教学课程资源库 更多>>

关键词： Africa   Botswana   cartography   climate   computer science   data science   drought   GMT   mapping   programming  

摘要： This articles presents a new series of maps showing the climate and environmental variability of Botswana. Situated in southern Africa, Botswana has an arid to semi-arid climate, which significantly varies in its different regions: Kalahari Desert, Makgadikgadi Pan and Okavango Delta. While desert regions are prone to droughts and periods of extreme heat during the summer months, other regions experience heavy downpours, as well as episodic and unpredictable rains that affect agricultural activities. Such climatic variations affect social and economic aspects of life in Botswana. This study aimed to visualise the non-linear correlations between the topography and climate setting at the country's scale. Variables included T degrees C min, T degrees C max, precipitation, soil moisture, evapotranspiration (PET and AET), downward surface shortwave radiation, vapour pressure and vapour pressure deficit (VPD), wind speed and Palmer Drought Severity Index (PDSI). The dataset was taken from the TerraClimate source and GEBCO for topographic mapping. The mapping approach included the use of Generic Mapping Tools (GMT), a console-based scripting toolset, which enables the use of a scripting method of automated mapping. Several GMT modules were used to derive a set of climate parameters for Botswana. The data were supplemented with the adjusted cartographic elements and inspected by the Geospatial Data Abstraction Library (GDAL). The PDSI in Botswana in 2018 shows stepwise variation with seven areas of drought: (1) -3.7 to -2.2. (extreme);(2) -2.2 to -0.8 (strong, southern Kalahari);(3) -0.8 to 0.7 (significant, central Kalahari;(4) 0.7 to 2.1 (moderate);(5) 2.1 to 3.5 (lesser);(6) 3.5 to 4.9 (low);(7) 4.9 to 6.4 (least). The VPD has a general trend towards the south-western region (Kalahari Desert, up to 3.3), while it is lower in the north-eastern region of Botswana (up to 1.4). Other values vary respectively, as demonstrated in the presented 12 maps of climate and environmen

关键词： Learning systems   Training   Task analysis   Computer architecture   Knowledge engineering   Computer science   Unsupervised learning   Broad learning system (BLS)   classification   feature learning   regression   research review   semisupervised learning (SSL)   unsupervised learning  

摘要： In recent years, the appearance of the broad learning system (BLS) is poised to revolutionize conventional artificial intelligence methods. It represents a step toward building more efficient and effective machine-learning methods that can be extended to a broader range of necessary research fields. In this survey, we provide a comprehensive overview of the BLS in data mining and neural networks for the first time, focusing on summarizing various BLS methods from the aspects of its algorithms, theories, applications, and future open research questions. First, we introduce the basic pattern of BLS manifestation, the universal approximation capability, and essence from the theoretical perspective. Furthermore, we focus on BLS's various improvements based on the current state of the theoretical research, which further improves its flexibility, stability, and accuracy under general or specific conditions, including classification, regression, semisupervised, and unsupervised tasks. Due to its remarkable efficiency, impressive generalization performance, and easy extendibility, BLS has been applied in different domains. Next, we illustrate BLS's practical advances, such as computer vision, biomedical engineering, control, and natural language processing. Finally, the future open research problems and promising directions for BLSs are pointed out.

关键词： Feature extraction   Training   Optimization   Support vector machines   Task analysis   Computer science   Computational modeling   Feature selection   generalization ability   joint learning   minimax optimization   unselected features  

摘要： Feature selection aims to select strongly relevant features and discard the rest. Recently, embedded feature selection methods, which incorporate feature weights learning into the training process of a classifier, have attracted much attention. However, traditional embedded methods merely focus on the combinatorial optimality of all selected features. They sometimes select the weakly relevant features with satisfactory combination abilities and leave out some strongly relevant features, thereby degrading the generalization performance. To address this issue, we propose a novel embedded framework for feature selection, termed feature selection boosted by unselected features (FSBUF). Specifically, we introduce an extra classifier for unselected features into the traditional embedded model and jointly learn the feature weights to maximize the classification loss of unselected features. As a result, the extra classifier recycles the unselected strongly relevant features to replace the weakly relevant features in the selected feature subset. Our final objective can be formulated as a minimax optimization problem, and we design an effective gradient-based algorithm to solve it. Furthermore, we theoretically prove that the proposed FSBUF is able to improve the generalization ability of traditional embedded feature selection methods. Extensive experiments on synthetic and real-world data sets exhibit the comprehensibility and superior performance of FSBUF.

关键词： Optimization   Search problems   Convergence   Space exploration   Linear programming   Dimensionality reduction   Computer science   Competitive swarm optimizer (CSO)   large-scale optimization   multiobjective optimization  

摘要： Competitive swarm optimizers (CSOs) have shown very promising search efficiency in large-scale decision space. However, they face difficulties when solving large-scale multi-/many-objective optimization problems (LMOPs), as their winner particles are selected by random pairwise competition based on only a single evaluation criterion, which does not provide diverse guidance for LMOPs. To alleviate this issue, this article proposes a comprehensive competitive learning (CCL) strategy for CSOs using three competition mechanisms to guide the particle search. Specifically, environmental competition classifies winner and loser particles from the swarm, while cognitive competition and social competition select one winner particle as the cognitive component and the social component, respectively, to guide the search for loser particles. This competitive learning strategy aims to enhance the search capability of loser particles and provides diverse search directions for solving LMOPs. When compared with eight competitive optimizers, the experimental results validate the high efficiency and effectiveness of our method in solving nine LMOPs with 2-10 objectives and 100-5000 variables.

关键词： Channelized 'a' (a)over-bar lava flow   Forest interaction   Tree molds   Cooling rates   Phenocrysts  

摘要： Forest destruction by 'a'(a) over bar lava flow is common. However, mechanical and thermal interactions between the invading lava and the invaded forest are poorly constrained. We complete mapping, thermal image and sample analyses of a channel-fed 'a'(a) over bar lava flow system that invaded forest on the NE flank of Mt. Etna (Italy) in 2002. These lava flows destroyed 231,000 trees, only 2% of which are still visible as felled trunks on the levees or at the channel-levee contact. The remaining 98% were first felled by the flow front, with the trunks then buried by the flow. Rare tree molds can be found at the rubble levee base where trees were buried by avalanching hot breccia and then burnt through, with a time scale for total combustion being a few days. Protruding trunks fell away from the flow, if felled by blocks avalanching down the levee flank, or became aligned with the flow if falling onto the moving stream. Estimated cooling rates (0.1-5.5 degrees C km(-1)) are normal for well-insulated 'a'(a) over bar flow, suggesting no thermal interaction. We find the highest phenocryst concentrations (of 50-60%, above an expected value of 30-40%) in low velocity (<0.5 m s(-1)) locations. These low velocity zones are also characterized by high trunk concentrations. Thus, the common factor behind crystal and trunk deposition is velocity. That is, when the lava slows down, crystal settling occurs and trunks are preferentially deposited. Thus, although we find no thermal or textural effects due to the presence of the forest, we do find mechanical and environmental interactions where the trees are consumed to become part of the flow.

关键词： Computational science   Computer science  

摘要： Interest in autonomous vehicles (AVs) is growing at a rapid pace due to increased convenience, safety benefits and potential environmental gains. Although several leading AV companies predicted that AVs would be on the road by 2020, they are still limited to relatively small-scale trials. The ability to know their precise location on the map is a challenging prerequisite for safe and reliable AVs due to sensor imperfections under adverse environmental and weather conditions, posing a formidable obstacle to their widespread use. Here we propose a deep learning-based self-supervised approach for ego-motion estimation that is a robust and complementary localization solution under inclement weather conditions. The proposed approach is a geometry-aware method that attentively fuses the rich representation capability of visual sensors and the weather-immune features provided by radars using an attention-based learning technique. Our method predicts reliability masks for the sensor measurements, eliminating the deficiencies in the multimodal data. In various experiments we demonstrate the robust all-weather performance and effective cross-domain generalizability under harsh weather conditions such as rain, fog and snow, as well as day and night conditions. Furthermore, we employ a game-theoretic approach to analyse the interpretability of the model predictions, illustrating the independent and uncorrelated failure modes of the multimodal system. We anticipate our work will bring AVs one step closer to safe and reliable all-weather autonomous driving. Changing weather conditions pose a challenge for autonomous vehicles. Almalioglu and colleagues use a geometry-aware learning technique that fuses visual, lidar and radar information, such that the benefits of each can be used under different weather conditions.

关键词： Bibliometrics   conference names   entity resolution   record linkage  

摘要： Conferences play a major role in some disciplines such as computer science and are often used in research quality evaluation exercises. Differently from journals and books, for which ISSN and ISBN codes provide unambiguous keys, recognizing the conference series in which a paper was published is a rather complex endeavor: There is no unique code assigned to conferences, and the way their names are written may greatly vary across years and catalogs. In this article, we propose a technique for the entity resolution of conferences based on the analysis of different semantic parts of their names. We present the results of an investigation of our technique on a dataset of 42,395 distinct computer science conference names excerpted from the DBLP computer science repository,(1) which we automatically link to different authority files. With suitable data cleaning, the precision of our record linkage algorithm can be as high as 94%. A comparison with results obtainable using state-of-the-art general-purpose record linkage algorithms rounds off the article, showing that our ad hoc solution largely outperforms them in terms of the quality of the results.

关键词： 过程性考核   计算机专业   数据库  

摘要： 职业教育作为类型教育应当注重学生能力的培养和综合素养的提升，过程性考核推进了职业教育向类型教育转化的步伐，是职业教育内涵式发展的必由之路。文章从分析传统考核方式存在的问题入手，以使用的网络学习平台为载体，深入挖掘平台功能，结合计算机专业固有特点，详细设计了数据库课程过程考核方案，并且提出过程性考核实施的保障举措，即建设网络化课程体系、设置多元评价方案、规划能力本位考核内容等，以确保过程性考核顺利进行。

摘要： This study presents an automated bibliometric analysis of 6569 research papers published in thirteen Brazilian Computer Science Society (SBC) conferences from 1999 to 2021. Our primary goal was to gather data to understand the gender representation in publications in the field of Computer Science. We applied a systematic assignment of gender to 23.573 listed papers authorships, finding that the gender gap for women is significant, with female authors being under-represented in all years of the study. © 2022, CC BY.