Privacy preserving in location data release: A differential privacy approach

Communication devices with GPS chips allow people to generate large volumes of location data. However, location datasets have been confronted with serious privacy concerns. Recently, several privacy techniques have been proposed but most of them lack a strict privacy notion, and can hardly resist the number of possible attacks. This paper proposes a private release algorithm to randomize location datasets in a strict privacy notion, differential privacy. This algorithm includes three privacy-preserving operations: Private Location Clustering shrinks the randomized domain and Cluster Weight Perturbation hides the weights of locations, while Private Location Selection hides the exact locations of a user. Theoretical analysis on utility confirms an improved trade-off between the privacy and utility of released location data. The experimental results further suggest this private release algorithm can successfully retain the utility of the datasets while preserving users’ privacy.

A differentially private algorithm for location data release

The rise of mobile technologies in recent years has led to large volumes of location information, which are valuable resources for knowledge discovery such as travel patterns mining and traffic analysis. However, location dataset has been confronted with serious privacy concerns because adversaries may re-identify a user and his/her sensitivity information from these datasets with only a little background knowledge. Recently, several privacy-preserving techniques have been proposed to address the problem, but most of them lack a strict privacy notion and can hardly resist the number of possible attacks. This paper proposes a private release algorithm to randomize location dataset in a strict privacy notion, differential privacy, with the goal of preserving users’ identities and sensitive information. The algorithm aims to mask the exact locations of each user as well as the frequency that the user visits the locations with a given privacy budget. It includes three privacy-preserving operations: private location clustering shrinks the randomized domain and cluster weight perturbation hides the weights of locations, while private location selection hides the exact locations of a user. Theoretical analysis on privacy and utility confirms an improved trade-off between privacy and utility of released location data. Extensive experiments have been carried out on four real-world datasets, GeoLife, Flickr, Div400 and Instagram. The experimental results further suggest that this private release algorithm can successfully retain the utility of the datasets while preserving users’ privacy.

Privacy preserving data release for tagging recommender systems

Tagging recommender systems allow Internet users to annotate resources with personalized tags. The connection among users, resources and these annotations, often called a folksonomy, permits users the freedom to explore tags, and to obtain recommendations. Releasing these tagging datasets accelerates both commercial and research work on recommender systems. However, tagging recommender systems has been confronted with serious privacy concerns because adversaries may re-identify a user and her/his sensitive information from the tagging dataset using a little background information. Recently, several private techniques have been proposed to address the problem, but most of them lack a strict privacy notion, and can hardly resist the number of possible attacks. This paper proposes an private releasing algorithm to perturb users' profile in a strict privacy notion, differential privacy, with the goal of preserving a user's identity in a tagging dataset. The algorithm includes three privacy-preserving operations: Private Tag Clustering is used to shrink the randomized domain and Private Tag Selection is then applied to find the most suitable replacement tags for the original tags. To hide the numbers of tags, the third operation, Weight Perturbation, finally adds Laplace noise to the weight of tags. We present extensive experimental results on two real world datasets, De.licio.us and Bibsonomy. While the personalization algorithm is successful in both cases, our results further suggest the private releasing algorithm can successfully retain the utility of the datasets while preserving users' identity.

An efficient solution for privacy-preserving, secure remote access to sensitive data

Sharing data that contains personally identifiable or sensitive information, such as medical records, always has privacy and security implications. The issues can become rather complex when the methods of access can vary, and accurate individual data needs to be provided whilst mass data release for specific purposes (for example for medical research) also has to be catered for. Although various solutions have been proposed to address the different aspects individually, a comprehensive approach is highly desirable. This paper presents a solution for maintaining the privacy of data released en masse in a controlled manner, and for providing secure access to the original data for authorized users. The results show that the solution is provably secure and maintains privacy in a more efficient manner than previous solutions.

Correlated differential privacy: hiding information in non-IID data set

Privacy preserving on data mining and data release has attracted an increasing research interest over a number of decades. Differential privacy is one influential privacy notion that offers a rigorous and provable privacy guarantee for data mining and data release. Existing studies on differential privacy assume that in a data set, records are sampled independently. However, in real-world applications, records in a data set are rarely independent. The relationships among records are referred to as correlated information and the data set is defined as correlated data set. A differential privacy technique performed on a correlated data set will disclose more information than expected, and this is a serious privacy violation. Although recent research was concerned with this new privacy violation, it still calls for a solid solution for the correlated data set. Moreover, how to decrease the large amount of noise incurred via differential privacy in correlated data set is yet to be explored. To fill the gap, this paper proposes an effective correlated differential privacy solution by defining the correlated sensitivity and designing a correlated data releasing mechanism. With consideration of the correlated levels between records, the proposed correlated sensitivity can significantly decrease the noise compared with traditional global sensitivity. The correlated data releasing mechanism correlated iteration mechanism is designed based on an iterative method to answer a large number of queries. Compared with the traditional method, the proposed correlated differential privacy solution enhances the privacy guarantee for a correlated data set with less accuracy cost. Experimental results show that the proposed solution outperforms traditional differential privacy in terms of mean square error on large group of queries. This also suggests the correlated differential privacy can successfully retain the utility while preserving the privacy.

Language and power in vocational education and training

In this paper I explore the way language is used in Training Packages, and the impact this language has when Training Packages are used to support work-based vocational programs. Training Packages are a fundamental component of the regulatory framework of the national vocational education and training (VET) system [in Australia]. The national strategy for VET places employers and individuals at the centre of VET, and policy commitments to access and equity are enshrined in the auditable standards of the Australian Quality Training Framework (AQTF). Yet Training Packages and related official VET texts are written in an abstract, generalised and complex language form which acts as an insurmountable barrier to many people at the front line of VET. My PhD research (a work in progress) explores the proposition that this language form is representative of, and constructive in, unequal power relationships. Early data analysis suggests that VET practitioners and training participants talk about their experience of this language in terms of power and exclusion. In contrast, the official VET response generally leaves the official language form above challenge, and instead largely focuses on the presumed deficient language and literacy skills of those who are excluded by these texts.

Noticing a flow of networks

The world of the classroom is no less a ‘flow of networks’ (Castells 1999) than the globalised world outside its doors. In this fluid context of the world outside and the inner world of identity, the linear and somewhat found understandings of reflective practice (Schon 1987) and observations of classroom practice may serve to limit rather than reveal. The authors of this paper have been engaging with the ways teachers shape personal and professional theory through a movement - oriented process of noticing (Moss et al 2004). Noticing,working at the elusive intersections of observation and construction, permits non-linear connections. Noticing theorised in this way draws on the physical (Mason 2002). The movement occurs between the seen and the seer – between beliefs, identity and responses. The movement of the eye in noticing touches the seen in various places – pulling in and out of focus that which is seen. The same movement brings in and out of focus the seer- the beliefs and values held and let go in the seeing. The focusing in the act requires convergence and divergence (‘Notitia’ being known -‘Middle English from Old French from Latin Notitia being known from notus past part. of noscere know’). The paper will report on early data on the impact of implementing this theoretical model in mass teacher education at the University of Melbourne, Australia.

A survey on differential privacy and applications

Privacy preserving in data release and mining is a hot topic in the information security field currently. As a new privacy notion, differential privacy (DP) has grown in popularity recently due to its rigid and provable privacy guarantee. After analyzing the advantage of differential privacy model relative to the traditional ones, this paper surveys the theory of differential privacy and its application on two aspects, privacy preserving data release (PPDR) and privacy preserving data mining (PPDM). In PPDR, we introduce the DP-based data release methodologies in interactive/non-interactive settings and compare them in terms of accuracy and sample complexity. In PPDM, we mainly summarize the implementation of DP in various data mining algorithms with interface-based/fully access-based modes as well as evaluating the performance of the algorithms. We finally review other applications of DP in various fields and discuss the future research directions.

The Early Prevention of Obesity in CHildren (EPOCH) collaboration : an individual patient data prospective meta-analysis

Background
Efforts to prevent the development of overweight and obesity have increasingly focused early in the life course as we recognise that both metabolic and behavioural patterns are often established within the first few years of life. Randomised controlled trials (RCTs) of interventions are even more powerful when, with forethought, they are synthesised into an individual patient data (IPD) prospective meta-analysis (PMA). An IPD PMA is a unique research design where several trials are identified for inclusion in an analysis before any of the individual trial results become known and the data are provided for each randomised patient. This methodology minimises the publication and selection bias often associated with a retrospective meta-analysis by allowing hypotheses, analysis methods and selection criteria to be specified a priori.

Methods/Design
The Early Prevention of Obesity in CHildren (EPOCH) Collaboration was formed in 2009. The main objective of the EPOCH Collaboration is to determine if early intervention for childhood obesity impacts on body mass index (BMI) z scores at age 18-24 months. Additional research questions will focus on whether early intervention has an impact on children's dietary quality, TV viewing time, duration of breastfeeding and parenting styles. This protocol includes the hypotheses, inclusion criteria and outcome measures to be used in the IPD PMA. The sample size of the combined dataset at final outcome assessment (approximately 1800 infants) will allow greater precision when exploring differences in the effect of early intervention with respect to pre-specified participant- and intervention-level characteristics.

Discussion
Finalisation of the data collection procedures and analysis plans will be complete by the end of 2010. Data collection and analysis will occur during 2011-2012 and results should be available by 2013.

Qualitative methods in early-phase drug trials : data and methods from a trial of N-acetylcysteine in schizophrenia

Objective: The pharmacokinetic profile of a drug often gives little indication of its potential therapeutic application, with many therapeutic uses of drugs being discovered serendipitously while being studied for different indications. As hypothesis-driven, quantitative research methodology is exclusively used in early-phase trials, unexpected but important phenomena may escape detection. In this context, this study aimed to examine the potential for integrating qualitative research methods with quantitative methods in early-phase drug trials. To our knowledge, this mixed methodology has not previously been applied to blinded psychopharmacologic trials.

Method: We undertook qualitative data analysis of clinical observations on the dataset of a randomized, double-blind, placebo-controlled trial of N-acetylcysteine (NAC) in patients with DSM-IV-TR–diagnosed schizophrenia (N = 140). Textual data on all participants, deliberately collected for this purpose, were coded using NVivo 2, and emergent themes were analyzed in a blinded manner in the NAC and placebo groups. The trial was conducted from November 2002 to July 2005.

Results: The principal findings of the published trial could be replicated using a qualitative methodology. In addition, significant differences between NAC- and placebo-treated participants emerged for positive and affective symptoms, which had not been captured by the rating scales utilized in the quantitative trial. Qualitative data in this study subsequently led to a positive trial of NAC in bipolar disorder.

Conclusions: The use of qualitative methods may yield broader data and has the potential to complement traditional quantitative methods and detect unexpected efficacy and safety signals, thereby maximizing the findings of early-phase clinical trial research.

Does stage of illness impact treatment response in bipolar disorder? Empirical treatment data and their implication for the staging model and early intervention

Objective: The staging model suggests that early stages of bipolar disorder respond better to treatments and have a more favourable prognosis. This study aims to provide empirical support for the model, and the allied construct of early intervention.

Methods: Pooled data from mania, depression, and maintenance studies of olanzapine were analyzed. Individuals were categorized as having had 0, 1–5, 6–10, or >10 prior episodes of illness, and data were analyzed across these groups.

Results: Response rates for the mania and maintenance studies ranged from 52–69% and 10–50%, respectively, for individuals with 1–5 previous episodes, and from 29–59% and 11–40% for individuals with >5 previous episodes. These rates were significantly higher for the 1–5 group on most measures of response with up to a twofold increase in the chance of responding for those with fewer previous episodes. For the depression studies, response rates were significantly higher for the 1–5 group for two measures only. In the maintenance studies, the chance of relapse to either mania or depression was reduced by 40–60% for those who had experienced 1–5 episodes or 6–10 episodes compared to the >10 episode group, respectively. This trend was statistically significant only for relapse into mania for the 1–5 episode group (p = 0.005).

Conclusion: Those individuals at the earliest stages of illness consistently had a more favourable response to treatment. This is consistent with the staging model and

Profiles of language development in pre-school children : a longitudinal latent class analysis of data from the early language in Victoria study

Background Pre-school language impairment is common and greatly reduces educational performance. Population attempts to identify children who would benefit from appropriately timed intervention might be improved by greater knowledge about the typical profiles of language development. Specifically, this could be used to help with the early identification of children who will be impaired on school entry.

Methods This study applied longitudinal latent class analysis to assessments at 8, 12, 24, 36 and 48 months on 1113 children from a population-based study, in order to identify classes exhibiting distinct communicative developmental profiles.

Results Five substantive classes were identified: Typical, i.e. development in the typical range at each age; Precocious (late), i.e. typical development in infancy followed by high probabilities of precocity from 24 months onwards; Impaired (early), i.e. high probabilities of impairment up to 12 months followed by typical language development thereafter; Impaired (late), i.e. typical development in infancy but impairment from 24 months onwards; Precocious (early), i.e. high probabilities of precocity in early life followed by typical language by 48 months. The entropy statistic (0.84) suggested classes were fairly well defined, although there was a non-trivial degree of uncertainty in classification of children. That half of the Impaired (late) class was expected to have typical language at 4 years and 6% of the numerically large Typical class was expected to be impaired at 4 years illustrates this. Characteristics indicative of social advantage were more commonly found in the classes with improving profiles.

Conclusions Developmental profiles show that some pre-schoolers' language is characterized by periods of accelerated development, slow development and catch-up growth. Given the uncertainty in classifying children into these profiles, use of this knowledge for identifying children who will be impaired on school entry is not straightforward. The findings do, however, indicate greater need for language enrichment programmes among disadvantaged children.

Investigating the effectiveness of teacher education for early career teachers in diverse settings: analysis of large-scale survey data

‘As researchers and practitioners in the field of teacher education, we seem ill prepared to respond to critics who question the value of professional education for teachers with evidence of our effectiveness’ (Grossman, 2008, p.13). While there are many small-scale, nuanced case studies that speak about the particularities of specific teacher education practices, large scale, systematic, longitudinal studies that can provide rich and comprehensive data about the effectiveness of teacher education are limited (Cochran-Smith & Zeichner, 2005). In Australia, the Studying the Effectiveness of Teacher Education (SETE) project is addressing this gap by investigating the effectiveness of teacher education programs in preparing teachers for the variety of school settings in which they begin their careers. This three-year study utilises large-scale surveys and case studies to construct a deeper understanding of early career teachers’ experiences. It tracks all 2010/2011 teacher education graduates in Queensland and Victoria to investigate the effectiveness of particular characteristics of their teacher education programs in equipping them with the capacity to meet the learning needs of young people in a diverse range of Australian school settings.

This paper will discuss findings from the first of a series of online surveys completed by teacher education graduates in Queensland and Victoria (March-April 2012). Survey data includes teacher demographic information which form independent variables to inform inferential statistical analysis. Beginning teacher responses are mapped against key characteristics of participants' pre-service programs and framed in relation to the key themes of curriculum, pedagogy, assessment, behaviour management, and engagement with school stakeholders and local community. The findings will assist teacher educators design teacher education programs for effective beginning teaching in diverse settings and will also provide an evidentiary basis for policy decisions regarding teacher education and beginning teaching.

Association of early childhood abdominal circumference and weight gain with blood pressure at 36 months of age: secondary analysis of data from a prospective cohort study

To assess whether changes in measures of fat distribution and body size during early life are associated with blood pressure at 36 months of age.

Online versus postal data collection methods: an examination of issues and a comparison of results

New communications technologies often allow new ways of conducting market research. Determining the advantages of a new data collection method over established alternatives is difficult without thorough comparative testing. Computer-mediated marketing research is one such example of a new technology that has been enthusiastically embraced by marketing organisations and those servicing them. While researchers using the Internet (Net) and World Wide Web (Web) in its early years reported benefits such as high response levels, there is little in the way of comparative evidence to support any claimed advantages. This paper reports on the outcomes of three separate studies in which members (subscribers) of various organisations have been surveyed using both postal and online (email invitation and HTML Web form) data collection methods. The conclusion here is that it would be unwise to assume that one method can be directly substituted for another and obtain the same response. Differences in both the response pattern and demographic profile of respondents between the groups are consistently noticed, such as to warrant further examination of the methods used in online marketing research, and to suggest the need for further study.