Showing items 1 - 14 of 14

Your selections:

Themes in data mining, big data, and crime analytics

- Oatley,Giles

  • Authors: Oatley,Giles
  • Date: 2022
  • Type: Text , Journal article , Review
  • Relation: Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery Vol. 12, no. 2 (2022), p.
  • Full Text:
  • Reviewed:
  • Description: This article examines the impact of new AI-related technologies in data mining and big data on important research questions in crime analytics. Because the field is so broad, the review focuses on a selection of the most important topics. Challenges for information management, and in turn law and society, include: AI-powered predictive policing; big data for legal and adversarial decisions; bias using big data and analytics in profiling and predicting criminality; forecasting crime risk and crime rates; and, regulating AI systems. This article is categorized under: Algorithmic Development > Spatial and Temporal Data Mining Fundamental Concepts of Data and Knowledge > Big Data Mining Technologies > Artificial Intelligence Application Areas > Data Mining Software Tools. © 2021 Wiley Periodicals LLC.

A smart healthcare monitoring system for heart disease prediction based on ensemble deep learning and feature fusion

- Ali, Farman, El-Sappagh, Shaker, Islam, S., Kwak, Daehan, Ali, Amjad, Imran, Muhammad, Kwak, Kyung-Sup

  • Authors: Ali, Farman , El-Sappagh, Shaker , Islam, S. , Kwak, Daehan , Ali, Amjad , Imran, Muhammad , Kwak, Kyung-Sup
  • Date: 2020
  • Type: Text , Journal article
  • Relation: Information Fusion Vol. 63, no. (2020), p. 208-222
  • Full Text: false
  • Reviewed:
  • Description: The accurate prediction of heart disease is essential to efficiently treating cardiac patients before a heart attack occurs. This goal can be achieved using an optimal machine learning model with rich healthcare data on heart diseases. Various systems based on machine learning have been presented recently to predict and diagnose heart disease. However, these systems cannot handle high-dimensional datasets due to the lack of a smart framework that can use different sources of data for heart disease prediction. In addition, the existing systems utilize conventional techniques to select features from a dataset and compute a general weight for them based on their significance. These methods have also failed to enhance the performance of heart disease diagnosis. In this paper, a smart healthcare system is proposed for heart disease prediction using ensemble deep learning and feature fusion approaches. First, the feature fusion method combines the extracted features from both sensor data and electronic medical records to generate valuable healthcare data. Second, the information gain technique eliminates irrelevant and redundant features, and selects the important ones, which decreases the computational burden and enhances the system performance. In addition, the conditional probability approach computes a specific feature weight for each class, which further improves system performance. Finally, the ensemble deep learning model is trained for heart disease prediction. The proposed system is evaluated with heart disease data and compared with traditional classifiers based on feature fusion, feature selection, and weighting techniques. The proposed system obtains accuracy of 98.5%, which is higher than existing systems. This result shows that our system is more effective for the prediction of heart disease, in comparison to other state-of-the-art methods. © 2020

Forensic intelligence and the analytical process

- Oatley, Giles, Chapman, Brendan, Speers, James

  • Authors: Oatley, Giles , Chapman, Brendan , Speers, James
  • Date: 2020
  • Type: Text , Journal article
  • Relation: Wiley interdisciplinary reviews. Data mining and knowledge discovery Vol. 10, no. 3 (2020), p.
  • Full Text: false
  • Reviewed:
  • Description: A review was undertaken of the developments made with integrating forensicevidence into the analytical process to support police investigations. Evidencesuch as DNA, fingerprints, fibers, accelerants, tyre marks, and so forth, cansupport to differing degrees the various working theories or hypotheses aboutthe nature of the alleged crime, the persons of interest and the modusoperandi. Investigators however, either forensic or detective, bring variousbiases to evidence capture and analysis, biases which are better understood inthe intelligence community. Structured analytical techniques have a long his-tory in intelligence analysis, for example analysis of competing hypotheses,which serves several purposes: information sharing, clarity of communication,and to highlight the common forms of bias brought to bear in an investigation.We illustrate the representation of links based on traces and intelligence, andhow these can be stored in databases permitting better“reasoning”with evi-dence. We also present some recommendations for integration of forensic intelligence into the investigative analytic process and review information sys-tems in this area

Establishing effective communications in disaster affected areas and artificial intelligence based detection using social media platform

- Raza, Mohsin, Awais, Muhammad, Ali, Kamran, Aslam, Nauman, Paranthaman, Vishnu, Imran, Muhammad, Ali, Farman

  • Authors: Raza, Mohsin , Awais, Muhammad , Ali, Kamran , Aslam, Nauman , Paranthaman, Vishnu , Imran, Muhammad , Ali, Farman
  • Date: 2020
  • Type: Text , Journal article
  • Relation: Future Generation Computer Systems Vol. 112, no. (2020), p. 1057-1069
  • Full Text:
  • Reviewed:
  • Description: Floods, earthquakes, storm surges and other natural disasters severely affect the communication infrastructure and thus compromise the effectiveness of communications dependent rescue and warning services. In this paper, a user centric approach is proposed to establish communications in disaster affected and communication outage areas. The proposed scheme forms ad hoc clusters to facilitate emergency communications and connect end-users/ User Equipment (UE) to the core network. A novel cluster formation with single and multi-hop communication framework is proposed. The overall throughput in the formed clusters is maximized using convex optimization. In addition, an intelligent system is designed to label different clusters and their localities into affected and non-affected areas. As a proof of concept, the labeling is achieved on flooding dataset where region specific social media information is used in proposed machine learning techniques to classify the disaster-prone areas as flooded or unflooded. The suitable results of the proposed machine learning schemes suggest its use along with proposed clustering techniques to revive communications in disaster affected areas and to classify the impact of disaster for different locations in disaster-prone areas. © 2020 Elsevier B.V.

Device-centric adaptive data stream management and offloading for analytics applications in future internet architectures

- Rehman, Muhammad, Liew, Chee, Wah, Teh, Imran, Muhammad, Salah, Khaled, Nasser, Nidal, Svetinovic, Davor

  • Authors: Rehman, Muhammad , Liew, Chee , Wah, Teh , Imran, Muhammad , Salah, Khaled , Nasser, Nidal , Svetinovic, Davor
  • Date: 2021
  • Type: Text , Journal article
  • Relation: Future Generation Computer Systems Vol. 114, no. (2021), p. 155-168
  • Full Text: false
  • Reviewed:
  • Description: Information-Centric Networking (ICN) enables in-network data management and communication between multiple parties by replicating data and activating interactions between decoupled senders and receivers. Existing data management and offloading schemes in ICNs primarily use the transport layer hence it becomes inefficient to actively develop and update the ICN standards because of continuously evolving heterogeneous future internet architectures such as mobile edge cloud computing (MECC) architectures. In this paper, we present an adaptive execution model for mobile data stream mining (MDSM) applications in MECC environments to enable device-centric adaptive data management and offloading. We designed the proposed execution model considering multiple factors of complexity such as volume and velocity of continuously streaming data, the selection of data fusion and data preprocessing methods, the choice of learning models, learning rates, learning modes, mobility, limited computational and memory resources in mobile devices, the high coupling between application components, and dependency over Internet connections. We integrated the proposed execution model with multiple MDSM applications mapping to a real-word use-case for activity detection using MECC as a future network architecture. We thoroughly evaluated the proposed execution model in terms of battery power consumption, memory utilization, makespan, accuracy, and the amount of data reduced during in-network communication. The comparison showed that our proposed adaptive execution model outperformed the static and dynamic execution models which were deployed in the same ICN architecture. © 2020 Elsevier B.V.

Transformer based deep intelligent contextual embedding for twitter sentiment analysis

- Naseem, Usman, Razzak, Imran, Musial, Katarzyna, Imran, Muhammad

  • Authors: Naseem, Usman , Razzak, Imran , Musial, Katarzyna , Imran, Muhammad
  • Date: 2020
  • Type: Text , Journal article
  • Relation: Future Generation Computer Systems Vol. 113, no. (2020), p. 58-69
  • Full Text: false
  • Reviewed:
  • Description: Along with the emergence of the Internet, the rapid development of handheld devices has democratized content creation due to the extensive use of social media and has resulted in an explosion of short informal texts. Although a sentiment analysis of these texts is valuable for many reasons, this task is often perceived as a challenge given that these texts are often short, informal, noisy, and rich in language ambiguities, such as polysemy. Moreover, most of the existing sentiment analysis methods are based on clean data. In this paper, we present DICET, a transformer-based method for sentiment analysis that encodes representation from a transformer and applies deep intelligent contextual embedding to enhance the quality of tweets by removing noise while taking word sentiments, polysemy, syntax, and semantic knowledge into account. We also use the bidirectional long- and short-term memory network to determine the sentiment of a tweet. To validate the performance of the proposed framework, we perform extensive experiments on three benchmark datasets, and results show that DICET considerably outperforms the state of the art in sentiment classification. © 2020 Elsevier B.V.

Attributed collaboration network embedding for academic relationship mining

- Wang, Wei, Liu, Jiaying, Tang, Tao, Tuarob, Suppawong, Xia, Feng, Gong, Zhiguo, King, Irwin

  • Authors: Wang, Wei , Liu, Jiaying , Tang, Tao , Tuarob, Suppawong , Xia, Feng , Gong, Zhiguo , King, Irwin
  • Date: 2021
  • Type: Text , Journal article
  • Relation: ACM Transactions on the Web Vol. 15, no. 1 (2021), p.
  • Full Text:
  • Reviewed:
  • Description: Finding both efficient and effective quantitative representations for scholars in scientific digital libraries has been a focal point of research. The unprecedented amounts of scholarly datasets, combined with contemporary machine learning and big data techniques, have enabled intelligent and automatic profiling of scholars from this vast and ever-increasing pool of scholarly data. Meanwhile, recent advance in network embedding techniques enables us to mitigate the challenges of large scale and sparsity of academic collaboration networks. In real-world academic social networks, scholars are accompanied with various attributes or features, such as co-authorship and publication records, which result in attributed collaboration networks. It has been observed that both network topology and scholar attributes are important in academic relationship mining. However, previous studies mainly focus on network topology, whereas scholar attributes are overlooked. Moreover, the influence of different scholar attributes are unclear. To bridge this gap, in this work, we present a novel framework of Attributed Collaboration Network Embedding (ACNE) for academic relationship mining. ACNE extracts four types of scholar attributes based on the proposed scholar profiling model, including demographics, research, influence, and sociability. ACNE can learn a low-dimensional representation of scholars considering both scholar attributes and network topology simultaneously. We demonstrate the effectiveness and potentials of ACNE in academic relationship mining by performing collaborator recommendation on two real-world datasets and the contribution and importance of each scholar attribute on scientific collaborator recommendation is investigated. Our work may shed light on academic relationship mining by taking advantage of attributed collaboration network embedding. © 2020 ACM.

Educational anomaly analytics : features, methods, and challenges

- Guo, Teng, Bai, Xiaomei, Tian, Xue, Firmin, Selena, Xia, Feng

  • Authors: Guo, Teng , Bai, Xiaomei , Tian, Xue , Firmin, Selena , Xia, Feng
  • Date: 2022
  • Type: Text , Journal article , Review
  • Relation: Frontiers in Big Data Vol. 4, no. (2022), p.
  • Full Text:
  • Reviewed:
  • Description: Anomalies in education affect the personal careers of students and universities' retention rates. Understanding the laws behind educational anomalies promotes the development of individual students and improves the overall quality of education. However, the inaccessibility of educational data hinders the development of the field. Previous research in this field used questionnaires, which are time- and cost-consuming and hardly applicable to large-scale student cohorts. With the popularity of educational management systems and the rise of online education during the prevalence of COVID-19, a large amount of educational data is available online and offline, providing an unprecedented opportunity to explore educational anomalies from a data-driven perspective. As an emerging field, educational anomaly analytics rapidly attracts scholars from a variety of fields, including education, psychology, sociology, and computer science. This paper intends to provide a comprehensive review of data-driven analytics of educational anomalies from a methodological standpoint. We focus on the following five types of research that received the most attention: course failure prediction, dropout prediction, mental health problems detection, prediction of difficulty in graduation, and prediction of difficulty in employment. Then, we discuss the challenges of current related research. This study aims to provide references for educational policymaking while promoting the development of educational anomaly analytics as a growing field. Copyright © 2022 Guo, Bai, Tian, Firmin and Xia.

Development and governance of FAIR thresholds for a data federation

- Wong, Megan, Levett, Kerry, Lee, Ashlin, Box, Paul, Simons, Bruce, David, Rakesh, Macleod, Andrew, Taylor, Nicolas, Schneider, Derek, Thompson, Helen

  • Authors: Wong, Megan , Levett, Kerry , Lee, Ashlin , Box, Paul , Simons, Bruce , David, Rakesh , Macleod, Andrew , Taylor, Nicolas , Schneider, Derek , Thompson, Helen
  • Date: 2022
  • Type: Text , Journal article
  • Relation: Data Science Journal Vol. 21, no. (2022), p.
  • Full Text:
  • Reviewed:
  • Description: The FAIR (findable, accessible, interoperable, and re-usable) principles and practice recommendations provide high level guidance and recommendations that are not research-domain specific in nature. There remains a gap in practice at the data provider and domain scientist level demonstrating how the FAIR principles can be applied beyond a set of generalist guidelines to meet the needs of a specific domain community. We present our insights developing FAIR thresholds in a domain specific context for self-governance by a community (agricultural research). ‘Minimum thresholds’ for FAIR data are required to align expectations for data delivered from providers’ distributed data stores through a community-governed federation (the Agricultural Research Federation, AgReFed). Data providers were supported to make data holdings more FAIR. There was a range of different FAIR starting points, organisational goals, and end user needs, solutions, and capabilities. This informed the distilling of a set of FAIR criteria ranging from ‘Minimum thresholds’ to ‘Stretch targets’. These were operationalised through consensus into a framework for governance and implementation by the agricultural research domain community. Improving the FAIR maturity of data took resourcing and incentive to do so, highlighting the challenge for data federations to generate value whilst reducing costs of participation. Our experience showed a role for supporting collective advocacy, relationship brokering, tailored support, and low-bar tooling access particularly across the areas of data structure, access and semantics that were challenging to domain researchers. Active democratic participation supported by a governance framework like AgReFed’s will ensure participants have a say in how federations can deliver individual and collective benefits for members. © 2022 The Author(s).

A new dimensionality-unbiased score for efficient and effective outlying aspect mining

- Samariya, Durgesh, Ma, Jiangang

  • Authors: Samariya, Durgesh , Ma, Jiangang
  • Date: 2022
  • Type: Text , Journal article
  • Relation: Data Science and Engineering Vol. 7, no. 2 (2022), p. 120-135
  • Full Text:
  • Reviewed:
  • Description: The main aim of the outlying aspect mining algorithm is to automatically detect the subspace(s) (a.k.a. aspect(s)), where a given data point is dramatically different than the rest of the data in each of those subspace(s) (aspect(s)). To rank the subspaces for a given data point, a scoring measure is required to compute the outlying degree of the given data in each subspace. In this paper, we introduce a new measure to compute outlying degree, called Simple Isolation score using Nearest Neighbor Ensemble (SiNNE), which not only detects the outliers but also provides an explanation on why the selected point is an outlier. SiNNE is a dimensionally unbias measure in its raw form, which means the scores produced by SiNNE are compared directly with subspaces having different dimensions. Thus, it does not require any normalization to make the score unbiased. Our experimental results on synthetic and publicly available real-world datasets revealed that (i) SiNNE produces better or at least the same results as existing scores. (ii) It improves the run time of the existing outlying aspect mining algorithm based on beam search by at least two orders of magnitude. SiNNE allows the existing outlying aspect mining algorithm to run in datasets with hundreds of thousands of instances and thousands of dimensions which was not possible before. © 2022, The Author(s).

Memetic moments : the speed of twitter memes

- Smith, Naomi, Copland, Simon

  • Authors: Smith, Naomi , Copland, Simon
  • Date: 2021
  • Type: Text , Journal article
  • Relation: Journal of Digital Social Research Vol. , no. (2021), p. 23-48
  • Full Text:
  • Reviewed:
  • Description: This paper examines how speed shapes internet culture. To do so, it analyses ‘memetic moments’ on Twitter, short-lived and rapidly circulated memes that quickly reach saturation. The paper examines two ‘memetic moments’ on Twitter in 2018 and 2019 to assess how they develop over time. Each case study comprises a week’s worth of relevant tweets that were analysed for temporal patterns. We analyse these ‘memetic moments’ through Lefebvre’s (2004) work on rhythmanalysis, arguing that the temporal patterns of memes on Twitter can be understood through his concepts of repetition, presence and dialogue. While seemingly trivial, memetic moments underscore the didactic relationship between social media and news media while also providing a way to approach complex social issues.

Finding compact and well-separated clusters : clustering using silhouette coefficients

- Bagirov, Adil, Aliguliyev, Ramiz, Sultanova, Nargiz

  • Authors: Bagirov, Adil , Aliguliyev, Ramiz , Sultanova, Nargiz
  • Date: 2023
  • Type: Text , Journal article
  • Relation: Pattern Recognition Vol. 135, no. (2023), p.
  • Relation: http://purl.org/au-research/grants/arc/DP190100580
  • Full Text: false
  • Reviewed:
  • Description: Finding compact and well-separated clusters in data sets is a challenging task. Most clustering algorithms try to minimize certain clustering objective functions. These functions usually reflect the intra-cluster similarity and inter-cluster dissimilarity. However, the use of such functions alone may not lead to the finding of well-separated and, in some cases, compact clusters. Therefore additional measures, called cluster validity indices, are used to estimate the true number of well-separated and compact clusters. Some of these indices are well-suited to be included into the optimization model of the clustering problem. Silhouette coefficients are among such indices. In this paper, a new optimization model of the clustering problem is developed where the clustering function is used as an objective and silhouette coefficients are used to formulate constraints. Then an algorithm, called CLUSCO (CLustering Using Silhouette COefficients), is designed to construct clusters incrementally. Three schemes are discussed to reduce the computational complexity of the algorithm. Its performance is evaluated using fourteen real-world data sets and compared with that of three state-of-the-art clustering algorithms. Results show that the CLUSCO is able to compute compact clusters which are significantly better separable in comparison with those obtained by other algorithms. © 2022 Elsevier Ltd

Methods and applications of clusterwise linear regression : a survey and comparison

- Long, Qiang, Bagirov, Adil, Taheri, Sona, Sultanova, Nargiz, Wu, Xue

MIRROR : Mining implicit relationships via structure-enhanced graph convolutional networks

- Liu, Jiaying, Xia, Feng, Ren, Jing, Xu, Bo, Pang, Guanson, Chi, Lianhua

  • Authors: Liu, Jiaying , Xia, Feng , Ren, Jing , Xu, Bo , Pang, Guanson , Chi, Lianhua
  • Date: 2023
  • Type: Text , Journal article
  • Relation: ACM Transactions on Knowledge Discovery from Data Vol. 17, no. 4 (2023), p.
  • Full Text: false
  • Reviewed:
  • Description: Data explosion in the information society drives people to develop more effective ways to extract meaningful information. Extracting semantic information and relational information has emerged as a key mining primitive in a wide variety of practical applications. Existing research on relation mining has primarily focused on explicit connections and ignored underlying information, e.g., the latent entity relations. Exploring such information (defined as implicit relationships in this article) provides an opportunity to reveal connotative knowledge and potential rules. In this article, we propose a novel research topic, i.e., how to identify implicit relationships across heterogeneous networks. Specially, we first give a clear and generic definition of implicit relationships. Then, we formalize the problem and propose an efficient solution, namely MIRROR, a graph convolutional network (GCN) model to infer implicit ties under explicit connections. MIRROR captures rich information in learning node-level representations by incorporating attributes from heterogeneous neighbors. Furthermore, MIRROR is tolerant of missing node attribute information because it is able to utilize network structure. We empirically evaluate MIRROR on four different genres of networks, achieving state-of-the-art performance for target relations mining. The underlying information revealed by MIRROR contributes to enriching existing knowledge and leading to novel domain insights. © 2023 Association for Computing Machinery.
  • 1