Qingquan Hu, Ping Liu, Jinfeng Yang
Vol. 19, No. 5, pp. 563-575, Oct. 2023
Keywords: Gauss Pseudospectral Optimization, Terminal Constraints, Trajectory Planning, UAV
Show / Hide AbstractTrajectory planning is a key technology for unmanned aerial vehicles (UAVs) to achieve complex flight missions. In this paper, a terminal constraints conversion-based Gauss pseudospectral trajectory planning optimization method is proposed. Firstly, the UAV trajectory planning mathematical model is established with considering the boundary conditions and dynamic constraints of UAV. Then, a terminal constraint handling strategy is presented to tackle terminal constraints by introducing new penalty parameters so as to improve the performance index. Combined with Gauss-Legendre collocation discretization, the improved Gauss pseudospectral method is given in detail. Finally, simulation tests are carried out on a four-quadrotor UAV model with different terminal constraints to verify the performance of the proposed method. Test studies indicate that the proposed method performances well in handling complex terminal constraints and the improvements are efficient to obtain better performance indexes when compared with the traditional Gauss pseudospectral method.
Guohui Fan, Chen Guo
Vol. 19, No. 5, pp. 576-589, Oct. 2023
Keywords: Interior Design, Location-Based Social Network, Personalized Recommendation
Show / Hide AbstractTo upgrade home style recommendations and user satisfaction, this paper proposes a personalized and optimized recommendation algorithm for interior design style based on local social network, which includes data acquisition by three-dimensional (3D) model, home-style feature definition, and style association mining. Through the analysis of user behaviors, the user interest model is established accordingly. Combined with the location-based social network of association rule mining algorithm, the association analysis of the 3D model dataset of interior design style is carried out, so as to get relevant home-style recommendations. The experimental results show that the proposed algorithm can complete effective analysis of 3D interior home style with the recommendation accuracy of 82% and the recommendation time of 1.1 minutes, which indicates excellent application effect.
Vol. 19, No. 5, pp. 590-601, Oct. 2023
Keywords: Electronic Resources, Internet, Sharing Strategy, University Books
Show / Hide AbstractUniversity books are an important information resource. University book resources can be shared not only in the traditional paper form, but also electronic form under the background of the Internet. In order to better manage the sharing of electronic book resources in universities, this study put forward three resource sharing strategies: centralized sharing strategy, distributed sharing strategy, and centralized-distributed sharing strategy by analyzing the combined development of books and the Internet as well as the significance and development of book resource sharing. The centralized sharing strategy, however simple, was difficult to handle large traffic; while the resource nodes were independent and self-consistent, the distributed sharing strategy was not easy to find and had a high repetition rate. Combining the advantages of both strategies, the centralized-distributed sharing strategy was more suitable for the heterogeneous form of university book sharing. Finally, a teaching resources sharing platform for university libraries was designed based on the strategy of centralized and distributed sharing, and three interfaces including platform login, resource search, and resource release were displayed. The results of the simulated comparison experiment showed that centralized and distributed sharing strategies had limitations in resource searching and had low efficiencies; the efficiency of the centralized strategy reduced with an increase in search subjects; however, the centralized-distributed sharing strategy was able to search more resources efficiently and main stability.
A Brief Survey into the Field of Automatic Image Dataset Generation through Web Scraping and Query ExpansionBart Dikmans, Dongwann Kang
Vol. 19, No. 5, pp. 602-613, Oct. 2023
Keywords: Image Dataset Generation, Query Expansion, Web Scraping
Show / Hide AbstractHigh-quality image datasets are in high demand for various applications. With many online sources providing manually collected datasets, a persisting challenge is to fully automate the dataset collection process. In this study, we surveyed an automatic image dataset generation field through analyzing a collection of existing studies. Moreover, we examined fields that are closely related to automated dataset generation, such as query expansion, web scraping, and dataset quality. We assess how both noise and regional search engine differences can be addressed using an automated search query expansion focused on hypernyms, allowing for user-specific manual query expansion. Combining these aspects provides an outline of how a modern web scraping application can produce large-scale image datasets.
Yuanhang Jin, Maolin Xu, Jiayuan Zheng
Vol. 19, No. 5, pp. 614-630, Oct. 2023
Keywords: Dead Tree, Deep Learning, MobileNetV3, Object Detection, Yolov4
Show / Hide AbstractDead trees significantly impact forest production and the ecological environment and pose constraints to the sustainable development of forests. A lightweight YOLOv4 dead tree detection algorithm based on unmanned aerial vehicle images is proposed to address current limitations in dead tree detection that rely mainly on inefficient, unsafe and easy-to-miss manual inspections. An improved logarithmic transformation method was developed in data pre-processing to display tree features in the shadows. For the model structure, the original CSPDarkNet-53 backbone feature extraction network was replaced by MobileNetV3. Some of the standard convolutional blocks in the original extraction network were replaced by depthwise separable convolution blocks. The new ReLU6 activation function replaced the original LeakyReLU activation function to make the network more robust for low-precision computations. The K-means++ clustering method was also integrated to generate anchor boxes that are more suitable for the dataset. The experimental results show that the improved algorithm achieved an accuracy of 97.33%, higher than other methods. The detection speed of the proposed approach is higher than that of YOLOv4, improving the efficiency and accuracy of the detection process.
Research on Keyword-Overlap Similarity Algorithm Optimization in Short English Text Based onLexical Chunk TheoryNa Li, Cheng Li, Honglie Zhang
Vol. 19, No. 5, pp. 631-640, Oct. 2023
Keywords: Keyword Overlap, Lexical Chunk Theory, Short English Text, Similarity Algorithm
Show / Hide AbstractShort-text similarity calculation is one of the hot issues in natural language processing research. The conventional keyword-overlap similarity algorithms merely consider the lexical item information and neglect the effect of the word order. And some of its optimized algorithms combine the word order, but the weights are hard to be determined. In the paper, viewing the keyword-overlap similarity algorithm, the short English text similarity algorithm based on lexical chunk theory (LC-SETSA) is proposed, which introduces the lexical chunk theory existing in cognitive psychology category into the short English text similarity calculation for the first time. The lexical chunks are applied to segment short English texts, and the segmentation results demonstrate the semantic connotation and the fixed word order of the lexical chunks, and then the overlap similarity of the lexical chunks is calculated accordingly. Finally, the comparative experiments are carried out, and the experimental results prove that the proposed algorithm of the paper is feasible, stable, and effective to a large extent.
Sanggeon Yun, Seungshik Kang, Hyeokman Kim
Vol. 19, No. 5, pp. 641-651, Oct. 2023
Keywords: BERT Embedding Model, Gender Bias, Hate Speech Detection, Logistics Ensemble
Show / Hide AbstractMalicious hate speech and gender bias comments are common in online communities, causing social problems in our society. Gender bias and hate speech detection has been investigated. However, it is difficult because there are diverse ways to express them in words. To solve this problem, we attempted to detect malicious comments in a Korean hate speech dataset constructed in 2020. We explored bidirectional encoder representations from transformers (BERT)-based deep learning models utilizing hyperparameter tuning, data sampling, and logits ensembles with a label distribution. We evaluated our model in Kaggle competitions for gender bias, general bias, and hate speech detection. For gender bias detection, an F1-score of 0.7711 was achieved using an ensemble of the Soongsil-BERT and KcELECTRA models. The general bias task included the gender bias task, and the ensemble model achieved the best F1-score of 0.7166.
Vol. 19, No. 5, pp. 652-662, Oct. 2023
Keywords: Ensemble Tree Model, Gradient Boosting Decision Tree, Gene Selection, ID3, Random Forest
Show / Hide AbstractIdentifying highly discriminating genes is a critical step in tumor recognition tasks based on microarray gene expression profile data and machine learning. Gene selection based on tree models has been the subject of several studies. However, these methods are based on a single-tree model, often not robust to ultra-highdimensional microarray datasets, resulting in the loss of useful information and unsatisfactory classification accuracy. Motivated by the limitations of single-tree-based gene selection, in this study, ensemble gene selection methods based on multiple-tree models were studied to improve the classification performance of tumor identification. Specifically, we selected the three most representative tree models: ID3, random forest, and gradient boosting decision tree. Each tree model selects top-n genes from the microarray dataset based on its intrinsic mechanism. Subsequently, three ensemble gene selection methods were investigated, namely multipletree model intersection, multiple-tree module union, and multiple-tree module cross-union, were investigated. Experimental results on five benchmark public microarray gene expression datasets proved that the multiple tree module union is significantly superior to gene selection based on a single tree model and other competitive gene selection methods in classification accuracy.
Jianing Shen, Rong Li
Vol. 19, No. 5, pp. 663-672, Oct. 2023
Keywords: BDD100K Dataset, cycleGAN, image enhancement, Style Transfer Model, Vehicle Detection at Night, YOLOv5s Network
Show / Hide AbstractMost vehicle detection methods have poor vehicle feature extraction performance at night, and their robustness is reduced; hence, this study proposes a night vehicle detection method based on style transfer image enhancement. First, a style transfer model is constructed using cycle generative adversarial networks (cycleGANs). The daytime data in the BDD100K dataset were converted into nighttime data to form a style dataset. The dataset was then divided using its labels. Finally, based on a YOLOv5s network, a nighttime vehicle image is detected for the reliable recognition of vehicle information in a complex environment. The experimental results of the proposed method based on the BDD100K dataset show that the transferred night vehicle images are clear and meet the requirements. The precision, recall, mAP@.5, and mAP@.5:.95 reached 0.696, 0.292, 0.761, and 0.454, respectively.
Jinyong Hwang, You-Rak Choi, Tae-Jin Park, Ji-Hoon Bae
Vol. 19, No. 5, pp. 673-687, Oct. 2023
Keywords: Artificial intelligence, Deep Learning, Ensemble, feature fusion, Transfer Learning
Show / Hide AbstractConvolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyper-parameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.
Vol. 19, No. 5, pp. 688-701, Oct. 2023
Keywords: Big data, BiLSTM, CNN, Feature selection, Network intrusion detection
Show / Hide AbstractThe conventional methods of network intrusion detection system (NIDS) cannot measure the trend of intrusiondetection targets effectively, which lead to low detection accuracy. In this study, a NIDS method which based on a deep neural network in a big-data environment is proposed. Firstly, the entire framework of the NIDS model is constructed in two stages. Feature reduction and anomaly probability output are used at the core of the two stages. Subsequently, a convolutional neural network, which encompasses a down sampling layer and a characteristic extractor consist of a convolution layer, the correlation of inputs is realized by introducing bidirectional long short-term memory. Finally, after the convolution layer, a pooling layer is added to sample the required features according to different sampling rules, which promotes the overall performance of the NIDS model. The proposed NIDS method and three other methods are compared, and it is broken down under the conditions of the two databases through simulation experiments. The results demonstrate that the proposed model is superior to the other three methods of NIDS in two databases, in terms of precision, accuracy, F1- score, and recall, which are 91.64%, 93.35%, 92.25%, and 91.87%, respectively. The proposed algorithm is significant for improving the accuracy of NIDS.
Junrui Han, Yongfei Ye
Vol. 19, No. 5, pp. 702-712, Oct. 2023
Keywords: load balancing, Session Sharing, Educational Administration, Reverse Proxy
Show / Hide AbstractLoad balancing plays a crucial role in ensuring the stable operation of information management systems during periods of high user access requests; therefore, load balancing approaches should be reasonably selected. Moreover, appropriate load balancing techniques could also result in an appropriate allocation of system resources, improved system service, and economic benefits. Nginx is one of the most widely used loadbalancing software packages, and its deployment is representative of load-balancing application research. This study introduces Nginx into an educational administration system, builds a server cluster, and compares and sets the optimal cluster working strategy based on the characteristics of the system, Furthermore, it increases the stability of the system when user access is highly concurrent and uses the Nginx reverse proxy service function to improve the cluster’s ability to resist illegal attacks. Finally, through concurrent access verification, the system cluster construction becomes stable and reliable, which significantly improves the performance of the information system service. This research could inform the selection and application of load-balancing software in information system services.