MyMedR

Displaying publications 1 - 20 of 54 in total

Abstract:

Sort:

Fulltext Incremental Learning of Human Activities in Smart Homes

Chua SL, Foo LK, Guesgen HW, Marsland S

Sensors (Basel), 2022 Nov 03;22(21).
PMID: 36366154 DOI: 10.3390/s22218458

Sensor-based human activity recognition has been extensively studied. Systems learn from a set of training samples to classify actions into a pre-defined set of ground truth activities. However, human behaviours vary over time, and so a recognition system should ideally be able to continuously learn and adapt, while retaining the knowledge of previously learned activities, and without failing to highlight novel, and therefore potentially risky, behaviours. In this paper, we propose a method based on compression that can incrementally learn new behaviours, while retaining prior knowledge. Evaluation was conducted on three publicly available smart home datasets.

Matched MeSH terms: Human Activities*
Fulltext A hybrid TCN-GRU model for classifying human activities using smartphone inertial signals

Raja Sekaran S, Pang YH, You LZ, Yin OS

PLoS One, 2024;19(8):e0304655.
PMID: 39137226 DOI: 10.1371/journal.pone.0304655

Recognising human activities using smart devices has led to countless inventions in various domains like healthcare, security, sports, etc. Sensor-based human activity recognition (HAR), especially smartphone-based HAR, has become popular among the research community due to lightweight computation and user privacy protection. Deep learning models are the most preferred solutions in developing smartphone-based HAR as they can automatically capture salient and distinctive features from input signals and classify them into respective activity classes. However, in most cases, the architecture of these models needs to be deep and complex for better classification performance. Furthermore, training these models requires extensive computational resources. Hence, this research proposes a hybrid lightweight model that integrates an enhanced Temporal Convolutional Network (TCN) with Gated Recurrent Unit (GRU) layers for salient spatiotemporal feature extraction without tedious manual feature extraction. Essentially, dilations are incorporated into each convolutional kernel in the TCN-GRU model to extend the kernel's field of view without imposing additional model parameters. Moreover, fewer short filters are applied for each convolutional layer to alleviate excess parameters. Despite reducing computational cost, the proposed model utilises dilations, residual connections, and GRU layers for longer-term time dependency modelling by retaining longer implicit features of the input inertial sequences throughout training to provide sufficient information for future prediction. The performance of the TCN-GRU model is verified on two benchmark smartphone-based HAR databases, i.e., UCI HAR and UniMiB SHAR. The model attains promising accuracy in recognising human activities with 97.25% on UCI HAR and 93.51% on UniMiB SHAR. Since the current study exclusively works on the inertial signals captured by smartphones, future studies will explore the generalisation of the proposed TCN-GRU across diverse datasets, including various sensor types, to ensure its adaptability across different applications.

Matched MeSH terms: Human Activities*
Sumatran rhinoceros on the brink of extinction

Lam SS, Ma NL, Peng W, Sonne C

Science, 2020 May 29;368(6494):958.
PMID: 32467384 DOI: 10.1126/science.abc2202
Matched MeSH terms: Human Activities*
Fulltext Mammal responses to global changes in human activity vary by trophic group and landscape

Burton AC, Beirne C, Gaynor KM, Sun C, Granados A, Allen ML, et al.

Nat Ecol Evol, 2024 May;8(5):924-935.
PMID: 38499871 DOI: 10.1038/s41559-024-02363-2

Wildlife must adapt to human presence to survive in the Anthropocene, so it is critical to understand species responses to humans in different contexts. We used camera trapping as a lens to view mammal responses to changes in human activity during the COVID-19 pandemic. Across 163 species sampled in 102 projects around the world, changes in the amount and timing of animal activity varied widely. Under higher human activity, mammals were less active in undeveloped areas but unexpectedly more active in developed areas while exhibiting greater nocturnality. Carnivores were most sensitive, showing the strongest decreases in activity and greatest increases in nocturnality. Wildlife managers must consider how habituation and uneven sensitivity across species may cause fundamental differences in human-wildlife interactions along gradients of human influence.

Matched MeSH terms: Human Activities*
Human Activities Attract Harmful Mosquitoes in a Tropical Urban Landscape

Lee JM, Wasserman RJ, Gan JY, Wilson RF, Rahman S, Yek SH

Ecohealth, 2020 03;17(1):52-63.
PMID: 31786667 DOI: 10.1007/s10393-019-01457-9

Knowledge of the interrelationship of mosquito communities and land use changes is of paramount importance to understand the potential risk of mosquito disease transmission. This study examined the effects of land use types in urban, peri-urban and natural landscapes on mosquito community structure to test whether the urban landscape is implicated in increased prevalence of potentially harmful mosquitoes. Three land use types (park, farm, and forest nested in urban, peri-urban and natural landscapes, respectively) in Klang Valley, Malaysia, were surveyed for mosquito larval habitat, mosquito abundance and diversity. We found that the nature of human activities in land use types can increase artificial larval habitats, supporting container-breeding vector specialists such as Aedes albopictus, a dengue vector. In addition, we observed a pattern of lower mosquito richness but higher mosquito abundance, characterised by the high prevalence of Ae. albopictus in the urban landscape. This was also reflected in the mosquito community structure whereby urban and peri-urban landscapes were composed of mainly vector species compared to a more diverse mosquito composition in natural landscape. This study suggested that good environmental management practices in the tropical urban landscape are of key importance for effective mosquito-borne disease management.

Matched MeSH terms: Human Activities*
Grain-dependent responses of mammalian diversity to land use and the implications for conservation set-aside

Wearn OR, Carbone C, Rowcliffe JM, Bernard H, Ewers RM

Ecol Appl, 2016 Jul;26(5):1409-1420.
PMID: 27755763 DOI: 10.1890/15-1363

Diversity responses to land-use change are poorly understood at local scales, hindering our ability to make forecasts and management recommendations at scales which are of practical relevance. A key barrier in this has been the underappreciation of grain-dependent diversity responses and the role that β-diversity (variation in community composition across space) plays in this. Decisions about the most effective spatial arrangement of conservation set-aside, for example high conservation value areas, have also neglected β-diversity, despite its role in determining the complementarity of sites. We examined local-scale mammalian species richness and β-diversity across old-growth forest, logged forest, and oil palm plantations in Borneo, using intensive camera- and live-trapping. For the first time, we were able to investigate diversity responses, as well as β-diversity, at multiple spatial grains, and across the whole terrestrial mammal community (large and small mammals); β-diversity was quantified by comparing observed β-diversity with that obtained under a null model, in order to control for sampling effects, and we refer to this as the β-diversity signal. Community responses to land use were grain dependent, with large mammals showing reduced richness in logged forest compared to old-growth forest at the grain of individual sampling points, but no change at the overall land-use level. Responses varied with species group, however, with small mammals increasing in richness at all grains in logged forest compared to old-growth forest. Both species groups were significantly depauperate in oil palm. Large mammal communities in old-growth forest became more heterogeneous at coarser spatial grains and small mammal communities became more homogeneous, while this pattern was reversed in logged forest. Both groups, however, showed a significant β-diversity signal at the finest grain in logged forest, likely due to logging-induced environmental heterogeneity. The β-diversity signal in oil palm was weak, but heterogeneity at the coarsest spatial grain was still evident, likely due to variation in landscape forest cover. Our findings suggest that the most effective spatial arrangement of set-aside will involve trade-offs between conserving large and small mammals. Greater consideration in the conservation and management of tropical landscapes needs to be given to β-diversity at a range of spatial grains.

Matched MeSH terms: Human Activities*
Africa: Restrict bush fires used in animal hunts

Dalu MTB, Dalu T, Wasserman RJ

Nature, 2017 07 19;547(7662):281.
PMID: 28726820 DOI: 10.1038/547281c
Matched MeSH terms: Human Activities*
Fulltext Robust video content analysis schemes for human action recognition

Aly CA, Abas FS, Ann GH

Sci Prog, 2021;104(2):368504211005480.
PMID: 33913378 DOI: 10.1177/00368504211005480

INTRODUCTION: Action recognition is a challenging time series classification task that has received much attention in the recent past due to its importance in critical applications, such as surveillance, visual behavior study, topic discovery, security, and content retrieval.
OBJECTIVES: The main objective of the research is to develop a robust and high-performance human action recognition techniques. A combination of local and holistic feature extraction methods used through analyzing the most effective features to extract to reach the objective, followed by using simple and high-performance machine learning algorithms.
METHODS: This paper presents three robust action recognition techniques based on a series of image analysis methods to detect activities in different scenes. The general scheme architecture consists of shot boundary detection, shot frame rate re-sampling, and compact feature vector extraction. This process is achieved by emphasizing variations and extracting strong patterns in feature vectors before classification.
RESULTS: The proposed schemes are tested on datasets with cluttered backgrounds, low- or high-resolution videos, different viewpoints, and different camera motion conditions, namely, the Hollywood-2, KTH, UCF11 (YouTube actions), and Weizmann datasets. The proposed schemes resulted in highly accurate video analysis results compared to those of other works based on four widely used datasets. The First, Second, and Third Schemes provides recognition accuracies of 57.8%, 73.6%, and 52.0% on Hollywood2, 94.5%, 97.0%, and 59.3% on KTH, 94.5%, 95.6%, and 94.2% on UCF11, and 98.9%, 97.8% and 100% on Weizmann.
CONCLUSION: Each of the proposed schemes provides high recognition accuracy compared to other state-of-art methods. Especially, the Second Scheme as it gives excellent comparable results to other benchmarked approaches.

Matched MeSH terms: Human Activities*
Fulltext Hunter-gatherer residential mobility and the marginal value of rainforest patches

Venkataraman VV, Kraft TS, Dominy NJ, Endicott KM

Proc Natl Acad Sci U S A, 2017 03 21;114(12):3097-3102.
PMID: 28265058 DOI: 10.1073/pnas.1617542114

The residential mobility patterns of modern hunter-gatherers broadly reflect local resource availability, but the proximate ecological and social forces that determine the timing of camp movements are poorly known. We tested the hypothesis that the timing of such moves maximizes foraging efficiency as hunter-gatherers move across the landscape. The marginal value theorem predicts when a group should depart a camp and its associated foraging area and move to another based on declining marginal return rates. This influential model has yet to be directly applied in a population of hunter-gatherers, primarily because the shape of gain curves (cumulative resource acquisition through time) and travel times between patches have been difficult to estimate in ethnographic settings. We tested the predictions of the marginal value theorem in the context of hunter-gatherer residential mobility using historical foraging data from nomadic, socially egalitarian Batek hunter-gatherers (n = 93 d across 11 residential camps) living in the tropical rainforests of Peninsular Malaysia. We characterized the gain functions for all resources acquired by the Batek at daily timescales and examined how patterns of individual foraging related to the emergent property of residential movements. Patterns of camp residence times conformed well with the predictions of the marginal value theorem, indicating that communal perceptions of resource depletion are closely linked to collective movement decisions. Despite (and perhaps because of) a protracted process of deliberation and argument about when to depart camps, Batek residential mobility seems to maximize group-level foraging efficiency.

Matched MeSH terms: Human Activities*
Fulltext Classifying Sources Influencing Indoor Air Quality (IAQ) Using Artificial Neural Network (ANN)

Saad SM, Andrew AM, Shakaff AY, Saad AR, Kamarudin AM, Zakaria A

Sensors (Basel), 2015;15(5):11665-84.
PMID: 26007724 DOI: 10.3390/s150511665

Monitoring indoor air quality (IAQ) is deemed important nowadays. A sophisticated IAQ monitoring system which could classify the source influencing the IAQ is definitely going to be very helpful to the users. Therefore, in this paper, an IAQ monitoring system has been proposed with a newly added feature which enables the system to identify the sources influencing the level of IAQ. In order to achieve this, the data collected has been trained with artificial neural network or ANN--a proven method for pattern recognition. Basically, the proposed system consists of sensor module cloud (SMC), base station and service-oriented client. The SMC contain collections of sensor modules that measure the air quality data and transmit the captured data to base station through wireless network. The IAQ monitoring system is also equipped with IAQ Index and thermal comfort index which could tell the users about the room's conditions. The results showed that the system is able to measure the level of air quality and successfully classify the sources influencing IAQ in various environments like ambient air, chemical presence, fragrance presence, foods and beverages and human activity.

Matched MeSH terms: Human Activities
Fulltext BeSafe B2.0 Smart Multisensory Platform for Safety in Workplaces

Márquez-Sánchez S, Campero-Jurado I, Robles-Camarillo D, Rodríguez S, Corchado-Rodríguez JM

Sensors (Basel), 2021 May 12;21(10).
PMID: 34066186 DOI: 10.3390/s21103372

Wearable technologies are becoming a profitable means of monitoring a person's health state, such as heart rate and physical activity. The use of the smartwatch is becoming consolidated, not only as a novelty but also as a very useful tool for daily use. In addition, other devices, such as helmets or belts, are beneficial for monitoring workers and the early detection of any anomaly. They can provide valuable information, especially in work environments, where they help reduce the rate of accidents and occupational diseases, which makes them powerful Personal Protective Equipment (PPE). The constant monitoring of the worker's health can be done in real-time, through temperature, falls, noise, impacts, or heart rate meters, activating an audible and vibrating alarm when an anomaly is detected. The gathered information is transmitted to a server in charge of collecting and processing it. In the first place, this paper provides an exhaustive review of the state of the art on works related to electronics for human activity behavior. After that, a smart multisensory bracelet, combined with other devices, developed a control platform that can improve operators' security in the working environment. Artificial Intelligence and the Internet of Things (AIoT) bring together the information to improve safety on construction sites, power stations, power lines, etc. Real-time and historic data is used to monitor operators' health and a hybrid system between Gaussian Mixture Model and Human Activity Classification. That is, our contribution is also founded on the use of two machine learning models, one based on unsupervised learning and the other one supervised. Where the GMM gave us a performance of 80%, 85%, 70%, and 80% for the 4 classes classified in real time, the LSTM obtained a result under the confusion matrix of 0.769, 0.892, and 0.921 for the carrying-displacing, falls, and walking-standing activities, respectively. This information was sent in real time through the platform that has been used to analyze and process the data in an alarm system.

Matched MeSH terms: Human Activities
Contributions of climate change and human activities to grassland degradation and improvement from 2001 to 2020 in Zhaosu County, China

Zhang M, Zhang F, Guo L, Dong P, Cheng C, Kumar P, et al.

J Environ Manage, 2023 Dec 15;348:119465.
PMID: 37924697 DOI: 10.1016/j.jenvman.2023.119465

Grassland degradation poses a serious threat to biodiversity, ecosystem services, and human well-being. In this study, we investigated grassland degradation in Zhaosu County, China, between 2001 and 2020, and analyzed the impacts of climate change and human activities using the Miami model. The actual net primary productivity (ANPP) obtained with CASA (Carnegie-Ames-Stanford Approach) modeling, showed a decreasing trend, reflecting the significant degradation that the grasslands in Zhaosu County have experienced in the past 20 years. Grassland degradation was found to be highest in 2018, while the degraded area continuously decreased in the last 3 years (2018-2020). Climatic factors for found to be the dominant factor affecting grassland degradation, particularly the decrease in precipitation. On the other hand, human activities were found to be the main factor affecting improvement of grasslands, especially in recent years. This finding profoundly elucidates the underlying causes of grassland degradation and improvement and helps implement ecological conservation and restoration measures. From a practical perspective, the research results provide an important reference for the formulation of policies and management strategies for sustainable land use.

Matched MeSH terms: Human Activities
Apes in the Anthropocene: flexibility and survival

Hockings KJ, McLennan MR, Carvalho S, Ancrenaz M, Bobe R, Byrne RW, et al.

Trends Ecol Evol, 2015 Apr;30(4):215-22.
PMID: 25766059 DOI: 10.1016/j.tree.2015.02.002

We are in a new epoch, the Anthropocene, and research into our closest living relatives, the great apes, must keep pace with the rate that our species is driving change. While a goal of many studies is to understand how great apes behave in natural contexts, the impact of human activities must increasingly be taken into account. This is both a challenge and an opportunity, which can importantly inform research in three diverse fields: cognition, human evolution, and conservation. No long-term great ape research site is wholly unaffected by human influence, but research at those that are especially affected by human activity is particularly important for ensuring that our great ape kin survive the Anthropocene.

Matched MeSH terms: Human Activities*
Fulltext Effects of temperature, humidity, air quality and anthropic activities on the transmission of SARS-CoV-2: a systematic review protocol

Jeevananthan C, Muhamad NA, Jaafar MH, Hod R, Ab Ghani RM, Md Isa Z, et al.

BMJ Open, 2020 11 04;10(11):e039623.
PMID: 33148753 DOI: 10.1136/bmjopen-2020-039623

INTRODUCTION: The current global pandemic of the virus that emerged from Hubei province in China has caused coronavirus disease in 2019 (COVID-19), which has affected a total number of 900 036 people globally, involving 206 countries and resulted in a cumulative of 45 693 deaths worldwide as of 3 April 2020. The mode of transmission is identified through airdrops from patients' body fluids such as during sneezing, coughing and talking. However, the relative importance of environmental effects in the transmission of the virus has not been vastly studied. In addition, the role of temperature and humidity in air-borne transmission of infection is presently still unclear. This study aims to identify the effect of temperature, humidity and air quality in the transmission of SARS-CoV-2.
METHODS AND ANALYSIS: We will systematically conduct a comprehensive literature search using various databases including PubMed, EMBASE, Scopus, CENTRAL and Google Scholar to identify potential studies. The search will be performed for any eligible articles from the earliest published articles up to latest available studies in 2020. We will include all the observational studies such as cohort case-control and cross-sectional studies that explains or measures the effects of temperature and/or humidity and/or air quality and/or anthropic activities that is associated with SARS-CoV-2. Study selection and reporting will follow the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines and Meta-Analysis of Observational Studies in Epidemiology guideline. All data will be extracted using a standardised data extraction form and quality of the studies will be assessed using the Newcastle-Ottawa Scale guideline. Descriptive and meta-analysis will be performed using a random effect model in Review Manager File.
ETHICS AND DISSEMINATION: No primary data will be collected, and thus no formal ethical approval is required. The results will be disseminated through a peer-reviewed publication and conference presentation.
PROSPERO REGISTRATION NUMBER: CRD42020176756.

Matched MeSH terms: Human Activities*
Pervasive human-driven decline of life on Earth points to the need for transformative change

Díaz S, Settele J, Brondízio ES, Ngo HT, Agard J, Arneth A, et al.

Science, 2019 12 13;366(6471).
PMID: 31831642 DOI: 10.1126/science.aax3100

The human impact on life on Earth has increased sharply since the 1970s, driven by the demands of a growing population with rising average per capita income. Nature is currently supplying more materials than ever before, but this has come at the high cost of unprecedented global declines in the extent and integrity of ecosystems, distinctness of local ecological communities, abundance and number of wild species, and the number of local domesticated varieties. Such changes reduce vital benefits that people receive from nature and threaten the quality of life of future generations. Both the benefits of an expanding economy and the costs of reducing nature's benefits are unequally distributed. The fabric of life on which we all depend-nature and its contributions to people-is unravelling rapidly. Despite the severity of the threats and lack of enough progress in tackling them to date, opportunities exist to change future trajectories through transformative action. Such action must begin immediately, however, and address the root economic, social, and technological causes of nature's deterioration.

Matched MeSH terms: Human Activities/trends*
Fulltext Hydrological responses to climate and land use change at watershed scale_ Malaysia

Mahboubeh Ebrahimian, Ahmad Ainuddin Nuruddin, Mohd Amin Mohd Soom, Alias Mohd Sood, Liew Juneng

The Pertanika Journal of Scholarly Research Reviews, 2017;3(2):10-32.
MyJurnal

The hydrological effects of climate variation and land use conversion can occur at various spatial scales, but the most important sources of these changes are at the regional or watershed scale. In addition, the managerial and technical measures are primarily implemented at local and watershed scales in order to mitigate adverse impacts of human activities on the renewable resources of the watershed. Therefore, quantitative estimation of the possible hydrological consequences of potential land use and climate changes on hydrological regime at watershed scale is of tremendous importance. This paper focuses on the impacts of climate change as well as land use change on the hydrological processes of river basin based on pertinent published literature which were precisely scrutinized. The various causes, forms, and consequences of such impacts were discussed to synthesize the key findings of literature in reputable sources and to identify gaps in the knowledge where further research is required. Results indicate that the watershed-scale studies were found as a gap in tropical regions. Also, these studies are important to facilitate the application of results to real environment. Watershed scale studies are essential to measure the extent of influences made to the hydrological conditions and understanding of causes and effects of climate variation and land use conversion on hydrological cycle and water resources.

Matched MeSH terms: Human Activities
Fulltext Development of a User-Adaptable Human Fall Detection Based on Fall Risk Levels Using Depth Sensor

Nizam Y, Mohd MNH, Jamil MMA

Sensors (Basel), 2018 Jul 13;18(7).
PMID: 30011823 DOI: 10.3390/s18072260

Unintentional falls are a major public health concern for many communities, especially with aging populations. There are various approaches used to classify human activities for fall detection. Related studies have employed wearable, non-invasive sensors, video cameras and depth sensor-based approaches to develop such monitoring systems. The proposed approach in this study uses a depth sensor and employs a unique procedure which identifies the fall risk levels to adapt the algorithm for different people with their physical strength to withstand falls. The inclusion of the fall risk level identification, further enhanced and improved the accuracy of the fall detection. The experimental results showed promising performance in adapting the algorithm for people with different fall risk levels for fall detection.

Matched MeSH terms: Human Activities
Fulltext Luminescent bacterial testing for monitoring hydrocarbon bioremediation – a review

Maryam, Z.

Journal of Biochemistry, Microbiology and Biotechnology, 2015;3(2):13-20.
MyJurnal

Human activities in a large array of industrial and agricultural sectors produce chemical contaminants which are chiefly hydrocarbons of various types that are potentially toxic and carcinogenic to aquatic and terrestrial organisms. Globally, millions of tons of these pollutants are generated annually, and in some areas, they are released indiscriminately to the environment. In order to overcome this problem, microbiological decontamination or bioremediation has been suggested. Bioremediation has been argued to be an efficient, economic, and adaptable alternative to physicochemical remediation. However, to date, such claims of successful bioremediation are often not supported by evidence from toxicity studies. In this regard, luminescent bacteria have been employed in some hydrocarbon remediation experiments to denote reduction in toxicity. In this review, the utilization of luminescence bacteria as toxicity monitoring agent for hydrocarbon remediation is discussed.

Matched MeSH terms: Human Activities
MSTCN: A multiscale temporal convolutional network for user independent human activity recognition

Raja Sekaran S, Pang YH, Ling GF, Yin OS

F1000Res, 2021;10:1261.
PMID: 36896393 DOI: 10.12688/f1000research.73175.1

Background: In recent years, human activity recognition (HAR) has been an active research topic due to its widespread application in various fields such as healthcare, sports, patient monitoring, etc. HAR approaches can be categorised as handcrafted feature methods (HCF) and deep learning methods (DL). HCF involves complex data pre-processing and manual feature extraction in which the models may be exposed to high bias and crucial implicit pattern loss. Hence, DL approaches are introduced due to their exceptional recognition performance. Convolutional Neural Network (CNN) extracts spatial features while preserving localisation. However, it hardly captures temporal features. Recurrent Neural Network (RNN) learns temporal features, but it is susceptible to gradient vanishing and suffers from short-term memory problems. Unlike RNN, Long-Short Term Memory network has a relatively longer-term dependency. However, it consumes higher computation and memory because it computes and stores partial results at each level. Methods: This work proposes a novel multiscale temporal convolutional network (MSTCN) based on the Inception model with a temporal convolutional architecture. Unlike HCF methods, MSTCN requires minimal pre-processing and no manual feature engineering. Further, multiple separable convolutions with different-sized kernels are used in MSTCN for multiscale feature extraction. Dilations are applied to each separable convolution to enlarge the receptive fields without increasing the model parameters. Moreover, residual connections are utilised to prevent information loss and gradient vanishing. These features enable MSTCN to possess a longer effective history while maintaining a relatively low in-network computation. Results: The performance of MSTCN is evaluated on UCI and WISDM datasets using a subject independent protocol with no overlapping subjects between the training and testing sets. MSTCN achieves accuracies of 97.42 on UCI and 96.09 on WISDM. Conclusion: The proposed MSTCN dominates the other state-of-the-art methods by acquiring high recognition accuracies without requiring any manual feature engineering.

Matched MeSH terms: Human Activities
Fulltext Multi-View Human Action Recognition Using Skeleton Based-FineKNN with Extraneous Frame Scrapping Technique

Malik NUR, Sheikh UU, Abu-Bakar SAR, Channa A

Sensors (Basel), 2023 Mar 02;23(5).
PMID: 36904953 DOI: 10.3390/s23052745

Human action recognition (HAR) is one of the most active research topics in the field of computer vision. Even though this area is well-researched, HAR algorithms such as 3D Convolution Neural Networks (CNN), Two-stream Networks, and CNN-LSTM (Long Short-Term Memory) suffer from highly complex models. These algorithms involve a huge number of weights adjustments during the training phase, and as a consequence, require high-end configuration machines for real-time HAR applications. Therefore, this paper presents an extraneous frame scrapping technique that employs 2D skeleton features with a Fine-KNN classifier-based HAR system to overcome the dimensionality problems.To illustrate the efficacy of our proposed method, two contemporary datasets i.e., Multi-Camera Action Dataset (MCAD) and INRIA Xmas Motion Acquisition Sequences (IXMAS) dataset was used in experiment. We used the OpenPose technique to extract the 2D information, The proposed method was compared with CNN-LSTM, and other State of the art methods. Results obtained confirm the potential of our technique. The proposed OpenPose-FineKNN with Extraneous Frame Scrapping Technique achieved an accuracy of 89.75% on MCAD dataset and 90.97% on IXMAS dataset better than existing technique.

Matched MeSH terms: Human Activities

Filters

Please provide feedback to Administrator ([email protected])

External Links