Search

Automatic related work generation is a new challenge in multi-document scientific summarization focusing on refining a related work section for a given scientific paper. In this paper, we propose a brand new framework ToC-RWG for related work generation by incorporating topic model and citation information. We present an unsupervised generative probabilistic model, called QueryTopicSum, which utilizes a LDA-style model to characterize the generative process of both the scientific paper and its reference papers. We also take advantage of citations of reference papers to identify Cited Text Spans (CTS) from reference papers. This approach provides us with a perspective of annotating the importance of the reference papers from the academic community. With QueryTopicSum and the identified CTS as candidate sentences, an optimization framework based on minimizing KL divergence is exerted to select the most representative sentences for related work generation. Our evaluation results on a set of 50 scientific papers along with their corresponding reference papers show that ToC-RWG achieves a considerable improvement over generic multi-document summarization and scientific summarization baselines.

With the improvement of the quality of life, the amount of time people spend indoors is constantly increasing, and the demand for indoor positioning is also increasing. In recent years, many wireless indoor positioning technologies have emerged, among which RFID has been favored by researchers due to its stability, low power consumption and price advantages. In order to reduce the great influence of RFID signal fluctuations on the positioning results, this paper proposes an indoor positioning technology based on Attention. The mobile reader collects the Received Signal Strength Indication, Time of Arrival and Angle information of the positioning tag as timing features, and the positioning coordinates as the target to train regression model; The model proposed in this paper is characterized by using the Attention mechanism to work as a filter, followed by a fully connected layer for features combination, to predict coordinates. The experimental results show that the naive Attention positioning model can predict the highest proportion of the error range of 0.2m, and the Multi-head Attention positioning model performs best in the overall positioning results.

Image captioning requires models to translate an image into natural language description. Recent captioning methods are mostly based on the popular encoder-decoder framework, which uses the encoder to encode an image into a set of vectors and a decoder to produce the caption word-by-word. However, when generating the next word, the decoder only looks back at the preceding words but fails to foresee the posterior ones that are supposed to be produced, lacking awareness of the global semantic information of the image. Moreover, the existing generated caption provides global semantic information of a given image but sometimes contains inconsistent content that needs to be fixed. This paper proposes a novel Temporal-Free Semantic-Guided attention mechanism (TFSG) to utilize the raw caption pre-generated by a primary decoder as the extra input to provide global semantic guidance during generation, deepening visual understanding by balancing the semantic and visual information. Specifically, we design two attention-based structures for TFSG to selectively take the essence from the semantic and visual information to produce refined descriptions. We apply TFSG to two popular captioning models and conduct extensive experiments on the public MS COCO benchmark. Results show that our proposed model achieves superior performance over many state-of-the-art models.

Current state-of-the-art approaches for image captioning mainly apply the encoder-decoder framework with attention mechanisms, most of which ignore interactions between different types of image features and perform attention operations only once per word. The mentioned problems limit the captioning model’s capability to capture sufficient information to generate high-quality captions. By contrast, humans often rethink to polish up descriptions by re-focusing on more correct and important information, which is hard to capture at first glance. In this paper, we introduce a novel topic-guided captioning model to imitate such a human’s rethinking process by modeling interactions between visual and hierarchical semantic features of topics. To the best of our knowledge, we are the first to effectively consider hierarchical semantic features as guidance to facilitate visual attention, achieving human-like rethinking for captioning. Extensive experiments on the MS COCO dataset show that our proposed model achieves superior performance over state-of-the-art methods.

Depression is a common mental disease, and it is committed to promote the research of depression assessment based on physiological signals. By collecting the resting state EEG data of depressive disorder, we collected the resting state EEG data of 14 patients with depression and 17 normal people. Through the analysis, the number of troughs of each person's data was statistically analyzed, combined with the convolution neural network model. The accuracy rate of some data is 94.88% by the statistical trough number method, and the accuracy rate of the remaining part of the test data set is 85.0% through the convolution neural network model, and the final fusion accuracy rate is 86.88%. The experimental results show that the combination of statistical trough number and convolution neural network can distinguish depression patients better in resting state EEG data.

In the era of big data, customer churn is a big problem faced by banks in the increasingly competitive market. Therefore, it is very important to establish an efficient early warning system for Customer Churn by mining the information that has an impact on churn from massive customer data. The purpose of this paper is to analyze the quarterly user data of banks, and establish user churn prediction model by using ensemble learning algorithm such as Catboost, Lightgbm, Random Forest, so as to improve the accuracy of prediction, so as to achieve the purpose of helping banks save costs. The experimental results show that the accuracy rate of the model has reached 90%, and the AUC value is more than 80%. The model can be used to predict whether the user may be lost in the future, reserve enough time for the user retention activities, and provide a lot of valuable information to help marketing personnel to formulate feasible user retention scheme, which has a wide range of industry application prospects.

To improve the performance of the Radio Frequency Identification (RFID) system and the multi-tag collision problem, a new anti-collision building algorithm is proposed based on the dynamic frame time slot Aloha algorithm and the analysis of binary search and four-slot binary search. In the new algorithm, the reader stack is used to form a further search command; the response tag is divided into four subsets, and the data information is sent in four-time slots, and up to eight tags can be recognized in one search. Simulation results show that the new algorithm greatly reduces the search times and recognition time.

Image captioning aims to generate descriptions of images with natural language sentences automatically. Most methods tackle this problem in an end-to-end fashion in recent years, which generates captions directly from image level features but ignores high-level semantic information. The method that introduced attribute concept into the CNN-RNN framework made a considerable improvement while the performance depended on the manually selected attributes heavily. In this paper, we propose a topic-guided neural image captioning model which incorporates a topic model into the CNN-RNN framework. Our model represents each image as a set of topics and each topic as various words with relevant distributions. We conduct experiments on Microsoft COCO dataset. The results show that our model outperforms the baselines and achieves promising performance. It verifies that the topic features are effective to represent high-level semantic information of images.

The exponential growth of Massive Open Online Courses (MOOCs) provides increasing learning options along with distinguishing difficulties in choosing courses or finding learning paths for learners. To improve online learning resource utilization, a knowledge graph, MOOC-KG, collecting and formulating the information of online courses on major platforms was constructed. The aim of MOOC-KG is to not only provide users with a new MOOC resource organization but also supply an easy approach for learning resource using among several platforms. In our work, an acknowledged educational ontology was adopted to model the knowledge of online learning resources and the web information extraction methods were developed to collect the metadata on major platforms. The entity disambiguation and conflict resolution methods were adopted to integrate the resources among different platforms. As a result, MOOC-KG is the biggest MOOC-related knowledge graph, which represents and stores 28591 instances with their corresponding relations, including 4 platforms, 604 universities, 18671 teachers and 9312 courses until now. Related valuable data analyses illustrate the fundamental information and reveal explorable parts of MOOC-KG. We have released the related project on GitHub to facilitates further improvement and extensive use.

During the past five years, tons of economic 360 VR cameras (e.g., Ricoh Theta, Samsumg Gear360, LG 360, Insta 360) are sold in the market. While 360 VR videos become ubiquitous very soon, 360 VR video standardization is still under discussion in the digital industry, and more concrete efforts are desired to accelerate its standardization and applications. Though ERP has been widely used for projection and packing layout while encoding 360 VR videos, it has severe projection distortion near poles. In this paper, we introduce a new format for encoding and storing 360 VR videos using hybrid cylindrical projection after thoroughly analyzing the problems with ERP. We show that our new hybrid format can minimize stretching distortion and generate well balanced pixel distribution in the resulting projection.

As the Internet of Vehicles (IoV) becomes flourishing and the data generated by sensors be ubiquitous, there exist various kinds of IoV applications with different performance requirements. Hence, different distributed data processing systems (DDPS) clusters will coexist, e.g., a stream processing system cluster for real-time tasks and a batch one for statistics based data mining tasks, to meet the requirements of such IoV applications. However, it is not an economical or convenient way to maintain varied systems clusters, as the developers and/or administrators have to be familiar with all of these DDPSs, and of course, the deployment of multiple DDPS means a waste of resources compared to the deployment of one DDPS. Based on these observations, this paper proposes the TDAG as a solution. TDAG allows users to adjust the data processing from the streaming style to the batch style by encapsulating the input data with specific packing strategies. We have implemented TDAG in a prototype called TStream. The experimental tests show that our TStream is both effective and efficient.

Relation extraction is very useful for many applications and has attracted much attention. The dominant prior methods for relation extraction were supervised methods which are relation-specific and limited by the availability of annotated training data. In this paper, we propose a method using hierarchical clustering to extract unbounded relations without relying on training data. The relation among entities in a sentence depends on the terms associated with the entities. Terms on the expandPath capture the relations between the entities. Given a relation, though an expandPath may have more than one dependency phrase, only the core dependency phrase describes the specific relation between the subject and the object. Our method uses heuristic rules to select the core dependency phrases and clusters entity pairs according to the similarity of the core dependency phrases in order to avoid irrelevant information and capture the semantics of the relation between entities more precisely. At last, our method automatically labels the relation clusters on basis of the semantics of core dependency phrases. The experimental results show that our method can cluster entity pairs which have the same relations more accurately and generate appropriate labels for the relations.

In order to be considered as Linked Data, the datasets on the web must be linked to other datasets. Current studies on dataset interlinking prediction researches do not distinguish the type of links, which are of less help for real application scenarios, as dataset publishers still do not know what kinds of RDF links can be established and furthermore how to configure the data linking algorithms. In this paper, we focus on predicting the possible links between datasets with the most important RDF link type, owl:sameAs. Since the goal is to discriminate between linked dataset pairs against not-linked ones, we formulate the link prediction problem as a classification problem. We adopt Random Forest as the basic classifier to incorporate features of the scores output by unsupervised predictors, and apply the bagging technique to combine multiple forests to reduce variance and improve the accuracy. Experiments show we can improve the prediction performance by about 10% in AUROC.

Traditional back propagating algorithms of artificial neural network are supervised batch-learning algorithms. And they are faced with challenges from the huge number of real-time data in Internet. In this paper, we put forward an unsupervised incremental learning model. This is an adaptive statistical neural network model. It is built on the foundation of statistical theory rather than gradient descent search. Experiments on classical datasets demonstrate that the clustering algorithm of this model is comparable with traditional clustering algorithms such as K-means. Moreover, it can also execute supervised learning in theory.

As a typical social media in web2.0 era, blogs have become more and more important to information diffusion. Different from the traditional news, the information spread on blogs is primarily driven by users and their relations. According to this phenomenon, this paper addresses the novel problem of measuring the influence of social structures on information diffusion. This paper extracts the hidden communities and information diffusion networks on blogs, and proposes a novel quantitative measurement to investigate the influence of social networks structure on diffusion networks. The proposed methods measure the influence by utilizing a simple but effective graph similarity measuring method. The experiments demonstrate the effectiveness of the proposed algorithms and measurements, and discover the correlation between social networks and the diffusion of the “interest” topics, which indicates the necessity of using social structures for information detection and tracking on blogs.

Blogs have become a typical online publication in Web2.0 era. The users of blogs interact with each other by publishing entries, reading and posting comments to other's entries, and discussing with friends. By these actions, information propagates from user to user on the social networks. This paper extracts the information flow hidden in entries and investigates the rules of information flow in both temporal and spatial dimensions. A new approach for information flow detection and tracking on blogs has been proposed by using both social features and text features. The proposed approach has been evaluated through experiments using large scale of real data collected from SOHU blogs. The results demonstrate that our approach is more effective in Web2.0 blogs. The rules of information flow have also been investigated by analyzing the results, which in turn proves the necessity of using social features for information detection and tracking on blogs.