A novel framework for deep knowledge tracing via gating-controlled forgetting and learning mechanisms

In this paper, we propose a framework called Gating-controlled Forgetting and Learning mechanisms for Deep Knowledge Tracing (GFLDKT for short). In GFLDKT, two gating-controlled mechanisms are designed to model explicitly forgetting and learning behaviors in students’ learning process. With the designed gating-controlled mechanisms, both the interaction records and students’ different backgrounds are combined effectively for tracing the dynamic changes of students’ mastery of knowledge concepts. Results from extensive experiments demonstrate that the proposed framework outperforms the state-of-the-art models on the KT task. In addition, the ablation study shows that designed forgetting and learning mechanisms contribute clearly to the performance improvement of GFLDKT.     

Financial system modeling using deep neural networks (DNNs) for effective risk assessment and prediction

Since the risk of loan defaulting in peer-to-peer (P2P) lending is notoriously difficult to evaluate, a deep neural network-based decision-making approach is proposed in this work for more effective assessment of P2P lending risks. Although normally a dozen features were used for neural network modeling in previous studies carried out by other researchers on similar topics, more comprehensive features including both numeric and categorical ones (e.g. home ownership and purpose of loan), are considered in this work for improved modeling. Since categorical data cannot be used directly as the input of neural networks, they are converted to numerical data using one-hot encoding function. The deep neural network (DNN) used in this work is a multilayer perceptron (MLP) with three hidden layers trained by the back-propagation algorithm. In empirical analysis, the loan data issued by the Lending Club through 2007–2015 are classified into three classes, i.e. safe loan, risky loan and bad loan using TensorFlow. The training and test data sets consist of 221,712 and 55,428 data observations, respectively. Since most of the data belong to the class of safe loan, Synthetic Minority Over-Sampling Technique (SMOTE) is used to improve the DNN prediction accuracy. It is shown that with the proposed approach the test data are classified at an accuracy of 93%, which is much higher than the predication accuracy of 75% obtained using MLP with only one hidden layer.     

Variable-structure-systems based approach for online learning of spiking neural networks and its experimental evaluation

Raising the level of biological realism by utilizing the timing of individual spikes, spiking neural networks (SNNs) are considered to be the third generation of artificial neural networks. In this work, a novel variable-structure-systems based approach for online learning of SNN is developed and tested on the identification and speed control of a real-time servo system. In this approach, neurocontroller parameters are used to define a time-varying sliding surface to lead the control error signal to zero. To prove the convergence property of the developed algorithm, the Lyapunov stability method is utilized. The results of the real-time experiments on the laboratory servo system for a number of different load conditions including nonlinear and time-varying ones indicate that the control structure exhibits a highly robust behavior against disturbances and sudden changes in the command signal.     

From statistical methods to deep learning,automatic keyphrase prediction: A survey

Keyphrase prediction aims to generate phrases (keyphrases) that highly summarizes a given document. Recently, researchers have conducted in-depth studies on this task from various perspectives. In this paper, we comprehensively summarize representative studies from the perspectives of dominant models, datasets and evaluation metrics. Our work analyzes up to 167 previous works, achieving greater coverage of this task than previous surveys. Particularly, we focus highly on deep learning-based keyphrase prediction, which attracts increasing attention of this task in recent years. Afterwards, we conduct several groups of experiments to carefully compare representative models. To the best of our knowledge, our work is the first attempt to compare these models using the identical commonly-used datasets and evaluation metric, facilitating in-depth analyses of their disadvantages and advantages. Finally, we discuss the possible research directions of this task in the future.     

Data fusion with factored quantization for stock trend prediction using neural networks

As compared to the continuous temporal distributions, discrete data representations may be desired for simplified and faster data analysis and forecasting. Data compression can introduce one of the efficient ways to reduce continuous historical stock market data and present them in discrete forms; while predicting stock trend, a primary concern is towards up and down directions of the price movement and thus, data discretization for a focused approach can be beneficial. In this article, we propose a quantization-based data fusion approach with a primary motivation to reduce data complexity and hence, enhance the prediction ability of a model. Here, the continuous time-series values are transformed into discrete quantum values prior to applying them to a prediction model. We extend the proposed approach and factorize quantization by integrating different quantization step sizes. Such fused data can reduce the data to mainly concentrate on the stock price movement direction. To empirically evaluate the proposed approach for stock trend prediction, we adopt long short-term memory, deep neural network, and backpropagation neural network models and compare our prediction results with five existing approaches on several datasets using ten performance metrics. We analyze the impact of specific quantization factors and determine the individual best as well as overall best factor sizes; the results indicate a consistent performance enhancement in stock trend prediction accuracy as compared to the considered baseline methods with an improvement up to 7%. To evaluate the impact of quantization-based data fusion, we analyze time required to execute the experiments along with percentage reduction in the number of unique numeric terms. Further, these results are statistically evaluated using Wilcoxon signed-rank test. We discuss the superiority and applicability of factored quantization-based data fusion approach and conclude our work with potential future research directions.     

A general motion control framework for an autonomous underwater vehicle through deep reinforcement learning and disturbance observers

This paper investigates the application of deep reinforcement learning (RL) in the motion control for an autonomous underwater vehicle (AUV), and proposes a novel general motion control framework which separates training and deployment. Firstly, the state space, action space, and reward function are customized under the condition of ensuring generality for various motion control tasks. Next, in order to efficiently learn the optimal motion control policy in the case that the AUV model is imprecise and there are unknown external disturbances, a virtual AUV model composed of the known and determined items of an actual AUV is put forward and a simulation training method is developed on this basis. Then, in the given deployment method, three independent extended state observers (ESOs) are designed to deal with the unknown items in different directions, and the final controller is obtained by compensating the estimated value of ESOs into the output of the optimal motion control policy obtained through simulation training. Finally, soft actor-critic is chosen as deep RL algorithm of the framework, and the generality and effectiveness of the proposed method are verified in four different AUV motion control tasks.     

从技术自立到创新——一个关于技术学习的概念框架

后进者技术学习的阶段性特征理应成为制定工业与技术政策的重要参考,但现有的技术学习研究并未对这种阶段性差异予以足够重视。通过对技术变化过程的分析,本文引入了"技术自立"的概念,以此刻画后进者以掌握国外现有技术为主的技术学习阶段,并说明了技术自立作为从技术依赖达到创新的一个必经阶段的重要性。在理论分析的基础上,本文强调了自主产品开发在摆脱技术依赖、达到技术自立过程中的决定性作用,并以四个行业的经验证据给出了初步说明。文章最后讨论了一个独立的技术自立概念对我们理解中国技术进步与工业发展的启示。     

A new Lyapunov functional approach to sampled-data synchronization control for delayed neural networks

This paper discusses the problem of synchronization for delayed neural networks using sampled-data control. We introduce a new Lyapunov functional, called complete sampling-interval-dependent discontinuous Lyapunov functional, which can adequately capture sampling information on both intervals from $r(t?\overline{\tau })$ to $r(t_k?\overline{\tau })$ and from $r(t?\overline{\tau })$ to $r(t_{k+1}?\overline{\tau })$. Based on this Lyapunov functional and an improved integral inequality, less conservative conditions are derived to ensure the stability of the synchronization error system, leading to the fact that the drive neural network is synchronized with the response neural network. The desired sampled-data controller is designed in terms of solutions to linear matrix inequalities. A numerical example is provided to demonstrate that the proposed approaches are effective and superior to some existing ones in the literature.     

EGC: A novel event-oriented graph clustering framework for social media text

With the popularity of social platforms such as Sina Weibo, Tweet, etc., a large number of public events spread rapidly on social networks and huge amount of textual data are generated along with the discussion of netizens. Social text clustering has become one of the most critical methods to help people find relevant information and provides quality data for subsequent timely public opinion analysis. Most existing neural clustering methods rely on manual labeling of training sets and take a long time in the learning process. Due to the explosiveness and the large-scale of social media data, it is a challenge for social text data clustering to satisfy the timeliness demand of users. This paper proposes a novel unsupervised event-oriented graph clustering framework (EGC), which can achieve efficient clustering performance on large-scale datasets with less time overhead and does not require any labeled data. Specifically, EGC first mines the potential relations existing in social text data and transforms the textual data of social media into an event-oriented graph by taking advantage of graph structure for complex relations representation. Secondly, EGC uses a keyword-based local importance method to accurately measure the weights of relations in event-oriented graph. Finally, a bidirectional depth-first clustering algorithm based on the interrelations is proposed to cluster the nodes in event-oriented graph. By projecting the relations of the graph into a smaller domain, EGC achieves fast convergence. The experimental results show that the clustering performance of EGC on the Weibo dataset reaches 0.926 (NMI), 0.926 (AMI), 0.866 (ARI), which are 13%–30% higher than other clustering methods. In addition, the average query time of EGC clustered data is 16.7ms, which is 90% less than the original data.     

Looking deep in the eyes: Investigating interpretation methods for neural models on reading tasks using human eye-movement behaviour

This paper provides the first broad overview of the relation between different interpretation methods and human eye-movement behaviour across different tasks and architectures. The interpretation methods of neural networks provide the information the machine considers important, while the human eye-gaze has been believed to be a proxy of the human cognitive process. Thus, comparing them explains machine behaviour in terms of human behaviour, leading to improvement in machine performance through minimising their difference. We consider three types of natural language processing (NLP) tasks: sentiment analysis, relation classification and question answering, and four interpretation methods based on: simple gradient, integrated gradient, input-perturbation and attention, and three architectures: LSTM, CNN and Transformer. We leverage two corpora annotated with eye-gaze information: the Zuco dataset and the MQA-RC dataset. This research sets up two research questions. First, we investigate whether the saliency (importance) of input-words conform with those from human eye-gaze features. To this end, we compute a saliency distance (SD) between input words (by an interpretation method) and an eye-gaze feature. SD is defined as the KL-divergence between the saliency distribution over input words and an eye-gaze feature. We found that the SD scores vary depending on the combinations of tasks, interpretation methods and architectures. Second, we investigate whether the models with good saliency conformity to human eye-gaze behaviour have better prediction performances. To this end, we propose a novel evaluation device called “SD-performance curve” (SDPC) which represents the cumulative model performance against the SD scores. SDPC enables us to analyse the underlying phenomena that were overlooked using only the macroscopic metrics, such as average SD scores and rank correlations, that are typically used in the past studies. We observe that the impact of good saliency conformity between humans and machines on task performance varies among the combinations of tasks, interpretation methods and architectures. Our findings should be considered when introducing eye-gaze information for model training to improve the model performance.     

A fuzzy control framework for interconnected nonlinear power networks under TDS attack: Estimation and compensation

This article focuses on time delay switch (TDS) attacks on power networks subject to highly nonlinear and interconnection. T–S model is utilized to represent each nonlinear power subsystem in the network. In order to attenuate adverse impacts from TDS attacks, a novel control technique of estimation and compensation is proposed. Combined with the method of finite time boundedness (FTB), transient stability of power systems could be achieved. First, an augmented fuzzy observer is constructed to capacitate a synchronous estimation for system states and TDS attacks, which ensures that the estimation error is limited via the intersection operation of ellipsoids within a specified finite time interval. Then, a compensation technique is employed to attenuate the influence from TDS attacks. Finally, simulation results of a distributed power network show the efficacy of the proposed method against TDS attacks.     

Assessing the contribution to innovation of private equity investors: A study on European buyouts

The paper provides an empirical analysis of the patenting activity of a sample of Western European manufacturing firms undergoing a buyout between 1998 and 2004. A panel data design is used to test whether the characteristics of the deal and of private equity (PE) firms can affect acquired companies’ subsequent innovation effort as measured by the number of patents granted by the EPO. Results support the view that the innovation activity of portfolio firms is affected by different types of investors, pursuing different objectives and differing in their risk propensity, expected returns and investment policies. The characteristics of lead investors (size, stage specialization, geographical location) and of the deal (amount invested, presence of multiple investors) are also investigated and are found to differently affect the post-buyout innovation activity of sample firms.     

Switching to online learning during COVID-19: Theorizing the role of IT mindfulness and techno eustress for facilitating productivity and creativity in student learning

Online learning environments facilitate improved student learning by offering IT tools to enhance student productivity- and creativity-in-learning. COVID-19 impacted social-distancing measures forced an abrupt switch to online learning in most universities, putting immense pressure on the students to creatively adapt to new ways of online learning. Despite the purported positives of online learning, in the COVID-19 scenario, students reported mixed outcomes. While some students could adapt to the ‘new normal’, others struggled to adjust to the transformed IT-enabled learning scenario. Grounding our work in IT mindfulness literature, we posit that an IT-enabled learning environment may have differential impact on students’ productivity- and creativity-in-learning, depending on the extent of their IT mindfulness. Besides leveraging the mindfulness-to-meaning theory, we hypothesize the mediating role of techno eustress in the relationship between student IT mindfulness and learning effectiveness. We test the theorized model through data collected via a two-wave survey in a university student population exclusively using IT-enabled learning environments during the pandemic lockdown period. Results indicate that IT mindfulness has significant positive relationships with both productivity- and creativity-in- learning. Moreover, these relationships are mediated by the students’ techno eustress perceptions. Theoretical and practical implications arising from our study are also discussed.     

HEMOS: A novel deep learning-based fine-grained humor detecting method for sentiment analysis of social media

In this paper we introduce HEMOS (Humor-EMOji-Slang-based) system for fine-grained sentiment classification for the Chinese language using deep learning approach. We investigate the importance of recognizing the influence of humor, pictograms and slang on the task of affective processing of the social media. In the first step, we collected 576 frequent Internet slang expressions as a slang lexicon; then, we converted 109 Weibo emojis into textual features creating a Chinese emoji lexicon. In the next step, by performing two polarity annotations with new “optimistic humorous type” and “pessimistic humorous type” added to standard “positive” and “negative” sentiment categories, we applied both lexicons to attention-based bi-directional long short-term memory recurrent neural network (AttBiLSTM) and tested its performance on undersized labeled data. Our experimental results show that the proposed method can significantly improve the state-of-the-art methods in predicting sentiment polarity on Weibo, the largest Chinese social network.     

Real-time processing of social media with SENTINEL: A syndromic surveillance system incorporating deep learning for health classification

Interest in real-time syndromic surveillance based on social media data has greatly increased in recent years. The ability to detect disease outbreaks earlier than traditional methods would be highly useful for public health officials. This paper describes a software system which is built upon recent developments in machine learning and data processing to achieve this goal. The system is built from reusable modules integrated into data processing pipelines that are easily deployable and configurable. It applies deep learning to the problem of classifying health-related tweets and is able to do so with high accuracy. It has the capability to detect illness outbreaks from Twitter data and then to build up and display information about these outbreaks, including relevant news articles, to provide situational awareness. It also provides nowcasting functionality of current disease levels from previous clinical data combined with Twitter data.The preliminary results are promising, with the system being able to detect outbreaks of influenza-like illness symptoms which could then be confirmed by existing official sources. The Nowcasting module shows that using social media data can improve prediction for multiple diseases over simply using traditional data sources.     

如何领导组织学习：家长式领导与组织学习的关系/FONT

为了对我国企业领导者领导组织学习提供指导,研究了家长式领导与组织学习的关系。通过问卷调查法得到10家企业的276份有效问卷。结构方程建模的结果显示,家长式领导的仁慈领导对组织学习的六个维度都有显著的推动作用,而威权领导对团体学习、组织间学习、开发式学习和利用式学习具有显著的阻碍作用。这启发我国企业领导者要继续保持仁慈的传统文化理念和行为风格,尽量避免威权领导。     

农业发展的新思路:第二农业

随着中国加入世界贸易组织,农业生产部门在面临着前所未有的挑战的同时,也存在一些难得的发展机遇。如果能在农业发展思路上更新观念,做到扬长避短,则我国的农业生产水平有可能迈上一个新台阶。笔者认为发展第二农业是提高我国农业生产水平、保障农业可持续发展的     

SAT-Geo: A social sensing based content-only approach to geolocating abnormal traffic events using syntax-based probabilistic learning

Social sensing has become an emerging and pervasive sensing paradigm to collect timely observations of the physical world from human sensors. In this paper, we study the problem of geolocating abnormal traffic events using social sensing. Our goal is to infer the location (i.e., geographical coordinates) of the abnormal traffic events by exploring the location entities from the content of social media posts. Two critical challenges exist in solving our problem: (i) how to accurately identify the location entities related to the abnormal traffic event from the content of social media posts? (ii) How to accurately estimate the geographic coordinates of the abnormal traffic event from the set of identified location entities? To address the above challenges, we develop a Social sensing based Abnormal Traffic Geolocalization (SAT-Geo) framework to accurately estimate the geographic coordinates of abnormal traffic events by exploring the syntax-based patterns in the content of social media posts and the geographic information associated with the location entities from the social media posts. We evaluate the SAT-Geo framework on three real-world Twitter datasets collected from New York City, Los Angeles, and London. Evaluation results demonstrate that SAT-Geo significantly outperforms state-of-the-art baselines by effectively identifying location entities related to the abnormal traffic events and accurately estimating the geographic coordinates of the events.