Analysis Of Activity Patterns Research Articles

Symmetry in Genetic Distance Metrics: Quantifying Variability in Neurological Disorders for Personalized Treatment of Alzheimer’s and Dementia

This paper aims to adapt and apply genetic distance metrics in biomedical signal processing to improve the classification and monitoring of neurological disorders, specifically Alzheimer’s disease and frontotemporal dementia. The primary objectives are: (1) to quantify the variability in EEG signal patterns among the distinct subtypes of neurodegenerative disorders and healthy individuals, and (2) to explore the potential of a novel genetic similarity metric in establishing correlations between brain signal dynamics and clinical progression. Using a dataset of resting-state EEG recordings (eyes closed) from 88 subjects (36 with Alzheimer’s disease, 23 with frontotemporal dementia, and 29 healthy individuals), a comparative analysis of brain activity patterns was conducted. Symmetry plays a critical role in the proposed genetic similarity metric, as it captures the balanced relationships between intra- and inter-group EEG signal patterns. Our findings demonstrate that this approach significantly improves disease subtype identification and highlights the potential of the genetic similarity metric to optimize the predictive models. Furthermore, this methodology supports the development of personalized therapeutic interventions tailored to individual patient profiles, making a novel contribution to the field of neurological signal analysis and advancing the application of EEG in personalized medicine.

Robust analysis of diel activity patterns.

Research Highlight: Iannarilli, F., Gerber, B. D., Erb, J., & Fieberg, J. R. (2024). A 'how-to' guide for estimating animal diel activity using hierarchical models. Journal of Animal Ecology, https://doi.org/10.1111/1365-2656.14213. Diel activity patterns are ubiquitous in living organisms and have received considerable research attention with advances in the collection of time-stamped data and the recognition that organisms may respond to global change via behaviour timing. Iannarilli etal. (2024) provide a roadmap for analysing diel activity patterns with hierarchical models, specifically trigonometric generalized linear mixed-effect models and cyclic cubic spline generalized additive models. These methods are improvements over kernel density estimators, which for nearly two decades have been the status quo for analysing activity patterns. Kernel density estimators have several drawbacks; most notably, data are typically aggregated (e.g. across locations) to achieve sufficient sample sizes, and covariates cannot be incorporated to quantify the influence of environmental variables on activity timing. Iannarilli etal. (2024) also provide a comprehensive tutorial which demonstrates how to format data, fit models, and interpret model predictions. We believe that hierarchical models will become indispensable tools for activity-timing research and envision the development of many extensions to the approaches described by Iannarilli etal. (2024).

Deep learning-based analysis of daily activity patterns of farmed dromedary camels

IntroductionThis study addresses the need for automated monitoring solutions to evaluate the daily activity patterns of camels, which is critical for improving animal welfare and farm management practices. By leveraging advanced deep learning techniques, this research aims to identify and analyze five key daily activities—sleeping, sitting, standing, eating, and drinking—using video recordings from a camel farm in Fujairah, United Arab Emirates.MethodsThe dataset was collected over two 7-day phases in November and December 2022. In Phase 1, video recordings were analyzed to monitor the activities of two camels and measure the duration of each activity. In Phase 2, the study expanded to include six camels, enabling an evaluation of individual behavioral variations. The YOLOv7 object detection algorithm was used to train and validate the model on images extracted from the recordings, achieving high accuracy in detecting and classifying the defined activities.ResultsThe results showed notable variations in activity patterns between Phases 1 and 2. Average standing time decreased from 9.8 hours (40.8%) to 6.0 hours (25.1%), and sleeping time dropped from 4.3 hours (18.0%) to 2.8 hours (11.7%). Conversely, sitting time increased from 6.2 hours (25.8%) to 9.9 hours (41.5%), and eating time rose from 3.1 hours (12.8%) to 4.6 hours (19.2%). Drinking time remained consistent at an average of 37 minutes (2.6%) across both phases. Activity peaks were observed during early mornings and after 16:00, with midday hours dominated by resting in shaded areas. Evening and nighttime activities primarily included sitting, minimal head movements, and occasional standing or walking.DiscussionThe established deep learning framework demonstrated reliable performance in detecting and analyzing camel activity patterns, offering a practical solution for continuous monitoring and improved farm management. However, further research is recommended to validate the model’s performance across different seasons and environmental conditions to enhance its robustness and adaptability.

Electroencephalogram biomarkers as predictors of mortality and functional recovery in patients with severe traumatic brain injury: Protocol study.

Traumatic brain injury (TBI) is a global public health condition that causes cognitive and behavioral deficits. This protocol assesses the potential of quantitative electroencephalogram (EEG) biomarkers, associated with inflammatory indicators, to predict mortality and functional recovery in patients with severe TBI. Through continuous monitoring and analysis of abnormal brain activity patterns, the protocol aims to personalize therapeutic interventions and improve patient quality of life. This randomized clinical trial includes 84 adult participants with severe TBI, followed at different stages of recovery, using validated scales for functional and predictive analysis. Traumatic brain injury (TBI) is a globally impactful public health condition characterized by initial brain injuries caused by traumatic forces, leading to cognitive and behavioral deficits. The trauma triggers inflammatory and neurochemical changes that exacerbate neuronal damage, resulting in neuropsychiatric complications. The use of electroencephalogram (EEG), particularly in its quantitative form (QEEG), is crucial for patients with severe TBI, as it allows early detection of abnormal brain activity patterns, such as slow waves, which indicate a worse prognosis. This continuous monitoring, combined with inflammatory biomarkers, guides personalized therapeutic interventions and improves the prediction of clinical outcomes, contributing to patient quality of life.

Increasing detections of the margay: occupancy, density, and activity patterns in Madre de Dios, Peru

This study provides novel insights into the ecology of the margay (Leopardus wiedii), focusing on its occupancy, density, and activity patterns in the Madre de Dios region, Peru, by utilizing both arboreal and terrestrial camera traps. Conducted across 10 km2, the research achieved 47 detections, utilizing semi-arboreal, lower canopy cameras for the first time to capture margay activities. Occupancy models revealed a mean occupancy probability of 53.82% and a detection probability of 6.57%. Among the environmental covariates, diameter at breast height (DBH) was identified as a significant predictor, negatively impacting occupancy, suggesting margays favor areas with smaller tree diameters. Contrary to expectations, the Normalized Difference Vegetation Index (NDVI) did not significantly influence occupancy. Tree density exhibited a positive, though non-significant, association with margay presence. Spatial capture-recapture (SECR) models estimated a margay density of 71.46 individuals per 100 km², with significant sex-based differences in spatial behavior. Males demonstrated larger home ranges (approximately 13.50 km²) compared to females (approximately 3.79 km²). Activity pattern analyses indicated primary nocturnal behavior with peaks at midnight to 3 am, 5 am, and 6 pm. Temporal overlap analysis revealed a low overlap coefficient with jaguarundis (Dhat1 = 0.21) and a higher overlap with ocelots (Dhat4 = 0.79), reflecting intricate interspecies dynamics. Our findings highlight important ecological aspects of margay behavior, including habitat preferences, nocturnal activity patterns, and interspecies interactions, which were effectively captured through the combined use of terrestrial and arboreal camera traps. The study emphasizes the importance of habitat preservation and the development of conservation strategies tailored to the ecological needs of margays, potentially influencing global practices for the management and protection of lesser-studied semi-arboreal wild cats.

A Study of Diurnal Activity Pattern and Time Budget Analysis of Captive Ostrich (Struthio camelus) in Monsoon, Winter and Summer Seasons at Alipore Zoological Garden, Kolkata, India

Understanding the behaviors of a particular species in captivity is crucial to compare them with the ones in wild for the overall growth of animal population. Hence, a study on diurnal behavioral pattern and time budget analysis of a male ostrich (Struthio camelus) was conducted at Alipore Zoological Garden, Kolkata, India, from August 2023 to June 2024, in order to explore all the seasonal variations. Data was collected from 10:00 h to 17:00 h by using focal sampling method with total 23,520 minutes of observations. The current study revealed total 18 different behaviors such as standing outside shade, standing inside shade, running, walking, eating of leaves, grasses, eating of mud, stones, self-maintenance, dust bathing, investigatory picking, sitting with head high, sitting with head low, flapping, preening, sleeping during standing, sleeping during sitting, defecation, keeper interaction and feeding of offered feed. The studied ostrich primarily displayed self-maintenance (16.10%) during monsoon, whereas, it was predominantly engaged in standing outside the shed (14.67%) and eating of leaves, grasses (13.86%) in winter and in summer also the standing outside the shed (13.86%). When the seasonal variation among activity budget data were considered, it was noted that, the ostrich primarily exhibited walking, eating of stones, mud, self-maintenance and investigatory picking during monsoon, compared to the other two seasons (p<0.05, DMRT), whereas, activities such as sitting with head high and sleeping during sitting were prevalent during summer season. This study will serve as a guide for further investigations on behaviors of captive male ostriches to take conservation efforts for their welfare.

Fusing convolutional learning and attention-based Bi-LSTM networks for early Alzheimer’s diagnosis from EEG signals towards IoMT

The Internet of Medical Things (IoMT) is poised to play a pivotal role in future medical support systems, enabling pervasive health monitoring in smart cities. Alzheimer’s disease (AD) afflicts millions globally, and this paper explores the potential of electroencephalogram (EEG) data in addressing this challenge. We propose the Convolutional Learning Attention-Bidirectional Time-Aware Long-Short-Term Memory (CL-ATBiLSTM) model, a deep learning approach designed to classify different AD phases through EEG data analysis. The model utilizes Discrete Wavelet Transform (DWT) to decompose EEG data into distinct frequency bands, allowing for targeted analysis of AD-related brain activity patterns. Additionally, the data is segmented into smaller windows to handle the dynamic nature of EEG signals, and these segments are transformed into spectrogram images, visually depicting brain activity distribution over time and frequency. The CL-ATBiLSTM model incorporates convolutional layers to capture spatial features, attention mechanisms to emphasize crucial data, and BiLSTM networks to explore temporal relationships within the sequences. To optimize the model’s performance, Bayesian optimization is employed to fine-tune the hyperparameters of the ATBiLSTM network, enhancing its ability to generalize and accurately classify AD stages. Incorporating Bayesian learning ensures the most effective model configuration, improving sensitivity and specificity for identifying AD-related patterns. Our model extracts discriminative features from EEG data to differentiate between AD, Mild Cognitive Impairment (MCI), and healthy controls (CO), offering a more comprehensive approach than existing two-class detection algorithms. By including the MCI category, our method facilitates earlier identification and potentially more impactful therapy interventions. Achieving a 96.52% accuracy on Figshare datasets containing AD, MCI, and CO groups, our approach demonstrates strong potential for practical use, accelerating AD identification, enhancing patient care, and contributing to the development of targeted treatments for this debilitating condition.

Cougar spatiotemporal response to human activities in a multi‐use forest landscape on southern Vancouver Island

Recreational activities have been shown to induce fear responses in carnivores, causing both spatial and temporal displacement that can have cascading effects on the wider ecological community. Cougars Puma concolor are one species that are particularly sensitive to human disturbances as they have been found to be impacted by various forms of recreational activities. This research aimed to quantify the spatial and temporal responses of cougars to human activities on southern Vancouver Island in British Columbia, Canada. Fifty camera traps were deployed in a systematic probabilistic sampling design and data from the summer season of 2022 was used for analyses. We modeled cougar weekly occurrence frequency in relation to human (hikers and bikers) occurrence frequency, vehicle occurrence frequency, and landscape features, using generalized linear mixed models. Temporal responses of cougars were investigated using activity pattern analysis to compare activity patterns within a recreation area and a restricted public access reserve. Cougars avoid occurring at sites where recreationalists frequently visited, but not sites frequented by vehicles on unpaved roads. We observed minimal influence of habitat features or prey availability on cougar occurrence frequency, as measured by information loss (AICc scores). Activity pattern analysis did not demonstrate significant differences in cougar daily activity patterns between the recreation area and no‐entry reserve, suggesting a lack of temporal response. These results suggest recreational activities on southern Vancouver Island are impacting cougar spatial – but not temporal – behavioral dynamics. Insights on how cougars respond to recreational activities can help inform landscape management and policies by providing information that can be used to mitigate negative impacts and thus ensure that recreational activities are remaining compatible with conservation efforts.

Semantic fMRI neurofeedback of emotions: from basic principles to clinical applications.

During fMRI neurofeedback participants learn to self-regulate activity in relevant brain areas and networks based on ongoing feedback extracted from measured responses in those regions. This closed-loop approach has been successfully applied to reduce symptoms in mood disorders such as depression by showing participants a thermometer-like display indicating the strength of activity in emotion-related brain areas. The hitherto employed conventional neurofeedback is, however, 'blind' with respect to emotional content, i.e. patients instructed to engage in a specific positive emotion could drive the neurofeedback signal by engaging in a different (positive or negative) emotion. In this future perspective, we present a new form of neurofeedback that displays semantic information of emotions to the participant. Semantic information is extracted online using real-time representational similarity analysis of emotion-specific activity patterns. The extracted semantic information can be provided to participants in a two-dimensional semantic map depicting the current mental state as a point reflecting its distance to pre-measured emotional mental states (e.g. 'happy', 'content', 'sad', 'angry'). This new approach provides transparent feedback during self-regulation training, and it has the potential to enable more specific training effects for future therapeutic applications such as clinical interventions in mood disorders.This article is part of the theme issue 'Neurofeedback: new territories and neurocognitive mechanisms of endogenous neuromodulation'.

Decoding and modifying dynamic attentional bias in gaming disorder.

With the spread of smartphones and computer games, concerns have escalated regarding the rising prevalence of gaming disorder. Patients often display attentional biases, unconsciously turning their attention towards gaming-related stimuli. However, attempts to discover and ameliorate these attentional deficits have yielded inconsistent outcomes, potentially due to the dynamic nature of attentional bias. This study investigated neural mechanisms underlying attentional bias state by combining neuroimaging (functional magnetic resonance imaging -fMRI) with an approach-avoidance task tailored to an individual's gaming preference. We conducted a multivariate pattern analysis of endogenous brain activity in 21 participants with probable gaming disorder. Our analyses revealed that activity patterns in the insula tracked temporal attentional bias states specific to gaming stimuli. A broad network of frontal and parietal regions instead appeared to predict a general temporal attentional bias state. Finally, we conducted a proof-of-concept study for 'just-in-time' attentional bias training through fMRI-decoded neurofeedback of insula activity patterns, named decoded attentional bias training (DecABT). Our preliminary results suggest that DecABT may help to decrease the attractiveness of gaming stimuli via a insula- and precuneus-based neural mechanism. This work provides new evidence for the insula as an endogenous regulator of attentional bias states in gaming disorder and a starting point to develop novel, individualized therapeutic approaches to treat addiction.This article is part of the theme issue 'Neurofeedback: new territories and neurocognitive mechanisms of endogenous neuromodulation'.

Resting state of human brain measured by fMRI experiment is governed more dominantly by essential mode as a global signal rather than default mode network

Resting-state of the human brain has been described by a combination of various basis modes including the default mode network (DMN) identified by fMRI BOLD signals in human brains. Whether DMN is the most dominant representation of the resting-state has been under question. Here, we investigated the unexplored yet fundamental nature of the resting-state. In the absence of global signal regression for the analysis of brain-wide spatial activity pattern, the fMRI BOLD spatiotemporal signals during the rest were completely decomposed into time-invariant spatial-expression basis modes (SEBMs) and their time-evolution basis modes (TEBMs). Contrary to our conventional concept above, similarity clustering analysis of the SEBMs from 166 human brains revealed that the most dominant SEBM cluster is an asymmetric mode where the distribution of the sign of the components is skewed in one direction, for which we call essential mode (EM), whereas the second dominant SEBM cluster resembles the spatial pattern of DMN. Having removed the strong 1/f noise in the power spectrum of TEBMs, the genuine oscillatory behavior embedded in TEBMs of EM and DMN-like mode was uncovered around the low-frequency range below 0.2 Hz.

A Temporospatial Analysis of Activity Patterns for Fall Risk Assessment in Older Adults with Comorbid Type 2 Diabetes.

This study explores how daily activities, including duration and location within the home, affect fall risk in older adults with type 2 diabetes. Body-worn cameras on 26 participants provided data on activity (e.g. exercise), time and location (kitchen, living room). Demographics and health factors were considered to understand their influence. By visualising activity patterns, this study aimed to identify behaviours linked to falls to inform personalised fall prevention strategies and digital technologies for independent living.

Prioritized adjustments in posture stabilization and adaptive reaching during neuromuscular fatigue of lower-limb muscles.

Neuromuscular fatigue (NMF) induces temporary reductions in muscle force production capacity, affecting various aspects of motor function. Although studies have extensively explored NMF's impact on muscle activation patterns and postural stability, its influence on motor adaptation processes remains less understood. This article investigates the effects of localized NMF on motor adaptation during upright stance, focusing on reaching tasks. Using a force-field perturbation paradigm, participants performed reaching movements while standing upright before and after inducing NMF in the ankle dorsiflexor muscles. Results revealed that despite maintained postural stability, participants in the NMF group exhibited larger movement errors during reaching tasks, suggesting impaired motor adaptation. This was evident in both initial and terminal phases of adaptation, indicating a disruption in learning processes rather than a decreased adaptation rate. Analysis of electromyography activation patterns highlighted distinct strategies between groups, with the NMF group showing altered activation of both fatigued and nonfatigued muscles. In addition, differences in coactivation patterns suggested compensatory mechanisms to prioritize postural stability despite NMF-induced disruptions. These findings underscore the complex interplay between NMF, motor adaptation, and postural control, suggesting a potential role for central nervous system mechanisms in mediating adaptation processes. Understanding these mechanisms has implications for sports performance, rehabilitation, and motor skill acquisition, where NMF may impact the learning and retention of motor tasks. Further research is warranted to elucidate the transient or long-term effects of NMF on motor adaptation and its implications for motor rehabilitation interventions.NEW & NOTEWORTHY We assessed motor adaptation during force-field reaching following exercise-induced neuromuscular fatigue (NMF) on postural muscles. NMF impaired adaptation in performance. Similarly, diverging activation strategies were observed in the muscles. No effects were seen on measures of postural control. These results suggest the remodulation of motor commands to the muscles in the presence of NMF, which may be relevant in settings where participants could be exposed to NMF while learning, such as sports and rehabilitation.

Mnemonic brain state engagement is diminished in healthy aging.

Healthy older adults typically show impaired episodic memory - memory for when and where an event oc-curred - but intact semantic memory - knowledge for general information and facts. As older adults also have difficulty inhibiting the retrieval of prior knowledge from memory, their selective decline in episodic memory may be due to a tendency to over engage the retrieval state, a brain state in which attention is focused internally in an attempt to access prior knowledge. The retrieval state trades off with the encoding state, a brain state which supports the formation of new memories. Therefore, episodic memory declines in older adults may be the result of differential engagement in mnemonic brain states. Our hypothesis is that older adults are biased toward a retrieval state. We recorded scalp electroencephalography while young, middle-aged and older adults performed a memory task in which they were explicitly directed to either encode the currently presented object stimulus or retrieve a previously presented, categorically-related object stimulus. We used multivariate pattern analysis of spectral activity to decode engagement in the retrieval vs. encoding state. We find that all three age groups can follow top-down instructions to selectively engage in encoding or retrieval and that we can decode mnemonic states for all age groups. However, we find that mnemonic brain state engagement is diminished for older adults relative to middle-aged adults. Our interpretation is that a combination of executive control deficits and a modest bias to retrieve modulates older adults' mnemonic state engagement. Together, these findings suggest that dif-ferential mnemonic state engagement may underlie age-related memory changes.

Comparative Analysis of Neuromuscular Activation Patterns Associated with Force between Semi-Professional Female Soccer Players with Previous Anterior Cruciate Ligament Surgery and Healthy Players in Thigh Musculature Related to Valgus Collapse

This study investigates electromyography activation and force development differences in key lower limb muscles between female football players with previous anterior cruciate ligament injuries compared with healthy players. Twenty-two semi-professional players were divided into ACL-injured (n = 11) and non-injured groups (n = 11). Participants underwent maximal voluntary isometric contractions while electromyography activation, peak and average, and peak torque of force were measured. Results indicated significant differences in electromyography activation patterns between anterior cruciate ligament players and non-injured players, particularly in biceps femoris and gluteus maximus muscles. These differences were also evident when comparing between limbs within anterior cruciate ligament players. Interestingly, both groups exhibited similar peak torque of force during maximal contractions, suggesting a compensatory neuromuscular strategy that supports a return to sport based on kinetic and kinematic factors. However, these findings underscore persistent muscle integration imbalances potentially contributing to the high rate of anterior cruciate ligament reinjury. In conclusion, this study highlights the importance of evaluating electromyography activation alongside force development in understanding neuromuscular adaptations post anterior cruciate ligament injury. These insights emphasize the need for comprehensive rehabilitation strategies that address muscle imbalance to mitigate the risk of recurrent anterior cruciate ligament injuries in female football players.

Human motion activity recognition and pattern analysis using compressed deep neural networks

ABSTRACT This work presents an on-device machine learning model with the ability to identify different mobility gestures called human activity recognition (HAR), which includes running, walking, squatting, jumping, and others. The data is collected through an Arduino Nano 33 BLE Sense board with a sampling rate of 119 Hz, which is embedded with an Inertial Measurement Unit (IMU) sensor. The same board is used as a microcontroller to identify human gestures by developing an end-to-end edge computing application. A deep neural network model is trained and then compressed for deployment on the board to create a self-contained, embedded device capable of identifying the type of gesture performed. Three deep learning models, namely Multi-Layer Perceptron (MLP), Convolutional Neural Network – Long Short Term Memory (CNN-LSTM) & CNN-Gated Recurrent Unit (CNN-GRU), are evaluated in the identification of the mobility gestures. The observed accuracy of the models is 96%, 97.1% and 97.8%, respectively, MLP, CNN-LSTM & CNN-GRU across the different gesture categories. The study shows the utility of embedded devices with deep neural network-based models, which can provide low cost, minimal power usage, and meet data privacy requirements in HAR.

Empathy from dissimilarity: Multivariate pattern analysis of neural activity during observation of somatosensory experience

Abstract Empathy seems to rely on our ability to faithfully simulate multiple aspects of others’ inferred experiences, often using brain structures we would use during a similar experience. Much neuroimaging work in this vein has related empathic tendencies to univariate correlates of simulation strength or salience. However, novel evidence suggests that empathy may rely on the multivariate distinctiveness of these simulations. Someone whose representations of painful and non-painful stimulation are more distinct from each other may more accurately simulate that experience upon seeing somebody else experience it. We sought to predict empathic tendencies from the dissimilarity between neural activity patterns evoked by observing other people experience pain and touch and compared those findings to traditional univariate analyses. In support of a simulationist perspective, diverse observed somatosensory experiences were best classified by activation patterns in contralateral somatosensory and insular cortices, the same areas that would be active were the subject experiencing the stimuli themselves. In support of our specific hypothesis, the degree of dissimilarity between patterns for pain and touch in distinct areas was each associated with different aspects of trait empathy. Furthermore, the pattern dissimilarity analysis proved more informative regarding individual differences than analogous univariate analyses. These results suggest that multiple facets of empathy are associated with an ability to robustly distinguish between the simulated states of others at corresponding levels of the processing hierarchy, observable via the distinguishability of neural patterns arising with those states. Activation pattern dissimilarity may be a useful tool for parsing the neuroimaging correlates of complex cognitive functions like empathy.

Remote heart failure patient monitoring: A comprehensive analysis of physical activity patterns

Remote heart failure patient monitoring: A comprehensive analysis of physical activity patterns

Population size and social structure of lions in a west African protected area

AbstractTo inform the conservation of the Regionally Critically Endangered West African lion, we studied lion population size and social structure in Niokolo Koba National Park (NKNP), Senegal. Calling station and camera trap surveys were conducted and opportunistic lion observations were documented from 2015 to 2020. The average lion density was calculated as 0.50 lion/100 km2 and the population size was estimated as 28–56 individuals. Average lion group size was 2.1 ± 1.45 lions (range 1–8 lions). There were no significant differences between observations of single individuals (43%), groups of two (22%), three (19%), four (4%) and more than four (5%) individual lions (X2 = 30.021, p‐value = 0.06452). Sex ratio showed a ratio of male:female of 1:1.1 to 1:2.8. About 13.59% of the lion population was composed of cubs while, respectively, 81.22% and 5.17% were adults and subadults. Based on the analysis of activity patterns, lions in NKNP are mainly nocturno‐crepuscular (18:00–01:00) and matutinal (06:00–08:00). Lion population size and density are still low in NKNP compared to earlier estimates from the same area, in the late 1990s. We therefore conclude that the conservation of lions in NKNP must be further improved to safeguard this population in the long term.

TAO

Translating fine-grained activity detection (e.g., phone ring, talking interspersed with silence and walking) into semantically meaningful and richer contextual information (e.g., on a phone call for 20 minutes while exercising) is essential towards enabling a range of healthcare and human-computer interaction applications. Prior work has proposed building ontologies or temporal analysis of activity patterns with limited success in capturing complex real-world context patterns. We present TAO, a hybrid system that leverages OWL-based ontologies and temporal clustering approaches to detect high-level contexts from human activities. TAO can characterize sequential activities that happen one after the other and activities that are interleaved or occur in parallel to detect a richer set of contexts more accurately than prior work. We evaluate TAO on real-world activity datasets (Casas and Extrasensory) and show that our system achieves, on average, 87% and 80% accuracy for context detection, respectively. We deploy and evaluate TAO in a real-world setting with eight participants using our system for three hours each, demonstrating TAO's ability to capture semantically meaningful contexts in the real world. Finally, to showcase the usefulness of contexts, we prototype wellness applications that assess productivity and stress and show that the wellness metrics calculated using contexts provided by TAO are much closer to the ground truth (on average within 1.1%), as compared to the baseline approach (on average within 30%).