Abstract: The difficulty of sports gesture recognition is the effective cooperation of hardware and software. Moreover, there are few studies on machine learning in the capture of the details of sports athletes’ gesture recognition. Therefore, based on the learning technology, this study uses the sensor with gesture recognition algorithm to analyze the detailed motion capture of sports athletes. At the same time, this study selects inertial sensor technology as the gesture recognition hardware through comparative analysis. In addition, by analyzing the actual needs of athletes’ gesture recognition, the Kalman filter algorithm is used to solve the athlete’s posture, construct a virtual…human body model, and perform sub-regional processing, so as to facilitate the effective identification of different limbs. Finally, in order to verify the validity of the algorithm model, the basketball exercise is taken as an example for experimental analysis. The research results show that the basketball gesture recognition method used in this paper is quite satisfactory.
Show more
Keywords: Machine learning, neural network, sensor network, action research
Abstract: BACKGROUND: Automatic segmentation of the pancreas and its tumor region is a prerequisite for computer-aided diagnosis. OBJECTIVE: In this study, we focus on the segmentation of pancreatic cysts in abdominal computed tomography (CT) scan, which is challenging and has the clinical auxiliary diagnostic significance due to the variability of location and shape of pancreatic cysts. METHODS: We propose a convolutional neural network architecture for segmentation of pancreatic cysts, which is called pyramid attention and pooling on convolutional neural network (PAPNet). In PAPNet, we propose a new atrous pyramid attention module to extract high-level features at different scales, and a spatial…pyramid pooling module to fuse contextual spatial information, which effectively improves the segmentation performance. RESULTS: The model was trained and tested using 1,346 CT slice images obtained from 107 patients with the pathologically confirmed pancreatic cancer. The mean dice similarity coefficient (DSC) and mean Jaccard index (JI) achieved using the 5-fold cross-validation method are 84.53% and 75.81%, respectively. CONCLUSIONS: The experimental results demonstrate that the proposed new method in this study enables to achieve effective results of pancreatic cyst segmentation.
Show more
Abstract: BACKGROUND: Pancreatic cancer is a highly lethal disease. The preoperative distinction between pancreatic serous cystic neoplasm (SCN) and mucinous cystic neoplasm (MCN) remains a clinical challenge. OBJECTIVE: The goal of this study is to provide clinicians with supportive advice and avoid overtreatment by constructing a convolutional neural network (CNN) classifier to automatically identify pancreatic cancer using computed tomography (CT) images. METHODS: We construct a CNN model using a dataset of 6,173 CT images obtained from 107 pathologically confirmed pancreatic cancer patients at Shanghai Changhai Hospital from January 2017 to February 2022. We divide CT slices into three categories namely, SCN,…MCN, and no tumor, to train the DenseNet201-based CNN model with multi-head spatial attention mechanism (MSAM-DenseNet201). The attention module enhances the network’s attention to local features and effectively improves the network performance. The trained model is applied to process all CT image slices and finally realize the two categories classification of MCN and SCN patients through a joint voting strategy. RESULTS: Using a 10-fold cross validation method, this new MSAM-DenseNet201 model achieves a classification accuracy of 92.52%, a precision of 92.16%, a sensitivity of 92.16%, and a specificity of 92.86%, respectively. CONCLUSIONS: This study demonstrates the feasibility of using a deep learning network or classification model to help diagnose MCN and SCN cases. This, the new method has great potential for developing new computer-aided diagnosis systems and applying in future clinical practice.
Show more
Abstract: Our previous studies revealed that Wilms' tumor 1 (WT-1) protein was highly expressed in breast myoepithelial (ME) and endothelial cells. As the human breast tissue is rich in ME cells and blood vessels, our current study intended to assess whether WT-1 immunohistochemistry may have dual usages in evaluation of the ME cells and micro-vessel density. Consecutive sections were prepared from breast tumors with co-existing normal, hyperplastic, and neoplastic components. Consecutive sections were immunostained for WT-1 and a panel of ME and endothelial cell markers. From each case, 4–5 randomly selected duct clusters were photographed, and the percentages of positive cells…for these molecules were compared. Similar to ME cell marker CD10 and smooth muscle actin (SMA), WT-1 expression was preferentially seen in ME cells, and over 90% of WT-1 positive ME cells were immunoreactive to CD10 and SMA. Distinct WT-1 expression was also seen in endothelial cells, and over 90% of WT-1 positive endothelial cells were positive for blood vessel specific markers. With tumor progression, the percentage and intensity of WT-1 positivity decreased in ME cells, whereas increased in endothelial cells. These finding suggest that WT-1 immunohistochemistry may be used to assess both the ME cells and micro-vessel density.
Show more
Abstract: BACKGROUND: Prosthetic knee is the most important component of lower limb prosthesis. Speed adaptive for prosthetic knee during swing flexion is the key method to realize physiological gait. OBJECTIVE: This study aims to discuss the target of physiological gait, propose a speed adaptive control method during swing flexion and research the damping adjustment law of intelligent hydraulic prosthetic knee. METHODS: According to the physiological gait trials of healthy people, the control target during swing flexion is defined. A new prosthetic knee with fuzzy logical control during swing flexion is designed to realize the damping adjustment automatically. The function simulation and…evaluation system of intelligent knee prosthesis is provided. Speed adaptive control test of the intelligent prosthetic knee in different velocities are researched. RESULTS: The maximum swing flexion of the knee angle is set between sixty degree and seventy degree as the target of physiological gait. Preliminary experimental results demonstrate that the prosthetic knee with fuzzy logical control is able to realize physiological gait under different speeds. The faster the walking, the bigger the valve closure percentage of the hydraulic prosthetic knee. CONCLUSIONS: The proposed fuzzy logical control strategy and intelligent hydraulic prosthetic knee are effective for the amputee to achieve physiological gait.
Show more
Keywords: Physiological gait, speed adaptive, prosthetic knee, fuzzy logical control, function simulation and evaluation
Abstract: Each pixel can be classified in the image by the semantic segmentation. The segmentation detection results of pixel level can be got which are similar to the contour of the target object. However, the results of semantic segmentation trained by Fully convolutional networks often lead to the loss of detail information. This paper proposes a CRF-FCN model based on CRF optimization. Firstly, the original image is detected based on feature pyramid networks, and the target area information is extracted, which is used to train the high-order potential function of CRF. Then, the high-order CRF is used as the back-end of…the complete convolution network to optimize the semantic image segmentation. The algorithm comparison experiment shows that our algorithm makes the target details more obvious, and improves the accuracy and efficiency of semantic segmentation.
Show more
Keywords: Conditional random field (CRF), fully convolutional networks (FCNs), semantic segmentation
Abstract: As cloud computing becomes prevalent, more and more sensitive data is being centralized into the cloud for sharing, which brings forth new challenges for outsourced data security and privacy. Attribute-based encryption (ABE) is a promising cryptographic primitive, which has been widely applied to design fine-grained access control system recently. However, ABE is criticized for its high scheme overhead as the computational cost grows with the complexity of the access formula. This disadvantage becomes more serious for mobile devices with constrained computing resources. Aiming at tackling the challenge above, we present a generic and efficient solution to implement attribute-based access control…system by introducing secure outsourcing techniques into ABE. More precisely, two cloud service providers (CSPs), namely key generation-cloud service provider (KG-CSP) and decryption-cloud service provider (D-CSP) are introduced to perform the outsourced key-issuing and decryption on behalf of attribute authority and users respectively. In order to outsource heavy computation to both CSPs without private information leakage, we formalize an underlying primitive called outsourced ABE (OABE) and propose several constructions with outsourced decryption and key-issuing. Finally, extensive experiment demonstrates that with the help of KG-CSP and D-CSP, efficient key-issuing and decryption are achieved in our constructions.
Show more
Abstract: Rifampin is an important drug used in the treatment of tuberculosis, and it increases the drug metabolism in human hepatocytes. Previous studies have shown that rifampin can indirectly influence drug deposition through the regulation of molecular interactions of miRNA, PXR and other genes. The potential functions of miRNAs associated with rifampin- induced drug disposition are poorly understood. In this study, significantly differentially expressed miRNAs (SDEM) were extracted and used to predict the miRNA-regulated co-expression target genes (MCeTG). Additionally, a miRNA-regulated co-expressed protein interaction network (MCePIN) was constructed for SDEM by extending from the protein interaction network (PIN). The functioning of…the miRNAs were analyzed using GO analysis and KEGG pathway enrichment analysis. A total of 20 miRNAs belonging to SDEM were identified, and 632 miRNA-regulated genes were predicted. The MCePIN was constructed by extending from PIN, and 10 miRNAs and 33 genes that are relevant to 7 functions, including response to wounding, wound healing, response to drug, defense response, inflammatory response, liver development and drug metabolism, were discerned. The results provided by this study offer valuable insights into the effect of rifampin on miRNAs, genes and protein levels.
Show more
Keywords: Rifampin, miRNA, gene, hepatocyte, PPI network, P450
Abstract: Dimethylsulfide (DMS) measurements in the surface seawater of China eastern coastline were conducted during March 9–10, 1993 in Bohai Sea along the cruise from Dalian to Tianjin and during September 24–25, 1994 in Yellow Sea along the cruise from Shanghai to Qingdao. On the cruise in Bohai Sea DMS concentrations varied from 0. 11 to 2.63 nmol/L with an average of 1.31 nmol/L, while DMS flux was estimated to be 0.85 µmol/(m2 ·d) with the range of 0.04–3.12 µmol/(m2 ·d). On the cruise in Yellow Sea DMS concentrations varied from 0.95 to 7.48 nmol/L with an average of 2.89 nmol/L,…and DMS flux was estimated to be 7.94 µmol/(m2 ·d) with the range of 0.11–18.88 µmol/(m2 ·d). Variations in DMS concentrations along the latitude in Yellow Sea were observed larger than those along the longitude in Bohai Sea. DMS concentrations and fluxes had a similar spatial trend both in Bohai Sea and Yellow Sea with the correlation coefficients of 0.75 and 0.64, respectively.
Show more
Keywords: dimethylsulfide, sea-to-air flux, China Bohai Sea, China Yellow Sea