Academic Journal of Computing & Information Science最新文献

{"title":"Method of rectal tumor segmentation based on ResUnet++","authors":"","doi":"10.25236/ajcis.2023.060801","DOIUrl":"https://doi.org/10.25236/ajcis.2023.060801","url":null,"abstract":"Rectal cancer is one of the most common malignant tumors. Electronic cross section examination (CT) is used as a screening tool in the diagnosis of rectal cancer. The application of computer aided diagnosis technology to help doctors distinguish between benign and malignant tumors in rectal CT images is of great significance to guide further clinical treatment. In this paper, we analyze the performance of the current mainstream neural network models using the rectal tumor data set from the 7th Teddy Cup Data Mining Challenge B. Among them, ResUnet ++ achieves Dice value of 83.32% and IoU value of 70.06%, which is the best performance among mainstream models.","PeriodicalId":387664,"journal":{"name":"Academic Journal of Computing & Information Science","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135749925","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction of Air Quality in the Beijing-Tianjin-Hebei Region Based on LSTM Model","authors":"","doi":"10.25236/ajcis.2023.061017","DOIUrl":"https://doi.org/10.25236/ajcis.2023.061017","url":null,"abstract":"The air environment plays a vital role in human life and is closely related to the soundness of the ecosystem and the safety of human life, and good air quality is one of the prerequisites for the sustainable development of cities and society. In this paper, the Beijing-Tianjin-Hebei region is selected as the research object to explore the regional air quality characteristics, predict air quality changes, and seek scientific and effective methods and suggestions to improve air quality. In this paper, an air quality prediction model based on the long- and Long Short-Term Memory Networks (LSTM) is established by using the daily average AQI data of six cities in the Beijing-Tianjin-Hebei region for a total of 1,953 days from January 1, 2018, to April 30, 2023, respectively. Finally, the established model was evaluated using several evaluation metrics such as root mean square error (RMSE). The results show that the LSTM-based neural network can predict the AQI more accurately, which provides a scientific and reasonable theoretical basis and prediction method for the environmental protection and related decision-making of governmental departments.","PeriodicalId":387664,"journal":{"name":"Academic Journal of Computing & Information Science","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135157271","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Analysis of Forecasting Stock Prices Using CNN Model","authors":"","doi":"10.25236/ajcis.2023.061012","DOIUrl":"https://doi.org/10.25236/ajcis.2023.061012","url":null,"abstract":"Creating a trading strategy and selecting the ideal time to purchase or sell stocks depends in large part on stock price expectations. This paper provides a CNN-based stock price time series forecasting method, which proves the optimality of the model by comparing the accuracy of different models, which provides a possible direction for the exploration of stock price forecasting. This paper first introduces the working principle of CNN, LSTM, and Conv1D, and then experiments are carried out by establishing a model, and finally the relevant conclusions are obtained. The experimental results show that the Trainscore RMSE, Train MAE, Testscore RMSE, Test MAE, and MAE of CNN has a smaller size. Thus, in comparison to the LSTM and Conv1D-LSTM, CNN is the model with the best efficiency and greatest accuracy in forecasting, which is more suitable for investors to predict future stock prices than LSTM and Conv1D-LSTM.","PeriodicalId":387664,"journal":{"name":"Academic Journal of Computing & Information Science","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135157615","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ARIMA time series based logistics route cargo volume forecasting research","authors":"","doi":"10.25236/ajcis.2023.060812","DOIUrl":"https://doi.org/10.25236/ajcis.2023.060812","url":null,"abstract":"In a commercial logistics network, logistics sites and logistics routes are the key links that make up the logistics transportation process. Therefore, accurate prediction of cargo volume of each logistics site and route is essential to improve logistics operation efficiency, reduce costs, and ensure smooth logistics transportation. In order to predict the cargo volume of logistics routes, the historical cargo volume data of the three routes to be predicted are firstly compiled, and the data are analyzed by using ARIMA time series due to the time-series nature of the data. Since the data are smoothed in the second-order difference, the optimal parameter values are calculated after the second-order difference, and the ARIMA(1,2,3) time series prediction model is established to predict the cargo volume data of the three routes from 2023-1-1 to 2023-1-31.","PeriodicalId":387664,"journal":{"name":"Academic Journal of Computing & Information Science","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135749028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Intelligent Facial Palsy Diagnostic System Based on Acupoint Identification","authors":"","doi":"10.25236/ajcis.2023.060912","DOIUrl":"https://doi.org/10.25236/ajcis.2023.060912","url":null,"abstract":"The methods for clinically diagnosing facial paralysis require doctors to possess a high degree of experience and specialized knowledge, often involving subjectivity. However, due to the uneven distribution of medical resources, many facial paralysis patients are unable to receive timely and accurate diagnosis and treatment. Traditional computer-assisted methods place high demands on hardware equipment and lack sufficient intelligence. With the continuous advancement of artificial intelligence, researchers have actively explored intelligent methods for facial paralysis detection. These methods mainly focus on extracting facial features and making judgments based on facial asymmetry, but they struggle to provide a scientific quantitative analysis of the severity of facial paralysis. This study is based on the lightweight network—MobileNetV2. By performing facial detection and processing on input images, it successfully identifies three groups of acupoints related to facial paralysis and conducts quantitative analysis based on this identification. Simultaneously, we have improved the network by constructing a two-stage network similar to object detection and regression, and optimizing the loss function. In the end, we compared the improved model with other mainstream frameworks through experiments. The results demonstrate that our proposed model achieves significant effectiveness in acupoint recognition and maintains low error in quantitative analysis.","PeriodicalId":387664,"journal":{"name":"Academic Journal of Computing & Information Science","volume":"250 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135750223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Ship course change control based on humanoid intelligent control","authors":"","doi":"10.25236/ajcis.2023.060913","DOIUrl":"https://doi.org/10.25236/ajcis.2023.060913","url":null,"abstract":"A ship heading intelligent control algorithm is designed in this paper. First, ship heading control objective is proposed by input of control rudder angle and output of ship heading; Then, according to the deviation trend of ship heading output and its ideal trajectory, information about course deviation and its rate is extracted; Finally, to achieve ship heading control, rudder angle control strategy is enactmented under specific state by adopting human thinking, reasoning and control strategy. The simulation is executed with MATLAB software, and the results show that the controllerwhich is stability has strong robustness.","PeriodicalId":387664,"journal":{"name":"Academic Journal of Computing & Information Science","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135750225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Forecast of O2O Coupon Consumption Based on XGBoost Model","authors":"","doi":"10.25236/ajcis.2023.060820","DOIUrl":"https://doi.org/10.25236/ajcis.2023.060820","url":null,"abstract":"A precise delivery of coupon is an important way to engage existing customers or attract new ones to physical stores in O2O marketing approach. And a suitable strategy of coupon distribution can significantly heighten the user experience and facilitate coupon re-consumption. In this paper, we design a prediction model of O2O coupon usage based on XGBoost and compare the performance of XGBoost with another model based on the average AUC value. By contrast, the XGBoost performs better than the other model with 0.9584 average AUC value. So this model can help merchants to locate the target accurately.","PeriodicalId":387664,"journal":{"name":"Academic Journal of Computing & Information Science","volume":"280 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135750940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Innovative PolSAR Image Classification Method Based on Non-Negative Constraints Stacked Sparse Autoencoder Network with Multi-Features Joint Representation Learning","authors":"","doi":"10.25236/ajcis.2023.060815","DOIUrl":"https://doi.org/10.25236/ajcis.2023.060815","url":null,"abstract":"This paper proposed a framework based on joint multi-feature representation learning to reduce the inherent speckle phenomenon in Polarimetric Synthetic Aperture Radar (PolSAR) images interfere with the scattering characteristics of land objects. Firstly, the corresponding 6-dimensional real vector is obtained from the covariance matrix of PolSAR data and combined with the polarized feature vector obtained by the polarization decomposition method to improve the differentiation ability of similar features in images. Secondly, the stacked sparse autoencoder (SSAE) is employed, where the non-negative constraint method is incorporated to make the sparse features in the depth space robust by filtering the weights. Finally, a non-negative constrained SSAE model is proposed to effectively accomplish the classification task of PolSAR images. In the experiments, the proposed classification network is trained layer by layer using unlabeled data, the softmax classifier is trained with a small number of labeled pixels. The parameters obtained from the above steps are used as initial parameters to train the entire classification framework with labeled pixels, the resulting well-trained model is used to predict the labels corresponding to pixels in the datasets. Through experiments using the Flevoland and San Francisco Bay datasets, the results demonstrate that the proposed method yields superior classification results compared with traditional SVM, AE, and Gray Level Co-generation Matrix (GLCM) classification methods.","PeriodicalId":387664,"journal":{"name":"Academic Journal of Computing & Information Science","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135749043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Prediction Based on Convolutional Neural Networks and Vision Transformer for GOES-XRS Solar Flare Time Series","authors":"","doi":"10.25236/ajcis.2023.060819","DOIUrl":"https://doi.org/10.25236/ajcis.2023.060819","url":null,"abstract":"Solar flare is a type of solar activity that occurs at active regions at the surface of the sun. The emission of solar flares has numerous consequences, including the dis- turbances of magnetic fields, disruptions from energetic particles, and geomagnetic explosions. All those consequences have numerous impacts on human civilization, including the degradation of communication systems, power grids, space navigation, and even natural disasters. Thus, those minor or catastrophic consequences are al- ways threatening to the normal operation of society and decision-makers of those systems always seek a precise and accurate prediction of hazardous solar flares. This paper aims to develop a forecast model that can accurately decide whether solar flares would happen in the future. The data is extracted from the NOAA (National Oceanic and Atmospheric Administration) GOES-16 X-Ray Sensor that monitors solar activity by measuring the flux intensity of X-Ray. The original data is in the form of time series. Markov Transition Field is applied to the time series data, transforming the data into the form of 3-dimensional images. Therefore, the data undergone pre-processing could be applied to computer vision models. The aim of these models is to accurately recognize the Markov Transition Field images that symbolize there would be solar flare emission one hour later through a binary classification. Deep learning architects are the major components to accomplish this forecast task. Convolutional Neural Network (CNN) is a common approach in doing clas- sification tasks, which is also frequently used in recent studies that aim to predict flare emission through X-Ray images of the active regions. There are several classic CNN undergone training and testing, including LeNet-5, AlexNet, VGGNet 16 and 19, and ResNet-18, that utilizes the residue block structure. These CNN architects provide fascinating reliability and accuracy in this prediction task of solar flares, with multiple structures providing accuracy greater than 80%. Furthermore, Vision Transformer, a deep learning architect also used in classification based on trans- former structure is applied to the flare task. It is comprised of the core structure of multiple-head self-attention, residue blocks, layer normalization, and multilayer perceptron. Vision Transformer has shown outstanding accuracy (89.89%) while making predictions of solar flare emissions.","PeriodicalId":387664,"journal":{"name":"Academic Journal of Computing & Information Science","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135749354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Short-Term Wind Power Prediction Model Based on Similar Historical Meteorological Data and WNN-HHO-BP Neural Network","authors":"","doi":"10.25236/ajcis.2023.060910","DOIUrl":"https://doi.org/10.25236/ajcis.2023.060910","url":null,"abstract":"A short-term wind power prediction model based on similar historical meteorological data and WNN-HHO-BP neural network is proposed. Firstly, K-means clustering is used to classify the daily meteorological data into three classes as well as wavelet decomposition to decompose the data. Then, a BP neural network with Harris Hawk optimization algorithm and a BP neural network only are used for short-term prediction of wind power, and finally, the prediction results are derived and compared.","PeriodicalId":387664,"journal":{"name":"Academic Journal of Computing & Information Science","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135750227","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}