Article
Mathematics
Samiha Fadloun, Khadidja Bennamane, Souham Meshoul, Mahmood Hosseini, Kheireddine Choutri
Summary: This paper proposes a novel approach that combines information visualization and machine learning analyses to automate the retrieval of information elements from complex terms of service. The approach involves creating a dataset and utilizing machine learning models for classification and text summarization. The results demonstrate the promising potential of the approach.
Article
Computer Science, Information Systems
Angela Locoro, William P. Fisher, Luca Mari
Summary: The research aims to explore methods for measuring the effectiveness and efficiency of data graphics, propose a definition of Visual Information Literacy, and design a model characterizing its developmental skills progression. The ultimate goal is to validate the model and contribute to the development of a standard measurement scale for Visual Information Literacy.
Article
Computer Science, Hardware & Architecture
Saeid Mofrad, Ishtiaq Ahmed, Fengwei Zhang, Shiyong Lu, Ping Yang, Heming Cui
Summary: In this article, the SecDATAVIEW distributed BDWMS is proposed, which employs heterogeneous workers like Intel SGX and AMD SEV to protect workflow and data execution. The three major security challenges addressed include reducing TCB size, supporting Java-written workflow tasks, and reducing SGX enclave memory paging overhead. Experimental results show that SecDATAVIEW imposes moderate overhead on workflow execution time.
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2022)
Article
Biochemical Research Methods
Kyle A. O'Connell, Zelaikha B. Yosufzai, Ross A. Campbell, Collin J. Lobb, Haley T. Engelken, Laura M. Gorrell, Thad B. Carlson, Josh J. Catana, Dina Mikdadi, Vivien R. Bonazzi, Juergen A. Klenk
Summary: As genome sequencing becomes more integrated into various fields, the challenge for researchers is shifting from generating raw data to analyzing the vast datasets. This study benchmarks the performance of NVIDIA Parabricks, a GPU-accelerated software suite, on different cloud platforms. The results show significant acceleration in germline variant calling, but variation in somatic variant calling, suggesting the need for platform-specific benchmarking.
BMC BIOINFORMATICS
(2023)
Article
Chemistry, Multidisciplinary
Sebastian Risco, German Molto
Summary: This paper presents a framework aimed at enabling multimedia processing to benefit from the elastic capabilities of serverless applications by supporting customized runtime environments in AWS Lambda. The framework allows for the simultaneous utilization of AWS Lambda and AWS Batch to execute different types of jobs, achieving highly parallel serverless workflows.
APPLIED SCIENCES-BASEL
(2021)
Article
Business
Jorge A. Romero, Cristina Abad
Summary: This study examines the integration of cloud-based big data analytics software with ERP platforms and its impact on productivity. The findings suggest that firms that had implemented SAP already had a competitive advantage over non-SAP adopters in terms of productivity and technology. The study also highlights the importance of understanding the sources of productivity improvement and technological advancements for managers.
MANAGEMENT DECISION
(2022)
Article
Mathematics, Applied
Xiangbin Wen, Zhenghui Wang
Summary: Big data has become an important tool for enterprises to improve efficiency, and effective data mining and analysis can enhance user experience and develop products based on user needs. This study explores the application of big data analytics from the perspective of cloud computing, reviewing references, online data, and conducting fieldwork visits. The results show that data analytics is used across various industries to enhance enterprise benefits. The market size of China's cross-border direct broadcast e-commerce using big data analytics technology is expected to exceed 100 billion yuan in 2022, with a growth rate of 210% compared to the previous year. Reasonable use of data is a problem that needs to be seriously considered.
APPLIED MATHEMATICS AND NONLINEAR SCIENCES
(2023)
Article
Computer Science, Information Systems
Xin Wang, Pei Guo, Xingyan Li, Aryya Gangopadhyay, Carl E. Busart, Jade Freeman, Jianwu Wang
Summary: This article introduces the use of serverless computing and containerization techniques to address the challenges of reproducing batch based Big Data analytics in the cloud. It also presents the development of an open-source toolkit for automated execution and reproducibility. Experiments on AWS and Azure demonstrate that the toolkit achieves good performance, scalability, and efficient reproducibility for cloud-based Big Data analytics.
IEEE TRANSACTIONS ON CLOUD COMPUTING
(2023)
Article
Computer Science, Software Engineering
Velitchko Filipov, Alessio Arleo, Silvia Miksch
Summary: Networks are abstract and ubiquitous data structures consisting of data points and their relationships. Network visualization helps researchers understand connections, gain insights, and detect patterns. In this paper, we provide a meta-survey that discusses and categorizes recent surveys and task taxonomies in the field of network visualization. We also analyze the varying support of available task taxonomies and establish a classification. This research provides an overview and roadmap for current trends and future work in network visualization.
COMPUTER GRAPHICS FORUM
(2023)
Article
Computer Science, Artificial Intelligence
Zeshui Xu, Zijing Ge, Xinxin Wang, Gang Kou
Summary: This paper reviews the research studies on big data for information technology (BDI) and decision making (BDD) from 1994 to 2020 using bibliometrics analysis. The aim is to explore the current status, correlation, future trends, and challenges of BDI and BDD. The study finds that big data has diverse applications in various fields, with the USA, China, and the UK leading in research. The main challenges for the future include big data processing capabilities and network security.
INTERNATIONAL JOURNAL OF INFORMATION TECHNOLOGY & DECISION MAKING
(2023)
Article
Computer Science, Information Systems
Blend Berisha, Endrit Meziu, Isak Shabani
Summary: Big Data and Cloud Computing are two mainstream technologies in the IT field. This paper provides an overview of the importance of Big Data Analytics in various sectors, with a focus on the case study of Google's BigQuery.
JOURNAL OF CLOUD COMPUTING-ADVANCES SYSTEMS AND APPLICATIONS
(2022)
Article
Computer Science, Software Engineering
Alessio Arleo, Christos Tsigkanos, Roger A. Leite, Schahram Dustdar, Silvia Miksch, Johannes Sorger
Summary: This paper presents Sabrina 2.0, a Visual Analytics approach for exploring financial data across different scales. It integrates heterogeneous information sources and generates firm-to-firm financial transaction networks. The evaluation with domain experts demonstrates its ability to generate insights and assist users in exploring a national economy.
COMPUTER GRAPHICS FORUM
(2023)
Article
Computer Science, Information Systems
Nikos Bikakis, Stavros Maroulis, George Papastefanatos, Panos Vassiliadis
Summary: The paper presents the RawVis framework for efficient query processing on large raw data files in interactive exploration and analytics scenarios, which is built on the lightweight in-memory tile-based index VALINOR. Experimental results demonstrate that the RawVis method outperforms existing solutions in terms of response time, disk accesses, and memory consumption, being significantly faster and requiring less memory resources, particularly during exploration scenarios.
INFORMATION SYSTEMS
(2021)
Article
Computer Science, Software Engineering
Matthias Miller, Daniel Fuerst, Hanna Hauptmann, Daniel A. Keim, Mennatallah El-Assady
Summary: This article proposes an approach to enhance the traditional music analysis workflow by complementing it with interactive visualization entities. Through gradual transitions and design-driven visual query filters, analysts can retrace and comprehend the relationship between common music notation (CMN) and abstract data representations, investigating statistical and semantic patterns.
COMPUTER GRAPHICS FORUM
(2022)
Article
Computer Science, Information Systems
Conor Power, Hiren Patel, Alekh Jindal, Jyoti Leeka, Bob Jenkins, Michael Rys, Ed Triou, Dexin Zhu, Lucky Katahanas, Chakrapani Bhat Talapady, Joshua Rowe, Fan Zhang, Rich Draves, Marc Friedman, Ivan Santa Maria Filho, Amrish Kumar
Summary: The paper discusses the evolution of the exabyte-scale Cosmos big data platform at Microsoft, focusing on improvements in scale, reliability, efficiency, and usability, as well as future plans to enhance security, compliance, and support for heterogeneous analytics scenarios. It also explores how the evolution of Cosmos aligns with the development of the big data field and how changes in Cosmos workloads mirror the evolving requirements of industry users.
PROCEEDINGS OF THE VLDB ENDOWMENT
(2021)
Article
Mathematical & Computational Biology
Nina Zhou, Robert D. Brook, Ivo D. Dinov, Lu Wang
Summary: The wide-scale adoption of electronic health records provides extensive information for precision medicine and personalized healthcare. By leveraging free-text clinical information extraction techniques, optimal dynamic treatment regimes can be estimated, allowing for individualized treatments based on patient characteristics and treatment history.
BIOMETRICAL JOURNAL
(2022)
Article
Computer Science, Artificial Intelligence
Rongqian Zhang, Yupeng Zhang, Yuyao Liu, Yunjie Guo, Yueyang Shen, Daxuan Deng, Yongkai Joshua Qiu, Ivo D. Dinov
Summary: This paper introduces a new method for representing, modeling, and analyzing repeated-measurement longitudinal data using tensor-based linear modeling and complex time transformations, providing unique analysis opportunities and techniques.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Computer Science, Interdisciplinary Applications
Nina Zhou, Lu Wang, Simeone Marino, Yi Zhao, Ivo D. Dinov
Summary: This study presents a partially synthetic data generation technique for creating anonymized data archives that closely resemble the original sensitive data. This technique reduces the risk of re-identification while preserving the analytical value of the obfuscated data. It provides an automated tool for effective and collaborative analytics for large time-varying datasets containing sensitive information.
JOURNAL OF ALGORITHMS & COMPUTATIONAL TECHNOLOGY
(2022)
Article
Computer Science, Interdisciplinary Applications
Wenbo Sun, Dipesh Niraula, Issam El Naqa, Randall K. Ten Haken, Ivo Dinov, Kyle Cuneo, Judy (Jionghua) Jin
Summary: This paper presents a systematic method to integrate expert human knowledge with AI recommendations for optimizing clinical decision making. It combines Gaussian process models with deep neural networks to quantify the uncertainty of treatment outcomes given by physicians and AI recommendations, providing guidance for clinical physicians and improving AI models performance.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Public, Environmental & Occupational Health
Apichai Wattanapisit, Hanif Abdul Rahman, Josip Car, Khadizah Haji Abdul-Mumin, Ma. Henrietta Teresa O. de la Cruz, Michael Chia, Michael Rosenberg, Moon-ho Ringo Ho, Surasak Chaiyasong, Trias Mahmudiono, Yuvadee Rodjarkpai, Ivo D. Dinov, Mohammad Ottom, Areekul Amornsriwatanakul
Summary: This study examines the associations between behavioral characteristics, mental wellbeing, demographic characteristics, and health among university students in the ASEAN University Network - Health Promotion Network. Through cluster analysis, the study identifies five clusters of student-types with distinct health behaviors. The findings suggest that interventions should focus on the dominant health-risk behavior, with consideration given to the associated health-risk behaviors within clusters.
Article
Neurosciences
Seok Woo Moon, Lu Zhao, William Matloff, Sam Hobel, Ryan Berger, Daehong Kwon, Jaebum Kim, Arthur W. W. Toga, Ivo D. D. Dinov
Summary: This study examined the association between genetic and neuroimaging biomarkers in late-onset dementia-related cognitive impairment. The results showed significant correlations between specific genomic markers and neuroimaging markers, and identified key markers for distinguishing Alzheimer's disease and mild cognitive impairment.
CNS NEUROSCIENCE & THERAPEUTICS
(2023)
Article
Oncology
Hanif Abdul Rahman, Mohammad Ashraf Ottom, Ivo D. Dinov
Summary: This study aimed to evaluate machine learning algorithms in large-scale datasets, taking into account both younger and older adults from various regions and sociodemographics. The study found that a prediction model based on an artificial neural network performed well in predicting CRC and non-CRC phenotypes.
Article
Multidisciplinary Sciences
Dipesh Niraula, Wenbo Sun, Jionghua Jin, Ivo D. Dinov, Kyle Cuneo, Jamalina Jamaluddin, Martha M. Matuszak, Yi Luo, Theodore S. Lawrence, Shruti Jolly, Randall K. Ten Haken, Issam El Naqa
Summary: This study developed an artificial intelligence-based decision-making framework to assist in dynamic treatment regimes (DTR) for oncology. The framework utilizes advanced machine learning analytics and information-rich multi-omics data to overcome the challenges posed by various variables, treatment response uncertainty, and patient heterogeneity. The framework, demonstrated in Knowledge Based Response-Adaptive Radiotherapy (KBR-ART) applications, consists of two main components and has shown promising results in improving clinical decision-making and treatment outcomes.
SCIENTIFIC REPORTS
(2023)
Article
Psychiatry
Alexander Weigard, Katherine L. McCurry, Zvi Shapiro, Meghan E. Martz, Mike Angstadt, Mary M. Heitzeg, Ivo D. Dinov, Chandra Sripada
Summary: This study developed and tested machine learning models to predict ADHD symptoms in children using neurocognitive abilities, demographics, and child and family characteristics. The models explained 15-20% of the variance in 1-year ADHD symptoms and 12-13% of the variance in 2-year ADHD symptoms. The models showed high generalizability and minimal predictive power loss when applied to new data.
TRANSLATIONAL PSYCHIATRY
(2023)
Article
Pharmacology & Pharmacy
Simeone Marino, Hassan Jassar, Dajung J. J. Kim, Manyoel Lim, Thiago D. D. Nascimento, Ivo D. D. Dinov, Robert A. A. Koeppe, Alexandre F. F. DaSilva
Summary: This study utilized a novel machine learning method to accurately identify migraine patients based on the analysis of central mu-opioid and dopamine D2/D3 receptors. The results showed that dysfunction in the μ-opioid and D2/D3 receptors in the neurotransmission of migraine patients may partly explain the severe impact of migraine and associated neuropsychiatric comorbidities.
FRONTIERS IN PHARMACOLOGY
(2023)
Article
Biotechnology & Applied Microbiology
Mohammad Ashraf Ottom, Hanif Abdul Rahman, Iyad M. Alazzam, Ivo D. Dinov
Summary: This study proposes an enhanced deep neural network approach, the 3D-Znet model, for segmenting brain tumors based on 3D neuroimaging data. It provides automated tumor diagnostics and can help in early tumor diagnosis, potentially saving lives.
BIOENGINEERING-BASEL
(2023)
Article
Biotechnology & Applied Microbiology
Hanif Abdul Rahman, Madeline Kwicklis, Mohammad Ottom, Areekul Amornsriwatanakul, Khadizah H. Abdul-Mumin, Michael Rosenberg, Ivo D. Dinov
Summary: This study utilized machine learning algorithms and artificial intelligence techniques to assess mental well-being and identified the most significant features associated with it. The findings are of great importance for providing cost-effective support and modernizing mental well-being assessment at both individual and university levels.
BIOENGINEERING-BASEL
(2023)
Meeting Abstract
Oncology
D. Niraula, W. Sun, J. Jin, I. D. Dinov, K. C. Cuneo, J. Jamaluddin, M. M. Matuszak, R. K. Ten Haken, I. El Naqa
INTERNATIONAL JOURNAL OF RADIATION ONCOLOGY BIOLOGY PHYSICS
(2022)
Article
Health Care Sciences & Services
Nina Zhou, Qiucheng Wu, Zewen Wu, Simeone Marino, Ivo D. Dinov
Summary: This article introduces a new method called DataSifterText, which can generate partially synthetic clinical free-text and provides high utility preservation while protecting privacy. Experiments have shown that this method is superior to traditional content suppression methods in terms of privacy protection and information preservation.
JOURNAL OF MEDICAL SYSTEMS
(2022)
Article
Engineering, Biomedical
Mohammad Ashraf Ottom, Hanif Abdul Rahman, Ivo D. Dinov
Summary: This paper presents a novel framework for segmenting brain tumors in MR images using deep neural networks and data augmentation strategies. The experimental results demonstrate high performance of the proposed method in localizing and segmenting brain tumors in MR images.
IEEE JOURNAL OF TRANSLATIONAL ENGINEERING IN HEALTH AND MEDICINE
(2022)