摘要 :
This article is an exposition of a recent study on automatic generation of a structured overview (SOV) over a very large corpus of documents, where an SOV is organized as sections and subsections according to the latent hierarchy ...
展开
This article is an exposition of a recent study on automatic generation of a structured overview (SOV) over a very large corpus of documents, where an SOV is organized as sections and subsections according to the latent hierarchy of topics contained in the documents. We present a new framework called AutoOverview that includes and extends our previous scheme called NDORGS (best paper runner-up in ACM DocEng'2019) [47]. Different from the standard NLP task of generating a coherent summary typically over a handful of documents, AutoOverview needs to balance between two competitive objectives of accuracy and efficiency over thousands of documents. It incorporates hierarchical topic clustering, single-document summarization, multiple-document summarization, title generation, and other text mining techniques into a single platform. To assess the quality of an SOV generated over many documents, while it is possible to rely on human annota-tors to judge its readability, the sheer size of the inputs would make it formidable for human judges to determine if an SOV has covered all major points contained in the original texts. To overcome this obstacle, we present a text mining mechanism to evaluate topic coverage of the SOV against the topics contained in the original documents. We use multi-attribute decision making to help determine a suitable suite of algorithms to implement AutoOverview and the values of parameters for achieving a satisfactory SOV with respect to both accuracy and efficiency. We use NDORGS as an implementation example to address these issues and present evaluation results over a corpus of over 2,000 classified news articles and a corpus of over 5,000 unclassified news articles in a span of 10 years obtained from a search of the same keyword.
收起
摘要 :
This article is an exposition of a recent study on automatic generation of a structured overview (SOV) over a very large corpus of documents, where an SOV is organized as sections and subsections according to the latent hierarchy ...
展开
This article is an exposition of a recent study on automatic generation of a structured overview (SOV) over a very large corpus of documents, where an SOV is organized as sections and subsections according to the latent hierarchy of topics contained in the documents. We present a new framework called AutoOverview that includes and extends our previous scheme called NDORGS (best paper runner-up in ACM DocEng'2019) [47]. Different from the standard NLP task of generating a coherent summary typically over a handful of documents, AutoOverview needs to balance between two competitive objectives of accuracy and efficiency over thousands of documents. It incorporates hierarchical topic clustering, single-document summarization, multiple-document summarization, title generation, and other text mining techniques into a single platform. To assess the quality of an SOV generated over many documents, while it is possible to rely on human annota-tors to judge its readability, the sheer size of the inputs would make it formidable for human judges to determine if an SOV has covered all major points contained in the original texts. To overcome this obstacle, we present a text mining mechanism to evaluate topic coverage of the SOV against the topics contained in the original documents. We use multi-attribute decision making to help determine a suitable suite of algorithms to implement AutoOverview and the values of parameters for achieving a satisfactory SOV with respect to both accuracy and efficiency. We use NDORGS as an implementation example to address these issues and present evaluation results over a corpus of over 2,000 classified news articles and a corpus of over 5,000 unclassified news articles in a span of 10 years obtained from a search of the same keyword.
收起
摘要 :
Visual saliency has recently attracted lots of research interest in the computer vision community. In this paper, we propose a novel computational model for bottom-up saliency detection based on manifold learning. A typical graph-...
展开
Visual saliency has recently attracted lots of research interest in the computer vision community. In this paper, we propose a novel computational model for bottom-up saliency detection based on manifold learning. A typical graph-based manifold learning algorithm, namely the diffusion map, is adopted for establishing our saliency model. In the proposed method, firstly, a graph is constructed using low-level image features. Then, the diffusion map algorithm is performed to learn the diffusion distances, which are utilized to derive the saliency measure. Compared to existing saliency models, our method has the advantage of being able to capture the intrinsic nonlinear structures in the original feature space. Moreover, due to the inherent characteristics of the diffusion map algorithm, our method can deal with the multi-scale issue effectively, which is crucial to any saliency model. Experimental results on publicly available data demonstrate that our method outperforms the state-of-the-art saliency models, both qualitatively and quantitatively.
收起
摘要 :
Aiming at the problems of the current agricultural crusher device with winding shaft reamer, outputting too long material, low pulverization rate, and ineffective treatment of high humidity, this paper uses TRIZ theory to analyze ...
展开
Aiming at the problems of the current agricultural crusher device with winding shaft reamer, outputting too long material, low pulverization rate, and ineffective treatment of high humidity, this paper uses TRIZ theory to analyze the problems in the real-time feed and high-level pulverization of biomass. In TRIZ theory, analyze and find technical conflicts in innovative design by transforming general parameters. According to the analysis of the conflict resolution principle, the conflicts in the system are resolved. The material conveying module, the synchronous feed cutting module, the secondary crushing module and the power control module is innovatively proposed and put forward an "object-field model" in the process of biomass crushing, finally, complete the modelling design of the modular biomass crusher and the production of the physical prototype. Through experiments, it is concluded that the qualified rate of the modular crusher in this article can reach 88%, and the average discharge length is 6 mm. It can effectively improve the utilization of rice stalks and provide a reliable reference for follow-up research.
收起
摘要 :
To realize intelligent express delivery and unmanned automatic transportation in different environments and terrains, this paper proposes an alternate wheel-leg transport robot (AWLBOT). First, this article combines the knowledge ...
展开
To realize intelligent express delivery and unmanned automatic transportation in different environments and terrains, this paper proposes an alternate wheel-leg transport robot (AWLBOT). First, this article combines the knowledge in the field of biomimetic robot design, uses a modular design to divide the basic functions of the transportation robot into independent unit modules. Focus on the statics analysis and modal analysis of the robot support legs and the fuselage frame, verifying the rationality of the structural design and material selection. The stability analysis of the robot based on the climbing environment verifies the rationality of the robot's gait planning and the accuracy of the motion analysis. Finally, the robot designed in this paper has good flexibility, stability, and safety by comparing it with the existing ones.
收起
摘要 :
Sparse support vector machine (SVM) is a popular classification technique that can simultaneously learn a small set of the most interpretable features and identify the support vectors. It has achieved great successes in many real-...
展开
Sparse support vector machine (SVM) is a popular classification technique that can simultaneously learn a small set of the most interpretable features and identify the support vectors. It has achieved great successes in many real-world applications. However, for large-scale problems involving a huge number of samples and extremely high-dimensional features, solving sparse SVM-s remains challenging. By noting that sparse SVMs induce sparsities in both feature and sample spaces, we propose a novel approach, which is based on accurate estimations of the primal and dual optima of sparse SVMs, to simultaneously identify the features and samples that are guaranteed to be irrelevant to the outputs. Thus, we can remove the identified inactive samples and features from the training phase, leading to substantial savings in both the memory usage and computational cost without sacrificing accuracy. To the best of our knowledge, the proposed method is the first static feature and sample reduction method for sparse SVM. Experiments on both synthetic and real datasets (e.g., the kddb dataset with about 20 million samples and 30 million features) demonstrate that our approach significantly outperforms state-of-the-art methods and the speedup gained by our approach can be orders of magnitude.
收起
摘要 :
A driver’s sensitivity to speed maybe is diminished gradually because of
lack of variation in visual scenery in a long underground road and he tends to drive a
vehicle faster and follow a vehicle closer than he should do uncons...
展开
A driver’s sensitivity to speed maybe is diminished gradually because of
lack of variation in visual scenery in a long underground road and he tends to drive a
vehicle faster and follow a vehicle closer than he should do unconsciously. This paper
focuses on the mechanism of vehicle operating characteristics affected by visual
environment in urban underground road based on information load. CONTENTS: 1)
Comparing differences of vehicle velocity and headway maintaining in different road
environment; 2) Calculating driver visual information load level in diver’s vision
scene; 3) Analyzing the mechanism of driving behaviors affected by visual
environment; 4) Taking technical measures to satisfy driver visual requirements in
underground road environment. DATA: vehicle velocity, headway and diver’s vision
scene. METHODS: 1) Revealing differences of vehicle operating characteristics in
different traffic environment with naturalistic driving; 2) Studying the influence
mechanism based on theoretical calculation. 3) Proposing measures to improve urban
underground traffic security on driving simulator.
收起
摘要 :
A driver’s sensitivity to speed maybe is diminished gradually because of
lack of variation in visual scenery in a long underground road and he tends to drive a
vehicle faster and follow a vehicle closer than he should do unconsci...
展开
A driver’s sensitivity to speed maybe is diminished gradually because of
lack of variation in visual scenery in a long underground road and he tends to drive a
vehicle faster and follow a vehicle closer than he should do unconsciously. This paper
focuses on the mechanism of vehicle operating characteristics affected by visual
environment in urban underground road based on information load. CONTENTS: 1)
Comparing differences of vehicle velocity and headway maintaining in different road
environment; 2) Calculating driver visual information load level in diver’s vision
scene; 3) Analyzing the mechanism of driving behaviors affected by visual
environment; 4) Taking technical measures to satisfy driver visual requirements in
underground road environment. DATA: vehicle velocity, headway and diver’s vision
scene. METHODS: 1) Revealing differences of vehicle operating characteristics in
different traffic environment with naturalistic driving; 2) Studying the influence
mechanism based on theoretical calculation. 3) Proposing measures to improve urban
underground traffic security on driving simulator.
收起
摘要 :
Cold-formed steel framed shear wall sheathed with corrugated steel sheets is a promising shear wall system for low- and mid-rise constructions in high wind and seismic zones due to its advantages of non-combustibility, high shear ...
展开
Cold-formed steel framed shear wall sheathed with corrugated steel sheets is a promising shear wall system for low- and mid-rise constructions in high wind and seismic zones due to its advantages of non-combustibility, high shear strength, and high stiffness. However recent research projects showed that the corrugated steel sheathing demonstrated low ductility. This paper presents an experimental study aimed at improving the ductility of cold-formed steel shear walls sheathed with corrugated steel sheathing. A method of using opening in the sheathing is employed to improve the shear wall's ductility meanwhile controlling the damage locations and failure mechanism. A total of 11 sheathing configurations were investigated and 19 monotonic and cyclic full-scale shear wall tests were conducted in this project. The research discovered that with proper opening in the sheathing, the corrugated sheet shear wall can yield significantly improved ductility while maintaining high-level shear strength. Additionally, nonlinear dynamic analyses were also carried on to verify the building's seismic performance when the innovative shear wall was installed. The dynamic analyses show that the new shear wall system can greatly reduce the seismic effects and decrease the building's collapse probability.
收起
摘要 :
Cold-formed steel framed shear wall sheathed with corrugated steel sheets is a promising shear wall system for low- and mid-rise constructions in high wind and seismic zones due to its advantages of non-combustibility, high shear ...
展开
Cold-formed steel framed shear wall sheathed with corrugated steel sheets is a promising shear wall system for low- and mid-rise constructions in high wind and seismic zones due to its advantages of non-combustibility, high shear strength, and high stiffness. However recent research projects showed that the corrugated steel sheathing demonstrated low ductility. This paper presents an experimental study aimed at improving the ductility of cold-formed steel shear walls sheathed with corrugated steel sheathing. A method of using opening in the sheathing is employed to improve the shear wall's ductility meanwhile controlling the damage locations and failure mechanism. A total of 11 sheathing configurations were investigated and 19 monotonic and cyclic full-scale shear wall tests were conducted in this project. The research discovered that with proper opening in the sheathing, the corrugated sheet shear wall can yield significantly improved ductility while maintaining high-level shear strength. Additionally, nonlinear dynamic analyses were also carried on to verify the building's seismic performance when the innovative shear wall was installed. The dynamic analyses show that the new shear wall system can greatly reduce the seismic effects and decrease the building's collapse probability.
收起