Performance Comparisson Human Activity Recognition Using Simple Linear Method

Objective Activities of daily living are activities that are formed in order to take care of the body and are essential for life and well-being and fundamental survival. These activities begin in infancy and are modified at different stages of development. Cultural values, parental expectations, social routines, and the physical environment influence daily activities. Concerns about children's use of time and daily activities are not new, but studies on them are rare. So to have more information and knowledge about children's lives and well-being, we need to have more information about their daily activities. The aim of this study was to investigate the time allocated to daily life activities based on the day of the week, age and gender in healthy children under 5 years in Isfahan. Materials & Methods In this survey (descriptive-analytical) study in which healthy children under 5 years old in Isfahan were present, from different age groups according to the population of that age group, 240 girls and boys so that the number of girls and boys were equal in the age categories of less than 1 month, 2 to 3 months, 4 to 6 months, 7 to 12 months, 1 to 2 years and 3 to 5 years, were selected by multi-stage, stratified, cluster and convenience sampling . In order to collect research data, demographic questionnaire and time use diary tools were used. Results The results showed that on weekdays, among the components of daily life activities, the most time with an average of 150.59 minutes per day is devoted to eating (and drinking) and the least time with an average of 0.02% per day is devoted to caring of Personal belongings, while in the last days on average the most time is spent eating (and drinking) and the least time is spent on other daily activities. In different age groups on weekdays, infants 0 to 1 month with an average of 273.35 minutes per day have the most time and children 25-60 months with an average of 154.65 minutes per day have the least time devoted to daily life activities on weekdays. Meanwhile, infants in the age group of 0-1 months on a weekend spent the most time on daily activities and children in the age group of 25-60 months spent the least time on daily activities. Girls and boys spent the most time eating (and drinking) among the activities of daily living on a weekend, while boys and girls spent the least time on other daily activities that are not categorized in this study. There was no significant difference Between the time allocated to daily life activities on weekdays and weekends and between the time allocated by girls and boys under 5 years old living in Isfahan on one day a week to activity of daily livings, both on weekdays and weekends (P>0.05). However, there is a significant difference between the time use of daily life activities in different age groups on weekdays and weekends (P<0.05), and finally, there is a difference between the time allocated to daily life activities on one day of the week and the weekend (P<0.05). Conclusion According to the results of the present study, age groups and days of the week are influential factors on daily activities, but gender has no effect on daily activity patterns.

Daily locomotor activity patterns of the desert iguana, Dipsosaurus dorsalis, were recorded under light (L):dark (D) conditions of 12L:12D. These animals produced daily patterns which (a) were monophasic, (b) showed a response of the lizard to onset of light. Both of these characteristics accord with those reported for other day-active animals. The laboratory-recorded daily activity rhythms correlate remarkably well with the field behavior of movement in burrows before emergence, basking early in the activity period, foraging, and retreating to shade or burrow in the later part of the activity period. It is likely that the laboratory-recorded daily activity patterns would change according to the temperature in the activity chamber. These changes would correlate with the seasonal variations in daily activity patterns reported in field studies. Wide individual differences in phase-angle relationships between activity onset and light onset among lizards was observed. It is possible that these differences are due to one or more of the following factors; (a) the low intensity difference between the light and dark phases of the cycle, (b) individual differences in preferred body temperature, and/or (c) individual differences in daily light requirements.

Smartphones are increasing ubiquitously due to the need and demand in the modern era. The world is transmuting into a global village with the cumulation of smart devices. Nowadays, smartphones are enriched with inertial sensors which can be used to recognize physical human activities in the wild. Human activity recognition (HAR) lies at the core of many applications like health monitoring, fall detection, road safety, personal assistance, and behavior-based context awareness. Context-based HAR is a new dimension that provides fine-grained information about the action being performed and leads us towards the automated and intelligent system design, which is useful to furnish the smart solution to real-life problems. In this paper, smartphone sensors are utilized to propose a framework for human activity and context recognition. This framework performs activity-dependent context recognition on the ExtraSensory dataset using random forest, decision tree, and k-nearest neighbor classifiers, and achieves an accuracy of 93.10%, demonstrating the effectiveness of the proposed framework.

With the popularity of wearable smart devices, human activity recognition (HAR) based on smart sensors has been widely applied in daily life and medical health fields. In order to balance the accuracy of HAR and the complexity of the algorithm, this paper proposes an HAR algorithm based on the extreme gradient boosting (XGBoost) method. The original data collected by sensors contains noise, thus denoising process is firstly performed. Then multi-dimensional features are extracted from the data because of the limited dimensional features, which cannot be directly utilized in the training process. After that, principal component analysis (PCA) is used to reduce the dimensionality of the data in order to alleviate the input complexity of the training model. Finally, the human activity is recognized using the XGBoost method, and the ultimate goal is to obtain the tradeoff between speed and accuracy of the HAR algorithm.

An increase in life expectancy is leading to an aging society, where gradual degradation in physical/cognitive health could result in fall injuries, cardiovascular, neurological/psychological problems, or a sedentary lifestyle. Sensor-based human activity recognition (HAR) is found to be a potential assistive technology in this context to improve the quality of life of an aging society. This chapter presents the state of the art and future trends of Internet of Things (IoT)-enabled sensor data-based Human Activity Recognition (HAR) systems, where machine learning (ML)/deep learning (DL) is used to classify human actions in the context of healthcare applications. In particular, the impact of IoT on the healthcare industry is so immense that a dedicated specialization, termed as Internet of Healthcare Things (IoHT), has emerged. Smart healthcare systems are equipped with different categories of sensors (wearable, wireless, and ambient). The huge amount of sensor data acquired by IoHT sensors allows for performing accurate HAR. The HAR involves detection/classification problems, e.g. fall detection and seizer detection, where ML is used extensively, at its heart. A lot of ML/DL techniques are being used in HAR including support vector machine (SVM), artificial neural network (ANN), recurrent neural network (RNN), convolutional neural network (CNN), deep neural network (DNN), long short-term memory (LSTM), etc. However, there are a few special aspects of HAR sensor data that make it difficult to handle. Involved research is still being pursued across the globe to solve these problems.KeywordsIoTIoHTHealth careHARSensorMachine learning (ML)Deep learning (DL)

BackgroundAnalyzing actigraphy data using standard circadian parametric models and aggregated nonparametric indices may obscure temporal information that may be a hallmark of the circadian impairment in psychiatric disorders. Functional data analysis (FDA) may overcome such limitations by fully exploiting the richness of actigraphy data and revealing important relationships with mental health outcomes. To our knowledge, no studies have extensively used FDA to study the relationship between sociodemographic, health and lifestyle, sampling, and psychiatric clinical characteristics and daily motor activity patterns assessed with actigraphy in a sample of individuals with and without depression/anxiety.ObjectiveWe aimed to study the association between daily motor activity patterns assessed via actigraphy and (1) sociodemographic, health and lifestyle, and sampling factors, and (2) psychiatric clinical characteristics (ie, presence and severity of depression/anxiety disorders).MethodsWe obtained 14-day continuous actigraphy data from 359 participants from the Netherlands Study of Depression and Anxiety with current (n=93), remitted (n=176), or no (n=90) depression/anxiety diagnosis, based on the criteria of the Diagnostic and Statistical Manual of Mental Disorders, fourth edition. Associations between patterns of daily motor activity, quantified via functional principal component analysis (fPCA), and sociodemographic, health and lifestyle, sampling, and psychiatric clinical characteristics were assessed using generalized estimating equation regressions. For exploratory purposes, function-on-scalar regression (FoSR) was applied to quantify the time-varying association of sociodemographic, health and lifestyle, sampling, and psychiatric clinical characteristics on daily motor activity.ResultsFour components of daily activity patterns captured 77.4% of the variability in the data: overall daily activity level (fPCA1, 34.3% variability), early versus late morning activity (fPCA2, 16.5% variability), biphasic versus monophasic activity (fPCA3, 14.8% variability), and early versus late biphasic activity (fPCA4, 11.8% variability). A low overall daily activity level was associated with a number of sociodemographic, health and lifestyle, and psychopathology variables: older age (P<.001), higher education level (P=.005), higher BMI (P=.009), greater number of chronic diseases (P=.02), greater number of cigarettes smoked per day (P=.02), current depressive and/or anxiety disorders (P=.05), and greater severity of depressive symptoms (P<.001). A high overall daily activity level was associated with work/school days (P=.02) and summer (reference: winter; P=.03). Earlier morning activity was associated with older age (P=.02), having a partner (P=.009), work/school days (P<.001), and autumn and spring (reference: winter; P=.02 and P<.001, respectively). Monophasic activity was associated with older age (P=.005). Biphasic activity was associated with work/school days (P<.001) and summer (reference: winter; P<.001). Earlier biphasic activity was associated with older age (P=.005), work/school days (P<.001), and spring and summer (reference: winter; P<.001 and P=.005, respectively). In FoSR analyses, age, work/school days, and season were the main determinants having a time-varying association with daily motor activity (all P<.05).ConclusionsFeatures of daily motor activity extracted with fPCA reflect commonly studied factors such as the intensity of daily activity and preference for morningness/eveningness. The presence and severity of depression/anxiety disorders were found to be associated mainly with a lower overall activity pattern but not with the time of the activity. Age, work/school days, and season were the variables most strongly associated with patterns and time of activity, and thus future epidemiological studies on motor activity in depression/anxiety should take these variables into account.

Background and objectiveThreatened abortion, a common pregnancy complication that often leading to abortion, is hard to predict due to its non-specific symptoms and difficulty in differentiating from other early pregnancy bleeding causes. Current diagnostic methods like serial ultrasounds and clinical monitoring are time-consuming and lack timeliness. To fill the gap in using advanced analytics for early detection and risk stratification, this study develops a machine learning (ML) model based on routine blood data to better predict threatened abortion, providing a reference for early detection and intervention.MethodsIn this study, we collected medical records from January 2022 to March 2024. We analyzed data from 1764 patients with threatened abortion and 1489 healthy controls. Blood test data of all participants were gathered. The Z-score normalization technique was applied to standardize blood routine indicators. This reduced the influence of outliers and noise. During hyperparameter optimization, ‘class_weight="balanced"’ was set to handle sample imbalance. The screening data was partitioned into a training set of 2928 cases (including the validation set) and a test set of 325 cases at an 8:1:1 ratio. Python was used to facilitate data transformation. Eight different ML algorithms—Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting (GBM), Extreme Gradient Boosting (XGB), Deep Neural Network (DNN), Decision Tree (DT) and Naive Bayes (NB)—were used to construct a threatened abortion prediction model. The prediction performances of the ML models were evaluated by calculating the area under the curve (AUC) values. We used the SHapley Additive exPlanation (SHAP) method to explain the models.ResultsComparatively, the DNN model showed the highest predictive performance among the eight models, with the highest AUC value of 96.76% and top metrics for accuracy (91.88%), specificity (91.62%), sensitivity (92.11%), and F1 score (92.48%). SHAP analysis identified Red Cell Distribution Width - Standard Deviation (RDW-SD), Platelet Distribution Width (PDW), Mean Platelet Volume (MPV), Red Cell Distribution Width - Coefficient of Variation (RDW-CV), Absolute Basophil Count (BAS#), Platelet Count (PLT), Mean Corpuscular Hemoglobin Concentration (MCHC) and Lymphocyte Percentage (LYM) as the most influential features in predicting threatened abortion, with PDW, RDW-CV, BAS#, PLT, MCHC and LYM positively contributing to the prediction, whereas RDW-SD and MPV had negative contributions.ConclusionsOur research on constructing a prediction model for threatened abortion through routine blood tests has revealed the great potential of ML algorithms in detecting threatened abortion. This algorithm is expected to analyse routine blood data to identify at-risk pregnancies at an early stage, significantly improving the early detection of this common pregnancy complication. It will assist healthcare providers in intervening earlier and reducing the incidence of abortion. However, before the model can be translated into routine clinical applications, more extensive validation studies are still needed.Supplementary InformationThe online version contains supplementary material available at 10.1186/s12884-025-08030-z.

Accurate histopathological grading of gliomas is critical for clinical management but remains dependent on subjective pathological assessment. This study developed a machine learning framework to predict glioma grade from clinicogenomic features in the TCGA cohort. A multimodal feature set was constructed, comprising demographic variables, mutation status of glioma-associated genes, and derived statistical features. Six machine learning algorithms—Logistic Regression, Random Forest, Support Vector Machine, k-Nearest Neighbors, Gradient Boosting, and a Multilayer Perceptron—were systematically evaluated. After hyperparameter optimization of the top-performing models, an ensemble model was implemented to improve predictive stability. The final ensemble achieved an area under the receiver operating characteristic curve (AUC-ROC) of 0.935 on an independent test set. Feature importance analysis identified mutations in IDH1 and TP53, alongside patient age at diagnosis, as the strongest predictive features, consistent with established neuro-oncological knowledge. Model robustness was confirmed through bootstrap validation. This work establishes a reproducible computational workflow that integrates multi-algorithm comparison, systematic hyperparameter tuning, and interpretable feature analysis, providing a framework to support objective glioma grading and the potential translation of genomic biomarkers into clinical practice.

Accurate prediction of geological hazard susceptibility forms the foundation of effective risk management, yet small-sample constraints often limit model generalization. In order to address this issue, this study applied an ensemble method based on predictive symmetry quantification, using Mount Tai, China, as a test case. Thirteen influencing factors were integrated using six machine learning algorithms—Logistic Regression (LR), Multilayer Perceptron (MLP), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), eXtreme Gradient Boosting (XGB), and Support Vector Machine (SVM)—trained on 34 hazard sites. Symmetry breaking in model outputs was quantified, and XGB and MLP, which showed the lowest correlation (0.59), were selected for dynamic weighted integration. Symmetry-adjusted weighting counteracts bias from individual models. For hyperparameter tuning, grid search was employed, while SHapley Additive exPlanations (SHAP) was used to quantify factor contributions. The performance of each model was evaluated using AUC and AP metrics. The key results show that all base models performed robustly (AUC &gt; 0.8), with XGB showing high consistency (AUC = 0.927), and the performance of the symmetry-optimized ensemble (MLP + XGB) exceeded that of all the individual models (AUC = 0.964). The dominant drivers of Geohazards included elevation, slope, the topographic wetness index, and road adjacency, with high-susceptibility zones clustered in southeastern high-altitude terrain, central mountains, and road-intensive north-central sectors. The approach presented here provides an ensemble method based on predictive symmetry quantification that is effective under the constraints of small sample sizes.

In this paper, we present a home-monitoring oriented human activity recognition benchmark database, based on the combination of a color video camera and a depth sensor. Our contributions are two-fold: 1) We have created a publicly releasable human activity video database (i.e., named as RGBD-HuDaAct), which contains synchronized color-depth video streams, for the task of human daily activity recognition. This database aims at encouraging more research efforts on human activity recognition based on multi-modality sensor combination (e.g., color plus depth). 2) Two multi-modality fusion schemes, which naturally combine color and depth information, have been developed from two state-of-the-art feature representation methods for action recognition, i.e., spatio-temporal interest points (STIPs) and motion history images (MHIs). These depth-extended feature representation methods are evaluated comprehensively and superior recognition performances over their uni-modality (e.g., color only) counterparts are demonstrated.

Human Activity Recognition (HAR) is essential for monitoring and analyzing human behavior, particularly in health applications such as fall detection and chronic disease management. Traditional methods, even those incorporating attention mechanisms, often oversimplify the complex temporal and spatial dependencies in sensor data by processing features uniformly, leading to inadequate modeling of high-dimensional interactions. To address these limitations, we propose a novel framework: the Temporal-Spatial Feature Decoupling Unit with Layer-wise Training Convolutional Neural Network (CNN-TSFDU-LW). Our model enhances HAR accuracy by decoupling temporal and spatial dependencies, facilitating more precise feature extraction and reducing computational overhead. The TSFDU mechanism enables parallel processing of temporal and spatial features, thereby enriching the learned representations. Furthermore, layer-wise training with a local error function allows for independent updates of each CNN layer, reducing the number of parameters and improving memory efficiency without compromising performance. Experiments on four benchmark datasets (UCI-HAR, PAMAP2, UNIMIB-SHAR, and USC-HAD) demonstrate accuracy improvements ranging from 0.9% to 4.19% over state-of-the-art methods while simultaneously reducing computational complexity. Specifically, our framework achieves accuracy rates of 97.90% on UCI-HAR, 94.34% on PAMAP2, 78.90% on UNIMIB-SHAR, and 94.71% on USC-HAD, underscoring its effectiveness in complex HAR tasks. In conclusion, the CNN-TSFDU-LW framework represents a significant advancement in sensor-based HAR, delivering both improved accuracy and computational efficiency, with promising potential for enhancing health monitoring applications.

Human Activity Recognition (HAR) has become one of the most important research fields to achieve real-time monitoring of human activities for timely decision making in various applications like fall detection, elderly care etc. Now-a-days, most people use smartphones which come with various embedded inertial sensors like accelerometer and gyroscope to monitor acceleration and angular velocity. These smartphone-based sensors have proven to be cost-effective solution in identification of activities belonging to ADL (Activities of Daily Living). Various Machine Learning, Deep learning and hybrid models have been proposed and implemented for HAR. This paper also proposes various hybrid deep learning approaches which combine Deep Neural Networks with other models like LSTM (Long Short Term Memory) Model and GRU (Gated Recurrent Unit) for effective classification of engineered features from CNN (Convolutional Neural Network) Model. A novel architecture that integrates CNN with Random Forest Classifier (DeepCNN-RF) is proposed to add randomness to the model. The proposed models have been tested on publicly available HAR Datasets like UCI HAR and WISDM Activity Recognition Datasets. Experimental results show that the hybrid models outperform the state-of-the-art data mining, machine learning techniques in UCI HAR and WISDM with an overall maximum accuracy of 97.77% and 98.2% respectively.

In the context of the ageing global population, researchers and scientists have tried to find solutions to many challenges faced by older people. Falls, the leading cause of injury among elderly, are usually severe enough to require immediate medical attention; thus, their detection is of primary importance. To this effect, many fall detection systems that utilize wearable and ambient sensors have been proposed. In this study, we compare three newly proposed data fusion schemes that have been applied in human activity recognition and fall detection. Furthermore, these algorithms are compared to our recent work regarding fall detection in which only one type of sensor is used. The results show that fusion algorithms differ in their performance, whereas a machine learning strategy should be preferred. In conclusion, the methods presented and the comparison of their performance provide useful insights into the problem of fall detection.

The concept of Human Activity Recognition (HAR) is integral to applications based on Internet of Things (IoT)-enabled devices, particularly in healthcare, fitness tracking, and smart environments. The streams of data from wearable sensors are rich in information, yet their high dimensionality and variability pose a significant challenge to proper classification. To address this problem, this paper proposes hybrid architectures that integrate traditional machine learning models with a deep neural network (DNN) to deliver improved performance and enhanced capabilities for HAR tasks. Multi-sensor HAR data were used to systematically test several hybrid models, including: RF + DNN (Random Forest + Deep Neural Network), XGB + DNN (XGBoost + DNN), GB + DNN (Gradient Boosting + DNN), KNN + DNN (K-Nearest Neighbors + DNN), and DT + DNN (Decision Tree + DNN). The RF + DNN model was the most accurate, achieving a 97.03% score with excellent precision, recall, and F1-score. These findings demonstrate that hybrid machine learning and deep learning systems have a promising future in IoT-based HAR applications. The model provides a novel solution for developing smart and trustworthy monitoring systems that support real-time analytics, patient surveillance, and other IoT applications.

Smartphone-Based Human Activity Recognition Using Bagging and Boosting