CIIC - Artigos em Revistas com Peer Review
URI permanente para esta coleção:
Navegar
Percorrer CIIC - Artigos em Revistas com Peer Review por Domínios Científicos e Tecnológicos (FOS) "Ciências Naturais::Ciências da Computação e da Informação"
A mostrar 1 - 10 de 20
Resultados por página
Opções de ordenação
- Automatic Transcription of Polyphonic Piano Music Using Genetic Algorithms, Adaptive Spectral Envelope Modeling, and Dynamic Noise Level EstimationPublication . Reis, Gustavo; Fernandez de Vega, Francisco; Ferreira, AníbalThis paper presents a new method for multiple fundamental frequency (F0) estimation on piano recordings. We propose a framework based on a genetic algorithm in order to analyze the overlapping overtones and search for the most likely F0 combination. The search process is aided by adaptive spectral envelope modeling and dynamic noise level estimation: while the noise is dynamically estimated, the spectral envelope of previously recorded piano samples (internal database) is adapted in order to best match the piano played on the input signals and aid the search process for the most likely combination of F0s. For comparison, several state-of-the-art algorithms were run across various musical pieces played by different pianos and then compared using three different metrics. The proposed algorithm ranked first place on Hybrid Decay/Sustain Score metric, which has better correlation with the human hearing perception and ranked second place on both onset-only and onset–offset metrics. A previous genetic algorithm approach is also included in the comparison to show how the proposed system brings significant improvements on both quality of the results and computing time.
- A Dataset of Photos and Videos for Digital Forensics Analysis Using Machine Learning ProcessingPublication . Ferreira, Sara; Antunes, Mário; Correia, Manuel E.Deepfake and manipulated digital photos and videos are being increasingly used in a myriad of cybercrimes. Ransomware, the dissemination of fake news, and digital kidnapping-related crimes are the most recurrent, in which tampered multimedia content has been the primordial disseminating vehicle. Digital forensic analysis tools are being widely used by criminal investigations to automate the identification of digital evidence in seized electronic equipment. The number of files to be processed and the complexity of the crimes under analysis have highlighted the need to employ efficient digital forensics techniques grounded on state-of-the-art technologies. Machine Learning (ML) researchers have been challenged to apply techniques and methods to improve the automatic detection of manipulated multimedia content. However, the implementation of such methods have not yet been massively incorporated into digital forensic tools, mostly due to the lack of realistic and well-structured datasets of photos and videos. The diversity and richness of the datasets are crucial to benchmark the ML models and to evaluate their appropriateness to be applied in real-world digital forensics applications. An example is the development of third-party modules for the widely used Autopsy digital forensic application. This paper presents a dataset obtained by extracting a set of simple features from genuine and manipulated photos and videos, which are part of state-of-the-art existing datasets. The resulting dataset is balanced, and each entry comprises a label and a vector of numeric values corresponding to the features extracted through a Discrete Fourier Transform (DFT). The dataset is available in a GitHub repository, and the total amount of photos and video frames is 40, 588 and 12, 400, respectively. The dataset was validated and benchmarked with deep learning Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) methods; however, a plethora of other existing ones can be applied. Generically, the results show a better F1-score for CNN when comparing with SVM, both for photos and videos processing. CNN achieved an F1-score of 0.9968 and 0.8415 for photos and videos, respectively. Regarding SVM, the results obtained with 5-fold cross-validation are 0.9953 and 0.7955, respectively, for photos and videos processing. A set of methods written in Python is available for the researchers, namely to preprocess and extract the features from the original photos and videos files and to build the training and testing sets. Additional methods are also available to convert the original PKL files into CSV and TXT, which gives more flexibility for the ML researchers to use the dataset on existing ML frameworks and tools.
- Elder care architecture - A physical and social approachPublication . Marcelino, Isabel; Barroso, João; Cruz, José Bulas; Pereira, AntónioAs we observe society in our days, we can see that people live longer; this means that we have an older population, more likely to have health issues. The special needs presented by the elderly are becoming a major concern for all of us, along with the lack of time demonstrated by society as a whole and, as a consequence, the lack of time is seen when families are not able to take care of their own elders. Many solutions are being presented in order to solve this problem. Some of them are taking advantage of the new technological developments in the body sensor networks area. In this paper we propose the architecture of a system called Elder Care. The Elder Care solution has two primary goals: monitoring vital signs, sending alerts to family and to specialized help and providing a social network in order to help end the elderly's social isolation.
- Evolving a Multi-Classifier System for Multi-Pitch Estimation of Piano Music and Beyond: An Application of Cartesian Genetic ProgrammingPublication . Miragaia, Rolando; Fernández, Francisco; Reis, Gustavo; Inácio, TiagoThis paper presents a new method with a set of desirable properties for multi-pitch estimation of piano recordings. We propose a framework based on a set of classifiers to analyze audio input and to identify piano notes present in a given audio signal. Our system’s classifiers are evolved using Cartesian genetic programming: we take advantage of Cartesian genetic programming to evolve a set of mathematical functions that act as independent classifiers for piano notes. Two significant improvements are described: the use of a harmonic mask for better fitness values and a data augmentation process for improving the training stage. The proposed approach achieves com-petitive results using F-measure metrics when compared to state-of-the-art algorithms. Then, we go beyond piano and show how it can be directly applied to other musical instruments, achieving even better results. Our system’s architecture is also described to show the feasibility of its parallelization and its implementation as a real-time system. Our methodology is also a white-box optimization approach that allows for clear analysis of the solutions found and for researchers to learn and test improvements based on the new findings.
- Evolving a multi-classifier system with cartesian genetic programming for multi-pitch estimation of polyphonic piano musicPublication . Miragaia, Rolando; Vega, Francisco Fernandez de; Reis, GustavoThis paper presents a new method for multi-pitch estimation on piano recordings. We propose a framework based on a set of classifiers to analyze the audio input and identify the piano notes present on the given audio signal. Our system's classifiers were evolved using Cartesian Genetic Programming: we take advantage of Cartesian Genetic Programming to evolve a set of mathematical functions that act as independent classifiers for piano notes. Our latest improvements are also presented, including test results using F-measure metrics. Our system architecture is also described to show the feasibility of its parallelization and implementation as a real time system. The proposed approach achieved competitive results, when compared to the state of the art.
- Exposing Manipulated Photos and Videos in Digital Forensics AnalysisPublication . Ferreira, Sara; Antunes, Mário; Correia, Manuel E.Tampered multimedia content is being increasingly used in a broad range of cybercrime activities. The spread of fake news, misinformation, digital kidnapping, and ransomware-related crimes are amongst the most recurrent crimes in which manipulated digital photos and videos are the perpetrating and disseminating medium. Criminal investigation has been challenged in applying machine learning techniques to automatically distinguish between fake and genuine seized photos and videos. Despite the pertinent need for manual validation, easy-to-use platforms for digital forensics are essential to automate and facilitate the detection of tampered content and to help criminal investigators with their work. This paper presents a machine learning Support Vector Machines (SVM) based method to distinguish between genuine and fake multimedia files, namely digital photos and videos, which may indicate the presence of deepfake content. The method was implemented in Python and integrated as new modules in the widely used digital forensics application Autopsy. The implemented approach extracts a set of simple features resulting from the application of a Discrete Fourier Transform (DFT) to digital photos and video frames. The model was evaluated with a large dataset of classified multimedia files containing both legitimate and fake photos and frames extracted from videos. Regarding deepfake detection in videos, the Celeb-DFv1 dataset was used, featuring 590 original videos collected from YouTube, and covering different subjects. The results obtained with the 5-fold cross-validation outperformed those SVM-based methods documented in the literature, by achieving an average F1-score of 99.53%, 79.55%, and 89.10%, respectively for photos, videos, and a mixture of both types of content. A benchmark with state-of-the-art methods was also done, by comparing the proposed SVM method with deep learning approaches, namely Convolutional Neural Networks (CNN). Despite CNN having outperformed the proposed DFT-SVM compound method, the competitiveness of the results attained by DFT-SVM and the substantially reduced processing time make it appropriate to be implemented and embedded into Autopsy modules, by predicting the level of fakeness calculated for each analyzed multimedia file.
- A Graph Database Representation of Portuguese Criminal-Related DocumentsPublication . Carnaz, Gonçalo; Nogueira, Vitor Beires; Antunes, MárioOrganizations have been challenged by the need to process an increasing amount of data, both structured and unstructured, retrieved from heterogeneous sources. Criminal investigation police are among these organizations, as they have to manually process a vast number of criminal reports, news articles related to crimes, occurrence and evidence reports, and other unstructured documents. Automatic extraction and representation of data and knowledge in such documents is an essential task to reduce the manual analysis burden and to automate the discovering of names and entities relationships that may exist in a case. This paper presents SEMCrime, a framework used to extract and classify named-entities and relations in Portuguese criminal reports and documents, and represent the data retrieved into a graph database. A 5WH1 (Who, What, Why, Where, When, and How) information extraction method was applied, and a graph database representation was used to store and visualize the relations extracted from the documents. Promising results were obtained with a prototype developed to evaluate the framework, namely a name-entity recognition with an F-Measure of 0.73, and a 5W1H information extraction performance with an F-Measure of 0.65.
- High dynamic range - a gateway for predictive ancient lightingPublication . Gonçalves, Alexandrino José Marques; Magalhães, Luís; Moura, João; Chalmers, AlanIn the last few years, the number of projects involving historical reconstruction has increased significantly. Recent technologies have proven a powerful tool for a better understanding of our cultural heritage through which to attain a glimpse of the environments in which our ancestors lived. However, to accomplish such a purpose, these reconstructions should be presented to us as they may really have been perceived by a local inhabitant, according to the illumination and materials used back then and, equally important, the characteristics of the human visual system. The human visual system has a remarkable ability to adjust itself to almost all everyday scenarios. This is particularly evident in extreme lighting conditions, such as bright light or dark environments. However, a major portion of the visible spectra captured by our visual system cannot be represented in most display devices. High dynamic range imagery is a field of research which is developing techniques to correct such inaccuracies. This new viewing paradigm is perfectly suited for archaeological interpretation, since its high contrast and chromaticity can present us with an enhanced viewing experience, closer to what an inhabitant of that era may have seen. In this article we present a case study of the reconstruction of a Roman site. We generate high dynamic range images of mosaics and frescoes from one of the most impressive monuments in the ruins of Conimbriga, Portugal, an ancient city of the Roman Empire. To achieve the requisite level of precision, in addition to having a precise geometric 3D model, it is crucial to integrate in the virtual simulation authentic physical data of the light used in the period under consideration. Therefore, in order to create a realistic physical-based environment, we use in our lighting simulations real data obtained from simulated Roman luminaries of that time.
- Illuminating the past: state of the artPublication . Happa, Jassim; Mudge, Mark; Debattista, Kurt; Artusi, Alessandro; Gonçalves, Alexandrino; Chalmers, AlanVirtual reconstruction and representation of historical environments and objects have been of research interest for nearly two decades. Physically based and historically accurate illumination allows archaeologists and historians to authentically visualise a past environment to deduce new knowledge. This report reviews the current state of illuminating cultural heritage sites and objects using computer graphics for scientific, preservation and research purposes. We present the most noteworthy and up-to-date examples of reconstructions employing appropriate illumination models in object and image space, and in the visual perception domain. Finally, we also discuss the difficulties in rendering, documentation, validation and identify probable research challenges for the future. The report is aimed for researchers new to cultural heritage reconstruction who wish to learn about methods to illuminate the past.
- IndoorCare: Low-Cost Elderly Activity Monitoring System through Image ProcessingPublication . Fuentes, Daniel; Correia, Luís; Costa, Nuno; Reis, Arsénio; Ribeiro, José; Rabadão, Carlos; Barroso, João; Pereira, AntónioThe Portuguese population is aging at an increasing rate, which introduces new problems, particularly in rural areas, where the population is small and widely spread throughout the territory. These people, mostly elderly, have low income and are often isolated and socially excluded. This work researches and proposes an affordable Ambient Assisted Living (AAL)‐based solution to monitor the activities of elderly individuals, inside their homes, in a pervasive and non-intrusive way, while preserving their privacy. The solution uses a set of low‐cost IoT sensor devices, computer vision algorithms and reasoning rules, to acquire data and recognize the activities performed by a subject inside a home. A conceptual architecture and a functional prototype were developed, the prototype being successfully tested in an environment similar to a real case scenario. The system and the underlying concept can be used as a building block for remote and distributed elderly care services, in which the elderly live autonomously in their homes, but have the attention of a caregiver when needed.