More Like this

1. Fuzzy-Based Conversational Recommender for Data-intensive Science Gateway Applications

   https://doi.org/10.1109/BigData.2018.8622046  

   Chandrashekara, A; Talluri, R; Sivarathri, S; Mitra, R; Calyam, P; Kee, K; Nair, S. S (January 2018, IEEE International Workshop on Conversational Agents and Chatbots with Machine Learning (ChatbotML), in conjunction with IEEE Big Data)

   Neuro-scientists are increasingly relying on parallel and distributed computing resources for analysis and visualization of their neuron simulations. Although science gateways have democratized relevant high performance/throughput resources, users require expert knowledge about programming and infrastructure configuration that is beyond the repertoire of most neuroscience programs. These factors become deterrents for the successful adoption and the ultimate diffusion (i.e., systemic spread) of science gateways in the neuroscience community. In this paper, we present a novel intuitionistic fuzzy logic based conversational recommender that can provide guidance to users when using science gateways for research and education workflows. The users interact with a context-aware chatbot that is embedded within custom web-portals to obtain simulation tools/resources to accomplish their goals. In order to ensure user goals are met, the chatbot profiles a user’s cyberinfrastructure and neuroscience domain proficiency level using a ‘usability quadrant’ approach. Simulation of user queries for an exemplary neuroscience use case demonstrates that our chatbot can provide step-by-step navigational support and generate distinct responses based on user proficiency. 

   more » « less
2. Recommender-as-a-Service with Chatbot Guided Domain-science Knowledge Discovery in a Science Gateway

   https://doi.org/10.1002/cpe.6080  

   Vekaria, K.; Calyam, P.; Sivarathri, S.; Wang, S.; Zhang, Y.; Pandey, A.; Chen, C.; Xu, D.; Joshi, T.; Nair, S.S. (January 2020, Wiley Concurrency and Computation: Practice and Experience)

   Scientists in disciplines such as neuroscience and bioinformatics are increasingly relying on science gateways for experimentation on voluminous data, as well as analysis and visualization in multiple perspectives. Though current science gateways provide easy access to computing resources, datasets and tools specific to the disciplines, scientists often use slow and tedious manual efforts to perform knowledge discovery to accomplish their research/education tasks. Recommender systems can provide expert guidance and can help them to navigate and discover relevant publications, tools, data sets, or even automate cloud resource configurations suitable for a given scientific task. To realize the potential of integration of recommenders in science gateways in order to spur research productivity,we present a novel “OnTimeRecommend" recommender system. The OnTimeRecommend comprises of several integrated recommender modules implemented as microservices that can be augmented to a science gateway in the form of a recommender-as-a-service. The guidance for use of the recommender modules in a science gateway is aided by a chatbot plug-in viz., Vidura Advisor. To validate our OnTimeRecommend, we integrate and show benefits for both novice and expert users in domain-specific knowledge discovery within two exemplar science gateways, one in neuroscience (CyNeuro) and the other in bioinformatics (KBCommons). 

   more » « less
3. Sifting Through Clutter and Finding Answers that Utter Among COVID-19 Data for Medical Users via Gateways

   https://doi.org/10.5281/zenodo.10028564  

   Shibo, Bruce Wang; Oruche, Roland; Goni, Muhammad Ashraful; Cheng, Xiyao; Milman, Eric; Calyam, Prasad; Kee, Kerk (January 2023, Zenodo)

   Science gateways have been a crucial tool that lowers the barriers of computer language proficiency for researchers and scientists alike to implement digital tools to further their research agendas. However, gateways remain somewhat esoteric and difficult to use for many potential users. A chatbot has been proposed as a solution to aid gateway users and for the improvement of gateway usability. Via in-depth interviews with 10 medical professionals, we investigated the challenges they faced when extracting data, namely, slow speed, limited scope, and mixed quality of data. We suggest future gateway developments to address the issues that medical professionals face when searching for publications and data. Findings suggest that gateways could serve practitioners (i.e., clinicians, healthcare providers in this case), beyond the original vision for research and education. Moreover, gateway projects could consider conducting similar market research interviews to better understand the work context (including challenges) faced by the intended users of specific gateways. 

   more » « less
4. "Bring-your-own" Plug-in Management Middleware for Programmable Science Gateways.

   Vekaria, K B; Calyam, P; Oruche, R; Zhang, Y; Wang, S (October 2020, Gateways 2020)

   There is a growing need for next-generation science gateways to increase the accessibility of data sets and cloud computing resources using latest technologies. Most science gateways today are built for specific purposes with pre-defined workflows, user interfaces, and fixed computing resources. There is a need to modernize them with middleware that can provide ‘plug in’ support to programmatically increase their extensibility and scalability to meet users’ growing needs. In this paper, we propose a novel middleware that can be integrated into science gate ways using a “bring-your-own” plug-in management approach. This approach features microservice architectures to decouple applications, and allows users (i.e., administrators, developers, researchers) to customize and incorporate domain-specific components in an existing science gateway. We detail the application programming interfaces in our middleware for creation of end-to end pipelines with diverse infrastructure, customized processes, detailed monitoring and flexible programmability for a scientific domain. We also demonstrate via a OnTimeRecommend case study on how our “bring-your-own” approach can be seamlessly integrated by a science gateway administrator/developer using a web application. 

   more » « less
5. Chatbot Guided Domain-science Knowledge Discovery in a Science Gateway Application

   S. Sivarathri, S.; Calyam, P.; Zhang, Y.; Pandey, A.; Chen, C.; Xu, D.; Joshi, T.; Nair, S.S. (January 2019, 14th Gateway Computing Environments Conference)

   Neuroscientists are increasingly relying on high performance/throughput computing resources for experimentation on voluminous data, analysis and visualization at multiple neural levels. Though current science gateways provide access to computing resources, datasets and tools specific to the disciplines, neuroscientists require guided knowledge discovery at various levels to accomplish their research/education tasks. The guidance can help them to navigate them through relevant publications, tools, topic associations and cloud platform options as they accomplish important research and education activities. To address this need and to spur research productivity and rapid learning platform development, we present “OnTimeRecommend”, a novel recommender system that comprises of several integrated recommender modules through RESTful web services. We detail a neuroscience use case in a CyNeuro science gateway, and show how the OnTimeRecommend design can enable novice/expert user interfaces, as well as template-driven control of heterogeneous cloud resources. 

   more » « less