Self-Building Artificial Intelligence and Machine Learning to Empower Big Data Analytics in Smart Cities

2023 | Information Systems Frontiers | Citations: 0

Authors: Alahakoon, Damminda; Nawaratne, Rashmika; Xu, Yan; De Silva, Daswin; Sivarajah, Uthayasankar; Gupta, Bhumika

Abstract: The emerging information revolution makes it necessary to manage vast amounts of ... Expand

Abstract: The emerging information revolution makes it necessary to manage vast amounts of unstructured data rapidly. As the world is increasingly populated by IoT devices and sensors that can sense their surroundings and communicate with each other, a digital environment has been created with vast volumes of volatile and diverse data. Traditional AI and machine learning techniques designed for deterministic situations are not suitable for such environments. With a large number of parameters required by each device in this digital environment, it is desirable that the AI is able to be adaptive and self-build (i.e. self-structure, self-configure, self-learn), rather than be structurally and parameter-wise pre-defined. This study explores the benefits of self-building AI and machine learning with unsupervised learning for empowering big data analytics for smart city environments. By using the growing self-organizing map, a new suite of self-building AI is proposed. The self-building AI overcomes the limitations of traditional AI and enables data processing in dynamic smart city environments. With cloud computing platforms, the self-building AI can integrate the data analytics applications that currently work in silos. The new paradigm of the self-building AI and its value are demonstrated using the IoT, video surveillance, and action recognition applications. Collapse

Topics: artificial intelligence smart city big data cloud computing distributed system

Methods: computational algorithm experiment unsupervised learning machine learning longitudinal research

Context-Aware Marketing Attribution Based on Survival Analysis

2023 | International Conference on Business Informatics | Citations: 0

Authors: Züllig, Kilian; Napirata, Stefan; Zimmermann, Steffen

Abstract: Companies increasingly invest in digital marketing channels to promote their pr ... Expand

Abstract: Companies increasingly invest in digital marketing channels to promote their products and services. While the expenditures for each marketing channel are known, the contribution of marketing channels to a successful conversion, and therefore the value they generate, is unknown, but highly relevant for strategic decision-making. In this paper, we develop a novel, context-aware additive hazard marketing attribution (CAHMA) model based on survival analysis to address this problem. In addition to channel-specific, time-decaying effects of marketing on the users' conversion rate, we control for the effects of contextual features, such as the device or country from which users interact with marketing channels. Based on a prototypical implementation, we demonstrate the model's applicability and evaluate it on real-world data from the industry. We find that CAHMA outperforms other models in terms of accuracy while offering unique interpretability of the results and hence, providing deep insights for practitioners into the effects of marketing. Collapse

Topics: marketing management iOS Android mobile system MapReduce

Methods: machine learning survival analysis hazard function design artifact Markov chain Monte Carlo

Theories: probability theory

Predicting Blood Donors Using Machine Learning Techniques

2022 | Information Systems Frontiers | Citations: 0

Authors: Kauten, Christian; Gupta, Ashish; Qin, Xiao; Richey, Glenn

Abstract: The United States’ blood supply chain is experiencing market decline due to rece ... Expand

Abstract: The United States’ blood supply chain is experiencing market decline due to recent innovations in surgical practice, transfusion management, and hospital policy. These innovations strain US blood centers, resulting in cuts to surge capacities, consolidation, and reduced funding for research and outreach programs. In this study, we use data from a regional blood center to explore the application of contemporary machine learning algorithms for modeling donor retention. Such predictive models of donor retention can be used to design more cost effective donor outreach programs. Using data from a large US blood center paired with random forest classifiers, we are able to build a model of donor retention with a Mathews correlation of coefficient of 0.851. Collapse

Topics: database system relational database supply chain management big data missing data

Methods: machine learning computational algorithm decision tree classification random forest classification gradient boosting

Exploring Decomposition for Solving Pattern Mining Problems

2021 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Djenouri, Youcef; Lin, Jerry Chun-Wei; Nørvåg, Kjetil; Ramampiaro, Heri; Yu, Philip S.

Abstract: This article introduces a highly efficient pattern mining technique called Clust ... Expand

Abstract: This article introduces a highly efficient pattern mining technique called Clustering-based Pattern Mining (CBPM). This technique discovers relevant patterns by studying the correlation between transactions in the transaction database based on clustering techniques. The set of transactions is first clustered, such that highly correlated transactions are grouped together. Next, we derive the relevant patterns by applying a pattern mining algorithm to each cluster. We present two different pattern mining algorithms, one applying an approximation-based strategy and another based on an exact strategy. The approximation-based strategy takes into account only the clusters, whereas the exact strategy takes into account both clusters and shared items between clusters. To boost the performance of the CBPM, a GPU-based implementation is investigated. To evaluate the CBPM framework, we perform extensive experiments on several pattern mining problems. The results from the experimental evaluation show that the CBPM provides a reduction in both the runtime and memory usage. Also, CBPM based on the approximate strategy provides good accuracy, demonstrating its effectiveness and feasibility. Our GPU implementation achieves significant speedup of up to 552× on a single GPU using big transaction databases. Collapse

Topics: database system big data high-performance computing Java application programming interface

Methods: computational algorithm experiment cluster analysis DBSCAN k-means clustering

How Data Analytics Competencies Can Foster Business Value– A Systematic Review and Way Forward

2021 | Information Systems Management | Citations: 0

Authors: Klee, Sven; Janson, Andreas; Leimeister, Jan Marco

Abstract: Several authors have illustrated the benefits of data in organizations. For real ... Expand

Abstract: Several authors have illustrated the benefits of data in organizations. For realizing benefits, we see two major challenges for organizations. First, there are necessary investments, which have to be justified. Second, adequate data analytics competencies can be seen as enablers for realizing benefits. We aim to support organizations by showing relevant competencies and achievable business values. We present theoretical propositions and a research agenda on how to move the field of data analytics competencies forward. Collapse

Topics: analytical information system organizational value data management database system programming language

Methods: qualitative interview structured literature research computational algorithm literature sample machine learning

DarkNetExplorer (DNE): Exploring dark multi-layer networks beyond the resolution limit

2021 | Decision Support Systems | Citations: 0

Authors: Pourhabibi, Tahereh; Ong, Kok-Leong; Kam, Booi H.; Boo, Yee Ling

Abstract: Timely identification of terrorist networks within civilian populations could as ... Expand

Abstract: Timely identification of terrorist networks within civilian populations could assist security and intelligence personnel to disrupt and dismantle potential terrorist activities. Finding “small” and “good” communities in multi-layer terrorist networks, where each layer represents a particular type of relationship between network actors, is a vital step in such disruption efforts. We propose a community detection algorithm that draws on the principles of discrete-time random walks to find such “small” and “good” communities in a multi-layer terrorist network. Our algorithm uses several parallel walkers that take short independent random walks towards hubs on a multi-layer network to capture its structure. We first evaluate the correlation between nodes using the extracted walks. Then, we apply an agglomerative clustering procedure to maximize the asymptotical Surprise, which allows us to go beyond the resolution limit and find small and less sparse communities in multi-layer networks. This process affords us a focused investigation on the more important seeds over random actors within the network. We tested our algorithm on three real-world multi-layer dark networks and compared the results against those found by applying two existing approaches – Louvain and InfoMap – to the same networks. The comparative analysis shows that our algorithm outperforms the existing approaches in differentiating “small” and “good” communities. Collapse

Topics: terrorist incident MapReduce IS problem communication service infrastructure knowledge sharing

Methods: computational algorithm agglomerative hierarchical clustering experiment cross sectional research literature study

Big Data Analytics in Building the Competitive Intelligence of Organizations

2021 | International Journal of Information Management | Citations: 6

Authors: Ranjan, Jayanthi; Foropon, Cyril

Abstract: Over recent years, organizations have started to capitalize on the significant u ... Expand

Abstract: Over recent years, organizations have started to capitalize on the significant use of Big Data and emerging technologies to analyze, and gain valuable insights linked to, decision-making processes. The process of Competitive Intelligence (CI) includes monitoring competitors with a view to delivering both actionable and meaningful intelligence to organizations. In this regard, the capacity to leverage and unleash the potential of big data tools and techniques is one of various significant components of successfully steering CI and ultimately infusing such valuable knowledge into CI strategies. In this paper, the authors aim to examine Big Data appli­ cations in CI processes within organizations by exploring how organizations deal with Big Data analytics, and this study provides a context for developing Big Data frameworks and process models for CI in organizations. Overall, research findings have indicated a preference for a rather centralized informal process as opposed to a clear formal structure for CI; the use of basic tools for queries, as opposed to reliance on dedicated methods such as advanced machine learning; and the existence of multiple challenges that companies currently face regarding the use of big data analytics in building organizational CI. Collapse

Topics: big data competitive intelligence decision making social media database system

Methods: qualitative interview business process modeling natural language processing grounded theory machine learning

TextBenDS: a Generic Textual Data Benchmark for Distributed Systems

2021 | Information Systems Frontiers | Citations: 0

Authors: Truică, Ciprian-Octavian; Apostol, Elena-Simona; Darmont, Jérôme; Assent, Ira

Abstract: Extracting top-k keywords and documents using weighting schemes are popular tech ... Expand

Abstract: Extracting top-k keywords and documents using weighting schemes are popular techniques employed in text mining and machine learning for different analysis and retrieval tasks. The weights are usually computed in the data preprocessing step, as they are costly to update and keep track of all the modifications performed on the dataset. Furthermore, calculation errors are introduced when analyzing only subsets of the dataset, i.e., wrong weighting are computed as weighting schemes use the number of documents for scoring keywords and documents. Therefore, in a Big Data context, it is crucial to lower the runtime of computing weighting schemes, without hindering the analysis process and the accuracy of the machine learning algorithms. To address this requirement for the task of computing top-k keywords and documents (which largely relies on weighting schemes), it is customary to design benchmarks that compare weighting schemes within various configurations of distributedframeworks and database management systems. Thus, we propose TextBenDS - a generic document-oriented benchmark for storing textual data and constructing weighting schemes. Our benchmark offers a generic data model designed with a multidimensional approach for storing text documents. We also propose using aggregation queries with various complexities and selectivities for constructing term weighting schemes, that are utilized in extracting top-k keywords and documents. We evaluate the computing performance of the queries on several distributed environments set within the Apache Hadoop ecosystem. Our experimental results provide interesting insights. As an example, MongoDB shows the best overall performance, while Spark’s execution time remains almost constant regardless of weighting schemes. Collapse

Topics: information retrieval MongoDB database system distributed system MapReduce

Methods: term frequency–inverse document frequency Okapi BM25 experiment design science qualitative content analysis

Upgrading Products based on Existing Dominant Competitors

2021 | HICSS | Citations: 0

Authors: Wijayanto, Heri; Thamrin, Syauki; Chen, Arbee L.P.

Abstract: In the Industry 4.0 era, manufacturers compete to produce better products that a ... Expand

Abstract: In the Industry 4.0 era, manufacturers compete to produce better products that are expected to satisfy a larger number of customers. We propose a recommendation system for upgrading products considering user preferences. This approach is based on the dominating regions of dominant competitors. The dominating region represents the estimation of the number of potential customers. However, examining overlapped dominating regions for a high dimensional space is NP-hard. We propose a novel method named TDRDFS which constructs a Dominant Graph of Intersection skyline points (DGI) for modeling the dominating regions. Our experiments show that TDRDFS significantly reduces computation. Based on our approach, product vendors are able to determine the strategy of upgrading products easily. Collapse

Topics: recommender system MapReduce parallel computing personal computer smartphone

Methods: computational algorithm experiment literature study

Big data management in healthcare: Adoption challenges and implications

2020 | International Journal of Information Management | Citations: 8

Authors: Chen, Peng-Ting; Lin, Chia-Li; Wu, Wan-Ning

Abstract: The computerized healthcare information system has undergone tremendous advancem ... Expand

Abstract: The computerized healthcare information system has undergone tremendous advancements in the previous two decades. Medical institutions are paying further attention to the replacement of traditional approaches that can no longer handle the increasing amount of patient data. In recent years, the healthcare information system based on big data has been growing rapidly and is being adapted to medical information to derive important health trends and support timely preventive care. This research aims to evaluate organization-driven barriers in implementing a healthcare information system based on big data. It adopts the analytic network process approach to determine the aspect weight and applies VlseKriterijumska Optimizacija I Kzompromisno Resenje (VIKOR) to conclude a highly appropriate strategy for overcoming such barriers. The proposed model can provide hospital managers with forecasts and implications that facilitate the withdrawal of organizational barriers when adopting the healthcare information system based on big data into their healthcare service system. Results can provide benefits for increasing the effectiveness and quality of the healthcare information system based on big data in the healthcare industry. Therefore, by understanding the sequence of the importance of resistance factors, managers can formulate efficient strategies to solve problems with appropriate priorities. Collapse

Topics: big data innovation management health information system internet of things mobile system

Methods: qualitative interview survey personal interview simulation VIKOR method