Rule-Based Data-Driven Thematic Mapping Technique

2013 ◽  
Vol 756-759 ◽  
pp. 4476-4481
Author(s):  
Hong Yun Zeng ◽  
Lv Hua Wang ◽  
Zhi Qiang Xie ◽  
Wei Bo Zeng
Keyword(s):  
Information Science ◽  
Spatial Information ◽  
Engineering Application ◽  
Data Driven ◽  
Mapping Technique ◽  
River Channels ◽  
Computer Mapping ◽  
Rule Based ◽  
Thematic Mapping ◽  
Representation Technique

Mapping automation is not only a key objective of cartology, but also a study hotspot of geo-spatial information science at present. Here, we take thematic mapping of river channels (pipelines) passing through Yunnan in Kunming City for example to study and discuss, with regard to the effect required by complicated mapping encountering in the process of project implementation and the requirements on high quality of mapping data, the representation of rule-based data-driven computer mapping by the Representation technique of Arcgis9.3 to partly accomplish such mapping task that needs a lot of manual editing in traditional mapping mode, especially achieve the some kinds of mapping effect that cannot be achieved by traditional mapping without destructing GIS spatial information. The findings indicate that, the representation technique of rule-based driven computer mapping can reflect the advantages of both GIS spatial database establishment and mapping. This technique can make map rapidly according to different data requirements, and achieve the effect of traditional mapping. Due to less demand on manpower and financial capacity, such technique has a broad prospect of promotion and engineering application.

scholarly journals Extraction of organic chemistry grammar from unsupervised learning of chemical reactions

2021 ◽  
Vol 7 (15) ◽  
pp. eabe4166
Author(s):  
Philippe Schwaller ◽  
Benjamin Hoover ◽  
Jean-Louis Reymond ◽  
Hendrik Strobelt ◽  
Teodoro Laino
Keyword(s):  
Organic Chemistry ◽  
Neural Networks ◽  
Chemical Synthesis ◽  
Unsupervised Learning ◽  
Chemical Reactions ◽  
Data Driven ◽  
Experimental Task ◽  
Rule Based ◽  
Atom Mapping ◽  
Mapping Information

Humans use different domain languages to represent, explore, and communicate scientific concepts. During the last few hundred years, chemists compiled the language of chemical synthesis inferring a series of “reaction rules” from knowing how atoms rearrange during a chemical transformation, a process called atom-mapping. Atom-mapping is a laborious experimental task and, when tackled with computational methods, requires continuous annotation of chemical reactions and the extension of logically consistent directives. Here, we demonstrate that Transformer Neural Networks learn atom-mapping information between products and reactants without supervision or human labeling. Using the Transformer attention weights, we build a chemically agnostic, attention-guided reaction mapper and extract coherent chemical grammar from unannotated sets of reactions. Our method shows remarkable performance in terms of accuracy and speed, even for strongly imbalanced and chemically complex reactions with nontrivial atom-mapping. It provides the missing link between data-driven and rule-based approaches for numerous chemical reaction tasks.

HISTORICAL RETE NETWORKS TO SUPPORT THE DEBUGGING OF FORWARD-CHAINING RULE-BASED PROGRAMS

1993 ◽  
Vol 02 (01) ◽  
pp. 47-70
Author(s):  
SHARON M. TUTTLE ◽  
CHRISTOPH F. EICK
Keyword(s):  
Working Memory ◽  
Data Driven ◽  
Rule Based ◽  
Historical Information ◽  
Forward Chaining ◽  
Changing Environments ◽  
Time Performance ◽  
Inference Network ◽  
One Step ◽  
Explanation System

Forward-chaining rule-based programs, being data-driven, can function in changing environments in which backward-chaining rule-based programs would have problems. But, degugging forward-chaining programs can be tedious; to debug a forward-chaining rule-based program, certain ‘historical’ information about the program run is needed. Programmers should be able to directly request such information, instead of having to rerun the program one step at a time or search a trace of run details. As a first step in designing an explanation system for answering such questions, this paper discusses how a forward-chaining program run’s ‘historical’ details can be stored in its Rete inference network, used to match rule conditions to working memory. This can be done without seriously affecting the network’s run-time performance. We call this generalization of the Rete network a historical Rete network. Various algorithms for maintaining this network are discussed, along with how it can be used during debugging, and a debugging tool, MIRO, that incorporates these techniques is also discussed.

Rule-Based Data-Driven Analytics for Wide-Area Fault Detection Using Synchrophasor Data

2017 ◽  
Vol 53 (3) ◽  
pp. 1789-1798 ◽  
Author(s):  
Xiaodong Liang ◽  
Scott A. Wallace ◽  
Duc Nguyen
Keyword(s):  
Fault Detection ◽  
Data Driven ◽  
Wide Area ◽  
Rule Based

Rule based classification of neurodegenerative diseases using data driven gait features

2018 ◽  
Vol 9 (4) ◽  
pp. 547-560 ◽  
Author(s):  
Kartikay Gupta ◽  
Aayushi Khajuria ◽  
Niladri Chatterjee ◽  
Pradeep Joshi ◽  
Deepak Joshi
Keyword(s):  
Neurodegenerative Diseases ◽  
Data Driven ◽  
Rule Based ◽  
Gait Features ◽  
Using Data

scholarly journals Digital archiving project of paper maps collected for the International Map Exhibition 1980 in Tokyo

2019 ◽  
Vol 1 ◽  
pp. 1-2
Author(s):  
Hideki Kaji ◽  
Ken’Ichi Tsuruoka ◽  
Ruochen Si ◽  
Min Lu ◽  
Masatoshi Arikawa ◽  
...  
Keyword(s):  
Information Science ◽  
New Technologies ◽  
Spatial Information ◽  
Fiscal Year ◽  
Digital Archive ◽  
Cooperative Research ◽  
Digital Archiving ◽  
Spatial Information Science ◽  
The University ◽  
And Storage

<p><strong>Abstract.</strong> The Kashiwa Library (KL), The University of Tokyo, holds a collection of old paper maps over the world, about a half of which were originally collected for the International Map Exhibition 1980 in Tokyo. The collection has 3,200 maps published in the 1970s and 1980s, and 1,260 of them were displayed at the exhibition. The map collection is important because it represents the cartography at the emerging era of new technologies and techniques such as satellite remote sensing, computers and GIS for map production (Arikawa et al., 2016). These maps were donated from the Japan Cartographers Association in March 2016, after their collection and storage by the association since the exhibition. In the Japanese fiscal year 2017, the Center for Spatial Information Science (CSIS), The University of Tokyo, and KL started a cooperative research project to produce a digital archive of this map collection, with support from the University of Tokyo Academic Archives Project that facilitates digital archiving of academic materials owned by various units at the university. This presentation explains the procedure of making our digital archive “Kashiwanoha Paper Maps Digital Archive”. “Kashiwanoha” is the address of the Kashiwa Campus of The University of Tokyo where KL and CSIS are located, and it literally means “oak leaf”.</p>

scholarly journals Comparative analysis of molecular representations in prediction of cancer drug combination synergy and sensitivity

2021 ◽  
Author(s):  
Bulat Zagidullin ◽  
Ziyan Wang ◽  
Yuanfang Guan ◽  
Esa Pitkänen ◽  
Jing Tang
Keyword(s):  
Drug Combination ◽  
High Throughput Screening ◽  
Data Driven ◽  
Cancer Drug ◽  
Molecular Fingerprints ◽  
Rule Based ◽  
Drug Synergy ◽  
The Past ◽  
Optimal Representation ◽  
Preclinical Drug Development

Application of machine and deep learning (ML/DL) methods in drug discovery and cancer research has gained a considerable amount of attention in the past years. As the field grows, it becomes crucial to systematically evaluate the performance of novel DL solutions in relation to established techniques. To this end we compare rule-based and data-driven molecular representations in prediction of drug combination sensitivity and drug synergy scores using standardized results of 14 high throughput screening studies, comprising 64,200 unique combinations of 4,153 molecules tested in 112 cancer cell lines. We evaluate the clustering performance of molecular fingerprints and quantify their similarity by adapting Centred Kernel Alignment metric. Our work demonstrates that in order to identify an optimal representation type it is necessary to supplement quantitative benchmark results with qualitative considerations, such as model interpretability and robustness, which may vary between and throughout preclinical drug development projects.

scholarly journals PREFACE: TECHNICAL COMMISSION IV ON SPATIAL INFORMATION SCIENCE

2020 ◽  
Vol XLIII-B4-2020 ◽  
pp. 7-9
Author(s):  
S. Zlatanova ◽  
S. Dragicevic ◽  
G. Sithole
Keyword(s):  
Data Fusion ◽  
Peer Review ◽  
Information Science ◽  
Review Process ◽  
Spatial Information ◽  
Peer Review Process ◽  
Human Society ◽  
Wide Range ◽  
Spatial Information Science ◽  
Advance Research

Abstract. The unusual circumstances created by the coronavirus pandemic has impacted recent activities of Commission IV. The situation also provides an excellent opportunity to connect the work of the Commission to addressing an important global problem. Managing the social and economic challenges brought by increased complexity and interconnectivity of activities in human society requires new dimensions of analysing information and specifically spatial information. The increased pressure on the usage of geographic space, maintaining sustainable development and creating liveable community environments increases the requirements for spatial decision-making tools. Commission IV Spatial Information Science (2016–2020) is dedicated to advance research activities in spatial information sciences for modelling, structuring, management, analysis, visualization and simulation of (big) data with focus on the third spatial dimension and taking into consideration dynamic changes. Special attention is given to linking information about real-world physical phenomena with societal, organizational and legal information in order to address the complexity of issues in their entirety. The Commission has contributed to advancements in data modelling, data fusion and management, visualization (web-based, VR and AR), simulation and city analytics, and 3D applications. The work had largely been implemented in cooperation with international organizations such as FIG, UDMS, 3DGeoinfo, ICA, OGC, ISO and Web3D.The Commission consists of 10 scientific areas of research that is coordinated by 10 working groups (WG) as follows - WG1: Strengthen the work on multidimensional spatial model and representations towards seamless data fusion; WG2: Advance the semantic modelling, development and linking of ontologies; WG3: Intensify research into data interpretation, quality and uncertainty modelling; WG4: Strengthen research on crowdsourced data and public participation, towards community-driven and participatory applications, collaborative mapping and use/usability of maps; WG5: Strengthen research on seamless indoor/outdoor location-based services, navigation and tracking, and analysis of human movement; WG6: Advance interoperable Internet of Things, Sensor web, SDI and linked data; WG7: Advance research on spatial data types, indexing methods and analysis to further contribute to development of spatial DBMS for management and analysis of multi-dimensional data; WG8: Encourage the use of functional programming and streaming algorithms in development of demos and applications as well as parallel and distributed processing paradigms; WG9: Advance visual analytics, online multi-dimensional visualization on mobile and desktop devices, considering human-centred applications, privacy and security issues; WG10: Advance knowledge on the use of spatial information (BIM/GIS) for urban modelling; ICWG IV/III: Global Mapping: Updating, Verification and Interoperability with the mission to promote the development of advanced methodologies and applications for the update, verification and interoperability of geospatial databases.The papers received for the ISPRS congress reflect the above-mentioned scientific research areas. The reported research ranges from advancements in new and emerging theories, through experiments and analysis to demonstration of technologies in different applications. The research was captured through papers and abstracts published in the collection of ISPRS Annals and ISPRS Archives. The papers and abstracts were selected for inclusion through a rigorous peer-review process. The ISPRS Annals contain 29 papers and the ISPRS Archives contain 114 papers. The diversity of the research topics presented in the published papers clearly indicate the wide range of topics within the field of Spatial Information Science. A rigorous peer-review process by the ISPRS TC IV Scientific Committee Working Group Chairs ensured hight quality and scientific innovation.

Integrating Rule-Based Systems and Data Analytics Tools Using Open Standard PMML

2015 ◽  
Author(s):  
Yunpeng Li ◽  
Utpal Roy ◽  
Y. Tina Lee ◽  
Sudarsan Rachuri
Keyword(s):  
Expert System ◽  
Expert Systems ◽  
Data Analytics ◽  
Domain Knowledge ◽  
Prediction Models ◽  
Data Driven ◽  
Sensor Data ◽  
Formal Representation ◽  
Rule Based ◽  
Open Standard

Rule-based expert systems such as CLIPS (C Language Integrated Production System) are 1) based on inductive (if-then) rules to elicit domain knowledge and 2) designed to reason new knowledge based on existing knowledge and given inputs. Recently, data mining techniques have been advocated for discovering knowledge from massive historical or real-time sensor data. Combining top-down expert-driven rule models with bottom-up data-driven prediction models facilitates enrichment and improvement of the predefined knowledge in an expert system with data-driven insights. However, combining is possible only if there is a common and formal representation of these models so that they are capable of being exchanged, reused, and orchestrated among different authoring tools. This paper investigates the open standard PMML (Predictive Model Mockup Language) in integrating rule-based expert systems with data analytics tools, so that a decision maker would have access to powerful tools in dealing with both reasoning-intensive tasks and data-intensive tasks. We present a process planning use case in the manufacturing domain, which is originally implemented as a CLIPS-based expert system. Different paradigms in interpreting expert system facts and rules as PMML models (and vice versa), as well as challenges in representing and composing these models, have been explored. They will be discussed in detail.

Sign in / Sign up

Export Citation Format

Share Document