Integration of machine learning and first principles models

Model building and parameter estimation are traditional concepts widely used in chemical, biological, metallurgical, and manufacturing industries. Early modeling methodologies focused on mathematically capturing the process knowledge and domain expertise of the modeler. The models thus developed are termed first principles models (or white-box models). Over time, computational power became cheaper, and massive amounts of data became available for modeling. This led to the development of cutting edge machine learning models (black-box models) and artificial intelligence (AI) techniques. Hybrid models (gray-box models) are a combination of first principles and machine learning models. The development of hybrid models has captured the attention of researchers as this combines the best of both modeling paradigms. Recent attention to this field stems from the interest in explainable AI (XAI), a critical requirement as AI systems become more pervasive. This work aims at identifying and categorizing various hybrid models available in the literature that integrate machine-learning models with different forms of domain knowledge. Benefits such as enhanced predictive power, extrapolation capabilities, and other advantages of combining the two approaches are summarized. The goal of this article is to consolidate the published corpus in the area of hybrid modeling and develop a comprehensive framework to understand the various techniques presented. This framework can further be used as the foundation to explore rational associations between several models.     

Determining robust reaction kinetics from limited data

Accurate chemical kinetics are essential for reactor design and operation. However, despite recent advances in “big data” approaches, availability of kinetic data is often limited in industrial practice. Herein, we present a comparative proof-of-concept study for kinetic parameter estimation from limited data. Cross-validation (CV) is implemented to nonlinear least-squares (LS) fitting and evaluated against Markov chain Monte Carlo (MCMC) and genetic algorithm (GA) routines using synthetic data generated from a simple model reaction. As expected, conventional LS is fastest but least accurate in predicting true kinetics. MCMC and GA are effective for larger data sets but tend to overfit to noise for limited data. LS-CV strongly outperforms these methods at much reduced computational cost, especially for significant noise. Our findings suggest that implementation of CV with conventional regression provides an efficient approach to kinetic parameter estimation with high accuracy, robustness against noise, and only minimal increase in complexity.     

Prediction of risk factors of cyberbullying-related words in Korea: Application of data mining using social big data

The study examined a decision tree analysis using social big data to conduct the prediction model on types of risk factors related to cyberbullying in Korea. The study conducted an analysis of 103,212 buzzes that had noted causes of cyberbullying and data were collected from 227 online channels, such as news websites, blogs, online groups, social network services, and online bulletin boards. Using opinion-mining method and decision tree analysis, the types of cyberbullying were sorted using SPSS 25.0. The results indicated that the total rate of types of cyberbullying in Korea was 44%, which consisted of 32.3% victims, 6.4% perpetrators, and 5.3% bystanders. According to the results, the impulse factor was also the greatest influence on the prediction of the risk factors and the propensity for dominance factor was the second greatest factor predicting the types of risk factors. In particular, the impulse factor had the most significant effect on bystanders, and the propensity for dominance factor was also significant in influencing online perpetrators. It is necessary to develop a program to diminish the impulses that were initiated by bystanders as well as victims and perpetrators because many of those bystanders have tended to aggravate impulsive cyberbullying behaviors.     

立井过砂岩富含水层工作面预注浆分析

郑煤集团杨河煤业43采区樊寨副立井施工中需要穿过预计涌水量187 m³/h、厚57 m的砂岩含水层。针对第1回次采用普通水泥工作面预注浆、吸浆量少、升压快、效果差、达不到预期目的等不利情况，在后3回次采用大压力，白银水泥、超细水泥等新材料、单孔上下端正反同时注浆新工艺，采用压注清水、水玻璃，利用水玻璃的黏性，反复冲洗钻孔把细小裂隙中锈蚀颗粒带出，打开注浆通道，同时针对竖向裂隙多、横向裂隙不联系，加密钻孔布置，缩小注浆段高，取得了较好的注浆效果。     

A single-phase algorithm for mining high utility itemsets using compressed tree structures

Mining high utility itemsets (HUIs) from transaction databases considers such factors as the unit profit and quantity of purchased items. Two-phase tree-based algorithms transform a database into compressed tree structures and generate candidate patterns through a recursive pattern-growth procedure. This procedure requires a lot of memory and time to construct conditional pattern trees. To address this issue, this study employs two compressed tree structures, namely, Utility Count Tree and String Utility Tree, to enumerate valid patterns and thus promote fast utility computation. Furthermore, the study presents an algorithm called single-phase utility computation (SPUC) that leverages these two tree structures to mine HUIs in a single phase by incorporating novel pruning strategies. Experiments conducted on both real and synthetic datasets demonstrate the superior performance of SPUC compared with IHUP, UP-Growth, and UP-Growth+ algorithms.     

Comparing open data benchmarks: Which metrics and methodologies determine countries’ positions in the ranking lists?

An understanding of the similar and divergent metrics and methodologies underlying open government data benchmarks can reduce the risks of the potential misinterpretation and misuse of benchmarking outcomes by policymakers, politicians, and researchers. Hence, this study aims to compare the metrics and methodologies used to measure, benchmark, and rank governments' progress in open government data initiatives. Using a critical meta-analysis approach, we compare nine benchmarks with reference to meta-data, meta-methods, and meta-theories. This study finds that both existing open government data benchmarks and academic open data progress models use a great variety of metrics and methodologies, although open data impact is not usually measured. While several benchmarks’ methods have changed over time, and variables measured have been adjusted, we did not identify a similar pattern for academic open data progress models. This study contributes to open data research in three ways: 1) it reveals the strengths and weaknesses of existing open government data benchmarks and academic open data progress models; 2) it reveals that the selected open data benchmarks employ relatively similar measures as the theoretical open data progress models; and 3) it provides an updated overview of the different approaches used to measure open government data initiatives’ progress. Finally, this study offers two practical contributions: 1) it provides the basis for combining the strengths of benchmarks to create more comprehensive approaches for measuring governments’ progress in open data initiatives; and 2) it explains why particular countries are ranked in a certain way. This information is essential for governments and researchers to identify and propose effective measures to improve their open data initiatives.     

From enfant terrible to problem-solver? Tracing the competing discourse to explain blockchain-related technological diffusion

Since the inception of blockchain-related technologies over a decade ago, investors’ uptake of the technologies has grown rapidly. But even with the advancement in standing from conceptual beginnings to real-world experimentation, mainstream adoption of the technologies in either organizational or individual contexts has yet to eventuate. To resolve this paradox, we examine progression of the technologies’ diffusion instead, and in the process, seek to uncover the underlying dynamics of sentiments at play. Diffusion involves multiple actions by different parties, with social discourses via diverse media playing an essential role. In demonstrating the interplay of support to resistance via media framing and the diffusion of innovation theory, findings from our paper contribute to the technology adoption literature. Understanding resistant behavior toward a new technology area could help resolve potential issues that may arise. This would hopefully lead to better technological implementation outcomes in future.     

Dynamic Oscillation via Negative Differential Resistance in Type III Junction Organic/Two-Dimensional and Oxide/Two-Dimensional Transition Metal Dichalcogenide Diodes

Among many of 2D semiconductor-based devices, type III PN junction diodes are given special attentions due to their unique function, negative differential resistance (NDR). However, it has been found uneasy to achieve well-matched type III PN junctions from 2D–2D van der Waals heterojunctions. Here, the authors present other alternatives of type III heterojunctions, using 2D p-MoTe₂/organic n-type dipyrazino[2,3-f:2′,3′-h]quinoxaline-2,3,6,7,10,11-hexacarbonitrile (HAT-CN) and 2D p-WSe₂/n-MoO_x systems. Those junction diodes appear to well-demonstrate static and dynamic NDR behavior via resonant tunneling and electron–hole recombination. Extended to an inverter circuit, p-MoTe₂/n-HAT-CN diode enables multilevel inverter characteristics as monolithically integrated with p-MoTe₂ channel field effect transistor. The same NDR diode shows dynamic LC oscillation behavior under a constant DC voltage, connected to an external inductor. From p-WSe₂/n-MoO_x oxide diode, similar NDR behavior to those of p-MoTe₂/n-HAT-CN is again observed along with LC oscillations. The authors attribute these visible oscillation results to high peak-to-valley current ratios of their organic or oxide/2D heterojunction diodes.     

Profiling of knowledge organisation systems for the annotation of Linked Data cultural resources

The importance of cultural heritage for supporting the knowledge economy has promoted its digitisation and online publication. Many cultural heritage repositories have published millions of digitised items using semantic web technologies and Linked Data approaches. These repositories frequently use knowledge organisation systems to classify the resources, but the domain heterogeneity makes it difficult to know if they are the most suitable ones. This paper describes the process used to discover and profile the knowledge organisation systems used in the cultural heritage domain. Additionally, for those knowledge organisation systems with a thesaurus-like structure, a detailed quality analysis is performed. The results of this analysis can be used as a key factor for the selection of knowledge organisation systems in classification tasks.     

基于线状特性的大数据地铁用户识别与定位方法

从MR原始数据特性出发研究数据结构与字段,采用基于线状特性分析MR大数据的地铁用户识别过滤方法和位置定位方法,该方法经过验证能够有效输出地铁用户数据并定位在地图上,解决人工地铁测试效率低且测试片面的问题,实现基于大数据的自动化地铁网络评估,提供海量的有效定位数据用于地铁评估与分析。