In software testing,the quality of test cases is crucial,but manual generation is time-consuming.Various automatic test case generation methods exist,requiring careful selection based on program features.Current evalu...In software testing,the quality of test cases is crucial,but manual generation is time-consuming.Various automatic test case generation methods exist,requiring careful selection based on program features.Current evaluation methods compare a limited set of metrics,which does not support a larger number of metrics or consider the relative importance of each metric to the final assessment.To address this,we propose an evaluation tool,the Test Case Generation Evaluator(TCGE),based on the learning to rank(L2R)algorithm.Unlike previous approaches,our method comprehensively evaluates algorithms by considering multiple metrics,resulting in a more reasoned assessment.The main principle of the TCGE is the formation of feature vectors that are of concern by the tester.Through training,the feature vectors are sorted to generate a list,with the order of the methods on the list determined according to their effectiveness on the tested assembly.We implement TCGE using three L2R algorithms:Listnet,LambdaMART,and RFLambdaMART.Evaluation employs a dataset with features of classical test case generation algorithms and three metrics—Normalized Discounted Cumulative Gain(NDCG),Mean Average Precision(MAP),and Mean Reciprocal Rank(MRR).Results demonstrate the TCGE’s superior effectiveness in evaluating test case generation algorithms compared to other methods.Among the three L2R algorithms,RFLambdaMART proves the most effective,achieving an accuracy above 96.5%,surpassing LambdaMART by 2%and Listnet by 1.5%.Consequently,the TCGE framework exhibits significant application value in the evaluation of test case generation algorithms.展开更多
Parameter inversions in oil/gas reservoirs based on well test interpretations are of great significance in oil/gas industry.Automatic well test interpretations based on artificial intelligence are the most promising t...Parameter inversions in oil/gas reservoirs based on well test interpretations are of great significance in oil/gas industry.Automatic well test interpretations based on artificial intelligence are the most promising to solve the problem of non-unique solution.In this work,a new deep reinforcement learning(DRL)based approach is proposed for automatic curve matching for well test interpretation,by using the double deep Q-network(DDQN).The DDQN algorithms are applied to train agents for automatic parameter tuning in three conventional well-testing models.In addition,to alleviate the dimensional disaster problem of parameter space,an asynchronous parameter adjustment strategy is used to train the agent.Finally,field applications are carried out by using the new DRL approaches.Results show that step number required for the DDQN to complete the curve matching is the least among,when comparing the naive deep Q-network(naive DQN)and deep Q-network(DQN).We also show that DDQN can improve the robustness of curve matching in comparison with supervised machine learning algorithms.Using DDQN algorithm to perform 100 curve matching tests on three traditional well test models,the results show that the mean relative error of the parameters is 7.58%for the homogeneous model,10.66%for the radial composite model,and 12.79%for the dual porosity model.In the actual field application,it is found that a good curve fitting can be obtained with only 30 steps of parameter adjustment.展开更多
Wheat seedling line detection is critical for precision agriculture and automatic guidance in early wheat field operation. Aiming at the complex wheat field environment, a method of detecting wheat seedling lines base...Wheat seedling line detection is critical for precision agriculture and automatic guidance in early wheat field operation. Aiming at the complex wheat field environment, a method of detecting wheat seedling lines based on deep learning was proposed in this study. Firstly, a rotated bounding box was created to improve the YOLOv3 model to predict the approximate position of the wheat seedling line;Then, according to the rotated bounding region obtained by the model, the wheat seedling line was detected by fitting the extracted center points. Finally, a comprehensive evaluation method combining angle error and distance error was proposed to evaluate the accuracy of the extracted crop line. By testing images of wheat seedlings in different environments, the results showed that the mean angle error and distance error respectively reached 0.75° and 10.84 pixels while the mean running time was 63.83 ms for a 1920×1080 pixels image. And compared to the original model the improved algorithm model improved the mAP value by 13.2%. The angle error and the distance error of the improved algorithm model were reduced by 51.4% and 39.7%, respectively. The method proposed in this study can accurately detect the wheat seedling lines at different stages and it is also suitable for the environments with weeds, shadow, bright light, and dark light. At the same time, it has a certain adaptability to wheat seedling images with a yaw angle in the shooting process. The research results could provide a reference for the automatic guidance of early wheat field machinery.展开更多
目的探讨医学汉语进阶学习与评测设计在来华医学留学生医学汉语水平考试(Medical Chinese Test,MCT)实践中的应用效果。方法2022年9月—2023年7月,以2018级秋季5~8班130名医学留学生为教学研究对象,通过问卷调查评估留学生医学汉语的学...目的探讨医学汉语进阶学习与评测设计在来华医学留学生医学汉语水平考试(Medical Chinese Test,MCT)实践中的应用效果。方法2022年9月—2023年7月,以2018级秋季5~8班130名医学留学生为教学研究对象,通过问卷调查评估留学生医学汉语的学习和测评应采用从低阶中介语至高阶单语的模式,以配合双语学习者的渐进过程。结果该套学习与测评框架让学习者对源语言理解、中介语言解码、目标语言考核评测结果、学习者双语能力与专业知识学习方面均有提升。观察组学生自学能力、学习兴趣、进阶效果满意度分别为84.6%、83.1%、86.2%,观察组对该套医学汉语进阶学习与评测设计框架整体认可度高。结论该医学汉语进阶学习与评测设计框架在医学汉语学习与评测中有很好的教学效果。展开更多
文摘In software testing,the quality of test cases is crucial,but manual generation is time-consuming.Various automatic test case generation methods exist,requiring careful selection based on program features.Current evaluation methods compare a limited set of metrics,which does not support a larger number of metrics or consider the relative importance of each metric to the final assessment.To address this,we propose an evaluation tool,the Test Case Generation Evaluator(TCGE),based on the learning to rank(L2R)algorithm.Unlike previous approaches,our method comprehensively evaluates algorithms by considering multiple metrics,resulting in a more reasoned assessment.The main principle of the TCGE is the formation of feature vectors that are of concern by the tester.Through training,the feature vectors are sorted to generate a list,with the order of the methods on the list determined according to their effectiveness on the tested assembly.We implement TCGE using three L2R algorithms:Listnet,LambdaMART,and RFLambdaMART.Evaluation employs a dataset with features of classical test case generation algorithms and three metrics—Normalized Discounted Cumulative Gain(NDCG),Mean Average Precision(MAP),and Mean Reciprocal Rank(MRR).Results demonstrate the TCGE’s superior effectiveness in evaluating test case generation algorithms compared to other methods.Among the three L2R algorithms,RFLambdaMART proves the most effective,achieving an accuracy above 96.5%,surpassing LambdaMART by 2%and Listnet by 1.5%.Consequently,the TCGE framework exhibits significant application value in the evaluation of test case generation algorithms.
基金funding support from National Natural Science Foundation of China(52074322)Beijing Natural Science Foundation(3204052)+1 种基金Science Foundation of China University of Petroleum,Beijing(No.2462018YJRC032)National Major Project of China(2017ZX05030002-005)。
文摘Parameter inversions in oil/gas reservoirs based on well test interpretations are of great significance in oil/gas industry.Automatic well test interpretations based on artificial intelligence are the most promising to solve the problem of non-unique solution.In this work,a new deep reinforcement learning(DRL)based approach is proposed for automatic curve matching for well test interpretation,by using the double deep Q-network(DDQN).The DDQN algorithms are applied to train agents for automatic parameter tuning in three conventional well-testing models.In addition,to alleviate the dimensional disaster problem of parameter space,an asynchronous parameter adjustment strategy is used to train the agent.Finally,field applications are carried out by using the new DRL approaches.Results show that step number required for the DDQN to complete the curve matching is the least among,when comparing the naive deep Q-network(naive DQN)and deep Q-network(DQN).We also show that DDQN can improve the robustness of curve matching in comparison with supervised machine learning algorithms.Using DDQN algorithm to perform 100 curve matching tests on three traditional well test models,the results show that the mean relative error of the parameters is 7.58%for the homogeneous model,10.66%for the radial composite model,and 12.79%for the dual porosity model.In the actual field application,it is found that a good curve fitting can be obtained with only 30 steps of parameter adjustment.
基金funded by the Natural Science Foundation of Shandong Province (Grant No. ZR2021MF096)Shandong Agricultural Machinery Equipment Research and Development Innovation Plan (Grant No. 2018YF009).
文摘Wheat seedling line detection is critical for precision agriculture and automatic guidance in early wheat field operation. Aiming at the complex wheat field environment, a method of detecting wheat seedling lines based on deep learning was proposed in this study. Firstly, a rotated bounding box was created to improve the YOLOv3 model to predict the approximate position of the wheat seedling line;Then, according to the rotated bounding region obtained by the model, the wheat seedling line was detected by fitting the extracted center points. Finally, a comprehensive evaluation method combining angle error and distance error was proposed to evaluate the accuracy of the extracted crop line. By testing images of wheat seedlings in different environments, the results showed that the mean angle error and distance error respectively reached 0.75° and 10.84 pixels while the mean running time was 63.83 ms for a 1920×1080 pixels image. And compared to the original model the improved algorithm model improved the mAP value by 13.2%. The angle error and the distance error of the improved algorithm model were reduced by 51.4% and 39.7%, respectively. The method proposed in this study can accurately detect the wheat seedling lines at different stages and it is also suitable for the environments with weeds, shadow, bright light, and dark light. At the same time, it has a certain adaptability to wheat seedling images with a yaw angle in the shooting process. The research results could provide a reference for the automatic guidance of early wheat field machinery.
文摘目的探讨医学汉语进阶学习与评测设计在来华医学留学生医学汉语水平考试(Medical Chinese Test,MCT)实践中的应用效果。方法2022年9月—2023年7月,以2018级秋季5~8班130名医学留学生为教学研究对象,通过问卷调查评估留学生医学汉语的学习和测评应采用从低阶中介语至高阶单语的模式,以配合双语学习者的渐进过程。结果该套学习与测评框架让学习者对源语言理解、中介语言解码、目标语言考核评测结果、学习者双语能力与专业知识学习方面均有提升。观察组学生自学能力、学习兴趣、进阶效果满意度分别为84.6%、83.1%、86.2%,观察组对该套医学汉语进阶学习与评测设计框架整体认可度高。结论该医学汉语进阶学习与评测设计框架在医学汉语学习与评测中有很好的教学效果。
