Search Results (190)

Developing interfaces for seizure diagnosis, often challenging to detect visually, is rising. However, their effectiveness is constrained by the need for diverse and extensive databases. This study aimed to create a seizure detection methodology incorporating detailed information from each EEG channel and accounts for frequency band variations linked to the primary brain pathology leading to ICU admission, enhancing our ability to identify epilepsy onset. This study involved 460 video-electroencephalography recordings from 71 patients under monitoring. We applied signal preprocessing and conducted a numerical quantitative analysis in the frequency domain. Various machine learning algorithms were assessed for their efficacy. The k-nearest neighbours (KNN) model was the most effective in our overall sample, achieving an average F1 score of 0.76. For specific subgroups, different models showed superior performance: Decision Tree for ‘Epilepsy’ (average F1 score of 0.80) and ‘Craniencephalic Trauma’ (average F1 score of 0.84), Random Forest for ‘Cardiorespiratory Arrest’ (average F1 score of 0.89) and ‘Brain Haemorrhage’ (average F1 score of 0.84). In the categorisation of seizure types, Linear Discriminant Analysis was most effective for focal seizures (average F1 score of 0.87), KNN for generalised (average F1 score of 0.84) and convulsive seizures (average F1 score of 0.88), and logistic regression for non-convulsive seizures (average F1 score of 0.83). Our study demonstrates the potential of using classifier models based on quantified EEG data for diagnosing seizures in ICU patients. The performance of these models varies significantly depending on the underlying cause of the seizure, highlighting the importance of tailored approaches. The automation of these diagnostic tools could facilitate early seizure detection. Full article

The efficient classification of body position is crucial for monitoring infants’ motor development. It may fast-track the early detection of developmental issues related not only to the acquisition of motor milestones but also to postural stability and movement patterns. In turn, this may facilitate and enhance opportunities for early intervention that are crucial for promoting healthy growth and development. The manual classification of human body position based on video recordings is labour-intensive, leading to the adoption of Inertial Motion Unit (IMU) sensors. IMUs measure acceleration, angular velocity, and magnetic field intensity, enabling the automated classification of body position. Many research teams are currently employing supervised machine learning classifiers that utilise hand-crafted features for data segment classification. In this study, we used a longitudinal dataset of IMU recordings made in the lab in three different play activities of infants aged 4–12 months. The classification was conducted based on manually annotated video recordings. We found superior performance of the CatBoost Classifier over the Random Forest Classifier in the task of classifying five positions based on IMU sensor data from infants, yielding excellent classification accuracy of the Supine (97.7%), Sitting (93.5%), and Prone (89.9%) positions. Moreover, using data ablation experiments and analysing the SHAP (SHapley Additive exPlanations) values, the study assessed the importance of various groups of features from both the time and frequency domains. The results highlight that both accelerometer and magnetometer data, especially their statistical characteristics, are critical contributors to improving the accuracy of body position classification. Full article

Non-contact heart monitoring is crucial in advancing telemedicine, fitness tracking, and mass screening. Remote photoplethysmography (rPPG) is a non-contact technique to obtain information about heart pulse by analyzing the changes in the light intensity reflected or absorbed by the skin during the blood circulation cycle. However, this technique is sensitive to environmental lightning and different skin pigmentation, resulting in unreliable results. This research presents a multimodal approach to non-contact heart rate estimation by combining facial video and physical attributes, including age, gender, weight, height, and body mass index (BMI). For this purpose, we collected local datasets from 60 individuals containing a 1 min facial video and physical attributes such as age, gender, weight, and height, and we derived the BMI variable from the weight and height. We compare the performance of two machine learning models, support vector regression (SVR) and random forest regression on the multimodal dataset. The experimental results demonstrate that incorporating a multimodal approach enhances model performance, with the random forest model achieving superior results, yielding a mean absolute error (MAE) of 3.057 bpm, a root mean squared error (RMSE) of 10.532 bpm, and a mean absolute percentage error (MAPE) of 4.2% that outperforms the state-of-the-art rPPG methods. These findings highlight the potential for interpretable, non-contact, real-time heart rate measurement systems to contribute effectively to applications in telemedicine and mass screening. Full article

The detection of the human mental fatigue state holds immense significance due to its direct impact on work efficiency, specifically in system operation control. Numerous approaches have been proposed to address the challenge of fatigue detection, aiming to identify signs of fatigue and alert the individual. This paper introduces an approach to human mental fatigue assessment based on the application of machine learning techniques to the video of a working operator. For validation purposes, the approach was applied to a dataset, “Human Fatigue Assessment Based on Video Data” (HFAVD) integrating video data with features computed by using our computer vision deep learning models. The incorporated features encompass head movements represented by Euler angles (roll, pitch, and yaw), vital signs (blood pressure, heart rate, oxygen saturation, and respiratory rate), and eye and mouth states (blinking and yawning). The integration of these features eliminates the need for the manual calculation or detection of these parameters, and it obviates the requirement for sensors and external devices, which are commonly employed in existing datasets. The main objective of our work is to advance research in fatigue detection, particularly in work and academic settings. For this reason, we conducted a series of experiments by utilizing machine learning techniques to analyze the dataset and assess the fatigue state based on the features predicted by our models. The results reveal that the random forest technique consistently achieved the highest accuracy and F1-score across all experiments, predominantly exceeding 90%. These findings suggest that random forest is a highly promising technique for this task and prove the strong connection and association among the predicted features used to annotate the videos and the state of fatigue. Full article

This paper introduces a classification model that detects and classifies argumentative behaviors between two individuals by utilizing a machine learning application, based on the MediaPipe Holistic model. The approach involves the distinction between two different classes based on the behavior of two individuals, argumentative and non-argumentative behaviors, corresponding to verbal argumentative behavior. By using a dataset extracted from video frames of hand gestures, body stance and facial expression, and by using their corresponding landmarks, three different classification models were trained and evaluated. The results indicate that Random Forest Classifier outperformed the other two by classifying argumentative behaviors with 68.07% accuracy and non-argumentative behaviors with 94.18% accuracy, correspondingly. Thus, there is future scope for advancing this classification model to a prediction model, with the aim of predicting aggressive behavior in patients suffering with dementia before their onset. Full article

Classroom EEG recordings classification has the capacity to significantly enhance comprehension and learning by revealing complex neural patterns linked to various cognitive processes. Electroencephalography (EEG) in academic settings allows researchers to study brain activity while students are in class, revealing learning preferences. The purpose of this study was to develop a machine learning framework to automatically classify different learning-style EEG patterns in real classroom environments. Method: In this study, a set of EEG features was investigated, including statistical features, fractal dimension, higher-order spectra, entropy, and a combination of all sets. Three different machine learning classifiers, random forest (RF), K-nearest neighbor (KNN), and multilayer perceptron (MLP), were used to evaluate the performance. The proposed framework was evaluated on the real classroom EEG dataset, involving EEG recordings featuring different teaching blocks: reading, discussion, lecture, and video. Results: The findings revealed that statistical features are the most sensitive feature metric in distinguishing learning patterns from EEG. The statistical features and RF classifier method tested in this study achieved an overall best average accuracy of 78.45% when estimated by fivefold cross-validation. Conclusions: Our results suggest that EEG time domain statistics have a substantial role and are more reliable for internal state classification. This study might be used to highlight the importance of using EEG signals in the education context, opening the path for educational automation research and development. Full article

Micro-expressions are very brief, involuntary facial expressions that reveal hidden emotions, lasting less than a second, while macro-expressions are more prolonged facial expressions that align with a person’s conscious emotions, typically lasting several seconds. Micro-expressions are difficult to detect in lengthy videos because they have tiny amplitudes, short durations, and frequently coexist alongside macro-expressions. Nevertheless, micro- and macro-expression analysis has sparked interest in researchers. Existing methods use optical flow features to capture the temporal differences. However, these optical flow features are limited to two successive images only. To address this limitation, this paper proposes LGNMNet-RF, which integrates a Lite General Network with MagFace CNN and a Random Forest classifier to predict micro-expression intervals. Our approach leverages Motion History Images (MHI) to capture temporal patterns across multiple frames, offering a more comprehensive representation of facial dynamics than optical flow-based methods, which are restricted to two successive frames. The novelty of our approach lies in the combination of MHI with MagFace CNN, which improves the discriminative power of facial micro-expression detection, and the use of a Random Forest classifier to enhance interval prediction accuracy. The evaluation results show that this method outperforms baseline techniques, achieving micro-expression F1-scores of 0.3019 on CAS(ME)² and 0.3604 on SAMM-LV. The results of our experiment indicate that MHI offers a viable alternative to optical flow-based methods for micro-expression detection. Full article

Long-range networks, renowned for their long-range, low-power communication capabilities, form the backbone of many Internet of Things systems, enabling efficient and reliable data transmission. However, detecting tampered frequency signals poses a considerable challenge due to the vulnerability of LoRa devices to radio-frequency interference and signal manipulation, which can undermine both data integrity and security. This paper presents an innovative method for identifying tampered radio frequency transmissions by employing five sophisticated anomaly detection algorithms—Local Outlier Factor, Isolation Forest, Variational Autoencoder, traditional Autoencoder, and Principal Component Analysis within the framework of a LoRa-based Internet of Things network structure. The novelty of this work lies in applying image-based tampered frequency techniques with these algorithms, offering a new perspective on securing LoRa transmissions. We generated a dataset of over 26,000 images derived from real-world experiments with both normal and manipulated frequency signals by splitting video recordings of LoRa transmissions into frames to thoroughly assess the performance of each algorithm. Our results demonstrate that Local Outlier Factor achieved the highest accuracy of 97.78%, followed by Variational Autoencoder, traditional Autoencoder and Principal Component Analysis at 97.27%, and Isolation Forest at 84.49%. These findings highlight the effectiveness of these methods in detecting tampered frequencies, underscoring their potential for enhancing the reliability and security of LoRa networks. Full article

YouTube is a popular social media platform in the contemporary digital landscape. The primary focus of this study is to explore the underlying sentiment in user comments about food-related videos on YouTube, specifically within two pivotal food categories: plant-based and hedonic product. We labeled comments using sentiment lexicons such as TextBlob, VADER, and Google’s Sentiment Analysis (GSA) engine. Comment sentiment was classified using advanced Machine-Learning (ML) algorithms, namely Support Vector Machines (SVM), Multinomial Naive Bayes, Random Forest, Logistic Regression, and XGBoost. The evaluation of these models encompassed key macro average metrics, including accuracy, precision, recall, and F1 score. The results from GSA showed a high accuracy level, with SVM achieving 93% accuracy in the plant-based dataset and 96% in the hedonic dataset. In addition to sentiment analysis, we delved into user interactions within the two datasets, measuring crucial metrics, such as views, likes, comments, and engagement rate. The findings illuminate significantly higher levels of views, likes, and comments in the hedonic food dataset, but the plant-based dataset maintains a superior overall engagement rate. Full article

Recently, the research community has taken great interest in human activity recognition (HAR) due to its wide range of applications in different fields of life, including medicine, security, and gaming. The use of sensory data for HAR systems is most common because the sensory data are collected from a person’s wearable device sensors, thus overcoming the privacy issues being faced in data collection through video cameras. Numerous systems have been proposed to recognize some common activities of daily living (ADLs) using different machine learning, image processing, and deep learning techniques. However, the existing techniques are computationally expensive, limited to recognizing short-term activities, or require large datasets for training purposes. Since an ADL is made up of a sequence of smaller actions, recognizing them directly from raw sensory data is challenging. In this paper, we present a computationally efficient two-level hierarchical framework for recognizing long-term (composite) activities, which does not require a very large dataset for training purposes. First, the short-term (atomic) activities are recognized from raw sensory data, and the probabilistic atomic score of each atomic activity is calculated relative to the composite activities. In the second step, the optimal features are selected based on atomic scores for each composite activity and passed to the two classification algorithms: random forest (RF) and support vector machine (SVM) due to their well-documented effectiveness for human activity recognition. The proposed method was evaluated on the publicly available CogAge dataset that contains 890 instances of 7 composite and 9700 instances of 61 atomic activities. The data were collected from eight sensors of three wearable devices: a smartphone, a smartwatch, and smart glasses. The proposed method achieved the accuracy of 96.61% and 94.1% by random forest and SVM classifiers, respectively, which shows a remarkable increase in the classification accuracy of existing HAR systems for this dataset. Full article

Forest landscape space is the basic unit of forest landscape resources. Healthy forest landscape resources can not only improve the sustainable cycle of forest ecological service function, but also have a positive impact on human health and well-being. Evidence supports the view that the forest environment is beneficial to people’s health, and further discussion of the dose response between environmental attributes and physical and mental recovery has been widely carried out by scholars. As an important component of environmental attributes, it is necessary to clarify the relationship between vegetation distribution and users’ health in order to better plan, design, and utilize forest environmental resources. This study mainly used the virtual immersive forest environment video in VR, and used the difference test in SPSS 23.0 to clarify whether the distribution of vegetation in the forest environment will affect the physiological and psychological recovery effect of users. The main results are as follows: (1) Experiencing the forest environment can promote users’ physiological and psychological health, and its recovery effect is significantly better than the indoor environment (p < 0.05). (2) The distribution of vegetation in the forest environment will affect users’ physiological and psychological recovery effect. Among them, in the cluster and randomly distributed forest environments, the relaxation and concentration of users can be improved mainly by alleviating their negative emotions. In the evenly distributed forest environment, users mainly achieve the purpose of relaxation by improving their vitality and positive emotions. These results show that the distribution of vegetation is one of the factors for the restoration of forest environment. In the future design and management of the forest environment, the health and well-being of users can be effectively enhanced by getting involved with the vegetation distribution in the site, aiming to provide a scientific basis for the promotion of the rehabilitation function of forest landscape space and its sustainable utilization, thus promoting the sustainable development of forest resources and improving people’s quality of life. Full article

The proliferation of fake news across multiple modalities has emerged as a critical challenge in the modern information landscape, necessitating advanced detection methods. This study proposes a comprehensive framework for fake news detection integrating text, images, and videos using machine learning and deep learning techniques. The research employs a dual-phased methodology, first analyzing textual data using various classifiers, then developing a multimodal approach combining BERT for text analysis and a modified CNN for visual data. Experiments on the ISOT fake news dataset and MediaEval 2016 image verification corpus demonstrate the effectiveness of the proposed models. For textual data, the Random Forest classifier achieved 99% accuracy, outperforming other algorithms. The multimodal approach showed superior performance compared to baseline models, with a 3.1% accuracy improvement over existing multimodal techniques. This research contributes to the ongoing efforts to combat misinformation by providing a robust, adaptable framework for detecting fake news across different media formats, addressing the complexities of modern information dissemination and manipulation. Full article

Contacting forests in different ways and conducting public perception evaluations of forests are important ways to evaluate forest construction. In order to explore the differences between on-site and manual post-collection indoor evaluations in forest landscape surveys, we combined subjective evaluation and objective indicator monitoring (eye movement characteristics, physiological indicators) based on different forest observation scales. We compared and analyzed the suitability of the following four visual approaches: on-site observation, manual collection, followed by indoor viewing normal photos (NP), videos (VD), and virtual reality panoramas (VR), in terms of public preference, perception, and psychological emotion. The results showed the following: (1) Compared with the on-site evaluation, the three indoor visual approaches (NP, VD, and VR) showed no significant difference in “landscape beauty” and “spatial perception”. VD also showed no significant difference in “landscape perception”, “seeing”, and “plant color preference” and had the strongest substitution for site evaluation. (2) With the exception of small-scale landscapes, in which on-site evaluation showed no substitutability, for the rest of the landscape scales, each of the three indoor visual approaches showed substitutability for on-site evaluation to varying degrees. (3) When conducting physiological and psychological surveys, watching videos and VR are more ideal. In terms of eye tracking, VR is closest to on-site observation. Practice shows that video was closer to on-site observation in most landscape preferences and perceptions. VR was suitable for presenting public visual behavioral characteristics, and NP showed some advantages in landscape beauty and spatial perceptions. The findings of the study can provide a scientific basis for the selection of visual approaches in future landscape evaluation. Full article

Background and Objectives: In recent years, there has been a significant increase in interest in the health benefits of contact with nature. The theoretical and practical aspects of this issue are constantly being investigated. It is worth noting, however, that there is a large group of people for whom the only available form of contact with nature can only be through images (the view outside the window, photos and films about nature), recorded sounds of nature or descriptions of nature. Research indicating how much exposure to nature in the dimension of virtual reality achieves improvements in well-being, mood and vitality is therefore urgently needed. Material and Methods: The main goal of the experiment was to examine whether watching a 20-min 2D video of forest environment or reading a textbook on forest knowledge for 20 min would bring any psychological benefits. The order of both exposures was intentionally changed (reversed) for every second participant in this study to reduce the order effect. A group of 16 volunteers, students of Warsaw University of Life Sciences, took part in the experiment. The psychological tests before and after each of the two parts of the experiment (viewing a picture with sound and reading a book) were established using five questionnaires: Profile of Mood State (POMS); Positive and Negative Affect Scale (PANAS); Restorative Outcome Scale (ROS); Subjective Vitality Scale (SVS) and State-Trait Anxiety Inventory (STAI). Results: As a result of the analyses, a 20-min viewing of a 2D video of a forest with natural sounds of nature was shown to have a positive effect on the psychological relaxation of the subjects in the form of an increase in restorativeness and vitality in the participants of the experiment, as well as a greater decrease in negative feelings, tension and anger than when reading a forest-themed book. Watching a video of a landscape can reduce tension and anger levels significantly, which can be an important guideline in relation to the interior design of public spaces and the protection of employees from the adverse effects of psychosocial working conditions, as well as the desire to stabilize anger and maintain emotional stability in everyday life. Full article

Geoffroy’s spider monkeys, an endangered, fast-moving arboreal primate species with a large home range and a high degree of fission–fusion dynamics, are challenging to survey in their natural habitats. Our objective was to evaluate how different flight parameters affect the detectability of spider monkeys in videos recorded by a drone equipped with a thermal infrared camera and examine the level of agreement between coders. We used generalized linear mixed models to evaluate the impact of flight speed (2, 4, 6 m/s), flight height (40, 50 m above ground level), and camera angle (−45°, −90°) on spider monkey counts in a closed-canopy forest in the Yucatan Peninsula, Mexico. Our results indicate that none of the three flight parameters affected the number of detected spider monkeys. Agreement between coders was “substantial” (Fleiss’ kappa coefficient = 0.61–0.80) in most cases for high thermal-contrast zones. Our study contributes to the development of standardized flight protocols, which are essential to obtain accurate data on the presence and abundance of wild populations. Based on our results, we recommend performing drone surveys for spider monkeys and other medium-sized arboreal mammals with a small commercial drone at a 4 m/s speed, 15 m above canopy height, and with a −90° camera angle. However, these recommendations may vary depending on the size and noise level produced by the drone model. Full article