Availability Of Partial Information Research Articles

Towards Data-Driven Vehicle Estimation for Signalised Intersections in a Partially Connected Environment.

Connected vehicles (CVs) have the potential to collect and share information that, if appropriately processed, can be employed for advanced traffic control strategies, rendering infrastructure-based sensing obsolete. However, before we reach a fully connected environment, where all vehicles are CVs, we have to deal with the challenge of incomplete data. In this paper, we develop data-driven methods for the estimation of vehicles approaching a signalised intersection, based on the availability of partial information stemming from an unknown penetration rate of CVs. In particular, we build machine learning models with the aim of capturing the nonlinear relations between the inputs (CV data) and the output (number of non-connected vehicles), which are characterised by highly complex interactions and may be affected by a large number of factors. We show that, in order to train these models, we may use data that can be easily collected with modern technologies. Moreover, we demonstrate that, if the available real data is not deemed sufficient, training can be performed using synthetic data, produced via microscopic simulations calibrated with real data, without a significant loss of performance. Numerical experiments, where the estimation methods are tested using real vehicle data simulating the presence of various penetration rates of CVs, show very good performance of the estimators, making them promising candidates for applications in the near future.

Dynamic Prediction of the Incident Duration Using Adaptive Feature Set

Non-recurring incidents such as accidents and vehicle breakdowns are the leading causes of severe traffic congestions in large cities. Consequently, anticipating the duration of such events in advance can be highly useful in mitigating the resultant congestion. However, availability of partial information or ever-changing ground conditions makes the task of forecasting the duration particularly challenging. In this paper, we propose an adaptive ensemble model that can provide reasonable forecasts even when a limited amount of information is available and further improves the prediction accuracy as more information becomes available during the course of the incidents. Furthermore, we consider the scenarios where the historical incident reports may not always contain accurate information about the duration of the incidents. To mitigate this issue, we first quantify the effective duration of the incidents by looking for the change points in traffic state and then utilize this information to predict the duration of the incidents. We compare the prediction performance of different traditional regression methods, and the experimental results show that the Treebagger outperforms other methods. For the incidents with duration in the range of 36 – 200 min, the mean absolute percentage error (MAPE) in predicting the duration is in the range of 25% – 55%. Moreover, for longer duration incidents (greater than 65 min), prediction improves significantly with time. For example, the MAPE value varies over time from 76% to 50% for incidents having a duration greater than 200 min. Finally, the overall MAPE value averaged over all incidents improves by 50% with elapsed time for prediction of reported as well as effective duration.

O papel da informação como medida preventiva ao uso de drogas entre jovens em situação de risco

Illicit drug consumption among youngsters is a public health concern that requires attention. However, little research has highlighted the importance of "drug information availability" among protection factors. The objective of the study is to identify, from the point of view of youngsters at risk, what factors could prevent them to try illicit drugs, focusing on the importance of "drug information availability". An intentional sample was selected, composed by 62 youngsters divided into two groups: (NU) non illicit users N=32 and (U) users N=30. The sample was recruited through key-informants and snowball and each participant was submitted to an in-depth semi-structured interview. According to NU, "drug information availability" was reported as the main protector factor. Family-based information was the main source of knowledge followed by observation of the drug negative consequences on lives of friends who have already consumed illicit drugs in a regular-basis. Among users, a lack of drug knowledge or availability of partial information was reported. Among youngsters at risk, drug information availability is the main protection factor against experimental and regular drug consumption. Family based information was reported as its main source.

O papel da informação como medida preventiva ao uso de drogas entre jovens em situação de risco

Illicit drug consumption among youngsters is a public health concern that requires attention. However, little research has highlighted the importance of "drug information availability" among protection factors. The aim of this article is to identify, from the point of view of youngsters at risk, what factors could prevent them to try illicit drugs, focusing on the importance of "drug information availability". An intentional sample was selected, composed by 62 youngsters divided into two groups: (NU) non illicit users N=32 and (U) users N=30. The sample was recruited through key-informants and "snowball" and each participant was submitted to an in-depth semi-structured interview. According to NU "drug information availability" was reported as the main protector factor. Family-based information was the main source of knowledge followed by observation of the drug negative consequences on lives of friends who have already consumed illicit drugs in a regular-basis. Among users, it was reported a lack of drug knowledge or availability of partial information. We can conclude that among youngsters at risk, drug information availability is the main protection factor against experimental and regular drug consumption. Family based information was reported as its main source.

Special issue on soft computing for digital information forensics

The emergence and evolution of new digital technologies are dramatically changing how information is captured, processed, analyzed, interpreted, transmitted, and stored. While digital technology has greatly improved the collection and analysis of evidences, the underlying research challenges primarily focus on the integrity and the reliability of validating the resulting forensic decisions accurately. Furthermore, digital evidences can be easily tampered, altered, or forged to commit fraud, identity theft, or impersonate someone else, to remain elusive from law enforcement. Using image processing techniques, it is easy to tamper the original image by replacing an individual’s face, and making the change difficult to detect. Image forensic techniques use natural properties of image to determine forgery or locate tampering. In another example, it is possible to determine whether an image is generated by a digital camera, a cell-phone camera, or a computer by analyzing the image properties and characteristics and comparing the statistics of various digital devices. With the rise of digital crime (signature forgery, image forgery, illegal transaction, etc.) and the pressing need for methods to combat these forms of criminal activities, there is an increasing awareness of the importance of information forensics for security applications. Fundamental areas of interest include attack models, cryptanalysis, steganalysis, authentication, human identification, signal classification, surveillance, transaction tracking, etc. In many practical applications, the evidences collected from a crime scene may be non-ideal due to poor quality or availability of partial information. It is imperative for new research approaches to fuse information from multiple evidences to make a forensic decision or reliably classify as genuine or imposter. In all these forensic applications, soft computing techniques such as neural networks, fuzzy logic, evolutionary computing, and rough set, play an important role in learning complex data structures and patterns, and classifying them to make intelligent decisions. Soft computing has been widely used in various applications, such as machine vision, pattern detection, data segmentation, data mining, adaptive control, biometrics, and information assurance. This special issue of the Soft Computing Journal invited authors to submit their original work that communicates current research on soft computing for digital information forensics regarding both the novel solutions and future trends in the field. In this special issue, we have 8 papers, which can demonstrate advanced works in the field.