Adverse drug reactions (ADRs) are a huge public health issue. Identifying text that mentions ADRs from a large volume of social media data is important. However, we need to address two challenges for ...high-performing ADR-related text detection: the data imbalance problem and the requirement of simultaneously using data-driven information and handcrafted information. Therefore, we propose an approach named multi-view active learning using domain-specific and data-driven document representations (MVAL4D), endeavoring to enhance the predictive capability and alleviate the requirement of labeled data. Specifically, a new view-generation mechanism is proposed to generate multiple views by simultaneously exploiting various document representations obtained using handcrafted feature engineering and by performing deep learning methods. Moreover, different from previous active learning studies in which all instances are chosen using the same selection criterion, MVAL4D adopts different criteria (i.e., confidence and informativeness) to select potentially positive instances and potentially negative instances for manual annotation. The experimental results verify the effectiveness of MVAL4D. The proposed approach can be generalized to many other text classification tasks. Moreover, it can offer a solid foundation for the ADR mention extraction task, and improve the feasibility of monitoring drug safety using social media data.
This paper studies the issue of segmentation results change over time, on which existing research paid limited attention, and proposes a dynamic segmentation method for power customers based on rough ...clustering. With the selection of power consumption indicators, value analysis systems of power customer are built and the weight of each indicator is determined by combination weighting. Rough k-means algorithm is used to construct a classifier and a two-dimension clustering segmentation method of current and potential value is presented. Two indicators, named the relative size and change rate of roughness of clusters, are proposed and describe changes of segmentation results in different periods combined with the changing cluster memberships of individual customers. Finally, a power supply company is taken as an example to illustrate the process of the proposed method and verify its feasibility.
In this paper, we focus on systems suffering from multiple dependent competing failure processes under coupled effects of zoned shocks and dynamic environments. A reliability and maintenance model is ...developed for a real-time inspected system subject to linear degradation and random shocks, in which the internal degradation rate and shock arrival rate are affected by a dynamic environment. Shocks are classified into four zones based on their magnitude, including the safety zone, probability damage zone, damage zone, and fatal zone. Explicit formulas for calculating reliability indexes of systems are derived, including the reliability function, availability function, and steady-state availability. Meanwhile, simulation algorithms for calculating these reliability indexes are provided based on the Monte Carlo method, which is beneficial to the verification of the analytical method. Finally, a case study of micro-engine systems is given to illustrate the proposed models and obtained results, exhibiting that zoned shocks and dynamic environments have a significant effect on system performance.
•Systems subject to degradation with zoned shocks in dynamic environments are studied.•Explicit formulas for simulation algorithms for reliability indexes are provided.•Availability analysis is performed under a real-time maintenance policy.•A case study of micro-engine systems to demonstrate models and results is presented.
•We develop a semi-supervised ensemble learning framework for adverse drug event (ADE) relation extraction.•We propose two semi-supervised ensemble algorithms under the guidance of the SSEL-ADE ...framework.•We develop six concrete semi-supervised ensemble methods under the guidance of the SSEL-ADE framework.
With the development of Web 2.0 technology, social media websites have become lucrative but under-explored data sources for extracting adverse drug events (ADEs), which is a serious health problem. Besides ADE, other semantic relation types (e.g., drug indication and beneficial effect) could hold between the drug and adverse event mentions, making ADE relation extraction – distinguishing ADE relationship from other relation types – necessary. However, conducting ADE relation extraction in social media environment is not a trivial task because of the expertise-dependent, time-consuming and costly annotation process, and the feature space’s high-dimensionality attributed to intrinsic characteristics of social media data. This study aims to develop a framework for ADE relation extraction using patient-generated content in social media with better performance than that delivered by previous efforts. To achieve the objective, a general semi-supervised ensemble learning framework, SSEL-ADE, was developed. The framework exploited various lexical, semantic, and syntactic features, and integrated ensemble learning and semi-supervised learning. A series of experiments were conducted to verify the effectiveness of the proposed framework. Empirical results demonstrate the effectiveness of each component of SSEL-ADE and reveal that our proposed framework outperforms most of existing ADE relation extraction methods The SSEL-ADE can facilitate enhanced ADE relation extraction performance, thereby providing more reliable support for pharmacovigilance. Moreover, the proposed semi-supervised ensemble methods have the potential of being applied to effectively deal with other social media-based problems.
Display omitted
•A framework is proposed for comparative text identification from user-generated content.•A syntax-aware and sentiment polarity-aware text augmentation method is proposed.•A series of ...experiments verify the feasibility and effectiveness of the framework.
Mining user-generated content on e-commerce platforms and social media is timely and more objective compared with other information access channels for gaining competitive intelligence. Identifying comparative text from large volumes of non-comparative text is an important but challenging task. On one hand, existing methods are time-consuming and not generalizable across different domains. On the other hand, the datasets for the task generally suffer from the severe imbalance issue. To address abovementioned problems, we propose a framework adopting advanced deep learning methods to automatically learn features and a novel textual data augmentation method named TA3S to deal with the data imbalance issue. Specifically, the TA3S method simultaneously considers the syntactic structure and semantic information of comparative text samples. Moreover, in order to support the successful implementation of TA3S, we develop a novel method based on word embedding and label propagation algorithm to distinguish between synonymous and antonymous substitute words. The experiments on two real-world datasets demonstrate the feasibility and effectiveness of our framework, and present that our framework outperforms state-of-the-art methods in identifying comparative text from user-generated content.
PurposeThis study aims to examine the impacts of the novelty-centered business model design (NBMD) and efficiency-centered business model design (EBMD) on mass customization capability (MCC), as well ...as the mediating role of supply chain integration.Design/methodology/approachUsing survey data from 277 Chinese manufacturing firms, we test the hypothesized relationships by conducting structural equation modeling.FindingsThe results indicate that both NBMD and EBMD have significantly positive impacts on product-oriented MCC and service-oriented MCC. In addition, three dimensions of supply chain integration play different mediating roles in the relationship between BMD and MCC. Specifically, relational integration partially mediates the impacts of NBMD and EBMD on service-oriented MCC, information integration partially mediates the impact of NBMD on product-oriented MCC and service-oriented MCC and operational integration partially mediates the impact of NBMD and EBMD on product-oriented MCC.Originality/valueThis study opens the “black box” in the relationship between business model design and MCC, which offers insights on the complex process of supply chain integration and considers business ecosystem for operational performance.
This paper presents a highly effective reinforcement learning enhancement of multi-neighborhood tabu search for the max-mean dispersion problem. The reinforcement learning component uses the ...Q-learning mechanism that incorporates the accumulated feedback information collected from the actions performed during the search to guide the generation of diversified solutions. The tabu search component employs 1-flip and reduced 2-flip neighborhoods to collaboratively perform the neighborhood exploration for attaining high-quality local optima. A learning automata method is integrated in tabu search to adaptively determine the probability of selecting each neighborhood. Computational experiments on 80 challenging benchmark instances demonstrate that the proposed algorithm is favorably competitive with the state-of-the-art algorithms in the literature, by finding new lower bounds for 3 instances and matching the best known results for the other instances. Key elements and properties are also analyzed to disclose the source of the benefits of our integration of learning mechanisms and tabu search.
Social media provides customers with great opportunities to share their opinions regarding certain products and services. Comparative text, as an important expression form, deserves further ...exploration, since it contains considerable comparative information between different products and services. In this study, we review existing research on Comparative Text Mining (CTM) in the past 16 years. Basic concepts related to CTM are first described, and a general research framework is subsequently proposed. We then dive into each component of the research framework, ranging from data acquisition, comparative text identification (CTI), comparative relation extraction (CRE), to potential applications. In addition, we conduct extensive experimental analysis on existing methods for CTI and CRE, and clarify their limitations. Accordingly, we provide corresponding insights, and point out future research directions.
It is a focal issue in the literature to explore the manufacturing transition. Many researchers pay attention to the studies on service-manufacturing concept and value mechanism, but not researched ...on service-manufacturing operation model. Therefore, this paper review the service-oriented manufacturing concepts, proposed service-manufacturing concepts; then analyzed the transformation of manufacturing and service development course, summarized the necessity of traditional manufacturing to service-manufacturing. Based on this, advanced service knowledge integrated model, and takes it as a platform to put forward a service-manufacturing mode. This mode reflects features of service-manufacturing. It has certain theoretical and practical significance on service-manufacturing.
The boolean quadratic programming problem with generalized upper bound constraints (BQP-GUB) is an NP-hard problem with many practical applications. In this study, we propose an effective multi-wave ...tabu search algorithm for solving BQP-GUB. The algorithm performs a sequence of search waves, where each wave alternates between the forward and reverse phases, and the transition between two adjacent waves depends on a hybrid perturbation phase. The forward phase employs tabu search to reach a critical solution and the reverse phase follows to reverse previously performed moves and perform an equal number of moves by referring to the search information gathered from the latest search process. The hybrid perturbation phase randomly chooses a directed strategy, a frequency guided strategy and a recency guided strategy to achieve search diversification. Experimental results on 78 standard instances indicate that the proposed algorithm is able to improve the lower bounds for 6 instances and match the best solutions in the literature for most instances within competitive time.
•Propose a multi-wave tabu search algorithm for BQP-GUB.•Design a tabu search based forward phase for intensification.•Design an information guided reverse phase for adjustments.•Employ memory based strategies to guide search process.•Find new lower bounds for 6 instances.
