Incorporation of explainability features in the decision-making web-based systems is considered a primary concern to enhance accountability,transparency,and trust in the community.Multi-domain Sentiment Analysis is a ...Incorporation of explainability features in the decision-making web-based systems is considered a primary concern to enhance accountability,transparency,and trust in the community.Multi-domain Sentiment Analysis is a significant web-based system where the explainability feature is essential for achieving user satisfaction.Conventional design methodologies such as object-oriented design methodology(OODM)have been proposed for web-based application development,which facilitates code reuse,quantification,and security at the design level.However,OODM did not provide the feature of explainability in web-based decision-making systems.X-OODM modifies the OODM with added explainable models to introduce the explainability feature for such systems.This research introduces an explainable model leveraging X-OODM for designing transparent applications for multidomain sentiment analysis.The proposed design is evaluated using the design quality metrics defined for the evaluation of the X-OODM explainable model under user context.The design quality metrics,transferability,simulatability,informativeness,and decomposability were introduced one after another over time to the evaluation of the X-OODM user context.Auxiliary metrics of accessibility and algorithmic transparency were added to increase the degree of explainability for the design.The study results reveal that introducing such explainability parameters with X-OODM appropriately increases system transparency,trustworthiness,and user understanding.The experimental results validate the enhancement of decision-making for multi-domain sentiment analysis with integration at the design level of explainability.Future work can be built in this direction by extending this work to apply the proposed X-OODM framework over different datasets and sentiment analysis applications to further scrutinize its effectiveness in real-world scenarios.展开更多
Due to the small size,variety,and high degree of mixing of herbaceous vegetation,remote sensing-based identification of grassland types primarily focuses on extracting major grassland categories,lacking detailed depic...Due to the small size,variety,and high degree of mixing of herbaceous vegetation,remote sensing-based identification of grassland types primarily focuses on extracting major grassland categories,lacking detailed depiction.This limitation significantly hampers the development of effective evaluation and fine supervision for the rational utilization of grassland resources.To address this issue,this study concentrates on the representative grassland of Zhenglan Banner in Inner Mongolia as the study area.It integrates the strengths of Sentinel-1 and Sentinel-2 active-passive synergistic observations and introduces innovative object-oriented techniques for grassland type classification,thereby enhancing the accuracy and refinement of grassland classification.The results demonstrate the following:(1)To meet the supervision requirements of grassland resources,we propose a grassland type classification system based on remote sensing and the vegetation-habitat classification method,specifically applicable to natural grasslands in northern China.(2)By utilizing the high-spatial-resolution Normalized Difference Vegetation Index(NDVI)synthesized through the Spatial and Temporal Non-Local Filter-based Fusion Model(STNLFFM),we are able to capture the NDVI time profiles of grassland types,accurately extract vegetation phenological information within the year,and further enhance the temporal resolution.(3)The integration of multi-seasonal spectral,polarization,and phenological characteristics significantly improves the classification accuracy of grassland types.The overall accuracy reaches 82.61%,with a kappa coefficient of 0.79.Compared to using only multi-seasonal spectral features,the accuracy and kappa coefficient have improved by 15.94%and 0.19,respectively.Notably,the accuracy improvement of the gently sloping steppe is the highest,exceeding 38%.(4)Sandy grassland is the most widespread in the study area,and the growth season of grassland vegetation mainly occurs from May to September.The sandy meadow exhibits a longer growing season compared with typical grassland and meadow,and the distinct differences in phenological characteristics contribute to the accurate identification of various grassland types.展开更多
As one of the main geographical elements in urban areas,buildings are closely related to the development of the city.Therefore,how to quickly and accurately extract building information from remote sensing images is o...As one of the main geographical elements in urban areas,buildings are closely related to the development of the city.Therefore,how to quickly and accurately extract building information from remote sensing images is of great significance for urban map updating,urban planning and construction,etc.Extracting building information around power facilities,especially obtaining this information from high-resolution images,has become one of the current hot topics in remote sensing technology research.This study made full use of the characteristics of GF-2 satellite remote sensing images,adopted an object-oriented classification method,combined with multi-scale segmentation technology and CART classification algorithm,and successfully extracted the buildings in the study area.The research results showed that the overall classification accuracy reached 89.5%and the Kappa coefficient was 0.86.Using the object-oriented CART classification algorithm for building extraction could be closer to actual ground objects and had higher accuracy.The extraction of buildings in the city contributed to urban development planning and provided decision support for management.展开更多
Structural development defects essentially refer to code structure that violates object-oriented design principles. They make program maintenance challenging and deteriorate software quality over time. Various detecti...Structural development defects essentially refer to code structure that violates object-oriented design principles. They make program maintenance challenging and deteriorate software quality over time. Various detection approaches, ranging from traditional heuristic algorithms to machine learning methods, are used to identify these defects. Ensemble learning methods have strengthened the detection of these defects. However, existing approaches do not simultaneously exploit the capabilities of extracting relevant features from pre-trained models and the performance of neural networks for the classification task. Therefore, our goal has been to design a model that combines a pre-trained model to extract relevant features from code excerpts through transfer learning and a bagging method with a base estimator, a dense neural network, for defect classification. To achieve this, we composed multiple samples of the same size with replacements from the imbalanced dataset MLCQ1. For all the samples, we used the CodeT5-small variant to extract features and trained a bagging method with the neural network Roberta Classification Head to classify defects based on these features. We then compared this model to RandomForest, one of the ensemble methods that yields good results. Our experiments showed that the number of base estimators to use for bagging depends on the defect to be detected. Next, we observed that it was not necessary to use a data balancing technique with our model when the imbalance rate was 23%. Finally, for blob detection, RandomForest had a median MCC value of 0.36 compared to 0.12 for our method. However, our method was predominant in Long Method detection with a median MCC value of 0.53 compared to 0.42 for RandomForest. These results suggest that the performance of ensemble methods in detecting structural development defects is dependent on specific defects.展开更多
XML已成为互联网事实上的数据表示标准,在数据交换和数据仓库中广泛应用。但XML文件特征不能保障数据的安全性和并发访问,而RDBMS严谨的关系理论和技术的成熟性可以弥补XML技术的不足。结合XML与RDBMS的优点,提出一个基于RDBMS的XML数...XML已成为互联网事实上的数据表示标准,在数据交换和数据仓库中广泛应用。但XML文件特征不能保障数据的安全性和并发访问,而RDBMS严谨的关系理论和技术的成熟性可以弥补XML技术的不足。结合XML与RDBMS的优点,提出一个基于RDBMS的XML数据存取方案,用于简化XML数据的管理和数据仓库的构建。利用Oracle XML DB技术实现XML在关系数据库中存储、更新和检索操作,使用户能透明地通过RDBMS来管理XML数据,相对于映射策略的数据转储方式,明显提高了XML数据存储效率。展开更多
基金support of the Deanship of Research and Graduate Studies at Ajman University under Projects 2024-IRG-ENiT-36 and 2024-IRG-ENIT-29.
文摘Incorporation of explainability features in the decision-making web-based systems is considered a primary concern to enhance accountability,transparency,and trust in the community.Multi-domain Sentiment Analysis is a significant web-based system where the explainability feature is essential for achieving user satisfaction.Conventional design methodologies such as object-oriented design methodology(OODM)have been proposed for web-based application development,which facilitates code reuse,quantification,and security at the design level.However,OODM did not provide the feature of explainability in web-based decision-making systems.X-OODM modifies the OODM with added explainable models to introduce the explainability feature for such systems.This research introduces an explainable model leveraging X-OODM for designing transparent applications for multidomain sentiment analysis.The proposed design is evaluated using the design quality metrics defined for the evaluation of the X-OODM explainable model under user context.The design quality metrics,transferability,simulatability,informativeness,and decomposability were introduced one after another over time to the evaluation of the X-OODM user context.Auxiliary metrics of accessibility and algorithmic transparency were added to increase the degree of explainability for the design.The study results reveal that introducing such explainability parameters with X-OODM appropriately increases system transparency,trustworthiness,and user understanding.The experimental results validate the enhancement of decision-making for multi-domain sentiment analysis with integration at the design level of explainability.Future work can be built in this direction by extending this work to apply the proposed X-OODM framework over different datasets and sentiment analysis applications to further scrutinize its effectiveness in real-world scenarios.
基金supported by the National Natural Science Foundation of China[grant number 42001386,42271407]within the ESA-MOST China Dragon 5 Cooperation(ID:59313).
文摘Due to the small size,variety,and high degree of mixing of herbaceous vegetation,remote sensing-based identification of grassland types primarily focuses on extracting major grassland categories,lacking detailed depiction.This limitation significantly hampers the development of effective evaluation and fine supervision for the rational utilization of grassland resources.To address this issue,this study concentrates on the representative grassland of Zhenglan Banner in Inner Mongolia as the study area.It integrates the strengths of Sentinel-1 and Sentinel-2 active-passive synergistic observations and introduces innovative object-oriented techniques for grassland type classification,thereby enhancing the accuracy and refinement of grassland classification.The results demonstrate the following:(1)To meet the supervision requirements of grassland resources,we propose a grassland type classification system based on remote sensing and the vegetation-habitat classification method,specifically applicable to natural grasslands in northern China.(2)By utilizing the high-spatial-resolution Normalized Difference Vegetation Index(NDVI)synthesized through the Spatial and Temporal Non-Local Filter-based Fusion Model(STNLFFM),we are able to capture the NDVI time profiles of grassland types,accurately extract vegetation phenological information within the year,and further enhance the temporal resolution.(3)The integration of multi-seasonal spectral,polarization,and phenological characteristics significantly improves the classification accuracy of grassland types.The overall accuracy reaches 82.61%,with a kappa coefficient of 0.79.Compared to using only multi-seasonal spectral features,the accuracy and kappa coefficient have improved by 15.94%and 0.19,respectively.Notably,the accuracy improvement of the gently sloping steppe is the highest,exceeding 38%.(4)Sandy grassland is the most widespread in the study area,and the growth season of grassland vegetation mainly occurs from May to September.The sandy meadow exhibits a longer growing season compared with typical grassland and meadow,and the distinct differences in phenological characteristics contribute to the accurate identification of various grassland types.
基金Research on Algorithm Model for Monitoring and Evaluating Typical Disaster Situations of Electric Power Equipment Based on Remote Sensing Imaging Technology of Heaven and Earth,South Grid Guangxi Power Grid Company Science and Technology Project(GXKJXM20222160).
文摘As one of the main geographical elements in urban areas,buildings are closely related to the development of the city.Therefore,how to quickly and accurately extract building information from remote sensing images is of great significance for urban map updating,urban planning and construction,etc.Extracting building information around power facilities,especially obtaining this information from high-resolution images,has become one of the current hot topics in remote sensing technology research.This study made full use of the characteristics of GF-2 satellite remote sensing images,adopted an object-oriented classification method,combined with multi-scale segmentation technology and CART classification algorithm,and successfully extracted the buildings in the study area.The research results showed that the overall classification accuracy reached 89.5%and the Kappa coefficient was 0.86.Using the object-oriented CART classification algorithm for building extraction could be closer to actual ground objects and had higher accuracy.The extraction of buildings in the city contributed to urban development planning and provided decision support for management.
文摘Structural development defects essentially refer to code structure that violates object-oriented design principles. They make program maintenance challenging and deteriorate software quality over time. Various detection approaches, ranging from traditional heuristic algorithms to machine learning methods, are used to identify these defects. Ensemble learning methods have strengthened the detection of these defects. However, existing approaches do not simultaneously exploit the capabilities of extracting relevant features from pre-trained models and the performance of neural networks for the classification task. Therefore, our goal has been to design a model that combines a pre-trained model to extract relevant features from code excerpts through transfer learning and a bagging method with a base estimator, a dense neural network, for defect classification. To achieve this, we composed multiple samples of the same size with replacements from the imbalanced dataset MLCQ1. For all the samples, we used the CodeT5-small variant to extract features and trained a bagging method with the neural network Roberta Classification Head to classify defects based on these features. We then compared this model to RandomForest, one of the ensemble methods that yields good results. Our experiments showed that the number of base estimators to use for bagging depends on the defect to be detected. Next, we observed that it was not necessary to use a data balancing technique with our model when the imbalance rate was 23%. Finally, for blob detection, RandomForest had a median MCC value of 0.36 compared to 0.12 for our method. However, our method was predominant in Long Method detection with a median MCC value of 0.53 compared to 0.42 for RandomForest. These results suggest that the performance of ensemble methods in detecting structural development defects is dependent on specific defects.
文摘XML已成为互联网事实上的数据表示标准,在数据交换和数据仓库中广泛应用。但XML文件特征不能保障数据的安全性和并发访问,而RDBMS严谨的关系理论和技术的成熟性可以弥补XML技术的不足。结合XML与RDBMS的优点,提出一个基于RDBMS的XML数据存取方案,用于简化XML数据的管理和数据仓库的构建。利用Oracle XML DB技术实现XML在关系数据库中存储、更新和检索操作,使用户能透明地通过RDBMS来管理XML数据,相对于映射策略的数据转储方式,明显提高了XML数据存储效率。
