Activity Classification Research Articles

A Critical Analysis of Falsification as Fraud

This paper critically evaluates the classification of research-related fraudulent activities, with an emphasis on the specific misconduct falsification. The analysis begins by interrogating the assumption that all acts of fraud in research are intentional, suggesting that some instances may inadvertently arise during the course of scholarly activities. Misconducts like fabrication and falsification are categorized as fraudulent primarily due to their generation during research activities and their direct contribution to the distortion of scientific knowledge. Plagiarism, while deceptive, does not necessarily originate from the research process nor lead directly to such distortion, and therefore is not classified as de facto fraud. The paper proposes that the definition of falsification – as established by the PHS – requires refinement to prevent wrongful allegations and convictions, enhance transparency, and offer clearer guidelines. This nuanced understanding is vital for safeguarding the credibility of the research process and protecting scientists from unfounded career-damaging accusations. Ultimately, this paper advocates for a clearer definition of falsification to protect the integrity of scientific research and prevent the miscarriage of justice.

Machine Learned Classification of Ligand Intrinsic Activities at Human μ-Opioid Receptor.

Opioids are small-molecule agonists of μ-opioid receptor (μOR), while reversal agents such as naloxone are antagonists of μOR. Here, we developed machine learning (ML) models to classify the intrinsic activities of ligands at the human μOR based on the SMILES strings and two-dimensional molecular descriptors. We first manually curated a database of 983 small molecules with measured Emax values at the human μOR. Analysis of the chemical space allowed identification of dominant scaffolds and structurally similar agonists and antagonists. Decision tree models and directed message passing neural networks (MPNNs) were then trained to classify agonistic and antagonistic ligands. The hold-out test AUCs (areas under the receiver operator curves) of the extra-tree (ET) and MPNN models are 91.5 ± 3.9% and 91.8 ± 4.4%, respectively. To overcome the challenge of a small data set, a student-teacher learning method called tritraining with disagreement was tested using an unlabeled data set comprised of 15,816 ligands of human, mouse, and rat μOR, κOR, and δOR. We found that the tritraining scheme was able to increase the hold-out AUC of MPNN models to as high as 95.7%. Our work demonstrates the feasibility of developing ML models to accurately predict the intrinsic activities of μOR ligands, even with limited data. We envisage potential applications of these models in evaluating uncharacterized substances for public safety risks and discovering new therapeutic agents to counteract opioid overdoses.

Imidazolium-based ionic liquids disrupt saccharomyces cerevisiae cell membrane integrity.

Ionic liquids (ILs) are interesting chemical compounds that have a wide range of industrial and scientific applications. They have extraordinary properties, such as the tunability of many of their physical properties and, accordingly, their activities; and the ease of synthesis methods. Hence, they became important building blocks in catalysis, extraction, electrochemistry, analytics, biotechnology, etc. This study determined antifungal activities of various imidazolium-based ionic liquids against yeast Saccharomyces cerevisiae via minimum inhibitory concentration (MIC) estimation method. Increasing the length of the alkyl group attached to the imidazolium cation, enhanced the antifungal activity of the ILs, as well as their ability of the disruption of the cell membrane integrity. FTIR studies performed on the S. cerevisiae cells treated with the ILs revealed alterations in the biochemical composition of these cells. Interestingly, the alterations in fatty acid content occurred in parallel with the increase in the activity of the molecules upon the increase in the length of the attached alkyl group. This trend was confirmed by statistical analysis and machine learning methodology. The classification of antifungal activities based on FTIR spectra of S. cerevisiae cells yielded a prediction accuracy of 83%, indicating the pharmacy and medicine industries could benefit from machine learning methodology. Furthermore, synthesized ionic compounds exhibit significant potential for pharmaceutical and medical applications.

A Consistent, Exhaustive Taxonomy of Inventive Activities

A classification of scientific and technological activities is put forth here, based on taxonomy of Inventive Activities' features. In the end, a description of Research & Innovation ensues that is consistent and more complete than current ones. Then, the gauging of R & I activities may result more meaningful and precise.

Associations between natural blue and green space and preschool children's movement behaviours

Abstract Natural outdoor environments provide important settings for children to engage in physical activity. It is unclear if these relationships also exist in preschool aged children. We examined associations between amount and type of neighbourhood vegetation and blue space, proximity to the beach and preschooler's device‐measured movement behaviours. Accelerometer data from 1081 preschool children were processed into physical activity and sedentary behaviours using a machine learned random forest physical activity classification model specifically developed for children under five. High‐resolution aerial imagery data and Geographic Information Systems were used to identify total percentage of neighbourhood vegetation and vegetation components (grass, shrubs and trees) and presence and total percentage of blue space (ocean, riverways and lakes and swamps) for 500, 1600 and 5000 m service areas around children's residences. Distance to the closest beach, patrolled beach, and dog beach were also calculated. Amount of neighbourhood vegetation was inversely associated with boys sedentary time in the 500 m (β = −0.91 min/day, p = 0.006, 95% CI [−1.55, −0.33]) and 1600 m (β = −1.30 min/day, p = 0.001, 95% CI [−2.08, −0.53]) service area, and positively associated with walking time in the 1600 m (β = 0.12 min/day, p = 0.045, 95% CI [0.02, 0.22]) service area. The presence of local riverways was positively associated with girls walking time in the 1600 m (β = 2.34 min/day, p = 0.009, 95% CI [0.59, 4.09]), and 5000 m (β = 1.67 min/day, p = 0.019, 95% CI [0.27, 3.06]) buffer. Distance to dog beach was positively associated with boys sedentary behaviours. Presence of lake and swamps were negatively associated with boys walking, and presence of riverways was negatively associated with girls moderate‐to‐vigorous activities and games and boys running in the 5000 m service area. These findings suggest higher amounts of neighbourhood vegetation and certain types of blue space such as riverways and dog beaches could facilitate positive movement behaviours in young children. Our findings that natural outdoor environments are associated with preschool children's movement behaviours add to evidence which could contribute to policy implications for urban planning and the provision and protection of natural environments within cities. Read the free Plain Language Summary for this article on the Journal blog.

Gait Activity Classification With Convolutional Neural Network Using Lower Limb Angle Measurement From Inertial Sensors

Gait Activity Classification With Convolutional Neural Network Using Lower Limb Angle Measurement From Inertial Sensors

VALUATION OF INTANGIBLE ASSETS IN THE MANUFACTURING INDUSTRY

From an economic and psychological point of view, building and maintaining a good reputation is essential for any branch of economic activity. This work evaluated goodwill using the weighted average return on assets method, WARA. This is according to the average company in the manufacturing industry in the Czech Republic between 2016-2020. The average enterprise was created by filtering enterprises determined according to the classification of economic activities of CZ NACE from section C. These data were transformed into a single entity valued on an accounting basis, and the value of its goodwill was determined. This value was determined from an accounting point of view as the difference between the revenue value of the business plant and the asset value of the business plant. The benefit is the value of goodwill expenses in connection with strengthening the competitive advantage in the market. The limitation of this work was determining which companies should filter out from the list of accounting data completely and which to keep. Further research could examine companies in individual subgroups in the manufacturing industry and other sections of the classification of economic activities.

MediaPipe with GNN for Human Activity Recognition

Human interaction and computer vision converge in the realm of Human Activity Recognition (HAR), which is a research field dedicated to the creation of automated systems capable of observing and categorizing human activities. This domain closely aligns with machine learning, involving the development of algorithms and models adept at learning to recognize and classify patterns within data. HAR typically unfolds in two pivotal phases: data acquisition and processing, followed by activity classification. In the initial phase of data acquisition and processing, information is gathered from various sensors or video sources, such as accelerometers, smartphones, or smartwatches. Subsequently, the collected data undergo preprocessing to extract relevant features. The subsequent phase, activity classification, employs machine learning algorithms to categorize these extracted features into distinct activity types, ranging from walking and running to sitting. This paper introduces an innovative approach grounded on these two fundamental phases. For the first phase, we leverage the MediaPipe algorithm to discern human articulations. Once these poses are detected, we contribute by extracting the coordinates of each articulation. These coordinates are then transformed into graphs, where nodes signify the articulation coordinates and edges represent the connections between them. In the second phase, we enhance existing methodologies by incorporating a diverse set of machine learning models. Notably, the utilization of Graph Neural Networks (GNNs) which stands out as a significant advancement. This choice proves instrumental in effectively learning and representing complex spatial and temporal patterns, surpassing the limi-tations of conventional machine learning algorithms. The developed system undergoes evaluation on the KTH and UCF50 datasets, demonstrating state-of-the-art performance in HAR.

Distance Education and the Use of Artificial Intelligence Through Agents as an Aggregate Factor in Intelligent Systems

It is proposed to investigate the technological changes that drive Distance Education (EaD) through Artificial Intelligence (AI). It can become a powerful tool, expanding possibilities to have more assertive and effective results in the process of evaluating the knowledge obtained by the student in pedagogical content taught by the teacher. The agents are the resources to the AI technique, working in an Intelligent Tutor System (STI), which allow for flexibility in part of this evaluation process, as their characteristics of responding to inferences from the environment, enable them to display future results, based on statistics, making them autonomous and intelligent. This work proposes to present a project or its insertion of AI agents in the STI, specifically to the MOODLE platform, which allows for a better way of learning in accordance with the needs of students, respecting their level of knowledge. Flexibility that will occur through the classification of activities, to be performed by students in a list of exercises, with difficulty levels in easy, medium and difficult levels. The MOODLE stores and makes available to the student all the material prepared for the teacher's class and, with the incorporation of this AI technique, the process will be flexible when measuring each student respecting their previous knowledge. Respect for their education profile by experiencing the limits of the cognitive aspect, their deficiencies in knowledge of the content(s) not assimilated in high school or in curricular unit(s) in the undergraduate course, encouraging to reach levels of overcoming and acquiring learning.

The Effect of Caffeine on Movement-Related Cortical Potential Morphology and Detection.

Movement-related cortical potential (MRCP) is observed in EEG recordings prior to a voluntary movement. It has been used for e.g., quantifying motor learning and for brain-computer interfacing (BCIs). The MRCP amplitude is affected by various factors, but the effect of caffeine is underexplored. The aim of this study was to investigate if a cup of coffee with 85 mg caffeine modulated the MRCP amplitude and the classification of MRCPs versus idle activity, which estimates BCI performance. Twenty-six healthy participants performed 2 × 100 ankle dorsiflexion separated by a 10-min break before a cup of coffee was consumed, followed by another 100 movements. EEG was recorded during the movements and divided into epochs, which were averaged to extract three average MRCPs that were compared. Also, idle activity epochs were extracted. Features were extracted from the epochs and classified using random forest analysis. The MRCP amplitude did not change after consuming caffeine. There was a slight increase of two percentage points in the classification accuracy after consuming caffeine. In conclusion, a cup of coffee with 85 mg caffeine does not affect the MRCP amplitude, and improves MRCP-based BCI performance slightly. The findings suggest that drinking coffee is only a minor confounder in MRCP-related studies.

Machine Learned Classification of Ligand Intrinsic Activities at Human μ-Opioid Receptor.

Opioids are small-molecule agonists of μ-opioid receptor (μOR), while reversal agents such as naloxone are antagonists of μOR. Here we developed machine learning (ML) models to classify the intrinsic activities of ligands at the human μOR based on the SMILE strings and two-dimensional molecular descriptors. We first manually curated a database of 983 small molecules with measured E max values at the human μOR. Analysis of the chemical space allowed identification of dominant scaffolds and structurally similar agonists and antagonists. Decision tree models and directed message passing neural networks (MPNNs) were then trained to classify agonistic and antagonistic ligands. The hold-out test AUCs (areas under the receiver operator curves) of the extra-tree (ET) and MPNN models are 91.5±3.9% and 91.8± 4.4%, respectively. To overcome the challenge of small dataset, a student-teacher learning method called tri-training with disagreement was tested using an unlabeled dataset comprised of 15,816 ligands of human, mouse, or rat μOR, κOR, or δOR. We found that the tri-training scheme was able to increase the hold-out AUC of MPNN to as high as 95.7%. Our work demonstrates the feasibility of developing ML models to accurately predict the intrinsic activities of μOR ligands, even with limited data. We envisage potential applications of these models in evaluating uncharacterized substances for public safety risks and discovering new therapeutic agents to counteract opioid overdoses.

Juxtacellular recordings from identified neurons in the mouse locus coeruleus.

The locus coeruleus (LC) is the primary source of noradrenergic transmission in the mammalian central nervous system. This small pontine nucleus consists of a densely packed nuclear core-which contains the highest density of noradrenergic neurons-embedded within a heterogeneous surround of non-noradrenergic cells. This local heterogeneity, together with the small size of the LC, has made it particularly difficult to infer noradrenergic cell identity based on extracellular sampling of in vivo spiking activity. Moreover, the relatively high cell density, background activity and synchronicity of LC neurons have made spike identification and unit isolation notoriously challenging. In this study, we aimed at bridging these gaps by performing juxtacellular recordings from single identified neurons within the mouse LC complex. We found that noradrenergic neurons (identified by tyrosine hydroxylase, TH, expression; TH-positive) and intermingled putatively non-noradrenergic (TH-negative) cells displayed similar morphologies and responded to foot shock stimuli with excitatory responses; however, on average, TH-positive neurons exhibited more prominent foot shock responses and post-activation firing suppression. The two cell classes also displayed different spontaneous firing rates, spike waveforms and temporal spiking properties. A logistic regression classifier trained on spontaneous electrophysiological features could separate the two cell classes with 76% accuracy. Altogether, our results reveal in vivo electrophysiological correlates of TH-positive neurons, which can be useful for refining current approaches for the classification of LC unit activity.

Application of Human Activity Recognition in Supermarkets with Human Pose Estimation

Human Activity Recognition is the ability to interpret human body movements or movements through sensors and to determine human activities or actions. Most everyday human tasks can be simplified or automated if they can be identified through an activity management system. The introduction of human activities in supermarkets has many benefits in its development, such as Just Walk Out technologies such as Amazon Go and the prevention of theft of goods. Proposed research with the theme of human activity recognition that has a focus on supermarkets. The methods that will be used in this research are Human Pose Estimation and Random Forest Classifier with data collected from the internet. The designed application will first detect skeletons with Blazepose from human objects, which will then be classified by the Random Forest Classifier. Activities that can be classified by the designed application are standing, walking, and fetching. The output of the application is a classification of activities carried out in real-time with the camera. The test results on the training data get an accuracy value of 100%, precision of 100%, recall of 100%, and F1-Score of 100%. Using the test data produces a confusion matrix which shows that the model being trained has an accuracy value of 100%, precision of 100%, recall of 100%, and an F1-Score of 100%.

The effect of social activities on the alienation and family resilience of Chinese caregivers for children with autism: a latent class analysis.

Caregivers of children with autism spectrum disorder (ASD) in China often experience alienation due to societal stigma. While this alienation detrimentally impacts their mental well-being, family resilience serves as a protective factor. Previous research has predominantly examined the social support derived from social activities but has neglected to delve into the specific patterns of these activities. The primary objective of this study was twofold: firstly, to gain insights into the various social activities engaged in by caregivers of children with autism in China, and secondly, to ascertain the influence of these social activities on alienation and family resilience. Between June and August 2023, a cross-sectional survey was carried out across multiple cities in Jilin Province, aiming to gather data from a total of 205 Chinese caregivers of children with autism. Data collection was conducted through the utilization of a structured questionnaire. The assessment of social activity involved the completion of 12 questionnaires, while alienation was evaluated using the Generalized Alienation Scale (GSAS), and family resilience was gauged through the Chinese version of the Family Resilience Scale (FaRE). The classification of social activities was conducted through latent class analysis (LCA), while the impact of these social activities on alienation and family resilience was examined using linear regression analysis. The findings revealed that social activities can be categorized into five types (Low, Self-Recreation, Communication, Web Surfing, High). Communication social activities were found to reduce family resilience(β=.332, p<0.01), while high social activities were associated with reduced alienation(β=-.349, p<0.05) and increased family resilience(β=.417, p<0.01). Supporting these particular types of social activities has the potential to reduce alienation and bolster family resilience among caregivers for children with autism in China.

Revolutionizing healthcare: IoMT-enabled digital enhancement via multimodal ADL data fusion

The present research develops a framework to refine the classification of an individual’s activities and recognize wellness associated with their routine. The framework improves the accuracy of the classification of routine activities of a person, the activation time data of sensors fixed on objects linked with the routine activities of the person, and the aptness of an incessant activity pattern with the routine activities. The existing techniques need continuous monitoring and are non-adaptive to a person’s persistent habitual variations or individualities. The research involves applying Internet of Medical Things (IoMT)-based sensor information fusion to the novel multimodel data analytics to develop Activities of Daily Living (ADL) pattern, behavioral pattern generation and anomaly recognition. The novel multimodel data analytics approach is named AiCareLiving. AicareLiving is an IoMT and artificial intelligence (AI) enabled approach. The research work describes activity data using an individual’s activities within a specified area before evaluating the activity data to detect the existence of an anomaly by identifying the deviation of the activity data from the activity profile, which indicates the anticipated behavior and activity of the person. This wellness information would be shared to the caregivers, related healthcare professionals, care providers and municipalities through the secured healthcare information exchange protocol and IoMT. AiCareLiving framework aims to least false positive in terms of anomaly detection and forecasting; the high precision is close to the confidence level of 95%.

Deep learning and quantization for accurate and efficient multi-target radar inference of moving targets

Real-time, radar-based human activity and target classification is useful for wide-area ground surveillance. However, the feasibility of deploying deep learning (DL) models in radar-based systems with limited computational resources remains unexplored. This paper investigated the effect of quantization on model throughput and accuracy for deployment in radar systems. A seven-layer residual network was proposed to classify ground-moving targets and achieved a test accuracy of 87.72%. The model was then quantized to 16-bit and 8-bit precision, resulting in a 3.8 times speedup in inference throughput, with less than a 0.4% drop in test and validation accuracy. The results showed that quantization can improve inference throughput with a negligible decrease in target classification accuracy. The increase in throughput and reduction in computational expense that comes with quantization promotes the feasibility of the deployment of DL models in systems with limited computational resources. The findings of this paper hold significant promise for the successful use of quantized models in modern radar systems, while adhering to stringent size, weight and power consumption constraints.

Application of the time-distributed layer in the controller of memory-augmented neural networks to classify brain activities into motor imagery and motor execution

Brain-Computer Interface (BCI) systems create a bridge between the human brain and the outside world, potentially rendering traditional methods of information transmission obsolete in the not-so-distant future. One of the key research areas in BCI is the classification of brain activity in electroencephalographic (EEG) data. On the other hand, new memory-augmented neural networks, such as the Neural Turing Machine (NTM) and the Differentiable Neural Computer (DNC), have demonstrated their impressive abilities in solving complex tasks. Therefore, it is useful to evaluate the capability of memory-augmented neural networks to enhance the classification of brain activity within EEG signals. Previous methods have suffered from low accuracy and generalizability in classifying brain activities; primarily due to a lack of proper classification of Motor Imagery/Execution brain activities, an inability to extract valuable information at different time steps in time series data, and a failure to learn from longer dependencies. This article introduces TDMANN (Time-Distributed Memory Augmented Neural Network), a framework that leverages the principles of NTM and DNC for the binary classification of brain activities in EEG signals. The controller component of the memory-augmented neural network is enhanced with a time-distributed approach, which significantly improves the performance of the network in binary classification tasks involving motor imagery/execution brain activities by extracting valuable information at each time step. The benchmark datasets used in this study are EEGmmidb BCI2000 (Imagery/Execution), BCI IV 2B, and BCI IV 2A, all containing motor imagery/execution brain activity data in EEG format. The results demonstrate that the classification accuracy achieved by the proposed DNC@TDMANN method exhibits a maximum improvement of 23.03% compared to baseline research works. The NTM@TDMANN method also shows a maximum improvement accuracy of 22.5%.

Metabolic equivalents intensity thresholds for physical activity classification in older adults

BackgroundAlthough the metabolic equivalents (METs) system is a common procedure to quantify the intensity of physical activity in older adults, it remains unclear whether the conventional METs intensity thresholds (CTs) used for this purpose are appropriate in this population. Therefore, this study aimed (i) to derive overall and fitness-specific METs intensity thresholds in older adults ≥ 60 years old (OATs) expressed both in standard METs (VO2/3.5 mL O2·kg−1·min−1) and older adults METs60+ (VO2/2.7 mL O2·kg−1·min−1), and (ii) to compare them with the CTs.MethodsA total of 93 subjects were assessed for cardiorespiratory fitness. Graded exercise test protocols using indirect calorimetry were performed to calculate individual VO2max and categorize subjects as "very poor/fair" or "good/superior" fitness. Overall and fitness-specific OATs expressed in standard METs (OATsstandard) and METs60+ (OATs60+) were derived based on the %VO2max and the ventilatory thresholds (VTs) physical intensity categories.ResultsSignificantly higher VO2max, VO2 at VT1 and VO2 at VT2 (p < 0.001) were obtained in the "good/superior" subgroup compared to the "very poor/fair" fitness subgroup. Accordingly, OATs were approximately 69% higher in individuals with a "good/superior" fitness compared to those with a "very poor/fair" fitness. Furthermore, this study showed that OATsstandard were approximately 21–24% lower than OATs60+, and 10–22% higher OATs were observed when following the VTs intensity categories (heavy-intensity physical activity [HPA] and severe-intensity physical activity [SPA]) compared to the %VO2max categories (moderate-intensity physical activity [MPA] and vigorous-intensity physical activity [VPA]). When compared with the CTs, similar or higher OATsstandard and OATs60+ for MPA, and HPA were obtained compared to the conventional MPA threshold (3.0 METs). Conversely, for VPA and SPA, lower, similar, or higher OATs were obtained depending on the METs derivation approach (OATsstandard or OATs60+) or the intensity categories (VO2max or VTs), compared to the conventional VPA threshold (6.0 METs).ConclusionsNone of the derived OATs were concurrently similar to the CTs, suggesting that fitness-specific METs intensity thresholds adapted to the METs derivation approach should be used in older adults.Trial registrationFenotipAGING (Non-health-care intervention study), PRO-Training (NCT05619250).

Role of Standard Setting Organizations in the Indian Ict Sector: an Intellectual Property Law Analysis

Introduction: Standard-setting organizations (SSOs) are critical policy-making bodies that have a decisive bearing on technical sectors that are not just global, but also in Indian society. They form rules that become the reference point for stepping up the development and deployment of the tech. This study is designed to open the curtains and delve into SSOs' standard-setting process in the Indian ICT sector and assess the challenges that emerge. Objectives: The worldwide efficient methods employed by the global SSOs and contrast them with the Indian ones to spot correlations. Moreover, Indian SSOs' IPRs hidden under Indian patent laws will be also looked at. In the end, apart from the recommendations for upgrading and aligning the policies regarding the standardization of ICT equipment in India, we will also provide some suggestions. Theoretical Framework: The sequel of this process will be the exploration of IP laws such as patents in India focused solely on patent licensing - the standardization practice carried out by patentees. Results and Discussion: Emphasize the standard-setting actions of Indian SSOs by highlighting the problems encountered. A comparative analysis of substantive cooperation between inter-planetary and Indian anti-space security organizations will be carried out. Lectures covering how Indian SSOs match the Indian Patent Act and Rules will accordingly be given. The implications of the high effect of ICT standardization in India will be suggested. Considerable facts will be culled from doctrinal law, and each of the methods used in the licensing of education institutions will be examined. Research Implications: Improving standard-setting processes by key Indian SSOs such as BIS(Bureau of Indian Standards), ISRO (Indian Space Research Organisation) and ISIF (Indian Standards and Industrial Classification of All Economic Activities) Moreover, the Indian IP legal system and licensing structure will be proposed to ensure integration barriers are addressed and the standardization of the ICT is improved.

Enhance micro-Doppler signatures-based human activity classification accuracy of FMCW radar using the threshold method

Nowadays, radar-based human activity classification is being widely adopted in healthcare systems due to its benefits in terms of personal privacy compliance, non-contact sensing, and being unaffected by weather conditions. This study proposes a threshold method in the pre-processing stage to improve human activity classification accuracy by determining the region of meaningful information (RMI) on the spectrogram. Initially, a mask function, which is created by a certain threshold value, is applied to the input spectrogram to highlight the RMI from the micro-Doppler (m-D) signatures. Only the highlighted RMI on the spectrogram is retained as input to the classifiers. Then, five Convolutional Neural Networks (CNNs) of varying complexity are employed to extract features, identify activities, and assess the effectiveness of the suggested approach. The experimental results demonstrate that the suggested approach has enhanced classification accuracy by up to 11% when compared to the original unprocessed dataset.