Effective privacy preserving data publishing by vectorization

Eom, Chris Soo-Hyun; Lee, Charles Cheolgi; Lee, Wookey; Leung, Carson K.

doi:10.1016/j.ins.2019.09.035

Cited by 56 publications

(19 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a general framework, it can be apply to predictive analytics for other purposes in a wide variety of domains (e.g., prediction of box office [15] or stock market [18]). We also consider to extend our framework as to deal with novel features of big data such as performance, privacy, and flexible paradigms (e.g., [2,5,6,9]).…”

Section: Discussionmentioning

confidence: 99%

An Innovative Big Data Predictive Analytics Framework over Hybrid Big Data Sources with an Application for Disease Analytics

Souza

Leung

Cuzzocrea

2020

Advanced Information Networking and Applications

Self Cite

View full text Add to dashboard Cite

Nowadays, big data are everywhere. Examples of big data include weather data, web-search data, disease reports, as well as epidemic data and statistics. These big data can be easily generated and collected from a wide variety of data sources. A data science frameworksuch as predictive analytics framework-helps mining data from various big data sources to find useful information and discover knowledge, which can then be transformed into wisdom for appropriate actions. In this paper, we present an innovative big data predictive analytics framework over hybrid big data sources. To demonstrate the effectiveness and practicality of our framework, we conduct several case studies, including one on applying the framework to disease analytics. More specifically, we integrate, incorporate and analyze weather data and web-search data to predict and forecast dengue cases based on a hybrid of three kernels in support vector machine (SVM) ensemble. Results show how our predictive analytics framework benefits health agencies in disease control and prevention.

show abstract

Section: Discussionmentioning

confidence: 99%

An Innovative Big Data Predictive Analytics Framework over Hybrid Big Data Sources with an Application for Disease Analytics

Souza

Leung

Cuzzocrea

2020

Advanced Information Networking and Applications

Self Cite

View full text Add to dashboard Cite

show abstract

“…Vid2speech is also an end-to-end model based on CNN to generate understandable speech signals in a speaker’s silent video. All three presented models are deep learning architectures that have made significant progress in the lip-reading field, indicating that AI lip readers can be used to analyze not only in simple speech readings but also users’ real-time thinking [ 65 ] and information security areas [ 96 ]. While the previously mentioned traditional methods were not universal, deep learning model including LipNet, Lip2Audspec and Vid2speech enabled deeper feature extraction through a general process of extracting lip parts for the image or each frame of the video and processing data through the neural network [ 94 ].…”

Section: Deep Learning Based Voice Recognitionmentioning

confidence: 99%

Biosignal Sensors and Deep Learning-Based Speech Recognition: A Review

Lee

Seong

Ozlu

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

Voice is one of the essential mechanisms for communicating and expressing one’s intentions as a human being. There are several causes of voice inability, including disease, accident, vocal abuse, medical surgery, ageing, and environmental pollution, and the risk of voice loss continues to increase. Novel approaches should have been developed for speech recognition and production because that would seriously undermine the quality of life and sometimes leads to isolation from society. In this review, we survey mouth interface technologies which are mouth-mounted devices for speech recognition, production, and volitional control, and the corresponding research to develop artificial mouth technologies based on various sensors, including electromyography (EMG), electroencephalography (EEG), electropalatography (EPG), electromagnetic articulography (EMA), permanent magnet articulography (PMA), gyros, images and 3-axial magnetic sensors, especially with deep learning techniques. We especially research various deep learning technologies related to voice recognition, including visual speech recognition, silent speech interface, and analyze its flow, and systematize them into a taxonomy. Finally, we discuss methods to solve the communication problems of people with disabilities in speaking and future research with respect to deep learning components.

show abstract

“…As shown in Fig. 2(b), the attacker knows that target user A has visited location points (1, 3), (2,5) and (4,7). Since only O 3 can contain these three location points in the published anonymous trajectory data set, the attacker can determine that O 3 is A.…”

Section: B Trajectory Attack Modelmentioning

confidence: 99%

“…While, analyzing trajectories of vehicles in a city may help government optimize the traffic management systems. However, publishing trajectories can also cause serious threats to the personal privacy [1], [2]. Spatio-temporal information [3] contained in trajectories may reveal individuals' personal information, such as, living habits, health conditions, social customs, work and home addresses, etc.…”

Section: Introductionmentioning

confidence: 99%

A Semantic-Based Approach for Privacy-Preserving in Trajectory Publishing

Zhang

Diao

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The increasing abundance of data in the trajectories of personal movement opens up new opportunities for analyzing and mining human mobility. But the inherent personal information in the data raises the privacy concern. In this paper, the trajectories are not simply considered as a sequence of the coordinates in Euclidean space, they combine the semantics-aware information with the background knowledge of underlying map for the location points. A novel approach is then proposed to conceal the actually visited sensitive places. To this end, a cloaking region for each personalized sensitive place is built before a reasonable dummy trajectory in the cloaking region is constructed. The performance of our approach is evaluated based on a real-world trajectories dataset. And the results show that the proposed approach outperforms the existing privacy-preserving approaches. INDEX TERMS Trajectory publishing, privacy-preserving, semantic.

show abstract

Effective privacy preserving data publishing by vectorization

Cited by 56 publications

References 10 publications

An Innovative Big Data Predictive Analytics Framework over Hybrid Big Data Sources with an Application for Disease Analytics

An Innovative Big Data Predictive Analytics Framework over Hybrid Big Data Sources with an Application for Disease Analytics

Biosignal Sensors and Deep Learning-Based Speech Recognition: A Review

A Semantic-Based Approach for Privacy-Preserving in Trajectory Publishing

Contact Info

Product

Resources

About