Lab Dataset Research Articles

HRMF-DRP: A next-generation solution for overcoming provisioning challenges in cloud environments

The cloud computing infrastructure is a distributed environment and the existing research works have some provisioning problems such as suboptimal resource utilization and high execution time. The Heterogeneity Resource Management Framework for Dynamic Resource Provisioning (HRMF-DRP) is proposed for focusing on task scheduling and workload management. This framework incorporates advanced algorithms for dataset preprocessing, task clustering, workload prediction, and dynamic resource provisioning. For data preprocessing, the real-world workload traces were captured from the Planet Lab dataset that are taken as input for the preprocessing stage. The data preprocessing is responsible for ensuring data quality and reliability by using different models like missing data handling, outlier detection and removal as well as standardization and normalization. In this paper, the tasks are grouped into clusters by utilizing Density-Based Spatial Clustering of Applications with Noise (DBSCAN) model and this model categorizes the data points into border points, core points and noise points based on their density. The temporal dependencies are captured for the workload prediction by using Long Short-Term Memory (LSTM) neural network model. A Gaussian Mixture Model (GMM) model is responsible for estimating the number of Virtual machines (VMs) present in the workload prediction process. The Self-Adaptive Genetic Algorithm (SAGA) is implemented for task mapping that adjusts the parameters to change workload patterns for contributing adaptability and robustness. The different experimental evaluations are conducted based on the task completion time, workload balance index, resource utilization efficiency and workload prediction accuracy. The proposed model achieved the workload prediction accuracy of 98.5%, cost of $89.6, execution time of 125ms, Task Completion Time (TCT) of 40ms, Workload Balance Index (WBI) of 0.96 and Resource Utilization Efficiency (RUE) of 0.93. The quantitative results collectively position HRMF-DRP as a practical and efficient solution, promising advancements in dynamic resource provisioning for cloud computing, particularly within the Infrastructure as a Service (IaaS) cloud model.

From the Lab to the Wild: Examining Generalizability of Video-based Mind Wandering Detection

AbstractStudent’s shift of attention away from a current learning task to task-unrelated thought, also called mind wandering, occurs about 30% of the time spent on education-related activities. Its frequent occurrence has a negative effect on learning outcomes across learning tasks. Automated detection of mind wandering might offer an opportunity to assess the attentional state continuously and non-intrusively over time and hence enable large-scale research on learning materials and responding to inattention with targeted interventions. To achieve this, an accessible detection approach that performs well for various systems and settings is required. In this work, we explore a new, generalizable approach to video-based mind wandering detection that can be transferred to naturalistic settings across learning tasks. Therefore, we leverage two datasets, consisting of facial videos during reading in the lab (N = 135) and lecture viewing in-the-wild (N = 15). When predicting mind wandering, deep neural networks (DNN) and long short-term memory networks (LSTMs) achieve F$$_{1}$$ 1 scores of 0.44 (AUC-PR = 0.40) and 0.459 (AUC-PR = 0.39), above chance level, with latent features based on transfer-learning on the lab data. When exploring generalizability by training on the lab dataset and predicting on the in-the-wild dataset, BiLSTMs on latent features perform comparably to the state-of-the-art with an F$$_{1}$$ 1 score of 0.352 (AUC-PR = 0.26). Moreover, we investigate the fairness of predictive models across gender and show based on post-hoc explainability methods that employed latent features mainly encode information on eye and mouth areas. We discuss the benefits of generalizability and possible applications.

AI-based model for automatic identification of multiple sclerosis based on enhanced sea-horse optimizer and MRI scans

This study aims to develop an AI-enhanced methodology for the expedited and accurate diagnosis of Multiple Sclerosis (MS), a chronic disease affecting the central nervous system leading to progressive impairment. Traditional diagnostic methods are slow and require substantial expertise, underscoring the need for innovative solutions. Our approach involves two phases: initially, extracting features from brain MRI images using first-order histograms, the gray level co-occurrence matrix, and local binary patterns. A unique feature selection technique combining the Sine Cosine Algorithm with the Sea-horse Optimizer is then employed to identify the most significant features. Utilizing the eHealth lab dataset, which includes images from 38 MS patients (mean age 34.1 ± 10.5 years; 17 males, 21 females) and matched healthy controls, our model achieved a remarkable 97.97% detection accuracy using the k-nearest neighbors classifier. Further validation on a larger dataset containing 262 MS cases (199 females, 63 males; mean age 31.26 ± 10.34 years) and 163 healthy individuals (109 females, 54 males; mean age 32.35 ± 10.30 years) demonstrated a 92.94% accuracy for FLAIR images and 91.25% for T2-weighted images with the Random Forest classifier, outperforming existing MS detection methods. These results highlight the potential of the proposed technique as a clinical decision-making tool for the early identification and management of MS.

Optimizing Energy Resources in WSNs: ARIMA Feature Selection Meets Adaptive Reinforcement Learning

ABSTRACT Efficient energy management in WSNs is pivotal for prolonged network lifetime and sustained performance. This research introduces a novel approach to energy optimization through the integration of an ARIMA-driven feature selection process and an Actor-Critic Reinforcement Learning model. The Intel Lab dataset, encompassing data from 54 nodes distributed over a month, serves as the basis for experimentation. In the proposed methodology, the experimental setup ensures the validity of the study, leveraging the realism of the Intel Lab dataset. The data collection process captures the intricacies of WSN dynamics, with temperature records collected from strategically positioned nodes. The ARIMA-driven feature selection method refines the dataset, capturing temporal dependencies critical for energy prediction. The Actor-Critic model, a hybrid of policy and value-based reinforcement learning, dynamically adapts energy allocation strategies based on learned policies and offers a dynamic solution to the challenges posed by WSNs’ ever-changing environments. Comparative analysis with methods reveals lower energy consumption of 0.32 mJ, an extended network lifetime of 1501 rounds, and higher prediction accuracy of 98%. The study’s implications extend beyond the specific algorithms, suggesting a shift toward adaptive learning models in WSNs. The findings open avenues for future research in the integration of machine learning models for sustainable and efficient WSN deployments, emphasizing the growing importance of dynamic adaptation in sensor networks. Moreover, limitations, such as simulation realism and computational complexity, are acknowledged, prompting avenues for future research.

Efficient LiDAR-Trajectory Affinity Model for Autonomous Vehicle Orchestration

Computation and memory resource management strategies are the backbone of continuous object tracking in intelligent vehicle orchestration. Multi-object tracking generates enormous measurements of targets and extended object positions using light detection and ranging (Lidar) sensors. Designing an adequate object-tracking system is a global challenge because of dynamic object detection and data association uncertainties during scene understanding. In this regard, we develop an intelligent multi-objective tracking (IMOT) system with a novel measurement model, called the box data association inflate (BDAI) model, to assess each target’s object state and trajectory without noise by using the Bayesian approach. The box object filter method filters ambiguous detection responses during data association. The theoretical proof of the box object filter is derived based on binomial expansion. Prognosticating a lower-dimension object than the original point object reduces the computational complexity of vehicle orchestration. Two datasets (NuScenes dataset and our lab dataset) are considered during the simulations, and our approach measures the kinematic states adequately with reduced computation complexity compared to state-of-the-art methods. The simulation outcomes show that our proposed method is effective and works well to detect and track objects. The NuScenes dataset contains 28130 samples for training, 6019 examples for validation and 6008 samples for testing. IMOT achieves 58.09% tracking accuracy and 71% mAP with 5 ms pre-processing time. The Jetson Xavier NX consumes 49.63% GPU and 9.37% average power and exhibits 25.32 ms latency compared to other approaches. Our system trains a single pair frame in 169.71 ms with affinity estimation time of 12.19 ms, track association time of 0.19 ms and mATE of 0.245 compared to state-of-the-art approaches

Acoustic and visual geometry descriptor for multi-modal emotion recognition fromvideos

<span>Recognizing human emotions simultaneously from multiple data modalities (e.g., face, and speech) has drawn significant research interest, and numerous research contributions have been investigated in the affective computing community. However, most methods concentrate less on facial alignment and keyframe selection for audio-visual input. Hence, this paper proposed a new audio-visual descriptor, mainly concentrating on describing the emotion through only a few frames. For this purpose, we proposed a new self-similarity distance matrix (SSDM), which computes the spatial, and temporal distances through landmark points on the facial image. The audio signal is described through an asset of composite features, including statistical features, spectral features, formant frequencies, and energies. A support vector machine (SVM) algorithm is employed to classify both models, and the final results are fused to predict the emotion. Surrey audio-visual expressed emotion (SAVEE) and Ryerson multimedia research lab (RML) datasets are utilized for experimental validation, and the proposed method has shown significant improvement from the state of art methods.</span>

What can entropy metrics tell us about the characteristics of ocular fixation trajectories?

In this study, we provide a detailed analysis of entropy measures calculated for fixation eye movement trajectories from the three different datasets. We employed six key metrics (Fuzzy, Increment, Sample, Gridded Distribution, Phase, and Spectral Entropies). We calculate these six metrics on three sets of fixations: (1) fixations from the GazeCom dataset, (2) fixations from what we refer to as the "Lund" dataset, and (3) fixations from our own research laboratory ("OK Lab" dataset). For each entropy measure, for each dataset, we closely examined the 36 fixations with the highest entropy and the 36 fixations with the lowest entropy. From this, it was clear that the nature of the information from our entropy metrics depended on which dataset was evaluated. These entropy metrics found various types of misclassified fixations in the GazeCom dataset. Two entropy metrics also detected fixation with substantial linear drift. For the Lund dataset, the only finding was that low spectral entropy was associated with what we call "bumpy" fixations. These are fixations with low-frequency oscillations. For the OK Lab dataset, three entropies found fixations with high-frequency noise which probably represent ocular microtremor. In this dataset, one entropy found fixations with linear drift. The between-dataset results are discussed in terms of the number of fixations in each dataset, the different eye movement stimuli employed, and the method of eye movement classification.

Prediction of the effluent chemical oxygen demand and volatile fatty acids for anaerobic treatment based on different feature selections machine-learning methods from lab-scale to pilot-scale

The effluent chemical oxygen demand (COD) and volatile fatty acids (VFA) are important indicators for measuring wastewater anaerobic treatment systems. Through lab and pilot experiments on the anaerobic treatment process of high-salt wastewater, combined with different prediction requirements, the feature variables are classified. The effluent-COD and VFA prediction models of five different Machine-learning methods (i.e., back propagation neural network (BPNN), Genetic algorithm optimizes BPNN(GA-BP), support vector machine (SVM), Least squares support vector machine (LSSVM), and random forest (RF)) were established. The modeling results on different dataset (i.e., lab dataset, pilot dataset and mixed dataset) showed that the SVM and LSSVM methods based on statistical learning had the best model prediction performance in lab and pilot datasets, and the RF method performed well in mixed dataset. Furthermore, the genetic algorithm was adopted to optimize the RF model. After optimization of mixed dataset, the effluent-COD prediction (i.e., R2 = 0.966, RMSE/MAE are 61.227/48.584 mg/L) and VFA prediction (i.e., R2 = 0.639, RMSE/MAE are 26.838/21.831 mg/L) have been improved compared with the original RF model (i.e., R2 = 0.918, RMSE/MAE are 86.232/65.03 mg/L of effluent-COD, and R2 = 0.539, RMSE/MAE are 35.489/26.726 mg/L of VFA). This research can provide a reference for the prediction of the anaerobic treatment of actual large-scale industrial wastewater.

A Multimodel-Based Screening Framework for C-19 Using Deep Learning-Inspired Data Fusion.

In recent times, there has been a notable rise in the utilization of Internet of Medical Things (IoMT) frameworks particularly those based on edge computing, to enhance remote monitoring in healthcare applications. Most existing models in this field have been developed temperature screening methods using RCNN, face temperature encoder (FTE), and a combination of data from wearable sensors for predicting respiratory rate (RR) and monitoring blood pressure. These methods aim to facilitate remote screening and monitoring of Severe Acute Respiratory Syndrome Coronavirus (SARS-CoV) and COVID-19. However, these models require inadequate computing resources and are not suitable for lightweight environments. We propose a multimodal screening framework that leverages deep learning-inspired data fusion models to enhance screening results. A Variation Encoder (VEN) design proposes to measure skin temperature using Regions of Interest (RoI) identified by YoLo. Subsequently, the multi-data fusion model integrates electronic records features with data from wearable human sensors. To optimize computational efficiency, a data reduction mechanism is added to eliminate unnecessary features. Furthermore, we employ a contingent probability method to estimate distinct feature weights for each cluster, deepening our understanding of variations in thermal and sensory data to assess the prediction of abnormal COVID-19 instances. Simulation results using our lab dataset demonstrate a precision of 95.2%, surpassing state-of-the-art models due to the thoughtful design of the multimodal data-based feature fusion model, weight prediction factor, and feature selection model.

Data Testing in Digital Transmission: Tamil Literature

The developing area of Optical Character Recognition (OCR) is digital handwriting recognition. Manual writing is replaced by a digital writing pad. The font and shape of the letters vary while writing digitally. The writer’s digital pen pressure and position on the digital pad cause covert text file problems during OCR recognition. When converting OCR to text, an error occurs because of the variations in letter shapes. In languages like Tamil, Chinese, Arabic, and Telugu, where the alphabet is made up of bends, curves, and rings, the aforementioned issue occurs. Tamil has more word mistakes in OCR-to-text conversion because the alphabet comprises curves and angles that must be correctly transcribed. The ResNet (Residual Neural Network) Two-Stage Bottleneck Architecture (RTSBA) is suggested in this paper. In order to recognize text written in Tamil on a digital writing pad, this article suggests using ResNet (Residual Neural Network) Two-Stage Bottleneck Architecture (RTSBA). The suggested RTSBA reduces the complexity of the Tamil alphabet recognition problem by using two distinct phases of neural networks. There are fewer inputs and variables in the early stages. Time and computational complexity are minimized in the last phase. A two-channel and two-stream transformer, long short-term memory, Inception-v3, recurrent neural networks, convolutional neural networks, and other conventional algorithms have been compared to the suggested algorithm. The digital writing pad-handwritten and HP lab datasets demonstrate the effectiveness of proposed methods like RTSBA, which yield accuracy rates of 98.7% and 97.1%, respectively.

Feature Engineering and Supervised Machine Learning to Forecast Biogas Production during Municipal Anaerobic Co-Digestion.

Municipalities with excess anaerobic digestion capacity accept offsite wastes for co-digestion to meet sustainability goals and create more biogas. Despite the benefits inherent to co-digestion, the temporal and compositional heterogeneity of external waste streams creates operational challenges that lead to upsets or conservative co-digestion. Given the complex microbial bioprocesses occurring during anaerobic digestion, prediction and modeling of the outcomes can be challenging, and machine learning has the potential to improve understanding and control of co-digestion processes. Biogas flows are a surrogate for process health, and here, we predicted biogas production from historical data collected by a water resource recovery facility (WRRF) during normal operation. We tested a daily lab and operational data set (n = 1089 after cleaning) and a minute-by-minute supervisory control and data acquisition (SCADA) operational data set (n = 491,761 after cleaning) to determine if forecasting biogas flow for a 24 h time horizon is feasible without collecting additional data. We found that a multilayer perceptron (MLP) neural network model outperformed tree-based and multiple linear regression models. Using a high-resolution SCADA data set for the first time, we showed that MLP neural networks could predict biogas production with an adjusted coefficient of determination (R2) of 0.78 and a mean absolute percentage error of 13.4% on a holdout test set. Adding daily laboratory analyses to the model did not appreciably improve the prediction of biogas flows. Feature engineering was essential to an accurate prediction, and 11 of the 15 most important features in the SCADA model were calculated from raw SCADA outputs. In summary, this paper demonstrates that minute-scale SCADA information collected at a municipal co-digestion facility can forecast biogas production, as a first step toward a digital twin model, without additional data collection.

VEAD: Variance profile Exploitation for Anomaly Detection in real-time IoT data streaming

The explosion of online streaming services in the Internet-of-Things (IoT) ecosystem poses new difficulties in detecting anomalies in real-time and continuous data. The IoT data anomalies are classified into long-term and short-term, with unique characteristics that make it difficult to develop a common detection mechanism for both. The existing techniques require excessive training data and suffer from high variability. This paper overcomes these challenges by proposing a Variance profile Exploitation for Anomaly Detection (VEAD) scheme using discrete wavelet transform and k-means clustering. VEAD is initialized by a fast training phase with a single data segment, from which a sensor variance profile is created. This variance profile reflects the degree of deviation in the collected data from different sensors at a specific time period and is continuously updated by integrating new data segments for effective anomaly detection. Overlapping data collection in the detection phase shows correlations among consecutive data segments, leading to improved detection accuracy (ACC). The Intel Berkeley Research Lab dataset with injected synthetic anomalies is used to perform numerical experiments. A comparative performance evaluation with state-of-the-art methods confirms the effectiveness of VEAD in achieving a higher ACC and a lower false-positive rate (FPR). Notably, 95% and 97% ACCs are achieved in detecting long-term and short-term anomalies, respectively. The high specificity of VEAD is also revealed by the low FPR of at most 2% in all cases. The low computational complexity and fast anomaly detection make VEAD suitable for deployment in live systems with massive data streams.

Labelling of Annotated Condition Monitoring Data Through Technical Language Processing

We propose a novel approach to facilitate supervised fault diagnosis on unlabelled but annotated industry datasets using human-centric technical language processing and weak supervision. Fault diagnosis through Condition Monitoring (CM) is vital for high safety and resource efficiency in the green transition and digital transformation of the process industry. Learning-based Intelligent Fault Diagnosis (IFD) methods are required to automate maintenance decisions and improve decision support for analysts. A major challenge is the lack of labelled industry datasets, limiting supervised IFD research to lab datasets. However, features learned from lab environments generalise poorly to field environments due to different signal distributions, artificial induction or acceleration of lab faults, and lab set-up properties such as average frequency profiles affecting learned features. In this study, we investigate how the unstructured free text fault annotations and maintenance work orders that are present in many industrial CM systems can be used for IFD through technical language processing, based on recent advances in natural language supervision. We introduce two distinct pipelines, one based on contrastive pre-training on large datasets, and one based on a small-data human-centric approach with unsupervised clustering methods. Finally, we showcase one example of the small-data fault classification implementation on a CM industry dataset with a SentenceBERT language model, kMeans clustering, and conventional signal processing methods. Fault class imbalance and time-shift uncertainty is overcome with weak supervision through aggregates of features, and human-centric clustering is used to integrate technical knowledge with the annotation-based fault classes. We show that our model can separate cable and sensor fault recordings from bearing-related fault recordings with an F1-score of 93. To our knowledge, this is the first system to classify faults in field industry CM data based only on associated unstructured fault annotations.

Developing nitrogen removal models for stormwater bioretention systems.

Bioretention systems have the potential of simultaneous runoff volume reduction and nitrogen removal. Internal water storage (IWS) layers and real-time control (RTC) strategies may further improve performance of bioretention systems. However, optimizing the design of these systems is limited by the lack of effective models to simulate nitrogen transformations under the influences of IWS design and environment conditions including soil moisture and temperature. In this study, nitrogen removal models (NRMs) are developed with two complexity levels of nitrogen cycling: the Single Nitrogen Pool (SP) models and the more complex 3 Nitrogen Pool (3P) models. The 0-order kinetics, 1st order kinetics, and the Michaelis-Menten equations are applied to both SP and 3P models, creating six different NRMs. The Storm Water Management Model (SWMM), in combination with each NRM, is calibrated and validated with a lab dataset. Results show that 0-order kinetics are not suitable in simulating nitrogen removal or transformations in bioretention systems, while 1st order kinetics and Michaelis-Menten equation models have similar performances. The best performing NRM (referred to as 3P-m) can accurately predict nitrogen event mean concentrations in bioretention effluent for 20% more events when compared to SWMM. When only calibrated with soil moisture conditions in bioretention systems without internal storage layers, 3P-m was sufficiently adaptable to predict cumulative nitrogen mass removal rates from systems with IWS or RTC rules with less than ±7% absolute error, while the absolute error from SWMM prediction can reach -23%. In general, 3P models provide higher prediction accuracy and improved time series of biochemical reaction rates, while SP models improve prediction accuracy with less required user input for initial conditions.

Improving Multiclass Classification of Fake News Using BERT-Based Models and ChatGPT-Augmented Data

Given the widespread accessibility of content creation and sharing, false information proliferation is a growing concern. Researchers typically tackle fake news detection (FND) in specific topics using binary classification. Our study addresses a more practical FND scenario, analyzing a corpus with unknown topics through multiclass classification, encompassing true, false, partially false, and other categories. Our contribution involves: (1) exploring three BERT-based models—SBERT, RoBERTa, and mBERT; (2) enhancing results via ChatGPT-generated artificial data for class balance; and (3) improving outcomes using a two-step binary classification procedure. Our focus is on the CheckThat! Lab dataset from CLEF-2022. Our experimental results demonstrate a superior performance compared to existing achievements but FND’s practical use needs improvement within the current state-of-the-art.

Enhancing Indoor Air Quality Estimation: A Spatially Aware Interpolation Scheme

The comprehensive and accurate assessment of the indoor air quality (IAQ) in large spaces, such as offices or multipurpose facilities, is essential for IAQ management. It is widely recognized that various IAQ factors affect the well-being, health, and productivity of indoor occupants. In indoor environments, it is important to assess the IAQ in places where it is difficult to install sensors due to space constraints. Spatial interpolation is a technique that uses sample values of known points to predict the values of other unknown points. Unlike in outdoor environments, spatial interpolation is difficult in large indoor spaces due to various constraints, such as being separated into rooms by walls or having facilities such as air conditioners or heaters installed. Therefore, it is necessary to identify independent or related regions in indoor spaces and to utilize them for spatial interpolation. In this paper, we propose a spatial interpolation technique that groups points with similar characteristics in indoor spaces and utilizes the characteristics of these groups for spatial interpolation. We integrated the IAQ data collected from multiple locations within an office space and subsequently conducted a comparative experiment to assess the accuracy of our proposed method in comparison to commonly used approaches, such as inverse distance weighting (IDW), kriging, natural neighbor interpolation, and the radial basis function (RBF). Additionally, we performed experiments using the publicly available Intel Lab dataset. The experimental results demonstrate that our proposed scheme outperformed the existing methods. The experimental results show that the proposed method was able to obtain better predictions by reflecting the characteristics of regions with similar characteristics within the indoor space.

Contactless Sensing-Aided Respiration Signal Acquisition Using Improved Empirical Wavelet Transform for Rhythm Detection.

Respiration is one of the most important vital signs indicating physical condition, while the signal detection is challenging due to the complex rhythm and effort in practical scenarios. In this paper, we propose a contactless sensing-aided respiration signal acquisition technique, which can adaptively extract the desired signal under time-varying respiration rhythms within a wide range. To be specific, respiration is perceived by piezoelectric ceramics sensors along with ballistocardiography and other interference in a contactless manner, and the proposed improved empirical wavelet transform (IEWT) performs spectrum division and recognition based on upper envelop and principal component criteria, respectively, to adaptively extract the respiration spectrum for signal reconstruction. For validations, we extracted respiration signals from 8 healthy individuals in lab breathing at specified rhythms from 0.2 Hz to 0.6 Hz as well as 38 in-patients suffering from sleep-disordered-breathing with reference of polysomnogram in practical clinic scenario. The results showed that the detected respiration rhythms perfectly fitted the ones in experimental lab dataset with a correlation coefficient of 0.98, which validated the effectiveness of the respiration spectrum extraction of the proposed IEWT method. Besides, in practical clinical dataset, the proposed IEWT method could yield mean absolute and relative errors of respiration intervals of 0.4 and 0.05 seconds, respectively, achieving significant improvement in comparison with conventional ones. Meanwhile, the performance of IEWT was robust to rhythm variation, individual difference and breathing cycle detection techniques, which demonstrated the feasibility and superiority of the proposed IEWT method for practical respiration monitoring.

MTR-SAM: Visual Multimodal Text Recognition and Sentiment Analysis in Public Opinion Analysis on the Internet

Existing methods for monitoring internet public opinion rely primarily on regular crawling of textual information on web pages but cannot quickly and accurately acquire and identify textual information in images and videos and discriminate sentiment. The problems make this a challenging research point for multimodal information detection in an internet public opinion scenario. In this paper, we look at how to dynamically monitor the internet opinion information (mostly images and videos) that different websites post. Based on the most recent advancements in text recognition, this paper proposes a new method of visual multimodal text recognition and sentiment analysis (MTR-SAM) for internet public opinion analysis scenarios. In the detection module, a LK-PAN network with large sensory fields is proposed to enhance the CML distillation strategy, and an RSE-FPN with a residual attention mechanism is used to improve feature map representation. Second, it proposes that the original CTC decoder be replaced with a GTC method to solve earlier problems with text detection at arbitrary rotation angles. Additionally, the performance of scene text detection for arbitrary rotation angles is improved using a sinusoidal loss function for rotation recognition. Finally, the improved sentiment analysis model is used to predict the sentiment polarity of the text recognition results. The experimental results show that the new method proposed in this paper improves recognition speed by 31.77%, recognition accuracy by 10.78% on the video dataset, and the F1 score of the multimodal sentiment analysis model by 4.42% on the self-built internet public opinion dataset (lab dataset). The method proposed provides significant technical support for internet public opinion analysis in multimodal domains.

An Integrated Framework for Data Quality Fusion in Embedded Sensor Systems.

The advancement of embedded sensor systems allowed the monitoring of complex processes based on connected devices. As more and more data are produced by these sensor systems, and as the data are used in increasingly vital areas of applications, it is of growing importance to also track the data quality of these systems. We propose a framework to fuse sensor data streams and associated data quality attributes into a single meaningful and interpretable value that represents the current underlying data quality. Based on the definition of data quality attributes and metrics to determine real-valued figures representing the quality of the attributes, the fusion algorithms are engineered. Methods based on maximum likelihood estimation (MLE) and fuzzy logic are used to perform data quality fusion by utilizing domain knowledge and sensor measurements. Two data sets are used to verify the proposed fusion framework. First, the methods are applied to a proprietary data set targeting sample rate inaccuracies of a micro-electro-mechanical system (MEMS) accelerometer and second, to the publicly available Intel Lab Data set. The algorithms are verified against their expected behavior based on data exploration and correlation analysis. We prove that both fusion approaches are capable of detecting data quality issues and providing an interpretable data quality indicator.

Korean Sign Language Recognition Using Transformer-Based Deep Neural Network

Sign language recognition (SLR) is one of the crucial applications of the hand gesture recognition and computer vision research domain. There are many researchers who have been working to develop a hand gesture-based SLR application for English, Turkey, Arabic, and other sign languages. However, few studies have been conducted on Korean sign language classification because few KSL datasets are publicly available. In addition, the existing Korean sign language recognition work still faces challenges in being conducted efficiently because light illumination and background complexity are the major problems in this field. In the last decade, researchers successfully applied a vision-based transformer for recognizing sign language by extracting long-range dependency within the image. Moreover, there is a significant gap between the CNN and transformer in terms of the performance and efficiency of the model. In addition, we have not found a combination of CNN and transformer-based Korean sign language recognition models yet. To overcome the challenges, we proposed a convolution and transformer-based multi-branch network aiming to take advantage of the long-range dependencies computation of the transformer and local feature calculation of the CNN for sign language recognition. We extracted initial features with the grained model and then parallelly extracted features from the transformer and CNN. After concatenating the local and long-range dependencies features, a new classification module was applied for the classification. We evaluated the proposed model with a KSL benchmark dataset and our lab dataset, where our model achieved 89.00% accuracy for 77 label KSL dataset and 98.30% accuracy for the lab dataset. The higher performance proves that the proposed model can achieve a generalized property with considerably less computational cost.