1,721,072 research outputs found
A brief overview of recent techniques in crowd counting and density estimation
No full textEstimating crowd counting from images is a difficult but important task given the large range of applications such as public safety, traffic monitoring, and urban planning. Occlusions, uneven density, variation in scale and perspective are all challenges in crowd analysis. Thanks to advancements in deep learning and constructing demanding databases, modern computer vision techniques have led to numerous cutting-edge methods that build the abilities needed to properly execute a wide range of scenarios. This article presents a brief description of pioneering methods based on hand-crafted representations, followed by an examination of contemporary approaches based on convolutional neural networks (CNNs) that have achieved significant performance. In addition, the most frequently utilized datasets are addressed, and lastly, promising research routes in this rapidly increasing area are indicated
Mel Spectrogram-Based CNN Framework for Explainable Audio Deepfake Detection
No full textThe rise of audio deepfakes is becoming a growing concern for media credibility, particularly on social platforms. This study explores an approach to detecting audio deepfakes using Convolutional Neural Networks (CNNs) applied to Mel spectrograms, which serve as visual representations of audio signals. Six CNN architectures (VGG16, VGG19, ResNet50, DenseNet121, MobileNetV2, and EfficientNetB0) were evaluated using the FakeAVCelebV2 dataset, considering metrics such as precision, recall, F1-score, and accuracy. To provide better insight into model decisions, Grad-CAM, an Explainable Artificial Intelligence (XAI) technique, was employed to highlight the most relevant regions of the spectrogram for distinguishing between real and fake audio. The study also tested the model’s performance under conditions with added Gaussian and white noise to assess its robustness. The results confirm that CNN-based Mel spectrogram analysis is an effective method for audio deepfake detection, and they underline the importance of interpretability to ensure trustworthy media detection systems
A Biometric-Based Adaptive Simulator for Driving Education
No full textDistracted driving emerges as a global threat, significantly contributing to the alarming toll of 1.3 million annual traffic fatalities. This paper presents an innovative solution employing a Unity-based driving simulator with biometric features to tackle distracted driving across educational and technological domains. The simulator uses the popular Mediapipe Solutions library and uncomplicated camera setups to capture pivotal biometric parameters: head rotation, gaze direction, and eyelid opening. The fusion of these parameters creates an immersive user experience, enabling self-assessment of distraction levels within simulated nighttime scenarios. The simulator incorporates alerts for incorrect gaze direction or signs of drowsiness, employing an acoustic signal. Furthermore, the simulator activates car headlights upon the driver’s proximity to the dashboard, indicating compromised visibility. The proposed solution’s efficacy is confirmed through experiments conducted under diverse conditions, including scenarios with sunglasses, eyeglasses, and low luminosity. With minimal hardware and software requirements, the simulator emerges as a valuable educational tool for drivers, holding potential for integration into assisted driving systems. The results highlight its significant contribution to road safety, effectively addressing the pervasive issue of distracted driving through a comprehensive and accessible framework
The effect of rain on photovoltaic systems
Full text linkPhotovoltaic technology can be considered a key energy source for the future sustainable development, therefore it's important to carry out a continuous and comprehensive investigation about its actual energy performance in various climatic conditions. More in detail, crystalline silicon technology is currently dominating the market, thus an in-depth assessment on its specific behaviour is essential. In this sense, numerous studies have been performed in the past decades to assess the influence on the energy production of crystalline photovoltaic modules of several factors, such as spectral quality of solar irradiance, temperature, wind speed, soiling, snow etc. but so far the effect of rain appears scarcely investigated. In such a framework, the present work represents a detailed assessment of the rain effect on the performances of crystalline silicon technology, carried out both under a theoretical and experimental viewpoint, with a focus on the temperate climates of European context. Obtained results are promising and confirm that the overall impact of rain can have non-negligible positive influences on the energy productivity of photovoltaic systems, mainly for thermal and optical reasons, paving the way for further studies on the topic
SOTTILE, messa a punto di un componente BIPV innovativo per l’integrazione architettonica
Full text linkI sistemi fotovoltaici integrati negli edifici (BIPV) stanno suscitando un interesse crescente nel settore
delle costruzioni, in quanto permettono di abbattere le emissioni di CO2, svolgendo al contempo funzioni
tipiche dei componenti edilizi tradizionali, come l’impermeabilizzazione all’acqua. Tuttavia, i sistemi fotovoltaici tradizionali devono spesso affrontare sfide legate all’estetica e all’integrazione architettonica con componenti esistenti. In questo ambito, SOTTILE (SOlar Technological TILE), sviluppato nel progetto europeo
H2020 HEART coordinato dal Politecnico di Milano, rappresenta una soluzione innovativa per trasformare
con estrema facilità una falda o un tetto tradizionale in un generatore di elettricità solare.
SOTTILE è un sistema formato da elementi componibili secondo la geometria e le dimensioni desiderate
ed appositamente progettato per l’installazione su coperture a falda, in abbinamento con qualsiasi tipo di tegola. Può essere utilizzato, infatti, in sostituzione del manto in laterizio esclusivamente nelle porzioni destinate
all’impianto solare, mentre le restanti porzioni del tetto possono essere rivestite con elementi tradizionali. Ciascun elemento di SOTTILE è formato da un supporto modulare in plastica riciclata, su cui si aggancia il laminato fotovoltaico. L’intero sistema ed i suoi sub-componenti sono progettati per essere montati e
smontati rapidamente, agevolando notevolmente le pratiche di installazione, manutenzione e dismissione
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
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Smart buildings features and key performance indicators: A review
Full text linkThe concept of Smart Buildings was introduced by the Energy Performance Building Directive, with the aim to promote energy flexibility, renewable energy production and user interaction. A wide range of definitions have been introduced in the literature to characterize smart buildings yet, at present, its’ concept and features are not clearly and uniquely defined. Simultaneously, building energy retrofit concept has been introduced to facilitate achieving the nearly Zero-Energy Building target and reduce energy consumption in existing buildings. Up to 90 % of the existing European building stock will still be standing and in use in 2050. Thus, there is a need to upgrade the existing retrofitting strategies into Smart Retrofitting, to achieve the nearly Zero Energy Building target and be able to respond to external dynamic conditions such as the weather and the grid. The aim of this research is first to review the concept of smartness in the built environment, highlighting the main features, functions, and technologies of smart buildings, also discussing the possible challenges for smart retrofit applications. The second part of the paper reviews the existing Key Performance Indicators that measure the performance and success in achieving goals in smart buildings. The need to develop a quantified guideline to improve energy and technological innovation is the basis for the increase of the smartness in buildings. Consequently, a set of nine groups of representative performance indicators for smart buildings is developed. This work shows current gaps in the literature and highlights the space for foreseeable future research
A Facial Expression Recognition Approach for Social IoT Frameworks
No full textSocial IoT has become a sensitive topic in the last years, mainly due to the attraction of social networks and the related digital activities amongst the population. These techniques are gaining even more importance in the current period, in which digital tools are the only ones allowed to maintain social distancing due to the COVID-19 restrictions. In order to aid patients and elderly people in-home healthcare context, this article explores the usage of facial patient images and emotional detection. In this regard, a Social IoT approach is proposed, which is based on a camera connected home, allowing medical examinations at a distance by keeping posted the preferred contacts of the patient. A facial expression analysis is done to infer the patient's emotional state, thus communicating to the doctor and the emergency contacts any change in the patient's state (pain, suffering, etc.). The proposed facial expression recognition system consists of three main steps: during the image preprocessing phase, face detection and normalization are performed; the feature extraction process involves the computation of discriminative patterns using the Spatial Pyramid Technique; finally, an expression recognition model is built using a multi-class linear Support Vector Machine classifier. The performance of the proposed system has been tested on two challenging benchmarks for facial expression recognition, namely KDEF and GENKI-4K, which show that the proposed system overcomes state-of-the-art methods
- …
