175 research outputs found
On the use of summarization and transformer architectures for profiling résumés
No full textProfiling professional figures is becoming more and more crucial, as companies and recruiters face the challenges of Industry 4.0. On the one hand, demand for specific knowledge in professional figures is rising. On the other hand, workers try to broaden the spectrum of their skills in order to remain appealing in the job market. Therefore, research related to these topics is receiving more and more attention. In this paper, we propose a methodology to profile résumés based on summarization and transformer architectures for generating résumé embeddings and on hierarchical clustering algorithms for grouping these embeddings. We evaluate different strategies and show that our approach achieves promising results on a public domain dataset containing 1202 résumés
A survey on fake news and rumour detection techniques
No full textFalse or unverified information spreads just like accurate information on the web, thus possibly going viral and influencing the public opinion and its decisions. Fake news and rumours represent the most popular forms of false and unverified information, respectively, and should be detected as soon as possible for avoiding their dramatic effects. The interest in effective detection techniques has been therefore growing very fast in the last years. In this paper we survey the different approaches to automatic detection of fake news and rumours proposed in the recent literature. In particular, we focus on five main aspects. First, we report and discuss the various definitions of fake news and rumours that have been considered in the literature. Second, we highlight how the collection of relevant data for performing fake news and rumours detection is problematic and we present the various approaches, which have been adopted to gather these data, as well as the publicly available datasets. Third, we describe the features that have been considered in fake news and rumour detection approaches. Fourth, we provide a comprehensive analysis on the various techniques used to perform rumour and fake news detection. Finally, we identify and discuss future directions
Enabling energy-efficient and lossy-aware data compression in wireless sensor networks by multi-objective evolutionary optimization
No full textNodes of wireless sensor networks (WSNs) are typically powered by batteries with a limited capacity. Thus, energy is a primary constraint in the design and deployment of WSNs. Since radio communication is in general the main cause of power consumption, the different techniques proposed in the literature to improve energy efficiency have mainly focused on limiting transmission/reception of data, for instance, by adopting data compression and/or aggregation. The limited resources available in a sensor node demand, however, the development of specifically designed algorithms. To this aim, we propose an approach to perform lossy compression on single node based on a differential pulse code modulation scheme with quantization of the differences between consecutive samples. Since different combinations of the quantization process parameters determine different trade-offs between compression performance and information loss, we exploit a multi-objective evolutionary algorithm to generate a set of combinations of these parameters corresponding to different optimal trade-offs. The user can therefore choose the combination with the most suitable trade-off for the specific application. We tested our lossy compression approach on three datasets collected by real WSNs. We show that our approach can achieve significant compression ratios despite negligible reconstruction errors. Further, we discuss how our approach outperforms LTC, a lossy compression algorithm purposely designed to be embedded in sensor nodes, in terms of compression rate and complexity
A simple algorithm for data compression in wireless sensor networks
No full textPower saving is a critical issue in wireless sensor networks (WSNs) since sensor nodes are powered by batteries which cannot be generally changed or recharged. As radio communication is often the main cause of energy consumption, extension of sensor node lifetime is generally achieved by reducing transmissions/receptions of data, for instance through data compression. Exploiting the natural correlation that exists in data typically collected by WSNs and the principles of entropy compression, in this Letter we propose a simple and efficient data compression algorithm particularly suited to be used on available commercial nodes of a WSN, where energy, memory and computational resources are very limited. Some experimental results and comparisons with, to the best of our knowledge, the only lossless compression algorithm previously proposed in the literature to be embedded in sensor nodes and with two well known compression algorithms are shown and discussed
A Multi-objective Evolutionary Approach to Data Compression in Wireless Sensor Networks
No full textEnergy is a primary constraint in the design and deployment of wireless sensor networks (WSNs) since sensor nodes are typically powered by batteries with a limited capacity. Since radio communication is, in general, the most energy hungry operation in a sensor node, most of the techniques proposed to extend the lifetime of a WSN have focused on limiting transmission/reception of data, for instance, through data compression. Since sensor nodes are equipped with limited computational and storage resources, enabling compression requires specifically designed algorithms. In this paper, we propose a lossy compressor based on a differential pulse code modulation scheme with quantization of the differences between consecutive samples. The quantization parameters, which allow achieving the desired trade-off between compression performance and information loss, are determined by a multi-objective evolutionary algorithm. Experiments carried out on three datasets collected by real WSN deployments show that our approach can achieve significant compression ratios despite negligible reconstruction errors
A Two-Objective Evolutionary Approach to Design Lossy Compression Algorithms for Tiny Nodes of Wireless Sensor Networks
No full textSince tiny nodes of a wireless sensor network (WSN) are typically powered by batteries with, due to miniaturization and costs, a limited capacity, with the aim of extending the lifetime of WSNs and making the exploitation of WSNs appealing, a lot of research has been devoted to save energy. Although a number of factors contribute to power consumption, radio communication has been generally considered its main cause and thus most of the techniques proposed for energy saving have mainly focused on limiting transmission/reception of data, for instance, through data compression. As sensor nodes are equipped with limited computational and storage resources, enabling compression requires to develop purposely-designed algorithms. To this aim, we propose an approach to generate lossy compressors to be deployed on single nodes based on a differential pulse code modulation scheme with quantization of the differences between consecutive samples. The quantization levels and thresholds, which allow achieving different trade-offs between compression performance and information loss, are determined by a two-objective evolutionary algorithm. We tested our approach on four datasets collected by real WSN deployments. We show that the lossy compressors generated by our approach can achieve significant compression ratios despite negligible reconstruction errors and outperform LTC, a lossy compression algorithm purposely designed to be embedded in sensor nodes
A data-driven approach to automatic extraction of professional figure profiles from Résumés
No full textThe process of selecting and interviewing suitable candidates for a job position is time-consuming and labour-intensive. Despite the existence of software applications aimed at helping professional recruiters in the process, only recently with Industry 4.0 there has been a real interest in implementing autonomous and data-driven approaches that can provide insights and practical assistance to recruiters. In this paper, we propose a framework that is aimed at improving the performances of an Applicant Tracking System. More specifically, we exploit advanced Natural Language Processing and Text Mining techniques to automatically profile resources (i.e. candidates for a job) and offers by extracting relevant keywords and building a semantic representation of résumés and job opportunities
An intelligent system for electrical energy management in buildings
No full textRecent studies have highlighted that a significant part of the electrical energy consumption in residential and business buildings is due to an improper use of the electrical appliances. In this context, an automated power management system - capable of reducing energy wastes while preserving the perceived comfort level - would be extremely appealing. To this aim, we propose GreenBuilding, a sensor-based intelligent system that monitors the energy consumption and automatically controls the behavior of appliances used in a building. GreenBuilding has been implemented as a prototype and has been experimented in a real household scenario. The analysis of the experimental results highlights that GreenBuilding is able to provide significant energy savings
An Efficient Lossless Compression Algorithm for Tiny Nodes of Monitoring Wireless Sensor Networks
No full textEnergy is a primary constraint in the design and deployment of wireless sensor networks (WSNs), since sensor nodes are typically powered by batteries with a limited capacity. Energy efficiency is generally achieved by reducing radio communication, for instance, limiting transmission/reception of data. Data compression can be a valuable tool in this direction. The limited resources available in a sensor node demand, however, the development of specifically designed compression algorithms. In this paper, we propose a simple lossless entropy compression (LEC) algorithm which can be implemented in a few lines of code, requires very low computational power, compresses data on the fly and uses a very small dictionary whose size is determined by the resolution of the analog-to-digital converter. We have evaluated the effectiveness of LEC by compressing four temperature and relative humidity data sets collected by real WSNs, and solar radiation, seismic and ECG data sets. We have obtained compression ratios up to 70.81% and 62.08% for temperature and relative humidity data sets, respectively, and of the order of 70% for the other data sets. Then, we have shown that LEC outperforms two specifically designed compression algorithms for WSNs. Finally, we have compared LEC with gzip, bzip2, rar, classical Huffman and arithmetic encodings
- …
