Artificial Intelligence

Sleep is a basic human need, making up around one-third of our lives and being essential to the recovery of our physical well-being and general standard of living. However, poor sleep quality can interfere with these critical restorative processes, leading to disorders such as apnea and insomnia. These conditions not only impair daily performance but also have long-term health consequences. Furthermore, the challenges imposed by modern lifestyles have increased the prevalence of these sleep disorders, emphasizing the need for effective diagnostic tools. This research aims to harness the capabilities of Machine Learning (ML), specifically the Random Forest algorithm, to detect and analyze patterns indicative of sleep disorders in collected data sets. Random Forest is particularly suited for this task due to its ability to manage complex data sets by building multiple decision trees, thus creating a comprehensive and robust model for classifying sleep disorders. The findings of the study are promising, showing that the Random Forest algorithm can achieve a high level of accuracy in sleep disorder detection. The model demonstrated a test accuracy rate of 97.33%, with a precision of 96%, and a recall rate of 100%. Additionally, it achieved an F1-Score of 98% and a Kappa Score of 0.945, validating the reliability of this algorithm in producing precise classifications. This research offers significant insights into the patterns of sleep disorders and contributes to the development of targeted interventions aimed at improving sleep quality. Ultimately, this could significantly enhance the quality of life for individuals suffering from sleep disorders.

Multivariate measurements of human brain white matter (WM) with diffusion MRI (dMRI) provide information about the role of WM in a variety of cognitive functions and in brain health. Statistical models take advantage of the regularities in these data to make inferences about individual differences. For example, dMRI data provide the basis for accurate brain-age models -models that predict the chronological age of participants from WM tissue properties. Deep learning (DL) models are powerful machine learning models, which have been shown to provide benefits in many multivariate analysis settings. We investigated whether DL would provide substantial improvements for brain-age models based on dMRI measurements of WM in a large sample of children and adolescents. We found that some DL models fit the data better than a linear baseline, but the differences are small. In particular, recurrent neural network architectures provide up to ~6% improvement in accuracy. This suggests that information about WM development is mostly accessible with linear models, and does not require the additional invariance and non-linearity offered by DL models. However, in some applications this incremental improvement may prove critical. We provide open-source software that fits DL models to dMRI data ().

Multivariate measurements of human brain white matter (WM) with diffusion MRI (dMRI) provide information about the role of WM in a variety of cognitive functions and in brain health. Statistical models take advantage of the regularities in these data to make inferences about individual differences. For example, dMRI data provide the basis for accurate brain-age models – models that predict the chronological age of participants from WM tissue properties. Deep learning (DL) models are powerful machine learning models, which have been shown to provide benefits in many multivariate analysis settings. We investigated whether DL would provide substantial improvements for brain-age models based on dMRI measurements of WM in a large sample of children and adolescents. We found that some DL models fit the data better than a linear baseline, but the differences are small. In particular, recurrent neural network architectures provide up to ∼6% improvement in accuracy. This suggests that inform...

The use of image processing schemes as part of the security systems have been increasing, to detect, classify as well as to tract object and human motion with a high precision. To this end several approaches have been proposed during the last decades using image processing techniques, because computer vision let us to manipulated digital image sequences to extract useful information contained in a video stream. In this paper we present a motion detection algorithm using the movement vectors estimation which are subsequently filtered to obtain better information about real motion into a given scenes. Experimental results show that the accuracy of proposed system.

This document describes the fundamental criteria in the design of an automated Cartesian table with three XYZ axes with an interchangeable head for plasma and oxyfuel cutting, as well as the selection of the processes implemented for its construction. For this purpose, the table is divided into four fundamental parts: X axis, Y axis, Z axis and control system. As it is a table for a high precision process such as plasma, a study of machine errors is carried out using the Denavit -Hartenberg method and the errors associated with deformation using simulation software. To conclude, it is determined that with the design detailed in this document, it is possible to build a CNC table with high precision and low cost.

State of the art audio source separation models rely on supervised data-driven approaches, which can be expensive in terms of labeling resources. On the other hand, approaches for training these models without any direct supervision are typically high-demanding in terms of memory and time requirements, and remain impractical to be used at inference time. We aim to tackle these limitations by proposing a simple yet effective unsupervised separation algorithm, which operates directly on a latent representation of time-domain signals. Our algorithm relies on deep Bayesian priors in the form of pre-trained autoregressive networks to model the probability distributions of each source. We leverage the low cardinality of the discrete latent space, trained with a novel loss term imposing a precise arithmetic structure on it, to perform exact Bayesian inference without relying on an approximation strategy. We validate our approach on the Slakh dataset [1], demonstrating results in line with state of the art supervised approaches while requiring fewer resources with respect to other unsupervised methods.

The number of devices linked to the Internet is continuously rising along with the development of the Internet of Things (IoT). The IoT and the expanding volume of data it communicates place constraints on cloud-based data processing and storage. Both fog and cloud computing allow users to store apps and data, but Fog has a broader geographic reach and is closer to the end user. Managing rapidly changing resource provisioning and allocation of resources in fog computing will create new challenges when developing IoT applications and satisfying user requests. To control resource consumption and Service Level Agreements (SLA), flexible and often autonomous systems must choose the appropriate virtual resources. This work presents a Deep Reinforcement Learning (DRL) based structure for resource provisioning for improving resource management efficiency in IoT ecosystems. A Deep Neural Network (DNN) is used for assessing value functions, and it allows for better compliance to diverse conditions, learning from prior sensible approaches, and acting as a self-learning adaptive system. Using the DRL algorithm and the Proximal Policy Optimization (PPO), IoT services can be established by reducing average consumption of energy and latency, cutting expenses, and wisely utilising and allocating resources. Simulations with the iFogSim show that the PPO policy increases utilization, reduces delay rates, and maintains acceptable service quality while reducing energy consumption and increasing utilization under varying loading rates.

Face recognition is a fast-growing technology that is widely used in forensics such as criminal identification, secure access and prison security.It contrasts from other classification issues in that there are normally a more number of classes in face recognition. Thus, the validation accuracy of the conventional subsystem face recognition is unsuitable. In order to overcome those problems the suggested method utilizes the spider monkey inspired optimization (SMO) algorithm for face clustering and recognition. At first feature reduction is done by advance principal component analysis (APCA) which is a hybridization of PCA and linear discriminant analysis (LDA). After reducing the features, the selected features are grouped and faces are recognized by means of SMO algorithm. From the food search behavior of spider monkeys, SMO algorithm is developed. The proposed performance is evaluated by means of sensitivity, specificity and accuracy. Here the proposed method accomplishes 98.66% accuracy. Using the MATLAB platform, the recommended technique is implemented.

Weather forecasting is a crucial phenomenon in today's world. Though weather prediction is completely automated, with the help of tools like Weather Research & Forecasting (WRF), Advanced Research WRF (ARW), Weather Processing System (WPS), it's a ever challenging and a topic of interest because prediction is not an accurate always. Weather forecasting is a continuous, high dimensional, dynamic and complicated process because it involves many entities of the atmosphere. The parameters required to predict the weather are enormously complex such that there is uncertainty in prediction even for a short period. The property of artificial neural networks is that they not only analyze the historical data, but also learn from it for future predictions make them suitable / ideal for weather forecasting. Weather prediction can be simplified by using the artificial neural networks (ANN) with back propagation for supervised learning using the data collected at a particular station at a specified period. After training the model, they are used to predict the weather conditions. As an experimental method, the model is made known to predict the values as unknown values. The output is promising and motivates us to work more towards this goal.

In the digital world, classifying real sensed data in huge volumes derived from numerical problems is a challenging task due to the computational complexity of the metaheuristic searching process. The deep learning approach includes convolutional neural network (CNN), long short-term memory (LSTM), and Bidirectional (BI)-LSTM, suitable for an optimistic processing time of analyzing XML datasets (i.e., social media, trade center, and surveillance data exchanged in the internet world). However, it faces process deviation when datasets extend their range beyond the expected volume. This paper proposes a novel deep learning formwork referred to as archimed improved numerical optimization deep learning (AINODL) to improve the classification of XML datasets. The proposed AINODL framework first extracts feature from XML documents using the vector space model. Secondly, it classifies the XML data using the inbuilt function of the AINODL framework. The experiments demonstrate that the perfor...

We automatically extract the summaries of spoken class lectures. This paper presents a novel method for sentence extraction-based automatic speech summarization. We propose a technique that extracts "cue phrases for important sentences (CPs)" that often appear in important sentences. We formulate CP extraction as a labeling problem of word sequences and use Conditional Random Fields (CRF) for labeling. Automatic summarization using CP extraction results as features yields precisions of 0.603 and 0.556 when using manual transcriptions and Automatic Speech Recognition (ASR) results, respectively. Combining the features derived from the CPs and traditional features (including repeated words, words repeated in a slide text, and term frequency (tf), which are surface linguistic information, and speech power and duration, which are prosodic features) [2, 3], we obtained better summarization performance with a κ-value of 0.380, a F -measure of 0.539, and a Rouge-4 of 0.709.

If a dialog system were to respond to a user as naturally as a human, interaction would be smoother. Imitating the human prosodic behavior of utterances is important in computer-human natural conversations. In this paper, to develop a cooperative/friendly spoken dialog system, we analyzed the correlations between F0 synchrony tendency or overlap frequency and subjective measures: "liveliness," "familiarity," and "informality" in human-human dialogs. We also modeled the properties of these features and implemented the model on our dialog system that generated the response timing of aizuchi (back-channel), turn-taking based on a decision tree in real time, and dynamical F0 changes to realize chat-like conversations.

We propose a method of detecting "task incomplete" dialogs in spoken dialog systems using N-gram-based dialog models. We used a database created during a field test in which inexperienced users used a client-server music retrieval system with a spoken dialog interface on their own PCs. In this study, the dialog for a music retrieval task consisted of a sequence of user and system tags that related their utterances and behaviors. The dialogs were manually classified into two classes: the dialog either completed the music retrieval task or it didn't. We then detected dialogs that did not complete the task, using N-gram probability models or a Support Vector Machine with N-gram feature vectors trained using manually classified dialogs. Offline and on-line detection experiments were conducted on a large amount of real data, and the results show that our proposed method achieved good classification performance.

In this study, we investigate the effect of blind spatial subtraction arrays (BSSA) on speech recognition systems by comparing the performance of a method using Mel-Frequency Cepstral Coefficients (MFCCs) with a method using Deep Bottleneck Features (DBNF) based on Deep Neural Networks (DNN). Performance is evaluated under various conditions, including noisy, in-vehicle conditions. Although performance of the DBNF-based system was much more degraded by noise than the MFCC-based system, BSSA improved the performance of both methods greatly, especially when matched condition training of acoustic models was employed. These results show the effectiveness of BSSA for speech recognition.

Recently, the performance of speech recognition was drastically improved, and the products with the interface based on speech recognition have been realized. However, when we communicate with computers through a speech interface, misrecognition is inevitable, and it is difficult to recover from it because of the immaturity of the interface. Users try to recover from misrecognition by a repetition of the same content. So, the detection of user's repetition is helpful for a system to detect its misunderstanding, and to recover from the misrecognition. In this paper, we assume the utterance which includes repetitions a correction and propose a method to detect correction utterances in spontaneously spoken dialog using a word spotting based on DTW (dynamic time warping) and N -best hypotheses overlapping measure. As a result, we achieved recall rate of 92.7% and precision of 89.1%. Moreover, we tried to improve recognition accuracy using the detection. Using the choice of vocabulary and grammar setup based on the detection, we achieved improvement in recognition performance from 42.7% to 50.0% for correction utterance and from 70.5% to 77.9% for non-correction utterance.

To improve speech recognition performance, acoustic feature transformation based on discriminant analysis has been widely used. For the same purpose, discriminative training of HMMs has also been used. In this letter we investigate the effectiveness of these two techniques and their combination. We also investigate the robustness of matched and mismatched noise conditions between training and evaluation environments.

To precisely model the time dependency of features is one of the important issues for speech recognition. Segmental unit input HMM with a dimensionality reduction method has been widely used to address this issue. Linear discriminant analysis (LDA) and heteroscedastic extensions, e.g., heteroscedastic linear discriminant analysis (HLDA) or heteroscedastic discriminant analysis (HDA), are popular approaches to reduce dimensionality. However, it is difficult to find one particular criterion suitable for any kind of data set in carrying out dimensionality reduction while preserving discriminative information. In this paper, we propose a new framework which we call power linear discriminant analysis (PLDA). PLDA can be used to describe various criteria including LDA, HLDA, and HDA with one control parameter. In addition, we provide an efficient selection method using a control parameter without training HMMs nor testing recognition performance on a development data set. Experimental results show that the PLDA is more effective than conventional methods for various data sets.

The aim of this research is to identify local Arabic dialects in texts from social media (Twitter) and link them to specific geographic areas. Dialect identification is studied as a subset of the task of language identification. The proposed method is based on unsupervised learning using simultaneously lexical and geographic distance. While this study focusses on Libyan dialects, the approach is general, and could produce resources to support human translators and interpreters when dealing with vernaculars rather than standard Arabic.

This work proposes a novel solution for detecting and tracing spatially varying edges of large manufacturing workpieces, using a consumer grade RGB depth camera, with only a partial view of the workpiece and without prior knowledge. The proposed system can visually detect and trace various edges, with a wide array of degrees, to an accuracy of 15 mm or less, without the need for any previous information, setup or planning. A combination of physical experiments on the setup and more complex simulated experiments were conducted. The effectiveness of the system is demonstrated via simulated and physical experiments carried out on both acute and obtuse edges, as well as typical aerospace structures, made from a variety of materials, with dimensions ranging from 400 mm to 600 mm. Simulated results show that, with artificial noise added, the solution presented can detect aerospace structures to an accuracy of 40 mm or less, depending on the amount of noise present, while physical aerospac...

Background: Within the structural and grammatical bounds of a common language, all authors develop their own distinctive writing styles. Whether the relative occurrence of common words can be measured to produce accurate models of authorship is of particular interest. This work introduces a new score that helps to highlight such variations in word occurrence, and is applied to produce models of authorship of a large group of plays from the Shakespearean era. Methodology: A text corpus containing 55,055 unique words was generated from 168 plays from the Shakespearean era (16th and 17th centuries) of undisputed authorship. A new score, CM1, is introduced to measure variation patterns based on the frequency of occurrence of each word for the authors John Fletcher, Ben Jonson, Thomas Middleton and William Shakespeare, compared to the rest of the authors in the study (which provides a reference of relative word usage at that time). A total of 50 WEKA methods were applied for Fletcher, Jonson and Middleton, to identify those which were able to produce models yielding over 90% classification accuracy. This ensemble of WEKA methods was then applied to model Shakespearean authorship across all 168 plays, yielding a Matthews' correlation coefficient (MCC) performance of over 90%. Furthermore, the best model yielded an MCC of 99%. Our results suggest that different authors, while adhering to the structural and grammatical bounds of a common language, develop measurably distinct styles by the tendency to over-utilise or avoid particular common words and phrasings. Considering language and the potential of words as an abstract chaotic system with a high entropy, similarities can be drawn to the Maxwell's Demon thought experiment; authors subconsciously favour or filter certain words, modifying the probability profile in ways that could reflect their individuality and style.

The date of the first performance of a play of Shakespeare's time must usually be guessed with reference to multiple indirect external sources, or to some aspect of the content or style of the play. Identifying these dates is important to literary history and to accounts of developing authorial styles, such as Shakespeare's. In this study, we took a set of Shakespeare-era plays (181 plays from the period 1585-1610), added the best-guess dates for them from a standard reference work as metadata, and calculated a set of probabilities of individual words in these samples. We applied 11 regression methods to predict the dates of the plays at an 80/20 training/test split. We withdrew one play at a time, used the best-guess date metadata with the probabilities and weightings to infer its date, and thus built a model of date-probabilities interaction. We introduced a memetic algorithm-based Continued Fraction Regression (CFR) which delivered models using a small number of variables, leading to an interpretable model and reduced dimensionality. An in-depth analysis of the most commonly occurring 20 words in the CFR models in 100 independent runs helps explain the trends in linguistic and stylistic terms. The analysis with the subset of words revealed an interesting correlation of signature words with the Shakespeare-era play's genre. Keywords Shakespeare-era plays • continued fraction regression • dating of plays • play's genre • Memetic Algorithm

Data warehouses are environments used for data analysis and efficient decision making within companies. They are tools that allow the execution of complex and multidimensional queries. One of the security vulnerabilities that can be used by malicious users is data inference, which is the deduction of private information by devious means. In the present work, we tried to show that the existence of functional dependencies in the data can help to perform an inference attack by using supervised learning algorithms to infer private information. These algorithms are Support Vector Machine (SVM), Random Forest (RF), Bayesian Regularized Neural Network (BRNN) and K-Nearest Neighbors (K-NN). The BRNN provided a better performance in our study. This paper implements an inference attack using regression learning algorithms, studies different dependency situations in the data, and uses the combination of COUNT, SUM, AVG and STDEV queries. The use of several methods in this study allows the prevention of inferences when one of these methods is used by a malicious user. We managed to achieve this attack by detecting 09.12% inferences on all methods compared to BRNN whose realized inference rate is 03.94%.

In a very noisy environment, the transmission of video sequences Motion JPEG 2000 is not entirely reliable since attending packet loss in the codestream the movie Motion JPEG 2000. For a reconstruction of the lost packets, the method of conditional replenishment has been proposed. However, with this method, the effects of blocks appear in motion areas making the quality of the video poor in these areas. In this paper, we propose the method of estimation and motion compensation for optimal recovery of lost packets in motion areas. Thus, the application implementation in Matlab can see firsthand the disappearance of the effects of blocks in the transmission of video sequence Motion JPEG 2000 in a very noisy environment.

advancement of the novel models for time-series prediction of COVID-19 is of utmost importance. Machine learning (ML) methods have recently shown promising results. The present study aims to engage an artificial neural networkintegrated by grey wolf optimizer for COVID-19 outbreak predictions by employing the Global dataset. Training and testing processes have been performed by time-series data related to January 22 to September 15, 2020 and validation has been performed by time-series data related to September 16 to October 15, 2020. Results have been evaluated by employing mean absolute percentage error (MAPE) and correlation coefficient (r) values. ANN-GWO provided a MAPE of 6.23, 13.15 and 11.4% for training, testing and validating phases, respectively. According to the results, the developed model could successfully cope with the prediction task.

Artificial intelligence (AI) is rapidly changing the world, and education is no exception. AI-powered technologies are being used to automate tasks, personalize learning, and create new educational experiences. This has led to a great deal of excitement about the potential of AI to transform education. However, there are also concerns about the ethical implications of AI in education. In this paper, we explore the potential benefits and risks of AI in education. We argue that AI has the potential to improve education in many ways, but that it is important to carefully consider the potential challenges before widespread adoption. By carefully planning for the future of AI in education, we can ensure that it is used to improve education for all students. The findings from this study contribute to the ongoing discussion on the role of AI in higher education institutions in the changing economic environment and provide insights into the effective integration of AI to enhance educational quality, relevance, and employability outcomes.

One of the world wide health care concerns in the last two decades has been the decrease in fertility rates. The problem is said to be more severe among the male population. Research has shown that environmental factors and life style habits have an impact on the quality of semen. Orthodox diagnosis of seminal quality employs a laboratory approach, involving expensive tests, which are also sometimes uncomfortable to the patient. Application of machine learning techniques has been on the rise and has demonstrated encouraging results in many fields, including health care. In this paper we propose Naïve Bayes and Artificial Neural Network classifiers for the characterization of seminal quality, based on environmental factors and life style habits Comparisons between the two classifier models show that their accuracy rate is the same and stands at 97%, on the training set.

The link between artificial intelligence (AI) and translation, as well as the repercussions of this complex relationship have enjoyed increased attention in today’s post-human translation studies. This paper problematizes how AI, with a special focus on machine translation (MT) and its current trends in the wake of the technological turn, has transformed the concept of translation, and has ultimately resulted in the emergence of new translator roles and competences. We aim to cast a fresh conceptual light on how and why AI continues to challenge the translation industry, imply what benefits and threats it may bring for language professionals and offer a theoretical model of the new roles of the human translator. We claim that the translator’s positioning on the cline between a utopian and dystopian future is a function of factors influencing their changing roles. From a utopian perspective, we view technology as an aid to the human translator where the translator’s toolkit of compet...

The unprecedented growth of computational capabilities in recent years has allowed Artificial Intelligence (AI) models to be developed for medical applications with remarkable results. However, a large number of Computer Aided Diagnosis (CAD) methods powered by AI have limited acceptance and adoption in the medical domain due to the typical blackbox nature of these AI models. Therefore, to facilitate the adoption of these AI models among the medical practitioners, the models' predictions must be explainable and interpretable. The emerging field of explainable AI (XAI) aims to justify the trustworthiness of these models' predictions. This work presents a systematic review of the literature reporting Alzheimer's disease (AD) detection using XAI that were communicated during the last decade. Research questions were carefully formulated to categorise AI models into different conceptual approaches (e.g., Post-hoc, Ante-hoc, Model-Agnostic, Model-Specific, Global, Local etc.) ...

Context: Artificial Intelligence (AI) in the medical domain has achieved remarkable results on various metrics primarily due to recent advancements in computational capabilities. However, AI models used for Computer Aided Diagnosis (CAD) have limited acceptance and trust due to their typical {Blackbox} nature. Consequently, explainable AI (XAI) is needed to justify the trustworthiness of the machine's predictions. Approach: In this work, we undertake a systematic review based on PRISMA guidelines on research articles investigating Alzheimer's Disease (AD) prediction with XAI for the past decade. The review was driven by carefully formulated research questions (RQ) which helped categorize AI models into different XAI methods(Post-hoc, Ante-hoc, Model-Agnostic, Model-Specific, etc) and frameworks (LIME, SHAP, GradCAM, LRP, etc.). Summary: This categorisation provides broad coverage of the interpretation spectrum from intrinsic (model-specific, ante-hoc models) to complex patte...

The purpose of this systematic literature review was to explore the status of the literature about the factors influencing the adoption of AI-based Smart Home Technologies (AI-SHT) among Chinese consumers. The study synthesizes findings from 18 peer-reviewed articles published between 2019 and 2024, focusing on behavioral, social, and technological factors that impact AI-SHT adoption. Prominent theoretical models, including the Technology Acceptance Model (TAM) and the Theory of Planned Behavior (TPB), were frequently used to explore perceived usefulness, ease of use, social influence, and trust. Key barriers, such as privacy concerns, data security issues, and economic considerations, are discussed within China's unique cultural and economic landscape. Methodologically, quantitative studies dominated the reviewed literature, relying heavily on survey-based approaches to assess consumer attitudes and behaviors. Findings highlight the complexity of Chinese consumers' adoption motivations, suggesting a need for further research into generational preferences, alternative adoption models, and cross-industry applications of AI-SHT. This review provides a foundation for future studies and industry strategies to enhance AI-SHT adoption in China.

Wireless communication channel scenario classification is crucial for new modern wireless technologies. Reducing the time consumed by the data preprocessing phase for such identification is also essential, especially for multiple-scenario transitions in 6G. Machine learning (ML) has been used for scenario identification tasks. In this paper, the least absolute shrinkage and selection operator (LASSO) is used instead of ElasticNet in order to reduce the computational time of data preprocessing for ML. Moreover, the computational time and performance of different ML models are evaluated based on a regularization technique. The obtained results reveal that the LASSO operator achieves the same feature selection performance as ElasticNet; however, the LASSO operator consumes less computational time. The achieved run time of LASSO is 0.33 s, while the ElasticNet corresponding value is 0.67 s. The identification for each specific class for K-Nearest Neighbor (KNN), Support Vector Machine (...

In this paper, a new framework is presented for indoor visible light communication (VLC) system, based on Yolo v3, EfficientNetB3, and DenseNet121 deep learning (DL) models, as well as an optimization strategy. The proposed framework consists of two steps: data collecting and DL model training. To start, data is acquired using MATLAB and Kalman Filtering (KF) with averaging approaches. Second, the received signal strength (RSS) is employed as the DL models input, with the Cartesian coordinates as the DL models output. The averaging RSS approach combined with KF algorithm are used in the suggested framework. This work introduces the impacts of Non-Line-of-Sight (NLoS) for initial reflection and Line-of-Sight (LoS) based on the three mentioned DL models. Furthermore, we used Bayesian optimization and automatic hyper-parameter (HP) optimization to increase system efficiency and to reduce positioning error in DL models. The obtained results show that the models outperform existing the H...

Choosing a proper Region of Interest (ROI) for Remote Photoplethysmography (rPPG) is essential and a challenging first step, and it has a direct effect on the accuracy and reliability of the overall heart rate (HR) algorithm. Non-skin areas have no contribution to the HR information; however, few works have tackled the issue of non-skin pixels included in the ROI. First, this paper considers improving the quality of the rPPG signal by filtering out non-skin pixels included within the ROI. The feasibility of employing skin segmentation for ROI definition is demonstrated. Then, this technique is compared with our previous real-time rPPG-based method. Moreover, we explore the effect of extracting the HR from three ROIs using signal fusion. Second, we give a comprehensive account of the examined methods in our algorithm for face detection, face tracking, skin detection, and blind signal separation. Finally, we compare our rPPG measurements with ground truth values obtained from a commercial pulse oximeter. Based on the simulation results, the proposed algorrithm significantly improves the quality of the rPPG technique. INDEX TERMS Heart rate, remote photoplethysmography (rPPG), unobtrusive monitoring, skin segmentation, real-time.

Sensor jitter introduces non-white noise fluctuations in imagery of cluttered scenes. These fluctuations are a major source of interference in the detection of weak time-dependent signals, which may be associated with a subject's appearance, motion, or brightness modulation. Due to the presence of sensor pattern noise and uncertainty in the scene's subpixel spatial structure, standard frame-to-frame registration methods have limited ability to model and remove these fluctuations. A simple temporal whitening approach, applicable to a wide variety of imaging systems, is found to be highly effective for suppressing subpixel jitter effects, leading to dramatic (up to several orders of magnitude) improvement in signal detection ability.

Business ethics is an ever-evolving field of theoretical and practical study that has enjoyed a steady stream of interest with a hockey stick of attention since globalization, especially global collaboration, which took off after 2000. There is a relatively new movement towards alterocentric ethics, a philosophical approach that places the "other" at the center of a company's consideration. Alterocentric ethics asks businesses to integrate responsibility toward stakeholders, the community, and the environment as intrinsic components of their operations. This study systematically reviews current literature on alterocentric business ethics. we applied a structured search methodology across academic databases, using predefined eligibility criteria to examine existing scholarly work comprehensively.

In this paper we investigate a technique for fusing approximate knowledge obtained from distributed, heterogeneous information sources. This issue is substantial, e.g., in modeling multiagent systems, where a group of loosely coupled heterogeneous agents cooperate in achieving a common goal. Information exchange, leading ultimately to knowledge fusion, is a natural and vital ingredient of this process. We use a generalization of rough sets and relations , which depends on allowing arbitrary similarity relations. The starting point of this research is , where a framework for knowledge fusion in multiagent systems is introduced. Agents' individual perceptual capabilities are represented by similarity relations, further aggregated to express joint capabilities of teams. This aggregation, expressing a shift from individual to social level of agents' activity, has been formalized by means of dynamic logic. The approach of Doherty et al. (2007) [6] uses the full propositional dynamic logic, which does not guarantee tractability of reasoning. Our idea is to adapt the techniques of Nguyen to provide an engine for tractable approximate database querying restricted to a Horn fragment of serial dynamic logic. We also show that the obtained formalism is quite powerful in applications.

This article compares the key-point extracted with a colour key-point detector and the location of fixation point thanks to an eye-tracking experiment. We hypothesize the first fixation points should correspond to key-points with the most significant gradients. The colour detector is based on Harris and Stephens corner detector extended to colour. The eye-tracking experiment was realised on medieval art work. We compare the location of both the detected key-points and the fixation points observed. Between 30% to 50% of the key-points coincide with fixation points. A second analysis display the number of matching key-points over the number of fixation points at a given time. The ratio decreases with the observation time which concur our initial hypothesis. Overall, several of the first fixation points correlate with high response key-points detected with our method.

Mathematical morphology is a popular framework for non-linear image processing, first introduced for binary and grey-level images, then extended to colour and multivariate images. Various pseudo-morphologies have been proposed as solutions to the problem of ordering multivariate data. Despite the lack of some properties, pseudomorphologies have proved useful in various applications, such as filtering or texture classification. The authors propose to improve the existing colour probabilistic pseudo-morphology by changing the way the local pseudoextrema are chosen. They show the usefulness of the new construction in the context of noise reduction in colour images using the open-close close-open filter, by highlighting the improvement over the original construction and comparing the authors' results with other relevant morphological and pseudo-morphological approaches.

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

This paper proposes a novel perceptual video quality assessment metric for streamed videos using optical flow statistical features. We analyze the impact of network losses on the decoded videos and the resulting error propagation. We show that the statistical features of the optical flow of the corrupted frames can be used to measure the distortion in the received video. We show that this approach is suitable for videos with complex motion patterns. Our technique does not make any assumptions on the coding conditions, network loss patterns or error concealment techniques. The proposed approach is pixelbased and relies only on the inconsistency of the optical flow of the corrupted frames. We validate our proposed quality metric by testing it on a variety of coded sequences subject to network losses from the recently proposed LIVE mobile database. Our results show that the proposed metric can estimate perceptual quality of channel-induced distortions at the frame and sequence levels. For the test videos, we report Pearson's and Spearman's correlation coefficients with the temporal mean opinion scores (MOSs) reported in the database. The results show average correlations of 0.91 and 0.92 for the test sequences, respectively.

The COVID-19 pandemic has precipitated an unprecedented surge in the proliferation of online E-learning platforms, designed to cater to a wide array of subjects across all age groups. However, a paucity of these platforms adopts a learner-centric approach or validates user learning, underscoring the need for effective E-learning validation and personalized learning recommendations. This paper addresses these challenges by implementing an innovative approach that leverages real-time electroencephalogram (EEG) signals collected from learners, who don neuro headsets while partaking in online courses. These EEG signals are subsequently classified using Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) deep learning models, with the intent of discerning the efficacy of the E-learning process. The proposed models have yielded promising classification accuracies of 68% and 97% for the CNN and LSTM models, respectively, demonstrating their rapidity and precision in classifying E-learning EEG signals. Thus, these models hold substantial potential for application in similar E-learning validation scenarios. Furthermore, this study introduces an automated framework designed to track the learning curve of users and furnish valuable recommendations for E-learning materials. The presented approach, therefore, not only validates the E-learning process but also aids in optimizing the learning experiences on E-learning platforms.

The lexical representation of the Chinese word '4A: has been an issue of on-going debate. The lexical form suggested by Her seemed to provide a complete representation of the different syntactic behaviours of `4ht.' within a Lexical-Functional Grammar (LFG) account. However, when ...

In recent work on the Lexical-Functional Grammar (LFG) formalism, argument structure (a-structure) and lexical mapping theory have been used to explain many linguistic behaviours across languages. It has been suggested that the combina-tion of c-structure, f-structure ...

Research has shown that lexical databases are good sources of lexical knowledge for various Natural Language Processing (NLP) tasks. Over the years, several lexical databases have been developed, eg HowNet [1], WordNet [2], EuroWordNet [3] and CCD [4]. These knowledge ...

In supervised learning the inductive algorithm seeks to develop a conceptual description, or prescriptive model, from examples or objects that have been pre-classified. On the other hand, in unsupervised learning, or clustering, the task of the algorithm is to group non-classified examples into clusters of examples, building a descriptive model. Central to all of the goals of clustering is the notion of similarity (or dissimilarity) between the individual objects being clustering. The key distinction between prediction and description is that prediction has as its objective a unique variable, known as the class attribute in supervised learning, while in descriptive problems no single variable is central to the problem. In this work we propose an approach, as well as a particular implementation of this approach, were a combination of traditional clustering and inductive learning are used to find and interpret special patterns from a database in order to extract useful knowledge to represent real world domains. This approach helps the user to make explicit his/her prior knowledge relevant to the problem allowing to organize the set of objects in different clusters into a set of classes considered to be semantically interpretable by the user.

In supervised learning the inductive algorithm seeks to develop a conceptual description, or prescriptive model, from examples or objects that have been pre-classified. On the other hand, in unsupervised learning, or clustering, the task of the algorithm is to group non-classified examples into clusters of examples, building a descriptive model. Central to all of the goals of clustering is the notion of similarity (or dissimilarity) between the individual objects being clustering. The key distinction between prediction and description is that prediction has as its objective a unique variable, known as the class attribute in supervised learning, while in descriptive problems no single variable is central to the problem. In this work we propose an approach, as well as a particular implementation of this approach, were a combination of traditional clustering and inductive learning are used to find and interpret special patterns from a database in order to extract useful knowledge to re...