About

Adrian S. Barb received his B.S. in industrial engineering from the University of Bucharest. He earned his Ph.D. in computer science and an MBA from the University of Missouri, where he also worked as a database programmer-analyst and web system coordinator. Dr. Barb teaches database management and information retrieval. His research interests include database management systems, knowledge discovery in databases, database indexing, knowledge representation and exchange in content-based retrieval systems, semantic modeling and retrieval, conceptual change in knowledge-based systems, ontology integration, and expert-in-the-loop knowledge exchange.

Research topics

• Computer science
• Information retrieval
• Data mining
• Artificial intelligence
• Knowledge management

Selected publications

• Toward Deriving a Digital Ontology for Systems Engineering and Acquisition Groups

  Conference on systems engineering research series · 2024-01-01

  book-chapterSenior author
  PublisherDOI

• Analysis of IoT Privacy Policies in Smart Transportation Systems

  Conference on systems engineering research series · 2024-01-01

  book-chapterSenior author
  PublisherDOI

• Knowledge elicitation methodology for evaluation of Internet of Things privacy characteristics in smart cities

  Systems Engineering · 2023 · 9 citations

  • Computer Science
  • Computer Security
  • Computer Science

  Abstract One of the impediments to transforming urban cities into smart cities is the security and privacy concerns that arise due to use of Internet of Things (IoT) devices in various smart city applications. While IoT device vendors publish their security and privacy policies, manual evaluation of these policies is tedious and prone to misinterpretation as there is a lot of variability in the language used across IoT vendors. Local administrations and policy analysts are faced with understanding the implications of integrating IoT devices with differing security and privacy characteristics but lack methods that support them in analysis of privacy characteristics from a holistic perspective. In this paper, a methodology for knowledge elicitation from textual information is outlined to evaluate privacy characteristics of IoT devices. The methodology includes natural language processing and deep learning techniques to evaluate the relevance of IoT privacy policies to the National Institute of Standards and Technology (NIST) security and privacy framework 5 . Based on the analysis, text similarity scores are calculated for each IoT privacy policy document and each section of the policy document is labeled to NIST categories and functions. Analysis of these resulting labels and scores helps analysts to gain insights on each privacy policy as well as provide a holistic perspective of the privacy characteristics of IoT devices used in smart city applications. For example, all the policy documents used in the study talk about Protect domain and half of the documents cover Detect domain. However, most of the policies contain gaps regarding the Identify , Respond , and Recover domains. The study has implications for policy analysts, IoT vendors, and smart city administrators in terms of understanding the privacy gaps in IoT devices with respect to the NIST framework which can ultimately support policy alignment to address privacy concerns for smart cities.

  PublisherOA PDFDOI

• Semantic Fusion with Deep Learning and Formal Ontologies for Evaluation of Policies and Initiatives in the Smart City Domain

  Applied Sciences · 2021-10-26 · 5 citations

  articleOpen accessSenior author

  Decision makers and policy analysts at different administrative levels often lack a holistic view of the problem as there are semantic variations in policy documents due to domain-specific content. For example, smart city initiatives are derived from national and international initiatives which may influence the incentives for local participants, but local initiatives reflect the local contextual elements of the city. Balanced assessment of smart city initiatives should include a systemic evaluation of the initiatives at multiple levels including the city, the country in which the city resides as well as at international level. In this paper, a knowledge elicitation methodology is presented for multi-granularity evaluation of policies and initiatives. The methodology is demonstrated on the evaluation of smart city initiatives generated at different administrative levels. Semantic networks are constructed using formal ontologies and deep learning methods for automatic semantic evaluation of initiatives to abstract knowledge found in text. Three smart city initiatives published by different administrative levels including international, national, and city level are evaluated in terms of relevance, coherence, and alignment of multi-level smart city initiatives. Experiments and analysis ultimately provide a holistic view of the problem which is necessary for decision makers and policy analysts of smart cities.

  PublisherOA PDFDOI

• Applications of Natural Language Techniques to Enhance Curricular Coherence

  Procedia Computer Science · 2020 · 7 citations

  1st authorCorresponding
  • Computer Science
  • Computer Science
  • Mathematics education

  An effective and highly efficient curriculum is the foundation of an optimal content delivery to students and may lead to the success of the academic program. Ensuring the effectiveness of curricular processes goes beyond the successful design of individual courses and it is subject to careful planning in accordance to appropriate policies and procedures that enable a high level of curriculum coherence. Such curriculum can guarantee that students are presented with a complete set of interrelated topics related to the area of study that can enable students to connect topics in individual courses and apply them in professional settings. The goal of this article is to evaluate the curriculum coherence of an Information Science program using ontologies and natural language processing techniques. Curricular coherence is evaluated using a possibilistic approach which evaluates academic gaps and overlaps that exist in the core courses offered in the degree. The use of ontologies enables us to perform a qualitative study of curricular coherence at different levels of ontological abstraction using mereotopological principles. The knowledge inferred from this process can be used at the universities to optimize their course offering and content for better academic content.

  PublisherDOI

• Smart City Document Evaluation to Support Policy Analysis

  2022 IEEE International Systems Conference (SysCon) · 2020 · 3 citations

  Senior author
  • Computer Science
  • Computer Science
  • Data science

  Local administrations face many challenges in their shift to smart city development. One of the main challenges is in the area of governance and identification of policy strategies that ensure successful integration of new technologies. In this article we explore a methodology for knowledge elicitation from textual information to identify smart city development trends. Our goal is to evaluate and predict the relevance of documents, especially press releases, to different areas of smart city development. Our methodology includes natural language processing techniques to possibilistically evaluate the relevance of a text to several smart city development areas. Relevant concepts are further associated to domain ontologies and expanded using data fusion techniques to evaluate the relevance of information in text to the areas of smart city development. We test our approach on a large number of documents from the smart city development community.

  PublisherDOI

• Study of Academic Writing Evolution in Geospatial Domain Using Natural Language Processing Techniques

  2020-09-26

  article1st authorCorresponding

  Academic writing is known for a formalized discourse that tends to persist over time. However, evolution of academic writings became an interesting topic due to the fast-pace dynamics of technology in recent years. In this article, we analyze changes in academic texts for the geospatial domain. We collected and analyzed articles submitted to the IGARSS conference over the past ten years and evaluated how the overall organization of written patterns relate to formalized knowledge in geospatial ontologies and how they have evolved over time.

  PublisherDOI

• Multi-level Evaluation of Smart City Initiatives Using the SUMO Ontology and Choquet Integral

  Smart innovation, systems and technologies · 2020-05-29 · 2 citations

  book-chapterSenior author
  PublisherDOI

• Program Committee and Reviewers

  2019-12-01

  articleOpen access
  PublisherOA PDFDOI

• A statistical study of the relevance of lines of code measures in software projects

  Innovations in Systems and Software Engineering · 2014-05-06 · 14 citations

  article1st authorCorresponding
  PublisherDOI

Frequent coauthors

• Chi‐Ren Shyu

  16 shared

• Nil Kilicay‐Ergin

  11 shared

• Mary S. Schaeffer

  Janssen (Belgium)

  5 shared

• Samira Sadaoui

  3 shared

• Namrata Chaudhary

  Datta Meghe Institute of Medical Sciences

  2 shared

• Curt H. Davis

  University of Missouri

  2 shared

• Jonathon Hare

  University of Southampton

  2 shared

• Morgan Chase

  University of Toledo

  2 shared