Mean Accuracy Rate Research Articles

Impaired processing of spatiotemporal visual attention engagement deficits in Chinese children with developmental dyslexia.

Emerging evidence suggests that visuospatial attention plays an important role in reading among Chinese children with dyslexia. Additionally, numerous studies have shown that Chinese children with dyslexia have deficits in their visuospatial attention orienting; however, the visual attention engagement deficits in Chinese children with dyslexia remain unclear. Therefore, we used a visual attention masking (AM) paradigm to characterize the spatiotemporal distribution of visual attention engagement in Chinese children with dyslexia. AM refers to impaired identification of the first (S1) of two rapidly sequentially presented mask objects. In the present study, S1 was always centrally displayed, whereas the spatial position of S2 (left, middle, or right) and the S1-S2 interval were manipulated. The results revealed a specific temporal deficit of visual attentional masking in Chinese children with dyslexia. The mean accuracy rate for developmental dyslexia (DD) in the middle spatial position was significantly lower than that in the left spatial position at a stimulus onset asynchrony (SOA) of 140ms, compared with chronological age (CA). Moreover, we further observed spatial deficits of visual attentional masking in the three different spatial positions. Specifically, in the middle spatial position, the AM effect of DD was significantly larger for the 140-ms SOA than for the 250-ms and 600-ms SOA compared with CA. Our results suggest that Chinese children with dyslexia are significantly impaired in visual attentional engagement and that spatiotemporal visual attentional engagement may play a special role in Chinese reading.

Cyberbullying Detection and Prevention System for Enhancing Online Platform Safety Using Maximum Entropy Model

ABSTRACTThe widespread proliferation of social media platforms in the 21st century has undoubtedly brought about a significant shift in how individuals establish connections. However, it is essential to acknowledge that this technological innovation has also given rise to negative repercussions. The proliferation of online abuse, harassment, cyberbullying, and trolling has emerged as a significant concern, overshadowing the otherwise advantageous aspects of digital networking platforms. The detrimental effect of cyberbullying is of considerable concern, which often causes profound psychological and physiological anguish among its targets, sometimes resulting in contemplation of suicide. The proliferation of online harassment occurrences, including disclosing confidential dialogues and spreading detrimental rumors, has engendered extensive apprehension. The present research aims to address the pressing need to identify and mitigate cyberbullying within the context of social media platforms. A rigorous approach was used to gather data from Kaggle, which was further processed utilizing sophisticated methods like tokenization, stemming, and lemmatization. The research used the Maximum Entropy Model to develop a detection system to identify instances of bullying in texts or messages shared on social media sites. The algorithm exhibited a praiseworthy mean accuracy rate of 77% in detecting cases of cyberbullying. The results highlight the capacity of the algorithm to anticipate if remarks entered by individuals on social media might be classified as cyberbullying, representing a noteworthy advancement in addressing this widespread problem. This study supports the broader deployment of the created cyberbullying detection system across all social media platforms. The proactive use of this novel technology enables online platforms to effectively detect and mitigate cyberbullying, cultivating a digital environment characterized by enhanced safety and respect. This research illuminates the significant issue of cyberbullying. It presents a concrete remedy to protect the welfare of those who engage in online activities, particularly those more susceptible to harm, such as women and children.

Enhancing hydrological predictions: optimised decision tree modelling for improved monthly inflow forecasting

ABSTRACT The utilisation of modelling tools in hydrology has been effective in predicting future floods by analysing historical rainfall and inflow data, due to the association between climate change and flood frequency. This study utilised a historical dataset of monthly inflow and rainfall for the Terengganu River in Malaysia, and it is renowned for its hydrological patterns that exhibit a high level of unpredictability. The evaluation of the predictive precision and effectiveness of the Optimised Decision Tree ODT model, along with the RF and GBT models, in this study involved analysing several indicators. These indicators included the correlation coefficient, mean absolute error, percentage of relative error, root mean square error, Nash-Sutcliffe efficiency, and accuracy rate. The research results indicated that the ODT and RF models performed better than the GBT model in predicting monthly inflows. The ODT model, as well as the RF and GBT models, showed validation results with average accuracies of 94%, 91%, and 92%, respectively. The R² values were 90.2%, 84.8%, and 96.0%, respectively, and the NES values ranged from 0.92 to 0.94. The results of this research have greater implications, extending beyond the forecasting of monthly inflow rates to encompass other hydro-meteorological variables that depend exclusively on historical input data.

IoT-FAR: A multi-sensor fusion approach for IoT-based firefighting activity recognition

Inadequate training poses a significant risk of injury among young firefighters. Although Human Activity Recognition (HAR) algorithms have shown potential in monitoring and evaluating performance, most existing studies focus on daily activities and have difficulty distinguishing complex firefighting tasks. This study introduces the Internet of things (IoT)-based wearable firefighting activity recognition (IoT-FAR) system which employs a multi-modal sensor fusion approach to achieve comprehensive activity recognition during firefighting training. The IoT-FAR comprises five wearable body sensor nodes and a coordinator node. This study explores the significance of features extracted from the surface electromyography, heart rate, and inertial measurement units in firefighting training activity recognition. A hybrid machine learning (HML)-based network is proposed, which integrates three models: one trained with all features (MA), another with upper body features (MU), and a third with lower body features (ML). The proposed HML-SVM-RBF1-RF2 network achieves superior performance, with a mean recall of 93.94%, mean precision of 90.94%, and a mean accuracy rate of 98.29%. Additionally, the study introduces the specialized firefighting training associated activities (SFTAA) dataset, which includes endurance training activities involving self-contained breathing apparatus (SCBA) conducted by eighteen firefighters. This dataset represents preliminary work towards building a comprehensive dataset covering various events and scenarios for tracking firefighter activities. The IoT-FAR system also demonstrates the potential use of misclassified activities as evaluation metrics for assessing firefighter training performance.

An intelligent deep augmented model for detection of banana leaves diseases.

One of the most popular fruits worldwide is the banana. Accurate identification and categorization of banana diseases is essential for maintaining global fruits security and stakeholder profitability. Four different types of banana leaves exist Healthy, Cordana, Sigatoka, and Pestalotiopsis. These types can be analyzed using four types of vision: RGB, night vision, infrared vision, and thermal vision. This paper presents an intelligent deep augmented learning model composed of VGG19 and passive aggressive classifier (PAC) to classify the four diseases types of bananas under each type of vision. Each vision consisted of 1600 images with a size of (224 × 224). The training-testing approach was used to evaluate the performance of the hybrid model on Kaggle dataset, which was justified by various methods and metrics. The proposed model achieved a remarkable mean accuracy rate of 99.16% for RGB vision, 98.02% for night vision, 96.05% for infrared vision, and 96.10% for thermal vision for training and testing data. Microscopy employed in this research as a validation tool. The microscopic examination of leaves confirmed the presence and extent of the disease, providing ground truth data to validate and refine the proposed model. RESEARCH HIGHLIGHTS: The model can be helpful for internet of things -based drones to identify the large scale of banana leaf-disease detection using drones for images acquisition. Proposed an intelligent deep augmented learning model composed of VGG19 and passive aggressive classifier (PAC) to classify the four diseases types of bananas under each type of vision. The model detected banana leaf disease with a 99.16% accuracy rate for RGB vision, 98.02% accuracy rate for night vision, 96.05% accuracy rate for infrared vision, and 96.10% accuracy rate for thermal vision The model will provide a facility for early disease detection which minimizes crop loss, enhances crop quality, timely decision making, cost saving, risk mitigation, technology adoption, and helps in increasing the yield.

AI showdown: info accuracy on protein quality content in foods from ChatGPT 3.5, ChatGPT 4, bard AI and bing chat

PurposeThis study aims to assess the effectiveness of different AI models in accurately aggregating information about the protein quality (PQ) content of food items using four artificial intelligence (AI) models -– ChatGPT 3.5, ChatGPT 4, Bard AI and Bing Chat.Design/methodology/approachA total of 22 food items, curated from the Food and Agriculture Organisation (FAO) of the United Nations (UN) report, were input into each model. These items were characterised by their PQ content according to the Digestible Indispensable Amino Acid Score (DIAAS).FindingsBing Chat was the most accurate AI assistant with a mean accuracy rate of 63.6% for all analyses, followed by ChatGPT 4 with 60.6%. ChatGPT 4 (Cohen’s kappa: 0.718, p < 0.001) and ChatGPT 3.5 (Cohen’s kappa: 0.636, p: 0.002) showed substantial agreement between baseline and 2nd analysis, whereas they showed a moderate agreement between baseline and 3rd analysis (Cohen’s kappa: 0.538, p: 0.011 for ChatGPT 4 and Cohen’s kappa: 0.455, p: 0.030 for ChatGPT 3.5).Originality/valueThis study provides an initial insight into how emerging AI models assess and classify nutrient content pertinent to nutritional knowledge. Further research into the real-world implementation of AI for nutritional advice is essential as the technology develops.

Research on intelligent monitoring technology for roof damage of traditional Chinese residential buildings based on improved YOLOv8: taking ancient villages in southern Fujian as an example

In the process of preserving historical buildings in southern Fujian, China, it is crucial to provide timely and accurate statistical data to classify the damage of traditional buildings. In this study, a method based on the improved YOLOv8 neural network is proposed to select aerial photographs of six villages in Xiamen and Quanzhou cities in Fujian Province as the dataset, which contains a total of 3124 photographs. Based on the high-resolution orthophotographs obtained from UAV tilt photography, the YOLOv8 model was used to make predictions. The main task in the first stage is to select the buildings with historical value in the area, and the model's mAP (Mean Accuracy Rate) can reach 97.2% in the first stage task. The second stage uses the YOLOv8 model to segment the images selected in the first stage, detecting possible defects on the roofs, including collapses, missing tiles, unsuitable architectural additions, and vegetation encroachment. In the second stage of the segmentation task, the mAP reaches 89.4%, which is a 1.5% improvement in mAP50 (mean accuracy) compared to the original YOLOv8 model, and the number of parameters and GFLOPs are reduced by 22% and 15%, respectively. This method can effectively improve the disease detection efficiency of historical built heritage in southern Fujian under complex terrain and ground conditions.

Smartphone application for artificial intelligence-based evaluation of stool state during bowel preparation before colonoscopy.

Colonoscopy (CS) is an important screening method for the early detection and removal of precancerous lesions. The stool state during bowel preparation (BP) should be properly evaluated to perform CS with sufficient quality. This study aimed to develop a smartphone application (app) with an artificial intelligence (AI) model for stool state evaluation during BP and to investigate whether the use of the app could maintain an adequate quality of CS. First, stool images were collected in our hospital to develop the AI model and were categorized into grade 1 (solid or muddy stools), grade 2 (cloudy watery stools), and grade 3 (clear watery stools). The AI model for stool state evaluation (grades 1-3) was constructed and internally verified using the cross-validation method. Second, a prospective study was conducted on the quality of CS using the app in our hospital. The primary end-point was the proportion of patients who achieved Boston Bowel Preparation Scale (BBPS) ≥6 among those who successfully used the app. The AI model showed mean accuracy rates of 90.2%, 65.0%, and 89.3 for grades 1, 2, and 3, respectively. The prospective study enrolled 106 patients and revealed that 99.0% (95% confidence interval 95.3-99.9%) of patients achieved a BBPS ≥6. The proportion of patients with BBPS ≥6 during CS using the developed app exceeded the set expected value. This app could contribute to the performance of high-quality CS in clinical practice.

Effects on brain structural and functional in deaf children after aerobic exercise training: a pilot cluster randomized controlled study

Purpose: To examine effects of aerobic exercise interventions on brain via the structural Magnetic Resonance Imaging (MRI), as well as functional change during working memory (WM) task using fMRI in deaf children.Method: The study applied a cluster randomized controlled design. Twelve deaf children in the intervention group were required to complete an eleven-week aerobic exercise intervention, while other twelve age and gender matched deaf children in the control group were required to keep their normal daily life. Task fMRI images of each participant were acquired in the baseline and post intervention period. The surface-based morphometry (SBM) analysis and functional activation analysis were employed to probe the effects of 11-week aerobic exercise on cerebral structural and functional in deaf children, respectively.Results: The 11-week aerobic exercise intervention did not change brain structure in deaf children. However, behavior performance (reaction time and mean accuracy rate) presented significant improvements after the 11-week aerobic exercise intervention. Compared to the control group, the intervention group showed decreased reaction time in the 2-back (p < 0.001) and 2-0 back (p < 0.001), and increased mean accuracy rate during 2-back (p = 0.034). Furthermore, enhanced brain activations in the left supplementary motor cortex (p < 0.05, FDR-corrected) and left paracentral lobule (p < 0.05, FDR-corrected) were observed in the intervention group.Conclusion: 11-week aerobic exercise intervention may not be able to modulate brain structure in deaf children, but may have significantly positive effects on behavior performance and brain functional activation during WM task.

Data Sorting Influence on Short Text Manual Labeling Quality for Hierarchical Classification

The precise categorization of brief texts holds significant importance in various applications within the ever-changing realm of artificial intelligence (AI) and natural language processing (NLP). Short texts are everywhere in the digital world, from social media updates to customer reviews and feedback. Nevertheless, short texts’ limited length and context pose unique challenges for accurate classification. This research article delves into the influence of data sorting methods on the quality of manual labeling in hierarchical classification, with a particular focus on short texts. The study is set against the backdrop of the increasing reliance on manual labeling in AI and NLP, highlighting its significance in the accuracy of hierarchical text classification. Methodologically, the study integrates AI, notably zero-shot learning, with human annotation processes to examine the efficacy of various data-sorting strategies. The results demonstrate how different sorting approaches impact the accuracy and consistency of manual labeling, a critical aspect of creating high-quality datasets for NLP applications. The study’s findings reveal a significant time efficiency improvement in terms of labeling, where ordered manual labeling required 760 min per 1000 samples, compared to 800 min for traditional manual labeling, illustrating the practical benefits of optimized data sorting strategies. Comparatively, ordered manual labeling achieved the highest mean accuracy rates across all hierarchical levels, with figures reaching up to 99% for segments, 95% for families, 92% for classes, and 90% for bricks, underscoring the efficiency of structured data sorting. It offers valuable insights and practical guidelines for improving labeling quality in hierarchical classification tasks, thereby advancing the precision of text analysis in AI-driven research. This abstract encapsulates the article’s background, methods, results, and conclusions, providing a comprehensive yet succinct study overview.

Hybrid federated learning with brain-region attention network for multi-center Alzheimer's disease detection

Identifying reproducible and interpretable biomarkers for Alzheimer's disease (AD) detection remains a challenge. AD detection using multi-center datasets can expand the sample size to improve robustness but might lead to a data privacy problem. Moreover, due to the high cost of labeling data, a lot of unlabeled data in each center is not fully utilized. To address this, a hybrid FL (HFL) framework is proposed that not only uses unlabeled data to train deep learning networks, but also achieves data privacy protection. We propose a novel Brain-region Attention Network (BANet), which highlights important regions via attention to represent the region of interest (ROIs).Specifically, we use a brain template to extract ROI signals from the preprocessed structure magnetic resonance imaging (sMRI) data. In addition, we add a self-supervised loss to the current loss to guide the attention map generation to learn the representations from unlabeled data. Finally, we evaluate our method on a multi-center database which is constructed using five AD datasets. The experimental results show that the proposed method performs better than state-of-the-art methods, achieving mean accuracy rates of 85.69 %, 63.34 %, and 69.89 % on the AD vs. NC, MCI vs. NC, and AD vs. MCI respectively. The source code is available for reproducibility at: https://github.com/yuliangCarmelo/HFL.

Vision-based measurement method for geometric dimensions of PVC pipe end faces

This study introduces a vision-based expedited methodology for assessing various geometric circular dimensions on the termini of PVC conduits. The process commences with delineating pipe profiles using the EDPF algorithm for edge detection. Successive steps employ a radius-constrained weighted circular approximation algorithm to form provisional circular profiles from closed-edge segments. These profiles are refined using a rapid circle arc fitting algorithm for multiple open-edge sections. Noise circles are sifted out with the Number of False Alarms algorithm, and upon calibration with actual dimensions, these profiles are quantified into physical sizes of the conduit's terminal geometries. Empirical evidence from the methodology demonstrates an ability to measure the circular dimensions with a mean accuracy rate surpassing 99.2%.

Accuracy of CBCT in Preoperative Assessment of Impacted Canines vs. Panoramic Radiography

ABSTRACT Background: Accurate assessment of impacted canines is crucial for successful treatment planning. Radiographic techniques like Cone Beam Computed Tomography (CBCT) and Panoramic Radiography are commonly used, but their comparative accuracy remains under scrutiny. Materials and Methods: In this study, 50 patients diagnosed with impacted canines were enrolled. Both CBCT and Panoramic Radiography images were obtained for each patient using standard protocols. Two experienced dentists independently analyzed the images to determine the position of impacted canines and their relationship with neighboring structures. Results: The findings of this study revealed that CBCT provided superior accuracy in assessing the position of impacted canines compared to Panoramic Radiography. Specifically, CBCT demonstrated a mean accuracy rate of 89.5%, while Panoramic Radiography showed a mean accuracy rate of 72.3%. Moreover, CBCT allowed for better visualization of impacted canine angulation, depth, and spatial orientation. Panoramic Radiography, on the other hand, displayed limitations in precisely identifying the impacted canine’s position. Conclusion: The study’s outcomes underscore the higher accuracy of CBCT over Panoramic Radiography in the preoperative assessment of impacted canines. CBCT’s detailed imaging provides valuable insights for treatment planning, potentially leading to improved surgical outcomes. Although CBCT entails greater radiation exposure and cost, its benefits in accurate diagnosis and treatment planning justify its use in cases of impacted canines.

Detection and prediction of pathogenic microorganisms in aquaculture (Zhejiang Province, China).

The detection and prediction of pathogenic microorganisms play a crucial role in the sustainable development of the aquaculture industry. Currently, researchers mainly focus on the prediction of water quality parameters such as dissolved oxygen for early warning. To provide early warning directly from the pathogenic source, this study proposes an innovative approach for the detection and prediction of pathogenic microorganisms based on yellow croaker aquaculture. Specifically, a method based on quantitative polymerase chain reaction (qPCR) is designed to detect the Cryptocaryon irritans (Cri) pathogenic microorganisms. Furthermore, we design a predictive combination model for small samples and high noise data to achieve early warning. After performing wavelet analysis to denoise the data, two data augmentation strategies are used to expand the dataset and then combined with the BP neural network (BPNN) to build the fusion prediction model. To ensure the stability of the detection method, we conduct repeatability and sensitivity tests on the designed qPCR detection technique. To verify the validity of the model, we compare the combined BPNN to long short-term memory (LSTM). The experimental results show that the qPCR method provides accurate quantitative measurement of Cri pathogenic microorganisms, and the combined model achieves a good level. The prediction model demonstrates higher accuracy in predicting Cri pathogenic microorganisms compared to the LSTM method, with evaluation indicators including mean absolute error (MAE), recall rate, and accuracy rate. Especially, the accuracy of early warning is increased by 54.02%.

An IoT-based cognitive impairment detection device: A newly proposed method in older adults care-choice reaction time-device development and data-driven validation.

Research shows that older adults' performance on choice reaction time (CRT) tests can predict cognitive decline. A simple CRT tool could help detect mild cognitive impairment (MCI) and preclinical dementia, allowing for further stratification of cognitive disorders on-site or via telemedicine. The primary objective was to develop a CRT testing device and protocol to differentiate between two cognitive impairment categories: (a) subjective cognitive decline (SCD) and non-amnestic mild cognitive impairment (na-MCI), and (b) amnestic mild cognitive impairment (a-MCI) and multiple-domain a-MCI (a-MCI-MD). A pilot study in Italy and Romania with 35 older adults (ages 61-85) assessed cognitive function using the Mini-Mental State Examination (MMSE) and a CRT color response task. Reaction time, accuracy, and demographics were recorded, and machine learning classifiers analyzed performance differences to predict preclinical dementia and screen for mild cognitive deficits. Moderate correlations were found between the MMSE score and both mean reaction time and mean accuracy rate. There was a significant difference between the two groups' reaction time for blue light, but not for any other colors or for mean accuracy rate. SVM and RUSBoosted trees were found to have the best preclinical dementia prediction capabilities among the tested classifier algorithms, both presenting an accuracy rate of 77.1%. CRT testing with machine learning effectively differentiates cognitive capacities in older adults, facilitating early diagnosis and stratification of neurocognitive diseases and can also identify impairments from stressors like dehydration and sleep deprivation. This study highlights the potential of portable CRT devices for monitoring cognitive function, including SCD and MCI.

Influencing factors of knowledge proficiency of general practitioners in rural China for esophageal cancer prevention and treatment: a cross-sectional study.

This study aims to investigate the knowledge of rural general practitioners (GPs) in esophageal cancer (EC) prevention and treatment in China and analyze relevant influencing factors, so as to improve the ability of rural GPs in EC prevention and treatment. This cross-sectional study was conducted from November 5, 2021, to November 20, 2021. A self-designed questionnaire was used to conduct an online survey. Multivariable logistic regression models were used to identify the influencing factors of knowledge proficiency of GPs in rural China for EC prevention and treatment. This study included 348 participants from 12 rural areas in Hebei Province. The mean accuracy rate on all question items was 42.3%±10.67%. Sex (OR = 2.870, 95% CI: 1.519-5.423), educational level (OR = 3.256, 95% CI: 1.135-9.339), and comprehension of clinical practice guidelines for EC (OR = 4.305, 95% CI: 2.023-9.161) were significant predictors for GPs' knowledge proficiency of EC prevention and treatment (P < 0.05). The study indicated that knowledge proficiency of rural GPs of EC prevention and control still awaits to be improved. Sex, educational level, and comprehension of clinical practice guidelines for EC were significant predictors for their proficiency.

Analysis of Artificial Intelligence-Based Approaches Applied to Non-Invasive Imaging for Early Detection of Melanoma: A Systematic Review.

Melanoma, the deadliest form of skin cancer, poses a significant public health challenge worldwide. Early detection is crucial for improved patient outcomes. Non-invasive skin imaging techniques allow for improved diagnostic accuracy; however, their use is often limited due to the need for skilled practitioners trained to interpret images in a standardized fashion. Recent innovations in artificial intelligence (AI)-based techniques for skin lesion image interpretation show potential for the use of AI in the early detection of melanoma. The aim of this study was to evaluate the current state of AI-based techniques used in combination with non-invasive diagnostic imaging modalities including reflectance confocal microscopy (RCM), optical coherence tomography (OCT), and dermoscopy. We also aimed to determine whether the application of AI-based techniques can lead to improved diagnostic accuracy of melanoma. A systematic search was conducted via the Medline/PubMed, Cochrane, and Embase databases for eligible publications between 2018 and 2022. Screening methods adhered to the 2020 version of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Included studies utilized AI-based algorithms for melanoma detection and directly addressed the review objectives. We retrieved 40 papers amongst the three databases. All studies directly comparing the performance of AI-based techniques with dermatologists reported the superior or equivalent performance of AI-based techniques in improving the detection of melanoma. In studies directly comparing algorithm performance on dermoscopy images to dermatologists, AI-based algorithms achieved a higher ROC (>80%) in the detection of melanoma. In these comparative studies using dermoscopic images, the mean algorithm sensitivity was 83.01% and the mean algorithm specificity was 85.58%. Studies evaluating machine learning in conjunction with OCT boasted accuracy of 95%, while studies evaluating RCM reported a mean accuracy rate of 82.72%. Our results demonstrate the robust potential of AI-based techniques to improve diagnostic accuracy and patient outcomes through the early identification of melanoma. Further studies are needed to assess the generalizability of these AI-based techniques across different populations and skin types, improve standardization in image processing, and further compare the performance of AI-based techniques with board-certified dermatologists to evaluate clinical applicability.

Intelligent ADL Recognition via IoT-Based Multimodal Deep Learning Framework.

Smart home monitoring systems via internet of things (IoT) are required for taking care of elders at home. They provide the flexibility of monitoring elders remotely for their families and caregivers. Activities of daily living are an efficient way to effectively monitor elderly people at home and patients at caregiving facilities. The monitoring of such actions depends largely on IoT-based devices, either wireless or installed at different places. This paper proposes an effective and robust layered architecture using multisensory devices to recognize the activities of daily living from anywhere. Multimodality refers to the sensory devices of multiple types working together to achieve the objective of remote monitoring. Therefore, the proposed multimodal-based approach includes IoT devices, such as wearable inertial sensors and videos recorded during daily routines, fused together. The data from these multi-sensors have to be processed through a pre-processing layer through different stages, such as data filtration, segmentation, landmark detection, and 2D stick model. In next layer called the features processing, we have extracted, fused, and optimized different features from multimodal sensors. The final layer, called classification, has been utilized to recognize the activities of daily living via a deep learning technique known as convolutional neural network. It is observed from the proposed IoT-based multimodal layered system's results that an acceptable mean accuracy rate of 84.14% has been achieved.

Development of a hand classification system for smart hand wearables

Research purpose: This study aimed to lay a research foundation for smart hand wearable design by classifying the right-hand data of 4545 adults aged 20 to 69. Further, to increase the practical applicability of the hand classification system, a hand type discrimination method and regression equations for the hand dimensions of each type were presented. Methods: This study statistically analyzed eighth Size Korea data with IBM SPSS Ver.26.0. Cluster analysis was performed to classify both finger length and circumference type. Discriminant analysis was conducted, yielding discriminant functions to aid potential smart hand wearable wearers in self-diagnosing their hand types. Linear regression analysis yielded regression equations for the detailed finger dimensions for the pattern-making of smart hand wearables. Results: The finger length type was categorized into four types: the Uphill type, Downhill type, Mountain type, and Horizon type for both men’s and women’s hands. The finger circumference type was categorized into two types, the Cone and Cylinder types, for both men’s and women’s hands. The discriminant function showed a mean accuracy rate of 89.9% and the regression equations a mean explanatory power of 72.9%. Conclusion: The hand classification system proposed in this study aimed to improve the fingertip fit of smart hand wearable products by analyzing the configuration of motion tracking gloves or haptic gloves. In addition, considering the practical applicability for both wearers and designers of smart hand wearables, a discrimination method of finger types for wearers’ self-diagnosis and regression functions of finger dimensions for designers’ pattern making were provided.

A powerful random forest-based pipeline for accurately identifying the structural variants on panel sequencing data.

e18898 Background: Numerous studies have reported that the identification of structural variants (SVs) can provide ideal targets for cancer targeting therapy. However, on the one hand, the current algorithms exhibited different performances in detecting different types and sizes of SVs; on the other hand, the whole-genome/exome sequencing for detecting SVs is costly, and only a portion of SVs can be used to guide the clinical treatment of cancer patients. Therefore, developing a powerful, highly accurate, and cost-effective pipeline to detect SVs for clinical application is urgently required. Methods: Based on simulated sequencing data, four common SV detection tools (Delly, Lumpy, SvABA, and Manta) were used to select the best performance one. This tool will be used for detecting SVs in panel sequencing data. Then, Integrative Genomics Viewer (IGV) was used to annotate these SVs as true positive (TP) and false positive (FP) SVs. These annotated TP and FP SVs were used as input in the random forest classifier (RFC) to train a model for predicting the true or false positive SVs. Two independent testing cohorts and standards were used to validate this constructed pipeline. In addition, IHC/FISH experiments were performed to further validate these predicted TP SVs. Results: In the simulation data, the detection tool with the highest SVs identification sensitivity was Delly. By Delly, a total of 1,303 SVs in 384 tumor samples were detected. Based on annotated TP and FP SVs, an RFC model was constructed in the training cohort, which predicted 334 and 560 TP and FP SVs, respectively. The accuracy rates (AR) were 99.85% and 100% of TP and FP SVs, respectively. The predicted TP and FP SVs by constructed pipeline also showed a high accuracy rate in cohort 1 (98.96% and 99.24% of TP and FP SVs, respectively), cohort 2 (98.48% and 100% of TP and FP SVs, respectively), and standards (the mean accuracy rate was 90%). Finally, based on these TP SVs predicted by the constructed pipeline, FISH/IHC experiment results further verified the robustness of this pipeline (the man accuracy rate was 95.83%). Conclusions: The constructed random forest-based pipeline can robustly and accurately identify SVs based on panel sequencing data, which will be helpful for clinical decision-making.