Search

The vulnerability of the speaker identity verification system to attacks using voice cloning was examined. The research project assumed creating a model for verifying the speaker's identity based on voice biometrics and then testing its resistance to potential attacks using voice cloning. The Deep Speaker Neural Speaker Embedding System was trained, and the Real-Time Voice Cloning system was employed based on the SV2TTS, Tacotron, WaveRNN, and GE2E neural networks. The results of attacks using voice cloning were analyzed and discussed in the context of a subjective assessment of cloned voice fidelity. Subjective test results and attempts to authenticate speakers proved that the tested biometric identity verification system might resist voice cloning attacks even if humans cannot distinguish cloned samples from original ones. [ABSTRACT FROM AUTHOR]

Simple Summary: Liquid biopsies are a non-invasive way to diagnose and monitor cancer using blood tests. Machine learning can help understand the genetic data from these tests, but it is challenging to validate clinical applications. In our study, we first compiled a large-scale dataset for cancer classification. Then, we extracted relevant features from the data and performed a binary classification, with the prediction outcome of either a sample collected from a cancer patient or a sample collected from an asymptomatic control. We used different convolutional neural networks (CNNs) and boosting methods to evaluate the classification performance. We have obtained an impressive result of 0.96 area under the curve. Finally, we tested the robustness of the models using test data from novel hospitals and performed data inspection to find the most relevant features for the prediction. Our work proves the great potential of using liquid biopsies for cancer patient classification. Liquid biopsies offer minimally invasive diagnosis and monitoring of cancer disease. This biosource is often analyzed using sequencing, which generates highly complex data that can be used using machine learning tools. Nevertheless, validating the clinical applications of such methods is challenging. It requires: (a) using data from many patients; (b) verifying potential bias concerning sample collection; and (c) adding interpretability to the model. In this work, we have used RNA sequencing data of tumor-educated platelets (TEPs) and performed a binary classification (cancer vs. no-cancer). First, we compiled a large-scale dataset with more than a thousand donors. Further, we used different convolutional neural networks (CNNs) and boosting methods to evaluate the classifier performance. We have obtained an impressive result of 0.96 area under the curve. We then identified different clusters of splice variants using expert knowledge from the Kyoto Encyclopedia of Genes and Genomes (KEGG). Employing boosting algorithms, we identified the features with the highest predictive power. Finally, we tested the robustness of the models using test data from novel hospitals. Notably, we did not observe any decrease in model performance. Our work proves the great potential of using TEP data for cancer patient classification and opens the avenue for profound cancer diagnostics. [ABSTRACT FROM AUTHOR]

Smart meters in road lighting systems create new opportunities for automatic diagnostics of undesirable phenomena such as lamp failures, schedule deviations, or energy theft from the power grid. Such a solution fits into the smart cities concept, where an adaptive lighting system creates new challenges with respect to the monitoring function. This article presents research results indicating the practical feasibility of real-time detection of anomalies in a road lighting system based on analysis of data from smart energy meters. Short-term time series forecasting was used first. In addition, two machine learning methods were used: one based on an autoregressive integrating moving average periodic model (SARIMA) and the other based on a recurrent network (RNN) using long short-term memory (LSTM). The algorithms were tested on real data from an extensive lighting system installation. Both approaches enable the creation of self-learning, real-time anomaly detection algorithms. Therefore, it is possible to implement them on edge computing layer devices. A comparison of the algorithms indicated the advantage of the method based on the SARIMA model. [ABSTRACT FROM AUTHOR]

Artificial Neural Network (ANN) models, specifically Convolutional Neural Networks (CNN), were applied to extract emotions based on spectrograms and mel-spectrograms. This study uses spectrograms and mel-spectrograms to investigate which feature extraction method better represents emotions and how big the differences in efficiency are in this context. The conducted studies demonstrated that mel-spectrograms are a better-suited data type for training CNN-based speech emotion recognition (SER). The research experiments employed five popular datasets: Crowd-sourced Emotional Multimodal Actors Dataset (CREMA-D), Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), Surrey Audio-Visual Expressed Emotion (SAVEE), Toronto Emotional Speech Set (TESS), and The Interactive Emotional Dyadic Motion Capture (IEMOCAP). Six different classes of emotions were used: happiness, anger, sadness, fear, disgust, and neutral. However, some experiments were prepared to recognize just four emotions due to the characteristics of the IEMOCAP dataset. A comparison of classification efficiency on different datasets and an attempt to develop a universal model trained using all datasets were also performed. This approach brought an accuracy of 55.89% when recognizing four emotions. The most accurate model for six emotion recognition was trained and achieved 57.42% accuracy on a combination of four datasets (CREMA-D, RAVDESS, SAVEE, TESS). What is more, another study was developed that demonstrated that improper data division for training and test sets significantly influences the test accuracy of CNNs. Therefore, the problem of inappropriate data division between the training and test sets, which affected the results of studies known from the literature, was addressed extensively. The performed experiments employed the popular ResNet18 architecture to demonstrate the reliability of the research results and to show that these problems are not unique to the custom CNN architecture proposed in experiments. Subsequently, the label correctness of the CREMA-D dataset was studied through the employment of a prepared questionnaire. [ABSTRACT FROM AUTHOR]

An approach to a new kind of recommendation system design that suggests safe speed on the road is presented. Real data obtained on roads were used for the simulations. As part of a project related to autonomous road sign development, a number of measurements were carried out on both local roads and expressways. A speed recommendation model was created based on gathered traffic data employing the traffic simulator. Depending on the traffic volume and atmospheric conditions prevailing on the road, as well as the surface conditions, the proposed system recommends the safe speed for passing vehicles by influencing the distance from the preceding vehicle to prevent collisions. The observed effect of the system application was an increase in the minimal distance between vehicles in most simulations. [ABSTRACT FROM AUTHOR]

The aim of this study is to identify the correlation between the amount of greenhouse gas emissions, added value from agriculture and economic growth in the Visegrad Group countries. Four countries of Central Europe were studied the Czech Republic, Hungary, Poland and Slovakia in 2008–2019. Due to the objectives of the article, it was decided to use the panel model. The temporal scope of the research covers the years 2008–2019, i.e., two economic periods: 2008–2014 (a downward trend, including agriculture), and 2015–2019 (an upward trend). Greenhouse gas emissions are positively correlated with value added from agriculture and economic growth. The increase in the level of these variables stimulates of the amount of greenhouse gas emissions in the countries of the Visegrad Group. The analysis of the eco-efficiency of greenhouse gas emissions in agriculture, in relation to the gross added value produced, shows that the country with the least pollution of this value was Hungary, followed by Slovakia. The Czech Republic was third, and Poland was the last. The results of the research can be treated as a premise for a strategy for the development of agriculture, limiting the negative effects of its industrial development for more sustainable development. [ABSTRACT FROM AUTHOR]

An evaluation of decision fusion methods based on Dempster-Shafer Theory (DST) and its modifications is presented in the article, studied over real biometric data from the engineered multimodal banking client verification system. First, the approaches for multimodal biometric data fusion for verification are explained. Then the proposed implementation of comparison scores fusion is presented, including details on the application of DST, required modifications, base probability, and mass conversions. Next, the biometric verification process is described, and the engineered biometric banking system principles are provided. Finally, the validation results of three fusion approaches on synthetic and real data are presented and discussed, considering the desired outcome manifested by minimized false non-match rates for various assumed thresholds and biometric verification techniques. [ABSTRACT FROM AUTHOR]

Traffic monitoring from closed-circuit television (CCTV) cameras on embedded systems is the subject of the performed experiments. Solving this problem encounters difficulties related to the hardware limitations, and possible camera placement in various positions which affects the system performance. To satisfy the hardware requirements, vehicle detection is performed using a lightweight Convolutional Neural Network (CNN), named SqueezeDet, while, for tracking, the Simple Online and Realtime Tracking (SORT) algorithm is applied, allowing for real-time processing on an NVIDIA Jetson Tx2. To allow for adaptation of the system to the deployment environment, a procedure was implemented leading to generating labels in an unsupervised manner with the help of background modelling and the tracking algorithm. The acquired labels are further used for fine-tuning the model, resulting in a meaningful increase in the traffic estimation accuracy, and moreover, adding only minimal human effort to the process allows for further accuracy improvement. The proposed methods, and the results of experiments organised under real-world test conditions are presented in the paper. [ABSTRACT FROM AUTHOR]

The emergence of innovative neurotechnologies in global brain projects has accelerated research and clinical applications of BCIs beyond sensory and motor functions. Both invasive and noninvasive sensors are developed to interface with cognitive functions engaged in thinking, communication, or remembering. The detection of eye movements by a camera offers a particularly attractive external sensor for computer interfaces to monitor, assess, and control these higher brain functions without acquiring signals from the brain. Features of gaze position and pupil dilation can be effectively used to track our attention in healthy mental processes, to enable interaction in disorders of consciousness, or to even predict memory performance in various brain diseases. In this perspective article, we propose the term 'CyberEye' to encompass emerging cognitive applications of eye-tracking interfaces for neuroscience research, clinical practice, and the biomedical industry. As CyberEye technologies continue to develop, we expect BCIs to become less dependent on brain activities, to be less invasive, and to thus be more applicable. [ABSTRACT FROM AUTHOR]

The aim of this article is to indicate the rationale for the development of the bioeconomy in selected EU countries depending on their overall level of economic development. The research was based on four highly developed countries, i.e., Germany, France, Finland and Denmark, and four medium-developed countries, i.e., Poland, Hungary, Czech Republic, and Slovakia for the period 2001–2018. Renewable energy consumption, biomass and agricultural production were analysed as determinants of the bioeconomy development. The question was also answered whether differences in terms of measures determining the level of bioeconomy development between countries with different levels of economic development during the studied period are decreasing or increasing, using sigma (σ)-convergence coefficients. It is shown that the development of the bioeconomy of the studied countries is related to their level of economic development. In the middle economically developed countries, real opportunities for the development of the bioeconomy are noted, through a high share of agriculture in national income; and in highly developed countries—high spending on research and development and the growth of eco-innovation, which contributes to maintaining a development advantage between these groups of countries. [ABSTRACT FROM AUTHOR]

A method of modeling the time of object transition between given pairs of cameras based on the Gaussian Mixture Model (GMM) is proposed in this article. Temporal dependencies modeling is a part of object re-identification based on the multi-camera experimental framework. The previously utilized Expectation-Maximization (EM) approach, requiring setting the number of mixtures arbitrarily as an input parameter, was extended with the algorithm that automatically adapts the model to statistical data. The probabilistic model was obtained by matching to the histogram of transition times between a particular pair of cameras. The proposed matching procedure uses a modified particle swarm optimization (mPSO). A way of using models of transition time in object re-identification is also presented. Experiments with the proposed method of modeling the transition time were carried out, and a comparison between previous and novel approach results are also presented, revealing that added swarms approximate normalized histograms very effectively. Moreover, the proposed swarm-based algorithm allows for modelling the same statistical data with a lower number of summands in GMM. [ABSTRACT FROM AUTHOR]

Handwriting biometrics applications in e-Security and e-Health are addressed in the course of the conducted research. An automated analysis method for the dynamic electronic representation of handwritten signature authentication was researched. The developed algorithms are based on the dynamic analysis of electronically handwritten signatures employing neural networks. The signatures were acquired with the use of the designed electronic pen described in the paper. The triplet loss method was used to train a neural network suitable for writer-invariant signature verification. For each signature, the same neural network calculates a fixed-length latent space representation. The hand-corrected dataset containing 10,622 signatures was used in order to train and evaluate the proposed neural network. After learning, the network was tested and evaluated based on a comparison with the results found in the literature. The use of the triplet loss algorithm to teach the neural network to generate embeddings has proven to give good results in aggregating similar signatures and separating them from signatures representing different people. [ABSTRACT FROM AUTHOR]

Real-time neural spike detection is an important step in understanding neurological activities and developing brain-silicon interfaces. Recent approaches exploit minimally invasive sensing techniques based on implanted complementary metal-oxide semiconductors (CMOS) multi transistors arrays (MTAs) that limit the damage of the neural tissue and provide high spatial resolution. Unfortunately, MTAs result in low signal-to-noise ratios due to the weak capacitive coupling between the nearby neurons and the sensor and the high noise power coming from the analog front-end. In this paper we investigate the performance achievable by using spike detection algorithms for MTAs, based on some variants of the smoothed non-linear energy operator (SNEO). We show that detection performance benefits from the correlation of the signals detected by the MTA pixels, but degrades when a high firing rate of neurons occurs. We present and compare different approaches and noise estimation techniques for the SNEO, aimed at increasing the detection accuracy at low SNR and making it less dependent on neurons firing rates. The algorithms are tested by using synthetic neural signals obtained with a modified version of NEUROCUBE generator. The proposed approaches outperform the SNEO, showing a more than 20% increase on averaged sensitivity at 0 dB and reduced dependence on the neuronal firing rate. [ABSTRACT FROM AUTHOR]

High density electrocorticography (ECoG)-based microelectrode arrays (MEAs) are fabricated to timely record the neural activities to provide the fundamental understanding in neuroscience and biomedical engineering. This paper aims to introduce a device-based concept and wafer-scale fabrication process for MEAs. Flexible and biocompatible polyimide is applied on MEAs to bear all possible stress and strain. Detailed fabrication key techniques, including surface treatment, polyimide stability measurement, evaporation process, and curing conditions, have been discussed thoroughly. Moreover, the fabricated polyimide-based MEAs are surface-mounted on well-packaged printed circuit boards (PCBs) via a slot-type connector without any additional wire bonding to make the signal recording process easier. An absence seizure was recorded during the in vivo test, which shows the availability of signal recording based on the presented MEAs. The proposed MEAs could be remained at the skull, while the connector and PCBs can be disassembled apart. Therefore, the testing sample will get less suffering. To verify the robustness of the fabricated MEAs, the impedance properties were characterized using electrochemical impedance spectroscopy. The measured results indicate an average impedance of 12.3 ± 0.675 kΩ at 1 kHz. In total, 10 groups of MEAs were sample tested, and over 90% of the total 60 channels per 1-MEAs operated efficiently. [ABSTRACT FROM AUTHOR]

This article studies the development and implementation of different electronic devices for measuring signals during stress situations, specifically in academic contexts in a student group of the Engineering Department at the University of Pamplona (Colombia). For the research's development, devices for measuring physiological signals were used through a Galvanic Skin Response (GSR), the electrical response of the heart by using an electrocardiogram (ECG), the electrical activity produced by the upper trapezius muscle (EMG), and the development of an electronic nose system (E-nose) as a pilot study for the detection and identification of the Volatile Organic Compounds profiles emitted by the skin. The data gathering was taken during an online test (during the COVID-19 Pandemic), in which the aim was to measure the student's stress state and then during the relaxation state after the exam period. Two algorithms were used for the data process, such as Linear Discriminant Analysis and Support Vector Machine through the Python software for the classification and differentiation of the assessment, achieving 100% of classification through GSR, 90% with the E-nose system proposed, 90% with the EMG system, and 88% success by using ECG, respectively. [ABSTRACT FROM AUTHOR]

Innovative road signs that can autonomously display the speed limit in cases where the traffic situation requires it are under development. The autonomous road sign contains many types of sensors, of which the subject of interest in this article is the Doppler sensor that we have improved and the constructed and calibrated acoustic probe. An algorithm for performing vehicle detection and tracking, as well as vehicle speed measurement, in a signal acquired with a continuous wave Doppler sensor, is discussed. A method is also experimentally presented and studied for counting vehicles and for determining their movement direction by means of acoustic vector sensor application. The assumptions of the method employing spatial distribution of sound intensity determined with the help of an integrated three-dimensional (3D) sound intensity probe are discussed. The enhanced Doppler radar and the developed sound intensity probe were used for the experiments that are described and analyzed in the paper. [ABSTRACT FROM AUTHOR]

Fine particulate matter (PM2.5) emissions are an important global issue as air pollutants lead to approximately 7 million deaths per year (World Health Organization). In an attempt to combat this global threat, countries in the European Union (EU) allocate relatively large funds for environmental policies. The main goal of this paper is to assess the long-term efficiency of the EU countries' environmental policy in reducing the pressure of particulates pollution on the natural environment. For this purpose, multilevel panel regression models based on seminal within–between specification are used. The models are run for a panel of 25 EU countries for the years 2004–2016. In the investigations, we tried to capture the effect of the share of utilized agricultural area (UAA) in non-urban areas of the analyzed countries, as it may potentially influence policy efficiency. It was found that environmental spending in all main categories (pollution abatement, biodiversity, R&D, and environmental protection) had a significant impact on decreasing pollution pressure; however, the policy was more efficient in countries which had a lower share of UAA in their non-urban areas. The study emphasized that the impact of "pollution abatement" expenditure may be underestimated in basic panel models. [ABSTRACT FROM AUTHOR]

Willard Cochrane was the first to introduce the notion that farmers are on a market treadmill, which, in spite of their constant efforts to improve productivity, wears away any profits that might result. Therefore, the essence of the treadmill is that agricultural income does not grow in line with the increase in productivity. Although reasons of this phenomenon are economic in nature, it has caused a serious social problem, i.e., the relative deprivation of farmers' income. Solving this problem is crucial for ensuring sustainable farming in its social dimension. The aim of the article was, firstly, to answer the question to what extent the concept of the market treadmill in agriculture is still valid for European countries; and secondly, to develop a sectoral model of agricultural income that would test whether the Common Agricultural Policy (CAP) has been successfully struggling with the Cochrane's treadmill. The authors carried out panel research in a group of 25 countries over the years 1980–2015 in various subperiods. The main conclusion was that the traditionally understood market treadmill has lost significance in Europe, which might be advocated as a long-term value-added aspect of the Common Agricultural Policy (CAP). [ABSTRACT FROM AUTHOR]