Analysis of Tourist Subjective Data in Smartphone Based Participatory Sensing System by Interactive Growing Hierarchical SOM
3
Citation
9
Reference
10
Related Paper
Citation Trend
Keywords:
Mobile phone
Participatory Sensing
Pruning
Self-organizing map
Participatory sensing is a revolutionary new paradigm that offers individuals and interest groups the opportunity to contribute to an application using their sensor equipped handheld devices. However, one of the main challenges that threatens the success of participatory sensing systems is "privacy." Data collected from participants' devices such as location, time, phone number, etc. are considered private. The collected data should not accidentally reveal any of the contributors' private information. This paper studies the proposed solutions pertaining to ease that challenge in participatory sensing privacy. The main contribution here is classifying the mainstream schemes in participatory sensing privacy based on our classification attributes. Moreover, we propose novel attributes that lay the foundation for privacy preserving sensing schemes in participatory sensing systems.
Participatory Sensing
Mainstream
Mobile phone
Differential Privacy
Private information retrieval
Participatory GIS
Cite
Citations (4)
Participatory Sensing is an emerging computing paradigm that enables the distributed collection of data by self-selected participants. It allows the increasing number of mobile phone users to share local knowledge acquired by their sensor-equipped devices, e.g., to monitor temperature, pollution level or consumer pricing information. While research initiatives and prototypes proliferate, their real-world impact is often bounded to comprehensive user participation. If users have no incentive, or feel that their privacy might be endangered, it is likely that they will not participate. In this article, we focus on privacy protection in Participatory Sensing and introduce a suitable privacy-enhanced infrastructure. First, we provide a set of definitions of privacy requirements for both data producers (i.e., users providing sensed information) and consumers (i.e., applications accessing the data). Then, we propose an efficient solution designed for mobile phone users, which incurs very low overhead. Finally, we discuss a number of open problems and possible research directions.
Participatory Sensing
Privacy software
Mobile phone
Information sensitivity
Citizen Science
Crowdsourcing
Cite
Citations (1)
In this paper, we introduce a new segmentation technique (called Kohonen snake) based on the neural simulation of deformable models designed to reconstruct 3D objects. Kohonen snake possesses all properties of Kohonen networks (lateral interaction during the learning process, topologically preserving mapping) and of deformable models (namely, elastic properties). Elastic properties of the physics-based Kohonen ring improves the shortcomings of the Kohonen network related to twisting, `dead' neurons, accumulation and rounding the network, whereas the data- driven approach of Kohonen snake improves the problem of initialization and local minima of the snakes. When integrating both models, the first question is how to combine their parameters. We simulate the Kohonen snake behavior with different parameter values using sequential and parallel weight updating, study the need of decreasing the parameters and of reordering image features. As a result, we conclude that Kohonen snake has better control on its shape that makes it less dependent on the values of its parameters and initial conditions. Our tests on segmentation of synthetic and real images illustrate the usefulness of the Kohonen snake technique.
Self-organizing map
Initialization
Maxima and minima
Cite
Citations (1)
Self-organizing map
Toolbox
Supervised Learning
Self-Organization
Cite
Citations (139)
자기조직화 지도(SOM)은 T. 코호넨의 주도하에 개발된 비지도 학습 신경망 모형이다. 그 동안 패턴인식과 문서검색 분야에 주로 응용되어 왔기 때문에 통계학 분야에서는 덜 알려졌으나, 최근 K-평균 군집화에 대한 대안적 데이터 마이닝 기법으로 활용되기 시작하였다. 본 연구에서는 SOM의 한 버전인 PC-SOM(주성분 자기조직화 지도)을 제안하고 활용 예를 제시하고자 한다. PC-SOM은 1차원적 SOM 알고리즘을 반복 수행하여 2차원, 3차원 등의 SOM을 얻는 방법이기 때문에 기존 SOM과는 달리 사전 Map의 크기를 확정할 필요가 없다. 또한, 기존 SOM에 비하여 향상된 시각화를 가능하게 한다. Self-organizing map (SOM), a unsupervised learning neural network, has been developed by T. Kohonen since 1980's. Main application areas were pattern recognition and text retrieval. Because of that, it has not been spread to statisticians until late. Recently, SOM's are frequently drawn in data mining fields. Kohonen's SOM, however, needs improvements to become a statistician's standard tool. First, there should be a good guideline as for the size of map. Second, an enhanced visualization mode is wanted. In this study, principal components self-organizing map (PC-SOM), a modification of Kohonen's SOM, is proposed to meet such needs. PC-SOM performs one-dimensional SOM during the first stage to decompose input units into node weights and residuals. At the second stage, another one-dimensional SOM is applied to the residuals of the first stage. Finally, by putting together two stages, one obtains two-dimensional SOM. Such procedure can be easily expanded to construct three or more dimensional maps. The number of grid lines along the second axis is determined automatically, once that of the first axis is given by the data analyst. Furthermore, PC-SOM provides easily interpretable map axes. Such merits of PC-SOM are demonstrated with well-known Fisher's iris data and a simulated data set.
Self-organizing map
Cite
Citations (2)
Self-organizing map (SOM) has been developed mainly by T. Kohonen and his colleagues as a unsupervised learning neural network. Because of its topological ordering property, SOM is known to be very useful in pattern recognition and text information retrieval areas. Recently, data miners use Kohonen´s mapping method frequently in exploratory analyses of large data sets. One problem facing SOM builder is that there exists no sensible criterion for evaluating goodness-of-fit of the map at hand. In this short communication, we propose valid evaluation procedures for the Kohonen SOM of any size. The methods can be used in selecting the best map among several candidates.
Self-organizing map
Cite
Citations (0)
With the increasing popularity of smart phones, a new collaborative sensing application, named participatory sensing, gradually appeared. The key idea of participatory sensing is to employ so many users to collect and share sensed data using their mobile phones. Current relevant applications are mainly focused on how to collect sensed data. Few methods have been proposed for user privacy in participatory sensing applications. We proposed a novel privacy protection scheme for participatory sensing applications. In this scheme, we use the pseudonym, encryption function and hash function to protect the user's privacy and meanwhile to carry out incentives. Finally, we present an analysis of our protocol to show that our protocol meets the security requirements of participatory sensing application.
Participatory Sensing
Pseudonym
Popularity
Cite
Citations (23)
This study was developed to provide an innovative methodology for designing steel alloys. Information on the general corrosion of a wide number of steel alloys in various electrolytes and environments was obtained from the National Institute of Standards and Technology (NIST). Parameters such as pH and conductivity used in each experiment (alloy in contact with an environment), along with alloy composition (from UNS number), and corrosion rates, were all collected in a single data row, or vector. To cluster by similarities, a web-based, publicly available Kohonen mapping software was used to perform the clustering analysis; Kohonen maps work by clustering together similar vectors and separating those vectors that differ. A vector was formed for each experiment for which corrosion rates were recorded; 1521 experiments were performed and each of those vectors was used to train the Kohonen Map. Once the Kohonen map is trained, each one of the cells forming the two-dimension Kohonen map will form clusters of vectors. Vectors containing similar information will be clustered together while dissimilar vectors will be clustered separately on the Kohonen map. The cells of the Kohonen map will adopt a “prototype” vector to be the representative of that cell; the prototype vector adopts the average values of all stored vectors in that cell. After the Kohonen map is trained, new vectors containing fabricated metal alloy composition (steels) and environment information can be input into the map. These new vectors, even though they do not contain corrosion rates, can be classified by the Kohonen map and entered into a cluster on the map. This methodology can be use to explore “if-then” scenarios of a new alloy in a different environment as well as obtain an expected corrosion rate of that particular alloy in that particular environment. Preliminary results of the trained Kohonen map are shown and discussed. The map results are used to explore the effects of the experiment environments and alloy composition on the general corrosion of the stainless steels.
Self-organizing map
Cite
Citations (0)
Participatory sensing, combining the power of crowd and the ubiquitously available smart phones, plays an important role to sense the urban environment and develop many exciting smart city applications to improve the quality of life and enable sustainability. The knowledge of the participatory sensing participants’ competence to collect data is vital for any effective urban data collection campaign and the success of these applications. In this paper, we present a methodology to compute the trustworthiness of the participatory sensing participants as the belief on their competence to collect high quality data. In our experiments, we evaluate trust on the sensing participants of BusWatch, a participatory sensing based bus arrival time prediction application. Our results show that our system effectively computes the sensing participants’ trustworthiness as the belief on their competence to collect high quality data and detect their dynamically varying sensing behavior.
Participatory Sensing
Citizen Science
Trustworthiness
Cite
Citations (4)
Participatory sensing is an emerging system that allows the increasing number of smartphone users to share effectively the minute statistical information collected by themselves. This system relies on participants' active contribution including intentional input data. However, a number of privacy concerns will hinder the spread of participatory sensing applications. It is difficult for resource-constrained mobile phones to rely on complicated encryption schemes. We should prepare a privacy-preserving participatory sensing scheme with low computation complexity. Moreover, an environment that can reassure participants and encourage their participation in participatory sensing is strongly required because the quality of the statistical data is dependent on the active contribution of general users. In this article, we present MNS-RRT algorithms, which is the combination of negative surveys and randomized response techniques, for preserving privacy in participatory sensing, with high levels of data integrity. By using our method, participatory sensing applications can deal with a data having two selections in a dimension. We evaluated how this scheme can preserve the privacy while ensuring data integrity.
Participatory Sensing
Information sensitivity
Cite
Citations (8)