Abstract
Existing approaches for detecting anomalous events in time-evolving networks usually focus on detecting events involving the majority of the nodes, which affect the overall structure of the network. Since events involving just a small subset of nodes usually do not affect the overall structure of the network, they are more difficult to spot. In this context, tensor decomposition based methods usually beat other techniques in detecting global events, but fail at spotting localized event patterns. We tackle this problem by replacing the batch decomposition with a sliding window decomposition, which is further mined in an unsupervised way using statistical tools. Via experimental results in one synthetic and four real-world networks, we show the potential of the proposed method in the detection and specification of local events.

Abstract

Abstract

Abstract
Crowdsourcing has become an essential source of information for tourism stakeholders. Every day, tourists leave large volumes of feedback data in the form of posts, likes, textual reviews, and ratings in dedicated crowdsourcing platforms. This behavior makes the analysis of crowdsourced information strategic, allowing the discovery of important knowledge regarding tourists and tourism resources. This paper presents a survey on the analysis and prediction of hotel ratings from crowdsourced data, covering both off-line (batch) and on-line (stream-based) processing. Specifically, it reports multiple rating-based profiling, recommendation, and evaluation techniques. While most of the surveyed works adopt entity-based multicriteria profiling, prerecommendation filtering, and off-line processing, the latest hotel rating prediction trends include feature-based, trust and reputation modeling, postrecommendation filtering, and on-line processing. Additionally, since the volume of crowdsourced ratings tends to increase, the deployment of profiling and recommendation algorithms on high-performance computing resources should be further explored.

Abstract
Overhead Power Distribution Lines (OPDLs) correspond to a large percentage of the medium-voltage electrical systems. In these networks, visual inspection activities are usually performed without resorting to automated systems, requiring a significant investment of time and human resources. We present a methodology to identify the defect and type of insulators using Convolutional Neural Networks (CNNs). More than 2500 photographs were collected both from inside a studio and from a realistic OPDL. A classification model is proposed to automatically recognize the insulators conformity. This model is able to learn from indoors photographs by augmenting these images with realistic details such as top ties and real-world backgrounds. Furthermore, Multi-Task Learning (MTL) was used to improve performance of defect detection by also predicting the insulator class. The proposed methodology is able to achieve an accuracy of 92% for material classification and 85% for defect detection, with F1-score of 0.75, surpassing available solutions.

Abstract
Dissolved carbon dioxide (dCO2) evaluation is very important in many different fields. In this work, a new, integrated, colorimetric-optical fiber-based system for dCO2 monitoring in aquaculture industry was developed. The sensing chemistry is based on colorimetric changes of the used indicator—poly p-nitrophenol (pNPh)—in contact with CO2. Preliminary tests were done in a laboratory environment (calibration) and in a laboratory Recirculating Aquaculture System (RAS) with controlled CO2 injection. The results have shown the suitability of the new sensor for assessing dCO2 dynamics in RAS and its fast detection of low dCO2 concentrations in an appropriate operation range.