1,720,980 research outputs found
Human Activity Recognition for the Identification of Bullying and Cyberbullying Using Smartphone Sensors
Full text linkThe smartphone is an excellent source of data; it is possible to extrapolate smartphone sensor values and, through Machine Learning approaches, perform anomaly detection analysis characterized by human behavior. This work exploits Human Activity Recognition (HAR) models and techniques to identify human activity performed while filling out a questionnaire via a smartphone application, which aims to classify users as Bullying, Cyberbullying, Victims of Bullying, and Victims of Cyberbullying. The purpose of the work is to discuss a new smartphone methodology that combines the final label elicited from the cyberbullying/bullying questionnaire (Bully, Cyberbully, Bullying Victim, and Cyberbullying Victim) and the human activity performed (Human Activity Recognition) while the individual fills out the questionnaire. The paper starts with a state-of-the-art analysis of HAR to arrive at the design of a model that could recognize everyday life actions and discriminate them from actions resulting from alleged bullying activities. Five activities were considered for recognition: Walking, Jumping, Sitting, Running and Falling. The best HAR activity identification model then is applied to the Dataset derived from the “Smartphone Questionnaire Application” experiment to perform the analysis previously described
E-learning at the University: an Experimental Investigation
No full textIn the Information Society e-learning represents a powerful approach to knowledge dissemination since e-learning systems allow to create didactic contents and to distribute them without space and time constraints.
Universities are certainly the most important institutions involved in e-learning applications. Furthermore, in the Universities relevant investments have been done and many projects have been realized. To this goal, several aspects need to be still analyzed and several difficulties are waiting for acceptable solutions, like those concerning cultural, economical and political aspects that strongly effect the motivations of teachers in adopting e-learning systems and methodologies.
In this paper, the e-learning advancements carried out at the University of Bari are presented and some issues concerning teacher interests, needs and expectations are investigated. For this purpose, a on-line questionnaire has been produces and responses are analyzed and discussed
Artificial Classifier Generation for Multi-expert System Evaluation
No full textThe evaluation of combination methods for multi-classifier systems is a difficult problem. In many cases multi-classifier combination methods are too complex to be formally studied and the experimental approach is the unique possible strategy. Of course, in order to simulate a multitude of real working conditions, sets of artificial classifiers with diverse characteristics must be generated.
This paper presents an effective technique for generating sets of artificial classifiers with different characteristics both at the individual-level (i.e. recognition performance) and at the collective-level (i.e. degree of similarity).
In the experimental tests, sets of artificial classifiers simulating different working conditions are generated and the performances of abstract-level combination methods are estimated. The results points out the effectiveness of the new technique for generating sets of artificial classifiers with different characteristics and their usefulness in estimating the performances of combination methods
A Controlled Benchmark of Video Violence Detection Techniques
Full text linkThis benchmarking study aims to examine and discuss the current state-of-the-art techniques for in-video violence detection, and also provide benchmarking results as a reference for the future accuracy baseline of violence detection systems. In this paper, the authors review 11 techniques for in-video violence detection. They re-implement five carefully chosen state-of-the-art techniques over three dierent and publicly available violence datasets, using several classifiers, all in the same conditions. The main contribution of this work is to compare feature-based violence detection techniques and modern deep-learning techniques, such as Inception V3
Diffusione dell'e-learning nell'Università degli Studi di Bari: Nuovi Avanzamenti
No full textL’acquisizione e la condivisione della conoscenza è uno degli aspetti chiave per il benessere individuale e collettivo nella attuale società. In questo scenario le moderne tecnologie e l’e-learning forniscono strumenti e metodi irrinunciabili per consentire la formazione continua e l’aggiornamento culturale e professionale. L’acquisizione delle conoscenze e delle competenze necessarie all’uso delle nuove tecnologie deve quindi rappresentare un obiettivo prioritario e trasversale della nostra società per il quale il mondo universitario deve impegnarsi per fornire adeguate risposte. Questo articolo presenta alcuni progetti di e-learning sviluppati nell’Università di Bari dal Centro “Rete Puglia”, per favorire la diffusione dell’e-learning nelle diverse Facoltà dell’Università di Bari “Aldo Moro”, nonché a favore delle pubbliche amministrazioni locali
TrafficWave: Generative deep learning architecture for vehicular traffic flow prediction
Full text linkVehicular traffic flow prediction for a specific day of the week in a specific time span is valuable information. Local police can use this information to preventively control the traffic in more critical areas and improve the viability by decreasing, also, the number of accidents. In this paper, a novel generative deep learning architecture for time series analysis, inspired by the Google DeepMind' Wavenet network, called TrafficWave, is proposed and applied to traffic prediction problem. The technique is compared with the most performing state-of-the-art approaches: stacked auto encoders, long-short term memory and gated recurrent unit. Results show that the proposed system performs a valuable MAPE error rate reduction when compared with other state of art techniques
MAGICIAN: Malware classification Approach through Generation Image using a Conditional and wassersteIn generative Adversarial Network variants
No full textOne of the main challenges of cybersecurity is the detection and classification of malware to prevent damage to systems by both companies and private users. Identifying the specific type of malware is critical to performing targeted actions. This study proposes a classification approach that generates synthetic images of malware using Conditional Generative Adversarial Networks (cGAN) and Wasserstein Generative Adversarial Networks (WGAN). Using the Malimg dataset, consisting of 25 malware classes, the ResNet50 model shows an overall accuracy of 91.4% and an F1-score of 90.8% for synthetic images generated with WGAN. Resizing and resampling were employed as preprocessing strategies to obtain images of size 48 × 48; resampling has been shown to be more effective. Thus, the proposed methodology allows malware to be classified quickly and efficiently, and, on the other hand, unbalanced datasets can be enriched to aid classification performance
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
