Search

Hypoxia contributes significantly to the development of chemoresistance of many malignancies including esophageal cancer (EC). Accumulating studies have indicated that long non-coding RNAs play important roles in chemotherapy resistance. Here, we identified a novel lncRNA-EMS/miR-758-3p/WTAP axis that was involved in hypoxia-mediated chemoresistance to cisplatin in human EC. Hypoxia induced the expressions of lncRNA EMS and WTAP, and reduced the expression of miR-758-3p in EC cell line ECA-109. In addition, the expressions of EMS and WTAP were required for the hypoxia-induced drug resistance to cisplatin in EC cells, while overexpression of miR-758-3p reversed such chemoresistance. The targeting relationships between EMS and miR-758-3p, as well as miR-758-3p and WTAP, were verified by luciferase-based reporter assays and multiple quantitative assays after gene overexpression/knockdown. Moreover, we found significant correlations between tumor expressions of these molecules. Notably, higher levels of EMS/WTAP, or lower levels of miR-758-3p in tumors predicted worse survivals of EC patients. Furthermore, in a xenograft mouse model, targeted knockdown of EMS and WTAP in ECA-109 cells markedly attenuated the resistance of tumors to cisplatin treatments. Our study uncovers a critical lncRNA-EMS/miR-758-3p/WTAP axis in regulating hypoxia-mediated drug resistance to cisplatin in EC.

Aim To investigate what cell death mode is dominat in non-small cell lung cancer (NSCLC) tissue and cell line, and the role played byMDM2-p53 pathway in the transition of pyroptosis to apoptosis during chemotherapy Materials and Methods Patients with NSCLC were consecutively recruited in Gansu Provincial Hospital from December 2016 to January 2018. The protein expressions of GSDMD, GSDME, and MDM2 were compared between cancer and adjacent tissues in NSCLC patients, as well as between normal human respiratory epithelium HBE cells and A549 carcinoma cells. A549 and HBE cells were treated with Nutlin-3 to inhibit the MDM2 function in the presence of 5-Fluorouracil (5-FU). Results Both GSDMD and GSDME were expressed in NSCLC tissues, while only GSDME was expressed in A549 and HBE cells. The execution effective N-terminal of GSDME, but not of GSDMD was expressed in NSCLC tissue, and A549 and HBE cells after chemotherapeutic drug treatments. GSDME overexpression in both A549 and HBE cells increased pyroptosis. The expression of MDM2 measured by IHC was significantly higher in cancer tissues. Nutlin-3, a specific inhibitor of MDM2 binding to P53, significantly decreased the total cell survival rate and pyroptosis, but increased apoptosis in A549 cells treated with 5-FU. Nutlin-3 did not show any effect on HBE cells. Conclusions GSDME expression in the lung carcinoma determines pyroptosis sensitivity and the occurrence of severe side effects. MDM2 inhibition shifts pyroptosis to apoptosis, which may be useful in increasing the anti-tumor effects and preventing pyroptosis-induced side effects in lung cancer chemotherapy.

As a kind of time series, the export volume of foreign trade has the characteristics of randomness, complexity, strong nonlinearity and noise, so it is difficult to describe it by using the traditional time series model algorithm. Support vector neural network (SVNN) has many unique advantages in solving small sample, nonlinear and high-dimensional pattern recognition problems. This paper uses the method of support vector neural network to predict and analyze China's foreign trade export and uses principal component analysis and regression analysis to analyze the contribution rate of different influencing factors to foreign trade export. The results show that:(1) the contribution rate of domestic economic factors to China's foreign trade export is the largest, reaching 59.65%, which also reflects the necessity and correctness of China's insistence on supply-side reform. (2) The nonlinear prediction results of the support vector neural network have a good fitting with the actual value of China's foreign trade export, and the prediction error of the support vector neural network is controlled within 10%, showing a good prediction effect; (3) neural network method has good modeling and generalization ability for nonstationary small sample import and export time series data and can achieve high prediction accuracy and decision judgment accuracy, especially for the prediction of its development trend, and the model has a high degree of fitting.

With the frequent occurrence of natural disasters, timely warning of flood disasters has become an issue of concern. This research mainly discusses flood disaster risk assessment based on random forest algorithm. This study uses the special functions of GIS to collect, manage, and analyze data to propose a method of flood disaster risk assessment based on GIS. This method is based on the characteristics of natural disaster-causing factors in the study area, selects an appropriate grid size, and finally realizes the function of visual expression of regional disaster risk. First, use ArcGIS10.1 to analyze and integrate each hazard factor into the flood disaster report index model. Second, the random forest algorithm is used as the weight of each parameter of the flood disaster index model. Finally, use ArcGIS spatial analysis tool map algebra function to model, carry out flood risk assessment in different periods, and use spatial analysis function to extract the median value to point function to extract the flood inundation depth of the study area in a specific scenario. In the experimental part, this research uses layer overlay to determine the number and types of affected areas. Using the natural break point method of ArcGIS 10.1 platform, the study area is divided according to the magnitude of the flood disaster risk value. At the same time, there are a total of 85 samples that have experienced flood disasters, of which only six have been misjudged as no flood disasters. Generally speaking, the model prediction accuracy is high. The research results show that the combination of random forest algorithm and GIS technology is convenient for analyzing the spatial pattern and internal laws of flood risk, and has good applicability.

Aiming at the problem that blog texts are the streaming data captured by different acquisition modality, each kind of which has its particular quality evaluation mode, this paper proposes a text quality evaluation (TQA) model based on 3D CNN correlated with blog text data. In order to achieve accurate TQA value, the model adopted a Bi-LSTM-based architecture to process video-related blog text as auxiliary part to provide additional information for our TQA architecture. First, the auxiliary part constructs feature vector for each video-related text by the model originating from Bi-LSTM and Seq2Seq. Then, the feature vector was feed to a well-trained decoder to reconstruct the original input data. Then, the feature vector complied with the blog textual data are inputted into end-to-end TQA modal based on the 3D CNN straightly. Comprehensive experimental results on the blog text/video dataset from the well-known truism website “ http://www.mafengwo.cn/ ” have shown that the proposed model reflects the subjective quality of online texts more accurately, and has better overall blog TQA assessment performance than the other state-of-the-art non-reference methods.

For the problems of inconsistent sample duration and unbalance of sample categories in the speech emotion corpus, this paper proposes a speech emotion recognition model based on Bi-GRU (Bidirection Gated Recurrent Unit) and Focal Loss. The model has been improved on the basis of learning CRNN (Convolutional Recurrent Neural Network) deeply. In CRNN, Bi-GRU is used to effectively lengthen the samples of the speech with short duration, and Focal Loss function is used to deal with the difficulties in classification caused by the imbalance of emotional categories of the samples. Through different methods for experimental comparison, weighted average recall (WAR), unweighted average recall (UAR) and confusion matrix (CM) are used as evaluation index of the algorithm. The experimental results show that the speech emotion recognition model proposed in this paper improves the recognition accuracy and the imbalance of IEMOCAP database samples, and can effectively prove that the improvement of speech emotion recognition performance is not due to the adjustment of model parameters or the change of the model topology.

The efficient biological signal processing method can effectively improve the efficiency of researchers to explore the work of life mechanism, so as to better reveal the relationship between physiological structure and function, thus promoting the generation of major biological discoveries; high-precision medical signal analysis strategy can, to a certain extent, share the pressure of doctors’ clinical diagnosis and assist them to formulate more favorable plans for disease prevention and treatment, so as to alleviate patients’ physical and mental pain and improve the overall health level of the society. This article in biomedical signal is very representative of the two types of signals: mammary gland molybdenum target X-ray image (mammography) and the EEG signal as the research object, combined with the deep learning field of CNN; the most representative model is two kinds of biomedical signal classification, and reconstruction methods conducted a series of research: (1) a new classification method of breast masses based on multi-layer CNN is proposed. The method includes a CNN feature representation network for breast masses and a feature decision mechanism that simulates the physician’s diagnosis process. By comparing with the objective classification accuracy of other methods for the identification of benign and malignant breast masses, the method achieved the highest classification accuracy of 97.0% under different values of c and gamma, which further verified the effectiveness of the proposed method in the identification of breast masses based on molybdenum target X-ray images. (2) An EEG signal classification method based on spatiotemporal fusion CNN is proposed. This method includes a multi-channel input classification network focusing on spatial information of EEG signals, a single-channel input classification network focusing on temporal information of EEG signals, and a spatial-temporal fusion strategy. Through comparative experiments on EEG signal classification tasks, the effectiveness of the proposed method was verified from the aspects of objective classification accuracy, number of model parameters, and subjective evaluation of CNN feature representation validity. It can be seen that the method proposed in this paper not only has high accuracy, but also can be well applied to the classification and reconstruction of biomedical signals.

The emergence of the Internet has brought great convenience to people, changing the way of life in many fields, such as food, clothing, housing and transportation. With the increasing popularity of the Internet and the rapid development of network technology, the Internet has become the main communication tool and information sharing channel for people. Network users bring not only convenience but also great challenges to network. The purpose is to study the practicability of statistical protocol recognition methods in network environment and to develop new solutions based on the existing protocol recognition methods. Based on the method step by step to study the identification of a complex application (CA) problems, usability issues, put forward the solution, and the solution of complex application, puts forward a set of perfect CA identification and analysis framework, greatly improved the accuracy and efficiency of complex application, to more than 80%. While promoting the development of recognition technology, it solves problems and finally implements a recognition and analysis system for complex applications. The complex private network mining technology proposed in this paper solves many difficulties and challenges of CA identification and analysis in network environment and can effectively improve the network management capability of network operators.

Purpose Esophageal cancer is a highly lethal and broad-spreading malignant tumor worldwide. Exosome-carrying lncRNAs play an essential role in the pathogenesis of various cancers. Results The results revealed that the expression of UCA1 was decreased in esophageal cancer tissues and plasma exosomes. UCA1 was enriched in exosomes, and exosomal UCA1 was a promising biomarker for the diagnosis of esophageal cancer with 86.7% sensitivity and 70.2% specificity. Overexpression of UCA1 played anticancer roles in esophageal cancer cells through inhibiting cell proliferation, invasion and migration, and colony formation. Also, exosomal UCA1 was taken up by esophageal cancer cells and inhibited the progression of esophageal cancer in vitro and tumor growth in vivo. Furthermore, exosomal UCA1 could directly target miRNA-613 in esophageal cancer cells. Conclusions The results suggested that exosomal UCA1 inhibits tumorigenesis and progression of esophageal cancer in vitro and in vivo, and might be a promising biomarker for esophageal cancer. Patient and methods In this study, we determined the expression of UCA1 in esophageal cancer tissues, plasma exosomes of patients with esophageal cancer. We determined the potential of exosomal UCA1 as a biomarker and its effect on the pathogenesis and progression of esophageal cancer in vitro and in vivo.

With the leaps and bounds of computer performance and the advent of the era of big data, deep learning has drawn more and more attention from all walks of life. It can combine low-level features to form more abstract high-level features and describe the data more essentially. Therefore, it is widely used in various fields such as computer vision. Image segmentation is one of the most basic research topics in the field of computer vision. The main purpose is to extract regions of interest from images for later image processing research. In 3D reconstruction based on sequence images, the segmentation accuracy and speed of sequence images determine the quality and efficiency of target reconstruction. Therefore, when facing large-scale sequence images, the biggest problem is how to improve the segmentation speed while ensuring accuracy. Based on the above background, the research content of this article is an indoor scene segmentation algorithm based on full convolutional neural network. According to the characteristics of indoor application scenes, this paper proposes a fast convolutional neural network image segmentation method to segment the indoor scene image and construct the fast fully convolutional networks (FFCN) for indoor scene image segmentation uses inter-layer fusion to reduce the amount of network calculation parameters and avoid the loss of picture feature information by continuous convolution. In order to verify the effectiveness of the network, in this paper, a basic living object data set (XAUT data set) in an indoor environment is created. The XAUT data set is used to train the FFCN network under the Caffe framework to obtain an indoor scene segmentation model. In order to compare the effectiveness of the model, the structure of the worn FCN8s, FCN16s, and FCN32s models was fine-tuned, and the corresponding algorithm model for indoor scene segmentation was obtained by training with the XAUT data set. The experimental results show that the pixel recognition accuracy of all types of networks has reached 86%, and the mean IU ratio has reached more than 63%. The mean IU of the FCN8s network is the highest at 70.38%, but its segmentation speed is only 1/5 of FFCN. On the premise that other types of indicators are not much different, the average segmentation speed on FFCN fast segmentation convolutional neural network reaches 40 fps. It can be seen that the scale fusion technology can well avoid the loss of image feature information in the network convolution and reddening process. Compared with other FCN networks, it has a faster speed and is conducive to real-time image preprocessing.

Mucin 13 (MUC13) is a glycoprotein that is expressed on the cell surface and participates in the tumorigenesis of multiple malignancies, including pancreatic cancer, colorectal cancer and renal cancer. However, to the best of our knowledge, the expression levels and function of MUC13 in lung cancer progression have not yet been demonstrated. Therefore, the present study examined the expression pattern and regulatory role of MUC13 in lung cancer tumorigenesis. The results demonstrated that MUC13 was highly expressed in lung cancer tissues and cell lines compared with that in normal tissues and cell lines. Functionally, knockdown of MUC13 inhibited cell proliferation and enhanced the apoptosis of A549 and NCI-H1650 lung cancer cells. Furthermore, silencing of MUC13 suppressed the migration and invasion of lung cancer cells. Additionally, a xenograft tumor model demonstrated that knockdown of MUC13 delayed the development of the lung cancer xenograft and suppressed the expression of proliferation marker Ki-67 in tumor tissues. Mechanistically, MUC13 activated the ERK signaling pathway by enhancing the phosphorylation of ERK, JNK and p38 in lung cancer tissues compared with that in normal tissues. Knockdown of MUC13 inhibited the phosphorylation of ERK/JNK/p38 in A549 and NCI-H1650 cells. Overall, these findings suggested that MUC13 could act as an oncogenic glycoprotein to accelerate the progression of lung cancer via abnormal activation of the ERK/JNK/p38 signaling pathway and might serve as a therapeutic target for lung cancer treatment.

Aim This study aimed to assess the clinical effectiveness of video-assisted thoracoscopic surgery (VATS) in early-stage lung cancer by indocyanine green (ICG) for tumor mapping. Material and methods Thirty patients with early-stage lung cancer with peripheral nodules smaller than 2 cm scheduled for computed tomography (CT)-guided microcoil placement followed by ICG tumor mapping by VATS wedge resection were enrolled. After microcoil deployment, 100 to 150 ml of diluted ICG was injected percutaneously near the nodule. The nodule initially was localized solely by using a near-infrared ray (NIR) thoracoscope to visualize ICG fluorescence. Thoracoscopic instruments were used to determine the staple line. Wedge resection was performed after confirmation of the location of the microcoil using fluoroscopy and pathology results. Results Thirty patients underwent VATS resection. The median tumor size was 1.3 cm by CT. The median depth from the pleural surface was 1.7 cm (range: 0.5-3.8 cm). The median CT-guided intervention time was 25 min, and VATS procedural time was 50 min. ICG fluorescence was clearly identified in 30 of 30 patients (100%). The surgical margins were all negative on final pathology in all included cases. The final diagnoses were 30 primary lung cancers; none needed additional resection. Conclusions CT-guided percutaneous ICG injection and intraoperative NIR localization of small nodules are safe and feasible. These offer surgeons the ease of localization through direct indocyanine green fluorescence imaging without the use of fluoroscopy and may be a complementary technique to preoperative microcoil placement for nonvisible, nonpalpable intrapulmonary nodules.

To compare the efficacy of omentoplasty with non-omentoplasty in the prevention of postoperative anastomotic leakage, and to investigate the safety of omentoplasty. Literature searches were performed of the Medline, EMBASE, and Cochrane Library databases. Studies that compared the efficacy of omentoplasty and non-omentoplasty after esophagectomy were selected. A meta-analysis was performed on anastomotic leakage, anastomotic stenosis, hospital mortality, and length of hospital stay. Results were reported as odds ratio (OR), weighted mean difference (WMD), or relative risk (RR), with 95% confidence intervals. Six studies involving a total of 1608 patients met inclusion criteria. Compared with the non-omentoplasty group, the incidence of anastomotic leakage in the omentoplasty group (OR, 0.37; 95% CI, 0.23–0.60; P

Let M = (V(M), E(M)) be a simple graph with finite vertices and edges. An N-covering of M is a family {N1, N2, ... , Nα} of subgraphs of M isomorphic to N such that every edge in E(M) belongs to Nl, for some l, l ∈ {1, 2, ... , α}. Such a graph is a (c, d)-N-antimagic if ∃ a bijection ψ : VM ∪EM → {1, 2, ... , |VM|+|EM|} such that for all Nl ≅ N, {wtψ(Nl)} = {c, c+d, ... , c+(α-1)d}. For ψ(V(M)) = {1, 2, 3, ... , |V(M)|}, the labeling ψ would be super (c, d)-N-antimagic and for d = 0 it would be N-supermagic. In this manuscript, we investigated that mCn-path has super (c, d)-Cn-antimagic labeling for differences d ∈ {0, 1, ... , 5} and extend the result for Cn-supermagic labeling of disjoint union of isomorphic copies of mCn-path.

In the process of carrying out quality-oriented education and promoting the reform of new curriculum, many teachers began to reform traditional teaching ideas and teaching models on the basis and premise of students' ability, combined with the practical conditions of professional curriculum teaching, and encouraged students to have an objective understanding of the study of professional courses in the process of autonomous learning and practical research, so as to realize the steady improvement of individual learning ability and learning level. But the long-term examination-oriented education leads teachers to ignore the subjective guidance to students in teaching practice, which seriously constrains students' individualized growth and development. Nowadays, the pressure of employment competition is increasing, teachers need to cultivate students' ability. As the starting point and foothold, the theoretical analysis and practical research are integrated into the subject teaching link, paying attention to the students' main position, and giving students more opportunities for independent performance. Based on the analysis of human resource management major of South China Business College of Guangdong University of Foreign Studies, this paper puts forward the teaching reform requirements and strategies based on the cultivation of practical ability, which can provide some reference for the improvement of teaching quality and level of this major.

The reasonable allocation and use of human resources is an important content in the process of complex system analysis and design. This paper studies the human resource allocation model of Petri net based on artificial intelligence and neural network. In this paper, combined with the characteristics of human resource scheduling, human resource mobility, concurrency, and obvious classification characteristics, the human resource allocation model based on Petri net is implemented. In this paper, the model is trained with the python version of human resource analysis data set. The training parameters are 100, the error coefficient is 0.001, and the learning speed is 0.01. First, the coding rules of human resource data are established. Then, the parameters are input into the model, and the human resource data are trained in the model. Finally, the results of the model output layer are analyzed. The research study shows that the average prediction accuracy of this model is 78.85%. Model training requires the addition of 25 neurons for every 0.01 increase to improve the accuracy of predicting dynamic data of human resources. If the accuracy rate exceeds 75%, the increase in the number of neurons cannot be compensated for by the increase in the accuracy rate, but it is most efficient when the amount of data for human resource scheduling is 2000 to 4000. Therefore, this system can effectively allocate small- and medium-sized human resources and has a high accuracy.

Face detection is to detect the face from the original image, which is the basis of face recognition technology. Face is a kind of natural structural object with quite complex details, which will be challenges to this kind of recognition. Face has the variability of pattern because of the different appearance, expression and skin color, and in general, there may be appendages such as glasses, beard and so on. Face image as a three-dimensional object has shadows caused by light also unavoidable. In this paper, the most mainstream Harr feature classifier algorithm is used, innovatively propose non-human rejection algorithm to reduce the impact of complex environment on detection results and improve detection accuracy.

ViBe algorithm is an efficient pixel level video background modeling algorithm. Aiming at the problem of ghost and dynamic background false detection in traditional ViBe algorithm, an improved algorithm based on improved ViBe algorithm is proposed. Firstly, the initial background model and the background update algorithm of three frame difference are constructed based on the time information to solve the problem of ghost elimination in the ViBe algorithm. Aiming at the problem of false detection in the process of dynamic background detection in the ViBe algorithm, an adaptive threshold dynamic background motion detection algorithm combined with the three frame difference method is proposed, Three frame difference method is used to determine the dynamic interference area, and adaptive threshold motion detection is used to detect the dynamic interference area. The algorithm can quickly remove ghosts and reduce the probability of false detection in dynamic background. Experimental results show that the algorithm is effective and robust.

BACKGROUND Germline mutations of BRCA2 have been reported in various malignancies. We investigated BRCA2 germline mutations in familial clusters with esophageal squamous cell carcinoma (ESCC). MATERIAL AND METHODS We screened the DNA of familial ESCC patients for BRCA2 germline mutations with whole gene sequencing. Multiple BRCA2 mutations including one novel splice variant, c.426-2A>G were identified. Other family members, sporadic ESCC patients, and controls were also assessed for the novel mutation. RESULTS The mutation c.426-2A>G was found in 2 affected ESCC sisters and 7 other family members. The splice variant mutation results in exon 5 skipping with a frame shift leading to a premature stop codon in exon 6 and truncation. Novel mutation tracking ruled out single nucleotide polymorphism (SNP) in 100 chromosomes of healthy individuals. CONCLUSIONS BRCA2 germline mutation in ESCC patients may play a role in genetic susceptibility to familial ESCC. Genetic analysis of BRCA2 in patients with familial ESCC could provide opportunities for targeted therapies.

Due to the small number of scientific research evaluation indicators of college teachers, the mathematical model of evaluation is uncertain and the subjective process of the evaluation process is too strong, this paper proposes a model of university teachers’ scientific research performance evaluation based on machine learning. The evaluation model uses the neighborhood rough set to reduce the index of the evaluation index and form the decision table as the input data of the support vector machine algorithm, which reduces the dimension of the sample data and improves the training speed of the evaluation model. The particle swarm optimization algorithm is used to optimize the parameter search of the support vector machine algorithm, which improves the prediction accuracy of the evaluation model. Finally, the feasibility and practicability of the scientific research performance evaluation model based on machine learning are proved through experiments.

The present work aims to study how deep learning approaches solve the safety problems in the interaction between autonomous vehicles and pedestrians. A Vehicle-Pedestrian Detection (VPD) algorithm based on Convolutional Neural Network (CNN) is proposed regarding the massive amounts of parameters during feature extraction of traditional vehicle–pedestrian interaction algorithms. Furthermore, the Squeezenet algorithm is applied to extract traffic characteristics with fewer parameters. The performance of the proposed algorithm is analyzed through simulation experiments. Results demonstrate that when the successful transmission probability reaches 100% and the λ value is 0.01–0.05, the proposed algorithm can provide the result closest to the actual value, with the smallest data delay and the highest data transmission security. In different categories, the proposed algorithm can provide the highest accuracy as the number of iterations increases compared with other algorithms (AlexNet, DenseNet, VGGNet, IGCNet, and ResNet), which can accurately forecast traffic safety accidents. The proposed algorithm can provide an accuracy of 81.98%, an improvement of at least 1.94% over other advanced CNNs, and at least 3.3% over algorithms included in comparative simulations. Hence, it can recognize and identify safe interactions between autonomous vehicles and pedestrians. Through experiments, the constructed algorithm can significantly reduce the data transmission delay, improve the prediction accuracy of the safe interaction between autonomous vehicles and pedestrians, and increase the recognition accuracy remarkably, which can provide experimental references for the intelligent development of the transportation industry in the future.

Emotion Model is the basis of facial expression recognition system. The constructed emotional model should not only match facial expressions with emotions, but also reflect the location relationship between different emotions. In this way, it is easy to understand the current emotion of an individual through the analysis of the acquired facial expression information. This paper constructs an improved three-dimensional model for emotion based on fuzzy theory, which corresponds to the facial features to emotions based on the basic emotions proposed by Ekman. What’s more, the three-dimensional model for motion is able to divide every emotion into three different groups which can show the positional relationship visually and quantitatively and at the same time determine the degree of emotion based on fuzzy theory.

Short Retraction Notice The authors claim that this paper needs modifications. This article has been retracted to straighten the academic record. In making this decision the Editorial Board follows COPE's Retraction Guidelines. The aim is to promote the circulation of scientific research by offering an ideal research publication platform with due consideration of internationally accepted standards on publication ethics. The Editorial Board would like to extend its sincere apologies for any inconvenience this retraction may have caused. Editor guiding this retraction: Prof. Baozong Yuan(EiC of JSIP) The full retraction notice in PDF is preceding the original paper, which is marked "RETRACTED".

In view of the problems existing in the traditional professional curriculum system at colleges and universities to cultivate applied undergraduate talents in computer software, this paper, following the concept of “demand-oriented, ability as the core, integration of science and engineering as well as theories and application” and on the basis of deep school-enterprise cooperation, integration of industry and teaching, proposes the “four-connection” professional curriculum system to cultivate applied undergraduate software talents: connecting ability cultivation with the demands for software positions, connecting the curriculum contents with software standard, connecting teaching with development, and connecting incubation projects with the industrial market. And this paper also proposes four measures to guarantee the construction of school-enterprise cooperation: the supporting platform, teaching team, teaching resources and quality guarantee system.

Collaborative filtering algorithm is the most widely used and recommended algorithm in major e-commerce recommendation systems nowadays. Concerning the problems such as poor adaptability and cold start of traditional collaborative filtering algorithms, this paper is going to come up with improvements and construct a hybrid collaborative filtering algorithm model which will possess excellent scalability. Meanwhile, this paper will also optimize the process based on the parameter selection of genetic algorithm and demonstrate its pseudocode reference so as to provide new ideas and methods for the study of parameter combination optimization in hybrid collaborative filtering algorithm.