenhuma imagem. A amostra foi composta por 109 sujeitos (G1 = 50 e G2 = 59) do sexo masculino, internados por causa da dependência do crack. Os instrumentos utilizados foram: Entrevista Clínica com dados sociodemográficos, CCQ-B Versão Adaptada para o Crack, Escala Analógico-Visual do Craving, Inventários Beck de Ansiedade e de Depressão e o Estímulo Visual indutor de craving para o G1. Resultados: Na análise fatorial, foram encontrados dois fatores: o fator 1, relacionado ao craving propriamente dito, e o fator 2, relacionado à percepção da falta de controle do uso do crack. Os dois fatores apresentaram variância total de 68,84%, e a correlação entre os fatores foi significativa e de baixa intensidade (r = 0,204; p = 0,041). O alfa de Cronbach do seu total de pontos foi 0,85. O instrumento no total de pontos foi correlacionado com a Escala Analógico-Visual (r = 0,515; p < 0,01). Conclusão: O CCQ-B - Versão Brasileira Adaptada para o Crack demonstrou ser, psicometricamente, satisfatório para utilização em pesquisas e em ambiente clínico.