abstract: The human motion is defined as an amalgamation of several physical traits such as bipedal locomotion, posture and manual dexterity, and mental expectation. In addition to the “positive” body form defined by these traits, casting light on the body produces a “negative” of the body: its shadow. We often interchangeably use with silhouettes in the place of shadow to emphasize indifference to interior features. In a manner of speaking, the shadow is an alter ego that imitates the individual. The principal value of shadow is its non-invasive behaviour of reflecting precisely the actions of the individual it is attached to. Nonetheless we can still think of the body’s shadow not as the body but its alter ego. Based on this premise, my thesis creates an experiential system that extracts the data related to the contour of your human shape and gives it a texture and life of its own, so as to emulate your movements and postures, and to be your extension. In technical terms, my thesis extracts abstraction from a pre-indexed database that could be generated from an offline data set or in real time to complement these actions of a user in front of a low-cost optical motion capture device like the Microsoft Kinect. This notion could be the system’s interpretation of the action which creates modularized art through the abstraction’s ‘similarity’ to the live action. Through my research, I have developed a stable system that tackles various connotations associated with shadows and the need to determine the ideal features that contribute to the relevance of the actions performed. The implication of Factor Oracle [3] pattern interpretation is tested with a feature bin of videos. The system also is flexible towards several methods of Nearest Neighbours searches and a machine learning module to derive the same output. The overall purpose is to establish this in real time and provide a constant feedback to the user. This can be expanded to handle larger dynamic data. In addition to estimating human actions, my thesis best tries to test various Nearest Neighbour search methods in real time depending upon the data stream. This provides a basis to understand varying parameters that complement human activity recognition and feature matching in real time. / Dissertation/Thesis / Masters Thesis Electrical Engineering 2016

Animais de laboratório estão sujeitos a uma variedade de ruídos diários que podem afetar seu bem estar, havendo estudos que apontam o trabalho humano nas salas de animais como uma importante fonte de ruídos com intensidades e frequências variáveis capazes de causar alterações comportamentais e fisiológicas nesses animais. Este trabalho teve como objetivo analisar os possíveis efeitos dos ruídos gerados durante a atividade humana na gestação de ratas wistar e no crescimento ponderal dos neonatos. Quarenta e quatro ratas wistar de 120 dias de idade, alojadas em sistema de gaiola aberta, oriundas do CREAL/UFRGS, foram acasaladas e submetidas à rotina de trabalho normal (grupo controle) ou expostas a ruídos em duas sessões de 20 minutos/dia com intervalo de 15 segundos entre cada ruído (grupo tratado) durante toda a gestação e na primeira semana de vida dos filhotes. Os ruídos foram previamente selecionados com base no trabalho humano realizado nas salas de animais e registrados por meio do microfone de um medidor de nível de pressão sonora com resposta de frequência 20 Hz-20kHz. As frequências foram avaliadas utilizando-se um software editor de áudio (Audacity® 1.3). Os partos de ambos os grupos (tratado e controle) foram acompanhados e durante os mesmos anotou-se o número de filhotes vivos e natimortos. Para avaliação do peso ponderal dos neonatos pesaram-se os três filhotes maiores de cada ninhada das fêmeas uma vez ao dia entre 14:00 e 16:00 hs. Utilizou-se o teste- T para análise do número de natimortos no qual demonstrou diferença significativa (p= 0,021) entre os grupos. O teste de variância Anova para medidas repetidas e o Tukey-Kramer foram utilizados para comparar o peso médio dos três filhotes maiores, o qual foi observado diferença significativa do peso médio dos três filhotes maiores nos dias 4 (p= 0,0026),5 (p<0,001),6 (p=0,0005) e 7 (p< 0,0001). Este estudo demonstra que ruídos gerados por atividade humana podem gerar filhotes natimortos e interferir no comportamento materno diminuindo o peso do filhote a partir do quarto dia na primeira semana de vida. / Laboratory animals are subjected to a variety of daily noises which can affect their well-being. There are studies that suggest the human work in animal rooms is an important source of noise with varying frequencies and intensities which may cause physiological and behavioral changes in the animals. This work had as its main objective the analysis of the possible effects that the noise generated by professionals while doing their activities may have on pregnancy of Wistar rats, evaluating the natimortality and the weight development of newborns. Fourty-for 120 days old Wistar rats from CREAL/UFRGS accommodated in an open cage system have been paired and have undergone a normal work routine (control group) or have been exposed to noise in two sessions of 20 minutes/day with interval of 15 seconds between each noise (treated group) throughout their pregnancy and in the first week of their offspring’s life. The noises were previously selected on the basis of the human work carried out in animal rooms and recorded through the use of a microphone sound pressure level meter frequency response of 20 Hz-20kHz. The frequencies were evaluated using an audio editor software (Audacity® 1.3). The delivery in both groups (treated and control) were accompanied and during them it was taken note the number of living and stillborn offspring. To evaluate the weight of newborns, the three biggest ones of each litter rats were weighed up once a day between 2:00 and 4:00 p.m. It was used the T-test for examining the number of stillborns which showed a significant difference (p = 0.021) between the groups. The Anova variance test for repeated measures and the Tukey- Kramer test were used to compare the average weight of the three biggest offspring. It was observed significant difference of average weight in the three biggest ones on day 4 (p = 0.0026), 5 (p < 0.001), 6 (p = 0.0005) and 7 (p < 0.0001). This study shows that noise generated by human activity may cause stillborn offspring and interfere with maternal behavior by decreasing the weight of the new born from the fourth day the first week of life.

abstract: This dissertation addresses the research challenge of developing efficient new methods for discovering useful patterns and knowledge in large volumes of electronically collected spatiotemporal activity data. I propose to analyze three types of such spatiotemporal activity data in a methodological framework that integrates spatial analysis, data mining, machine learning, and geovisualization techniques. Three different types of spatiotemporal activity data were collected through different data collection approaches: (1) crowd sourced geo-tagged digital photos, representing people's travel activity, were retrieved from the website Panoramio.com through information retrieval techniques; (2) the same techniques were used to crawl crowd sourced GPS trajectory data and related metadata of their daily activities from the website OpenStreetMap.org; and finally (3) preschool children's daily activities and interactions tagged with time and geographical location were collected with a novel TabletPC-based behavioral coding system. The proposed methodology is applied to these data to (1) automatically recommend optimal multi-day and multi-stay travel itineraries for travelers based on discovered attractions from geo-tagged photos, (2) automatically detect movement types of unknown moving objects from GPS trajectories, and (3) explore dynamic social and socio-spatial patterns of preschool children's behavior from both geographic and social perspectives. / Dissertation/Thesis / Ph.D. Geography 2012

Animais de laboratório estão sujeitos a uma variedade de ruídos diários que podem afetar seu bem estar, havendo estudos que apontam o trabalho humano nas salas de animais como uma importante fonte de ruídos com intensidades e frequências variáveis capazes de causar alterações comportamentais e fisiológicas nesses animais. Este trabalho teve como objetivo analisar os possíveis efeitos dos ruídos gerados durante a atividade humana na gestação de ratas wistar e no crescimento ponderal dos neonatos. Quarenta e quatro ratas wistar de 120 dias de idade, alojadas em sistema de gaiola aberta, oriundas do CREAL/UFRGS, foram acasaladas e submetidas à rotina de trabalho normal (grupo controle) ou expostas a ruídos em duas sessões de 20 minutos/dia com intervalo de 15 segundos entre cada ruído (grupo tratado) durante toda a gestação e na primeira semana de vida dos filhotes. Os ruídos foram previamente selecionados com base no trabalho humano realizado nas salas de animais e registrados por meio do microfone de um medidor de nível de pressão sonora com resposta de frequência 20 Hz-20kHz. As frequências foram avaliadas utilizando-se um software editor de áudio (Audacity® 1.3). Os partos de ambos os grupos (tratado e controle) foram acompanhados e durante os mesmos anotou-se o número de filhotes vivos e natimortos. Para avaliação do peso ponderal dos neonatos pesaram-se os três filhotes maiores de cada ninhada das fêmeas uma vez ao dia entre 14:00 e 16:00 hs. Utilizou-se o teste- T para análise do número de natimortos no qual demonstrou diferença significativa (p= 0,021) entre os grupos. O teste de variância Anova para medidas repetidas e o Tukey-Kramer foram utilizados para comparar o peso médio dos três filhotes maiores, o qual foi observado diferença significativa do peso médio dos três filhotes maiores nos dias 4 (p= 0,0026),5 (p<0,001),6 (p=0,0005) e 7 (p< 0,0001). Este estudo demonstra que ruídos gerados por atividade humana podem gerar filhotes natimortos e interferir no comportamento materno diminuindo o peso do filhote a partir do quarto dia na primeira semana de vida. / Laboratory animals are subjected to a variety of daily noises which can affect their well-being. There are studies that suggest the human work in animal rooms is an important source of noise with varying frequencies and intensities which may cause physiological and behavioral changes in the animals. This work had as its main objective the analysis of the possible effects that the noise generated by professionals while doing their activities may have on pregnancy of Wistar rats, evaluating the natimortality and the weight development of newborns. Fourty-for 120 days old Wistar rats from CREAL/UFRGS accommodated in an open cage system have been paired and have undergone a normal work routine (control group) or have been exposed to noise in two sessions of 20 minutes/day with interval of 15 seconds between each noise (treated group) throughout their pregnancy and in the first week of their offspring’s life. The noises were previously selected on the basis of the human work carried out in animal rooms and recorded through the use of a microphone sound pressure level meter frequency response of 20 Hz-20kHz. The frequencies were evaluated using an audio editor software (Audacity® 1.3). The delivery in both groups (treated and control) were accompanied and during them it was taken note the number of living and stillborn offspring. To evaluate the weight of newborns, the three biggest ones of each litter rats were weighed up once a day between 2:00 and 4:00 p.m. It was used the T-test for examining the number of stillborns which showed a significant difference (p = 0.021) between the groups. The Anova variance test for repeated measures and the Tukey- Kramer test were used to compare the average weight of the three biggest offspring. It was observed significant difference of average weight in the three biggest ones on day 4 (p = 0.0026), 5 (p < 0.001), 6 (p = 0.0005) and 7 (p < 0.0001). This study shows that noise generated by human activity may cause stillborn offspring and interfere with maternal behavior by decreasing the weight of the new born from the fourth day the first week of life.

Orientador: Maria Ines Rosa / Dissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Educação / Made available in DSpace on 2018-08-06T14:23:14Z (GMT). No. of bitstreams: 1 Souza_DorivalPereira_M.pdf: 14954256 bytes, checksum: 2917300ec63650a957d35a4f1bd8e754 (MD5) Previous issue date: 2006 / Mestrado / Educação, Sociedade, Politica e Cultura / Mestre em Educação

Human-machine interaction could support many daily activities in making it more convenient. The development of smart devices has flourished the underlying smart systems that process smart and personalized control of devices. The first step in controlling any device is observation; through understanding the surrounding environment and human activity, a smart system can physically control a device. Human activity recognition (HAR) is essential in many smart applications such as self-driving cars, human-robot interaction, and automatic systems such as infrared (IR) taps. For human-centric systems, there are some requirements to perform a physical task in real-time. For human-machine interactions, the anticipation of human actions is essential. IR taps have delay limitations because of the proximity sensor that signals the solenoid valve only when the user’s hands are exactly below the tap. The hardware and electronics delay causes inconvenience in use and water waste. In this thesis, an alternative control based on deep learning action anticipation is proposed. Humans interact with taps for various tasks such as washing hands, face, brushing teeth, just to name a few. We focus on a small subset of these activities. Specifically, we focus on the activities carried out sequentially during an Islamic cleansing ritual called Wudu. Skeleton modality is widely used in HAR because of having abstract information that is scale-invariant and robust against imagery variances. We used depth cameras to obtain accurate 3D human skeletons of users performing Wudu. The sequences were manually annotated with ten atomic action classes. This thesis investigated the use of different Deep Learning networks with architectures optimized for real-time action anticipation. The proposed methods were mainly based on the Spatial-Temporal Graph Convolutional Network. With further improvements, we proposed a Gated Recurrent Unit (GRU) model with Spatial-Temporal Graph Convolution Network (ST-GCN) backbone to extract local temporal features. The GRU process the local temporal latent features sequentially to predict future actions. The proposed models scored 94.14% recall on binary classification to turn on and off the water tap. And higher than 81.58-89.08% recall on multiclass classification.

No description available.

In this paper, we detect the occurrence of epileptic seizures in patients as well as activities namely stand, walk, and exercise in healthy persons, leveraging EEG (electroencephalogram) signals. Using Hilbert vibration decomposition (HVD) on non-linear and non-stationary EEG signal, we obtain multiple monocomponents varying in terms of amplitude and frequency. After decomposition, we extract features from the monocomponent matrix of the EEG signals. The instantaneous amplitude of the HVD monocomponents varies because of the motion artifacts present in EEG signals. Hence, the acquired statistical features from the instantaneous amplitude help in identifying the epileptic seizures and the normal human activities. The features selected by correlation-based Q-score are classified using an LSTM (Long Short Term Memory) based deep learning model in which the feature-based weight update maximizes the classification accuracy. For epilepsy diagnosis using the Bonn dataset and activity recognition leveraging our Sensor Networks Research Lab (SNRL) data, we achieve testing classification accuracies of 96.00% and 83.30% respectively through our proposed method.

Den här studien undersöker möjligheten att använda sig utav Human Activity Recognition (HAR) i ett mobilspel, Bamblup, som använder sig utav fysiska rörelser för att upptäcka om en spelare fuskar eller om denne verkligen utför den verkliga aktiviteten. Sensordata från en accelerometer och ett gyroskop i en iPhone 7 användes för att samla data från olika människor som utförde ett antal aktiviteter utav intresse. Aktiviteterna som är utav intresse är hopp, knäböj, stampa och deras fuskmotsvarigheter, fuskhopp, fuskknäböj och fuskstampa. En sekventiell modell skapades med hjälp av det öppna programvarubiblioteket, TensorFlow. Feature Selection gjordes i programmet WEKA (Waikato Environment for Knowledge Analysis), för att välja ut attributen som var mest relevanta för klassificeringen. Dessa attribut användes för att träna modellen i TensorFlow, vilken gav en klassificeringsprecision på 66%. Fuskaktiviteterna klassificerades relativt bra, och det gjorde även stampaktiviteten. Hopp och knäböj hade lägst klassificeringsprecision med 21.43% respektive 28.57%. Dessutom testades Random Forest klassificeraren i WEKA på vårt dataset med 10-delad korsvalidering, vilket gav en klassifieringsnoggranhet på 90.47%. Våra resultat tyder på att maskininlärning är en stark kandidat för att hjälpa till att identifiera fuskbeteenden inom fysisk aktivitetsbaserade mobilspel. / This study investigates the possibility to use machine learning for Human Activity Recognition (HAR) in Bamblup, a physical activity-based game for smartphones, in order to detect whether a player is cheating or is indeed performing the required activity. Sensor data from an accelerometer and a gyroscope from an iPhone 7 was used to gather data from various people performing a set of activities. The activities of interest are jumping, squatting, stomping, and their cheating counterparts, fake jumping, fake squatting, and fake stomping. A Sequential model was created using the free open-source library TensorFlow. Feature Selection was performed using the program WEKA (Waikato Environment for Knowledge Analysis), to select the attributes which provided the most information gain. These attributes were subsequently used to train the model in TensorFlow, which gave a classification accuracy of 66%. The fake activities were classified relatively well, and so was the stomping activity. Jumping and squatting had the lowest accuracy of 21.43% and 28.57% respectively. Additionally, the Random Forest classifier in WEKA was tested on the dataset using 10-fold cross validation, providing a classification accuracy of 90.47%. Our findings imply that machine learning is a strong candidate for aiding in the detection of cheating behaviours in mobile physical activity-based games.

Environmental enrichment is a technique used at many captive animal facilities that can improve the well-being of their animals. It seeks to enhance habitat features and promote natural behavior by providing a variety of practical ways for captive animals to control their environmental settings, especially during stressful circumstances. Enclosure features, such as shelter structures, are one tool that promotes wild behavior by adding complexity to an enclosure’s physical environment. Enrichment efforts for captive wildlife are most effective when they are specialized to the biological needs of the animals. Human activity may alter captive animal behavior and utility of enclosure features, and there is concern that human presence can negatively impact the welfare of some captive animals. Captive coyotes (Canis latrans) at the USDA-National Wildlife Research Center (NWRC) Predator Research Facility in Millville, UT, USA, are maintained for research on biology, ecology, physiology and behavior. Coyotes at the research facility are routinely noticed utilizing shelter structures to hide, rest, and display vigilant behavior. Because they regularly use these simple structures, new and more complex enrichment shelter structures were installed to be evaluated. Specific research objectives aimed to assess (1) coyote enclosure utilization and shelter structure preferences, and (2) coyote spatial and behavioral responses to human activity. Using 32 mated coyote pairs rotated through eight 1.5-acre enclosures for 28-day trials over the winter months (January – March) of 2015 and 2016, spatial and behavioral patterns were monitored via the implementation of GPS-collars and live behavioral observations. Coyotes showed preference for shelter structure designs, but still spent most of their time at the perimeter and open areas of their enclosures. Complex structures were preferred over simple structures. Coyotes most often demonstrated inactive and vigilant behavior without human activity, but showed increased vigilance when there was human activity. Human activity also stimulated coyotes to become more active than inactive and reduce their utilization of enrichment structures. Although there was no clear preference for one specific type of enrichment structure, composite evidence from GPS-collars and behavioral data suggest the ramp may have heightened biological suitability. This study advances the knowledge of captive coyote spatial patterns and helps improve environmental enrichment planning for captive animals by exploring effective methods of adding complexity to animal enclosures.