A prediction model of the sum of container based on combined BP neural network and SVM

Min-jie Ding,Shao-zhong Zhang,Haidong Zhong,Yao-hui Wu,Liang-bin Zhang 한국정보처리학회 2019 Journal of information processing systems Vol.15 No.2

The prediction of the sum of container is very important in the field of container transport. Many influencingfactors can affect the prediction results. These factors are usually composed of many variables, whosecomposition is often very complex. In this paper, we use gray relational analysis to set up a proper forecastindex system for the prediction of the sum of containers in foreign trade. To address the issue of the lowaccuracy of the traditional prediction models and the problem of the difficulty of fully considering all the factorsand other issues, this paper puts forward a prediction model which is combined with a back-propagation (BP)neural networks and the support vector machine (SVM). First, it gives the prediction with the data normalizedby the BP neural network and generates a preliminary forecast data. Second, it employs SVM for the residualcorrection calculation for the results based on the preliminary data. The results of practical examples show thatthe overall relative error of the combined prediction model is no more than 1.5%, which is less than the relativeerror of the single prediction models. It is hoped that the research can provide a useful reference for theprediction of the sum of container and related studies.

A Prediction Model of the Sum of Container Based on Combined BP Neural Network and SVM

Ding, Min-jie,Zhang, Shao-zhong,Zhong, Hai-dong,Wu, Yao-hui,Zhang, Liang-bin Korea Information Processing Society 2019 Journal of information processing systems Vol.15 No.2

The prediction of the sum of container is very important in the field of container transport. Many influencing factors can affect the prediction results. These factors are usually composed of many variables, whose composition is often very complex. In this paper, we use gray relational analysis to set up a proper forecast index system for the prediction of the sum of containers in foreign trade. To address the issue of the low accuracy of the traditional prediction models and the problem of the difficulty of fully considering all the factors and other issues, this paper puts forward a prediction model which is combined with a back-propagation (BP) neural networks and the support vector machine (SVM). First, it gives the prediction with the data normalized by the BP neural network and generates a preliminary forecast data. Second, it employs SVM for the residual correction calculation for the results based on the preliminary data. The results of practical examples show that the overall relative error of the combined prediction model is no more than 1.5%, which is less than the relative error of the single prediction models. It is hoped that the research can provide a useful reference for the prediction of the sum of container and related studies.

A Resting-state Functional Magnetic Resonance Imaging Study of Whole-brain Functional Connectivity of Voxel Levels in Patients With Irritable Bowel Syndrome With Depressive Symptoms

( Jie Li ),( Ping He ),( Xingqi Lu ),( Yun Guo ),( Min Liu ),( Guoxiong Li ),( Jianping Ding ) 대한소화기기능성질환·운동학회(구 대한소화관운동학회) 2021 Journal of Neurogastroenterology and Motility (JNM Vol.27 No.2

Background/Aims Depressive symptom is one of the most common symptoms in patients with irritable bowel syndrome (IBS), but its pathogenetic mechanisms remain unclear. As a voxel-level graph theory analysis method, degree centrality (DC) can provide a new perspective for exploring the abnormalities of whole-brain functional network of IBS with depressive symptoms (DEP-IBS). Methods DC, voxel-wise image and clinical symptoms correlation and seed-based functional connectivity (FC) analyses were performed in 28 DEP-IBS patients, 21 IBS without depressive symptoms (nDEP-IBS) patients and 36 matched healthy controls (HC) to reveal the abnormalities of whole brain FC in DEP-IBS. Results Compared to nDEP-IBS patients and HC, DEP-IBS patients showed significant decrease of DC in the left insula and increase of DC in the left precentral gyrus. The DC’s z-scores of the left insula negatively correlated with depression severity in DEP-IBS patients. Compared to nDEP-IBS patients, DEP-IBS patients showed increased left insula-related FC in the left inferior parietal lobule and right inferior occipital gyrus, and decreased left insula-related FC in the left precentral gyrus, right supplementary motor area (SMA), and postcentral gyrus. In DEP-IBS patients, abstracted clusters’ mean FC in the right SMA negatively correlated with depressive symptoms. Conclusions DEP-IBS patients have abnormal FC in brain regions associated with the fronto-limbic and sensorimotor networks, especially insula and SMA, which explains the vicious circle between negative emotion and gastrointestinal symptoms in IBS. Identification of such alterations may facilitate earlier and more accurate diagnosis of depression in IBS, and development of effective treatment strategies. (J Neurogastroenterol Motil 2021;27:248-256)

Suspension Footbridge Form-Finding with Laplacian Smoothing Algorithm

Zhuo-ju Huang,Jie-min Ding,Sheng-yi Xiang 한국강구조학회 2020 International Journal of Steel Structures Vol.20 No.6

In this paper, Laplacian smoothing, which is an algorithm originally used to smooth polygon meshes in computer graphics (CG), is applied to solve a structural form-fi nding problem with the proof that the result of such algorithm is equivalent to force density method. Such CG algorithm is used on the design of a new-built suspension footbridge in Shaoxing, China and the algorithm works well. Since Laplacian smoothing is a pure geometric algorithm without any mechanical concept, the algorithm shows the inner relationship between force and shape, more structural applicable CG algorithms are expected to be found in the future.

Transmembrane Protein 166 Expression in Esophageal Squamous Cell Carcinoma in Xinjiang, China

Sun, Wei,Ma, Xiu-Min,Bai, Jing-Ping,Zhang, Guo-Qing,Zhu, Yue-Jie,Ma, Hai-Mei,Guo, Hui,Chen, Ying-Yu,Ding, Jian-Bing Asian Pacific Journal of Cancer Prevention 2012 Asian Pacific journal of cancer prevention Vol.13 No.8

Objective: Transmembrane protein 166 (TMEM166) expression in esophageal squamous cell carcinoma (ESCC) and remote normal esophageal tissues was examined to assess any role in tumour biology. Methods: TMEM166 mRNA expression in 36 cases with ESCC (36 tumour samples, 36 remote normal esophageal tissue samples) was detected by RT-PCR. TMEM166 protein expression was analysed in paraffin-embedded tissue samples from the same cases by immunohistochemistry. Results: Semi-quantitative analysis showed TMEM166 mRNA expression in ESCCs to be significantly lower than in remote normal esophageal tissues ($0.759{\pm}0.713$ vs. $2.622{\pm}1.690$, P=0.014). TMEM166 protein expression was also significantly reduced (69.4% vs. 94.4%, P<0.01). Conclusion: TMEM166 mRNA and protein expression demonstrated significant reduction in ESCCs compared with remote esophageal tissues, albeit with no correlation with tumour size, differentiation, stage, and lymph node metastasis, suggesting a role in regulating autophagic and apoptotic processes in the ESCC.

Use of an Artificial Neural Network to Construct a Model of Predicting Deep Fungal Infection in Lung Cancer Patients

Chen, Jian,Chen, Jie,Ding, Hong-Yan,Pan, Qin-Shi,Hong, Wan-Dong,Xu, Gang,Yu, Fang-You,Wang, Yu-Min Asian Pacific Journal of Cancer Prevention 2015 Asian Pacific journal of cancer prevention Vol.16 No.12

Background: The statistical methods to analyze and predict the related dangerous factors of deep fungal infection in lung cancer patients were several, such as logic regression analysis, meta-analysis, multivariate Cox proportional hazards model analysis, retrospective analysis, and so on, but the results are inconsistent. Materials and Methods: A total of 696 patients with lung cancer were enrolled. The factors were compared employing Student's t-test or the Mann-Whitney test or the Chi-square test and variables that were significantly related to the presence of deep fungal infection selected as candidates for input into the final artificial neural network analysis (ANN) model. The receiver operating characteristic (ROC) and area under curve (AUC) were used to evaluate the performance of the artificial neural network (ANN) model and logistic regression (LR) model. Results: The prevalence of deep fungal infection from lung cancer in this entire study population was 32.04%(223/696), deep fungal infections occur in sputum specimens 44.05%(200/454). The ratio of candida albicans was 86.99% (194/223) in the total fungi. It was demonstrated that older (${\geq}65$ years), use of antibiotics, low serum albumin concentrations (${\leq}37.18g/L$), radiotherapy, surgery, low hemoglobin hyperlipidemia (${\leq}93.67g/L$), long time of hospitalization (${\geq}14$days) were apt to deep fungal infection and the ANN model consisted of the seven factors. The AUC of ANN model($0.829{\pm}0.019$)was higher than that of LR model ($0.756{\pm}0.021$). Conclusions: The artificial neural network model with variables consisting of age, use of antibiotics, serum albumin concentrations, received radiotherapy, received surgery, hemoglobin, time of hospitalization should be useful for predicting the deep fungal infection in lung cancer.

Comparative Proteomic Analysis of Yak Follicular Fluid during Estrus

Guo, Xian,Pei, Jie,Ding, Xuezhi,Chu, Min,Bao, Pengjia,Wu, Xiaoyun,Liang, Chunnian,Yan, Ping Asian Australasian Association of Animal Productio 2016 Animal Bioscience Vol.29 No.9

The breeding of yaks is highly seasonal, there are many crucial proteins involved in the reproduction control program, especially in follicular development. In order to isolate differential proteins between mature and immature follicular fluid (FF) of yak, the FF from yak follicles with different sizes were sampled respectively, and two-dimensional gel electrophoresis (2-DE) of the proteins was carried out. After silver staining, the Image Master 2D platinum software was used for protein analysis and matrix-assisted laser desorption ionization time of flight mass spectrometry (MALDI-TOF-MS) was performed for differential protein identification. The expression level of transferrin and enolase superfamily member 1 (ENOSF1) was determined by Western blotting for verification analysis. The results showed that 2-DE obtained an electrophoresis map of proteins from mature and immature yak FF with high resolution and repeatability. A comparison of protein profiles identified 12 differently expressed proteins, out of which 10 of them were upregulated while 2 were downregulated. Western blotting showed that the expression of transferrin and ENOSF1 was enhanced with follicular development. Both the obtained protein profiles and the differently expressed proteins identified in this study provided experimental data related to follicular development during yak breeding seasons. This study also laid the foundation for understanding the microenvironment during oocyte development.