Objective: The heart sound signals captured via a digital stethoscope are often distorted by environmental and physiological noise, altering their salient and critical properties. The problem is exacerbated in crowded low-resource hospital settings with high noise levels which degrades the diagnostic performance. In this study, we present a novel deep encoder-decoder based denoising architecture (LU-Net) to suppress ambient and internal lung sound noises. Methods: Training is done using a large benchmark PCG dataset mixed with physiological noise, i.e., breathing sounds. Two different noisy datasets were prepared for experimental evaluation by mixing unseen lung sounds and hospital ambient noises with the clean heart sound recordings. We also use the inherently noisy portion of the PASCAL heart sound dataset for evaluation. Results: The proposed framework showed effective suppression of background noises in both un?seen real-world data and synthetically generated noisy heart sound recordings, improving the signal-to-noise ratio (SNR) level by 5.575 dB on an average using only 1.32 M parameters. The proposed model outperforms the current state-of-the-art U-Net model with an average SNR improvement of 5.613 dB and 5.537 dB in the presence of lung sound and unseen hospital noise, respectively. LU-Net also outperformed the state-of-the-art Fully Convolutional Network (FCN) by 1.750 dB and 1.748 dB for lung sound and unseen hospital noise conditions, respectively. In addition, the proposed denoising method model improves classification accuracy by 38.93% in the noisy portion of the PASCAL heart sound dataset. Conclusion: The results presented in the paper indicate that our proposed architecture demonstrated a robust denoising performance on different datasets with diverse levels and characteristics of noise. Significance: The proposed deep learning-based PCG denoising approach is a pioneering study that can significantly improve the accuracy of computer-aided auscultation systems for detecting cardiac diseases in noisy, low-resource hospitals and underserved communities.

The detection and recognition of road traffic signs and panel guides content has become challenging in recent years. Few studies have been made to solve these two issues at the same time especially in Arabic language. Additionally, the limited number of datasets for traffic signs and panel guide content makes the investigation more interesting. In our work, we propose a Deep Active Learning Approach for Traffic Sign and Panel Guide Arabic-Latin Text Content Annotation in Natural Scene Images. Convolution neural network (CNN) and active learning are combined in the proposed system to detect and recognize traffic sign and multilingual scene text from panels guides, particularly those with Arabic Latin characters. The annotation system based on active learning method is applied to the Natural Scene Traffic Sign and Panel Guide Arabic-Latin Text dataset (NaSTSArLaT) of Tunisian highway road. The defined dataset contains initially 3000 collected images with only 181 annotated samples. Progressively, un-annotated training images, are automatically annotated when they provide high confidence with the YOLOv5 detection model and only the less confident examples are manually annotated. The annotation output consists of a class label and its bounding box for every traffic sign and panel guide text content. The performance of the proposed system is done on test data that represents 10% of the available annotated set. The proposed active learning strategy gives 62.7% in terms of mean Average Precision (mAP) only with the manual annotation of about 1⁄4 of the samples, whereas if the learning is performed using all the data after a complete annotation, the obtained performance is 69.2% which is comparable to our approach.

Europe is on the brink of a significant demographic shift that will increase the silver population and a decline in the working age group. This change highlights the importance of addressing the evolving needs of individuals, especially older adults. With this in mind, the European Union and the Baltic Sea Region are leading the way in groundbreaking research in aging and technology-driven services aimed at empowering older adults to live fulfilling lives. The OSIRIS project, funded by the European Union, is a vital initiative in this regard. Its primary focus is on creating a ‘Digital Silver Hub’ that provides solutions specifically designed to tackle the challenges faced by the silver population. The Digital Silver Hub is an ecosystem that fosters collaboration between various stakeholders, including private companies, public institutions, academic organizations, and, most importantly, older adults themselves. This document provides an in-depth exploration of the user dialogue model and system architecture of the Digital Silver Hub, which are the intertwined components driving its functioning. We use the Unified Modeling Language (UML) to represent the parts of the platform and show how it brings together collective intelligence to support the silver economy. This research is a testament to the dedication, innovation, and forward-thinking of those committed to improving the quality of life for the silver population. It shows that technology and collaboration can combine to meet the preferences and needs of older adults, ensuring they can live independently with dignity and a strong sense of community. As demographics continue to shift, this research is a step towards a future where aging is not seen as a burden but as an opportunity to celebrate experience, wisdom, and ongoing participation in society.

Interfacial Layer Engineering to Enhance Endurance and Noise Immunity of FeFETs for IMC Applications

The article presents the results of a study of a modal filter (MF) based on a microstrip line with two side conductors grounded at both ends. New analytical expressions for calculating the time response in such a structure are given. For their validation, an MF prototype was made and the transmission coefficient was measured in the frequency range from 0 to 12 GHz. In addition, the full-wave electrodynamic simulation and the analysis based on the transmission line theory were carried out. The frequency responses of the MF were converted into time domain responses in the ADS system. At the MF output, the response to an ultra-wideband (UWB) pulse was analyzed. The results for the analytical model are in good agreement with the results of measurements and simulations by the two approaches. It was experimentally proven that the structure under study provides the protection of electrical circuits from a UWB pulse by separating it in time and decreasing its effect on the components.

This paper proposes a novel physical layer one-time pad (OTP) encryption scheme for modulated signals based on the wireless channel. By imitating the OTP encryption for bit sequence, the sufficient conditions of perfect encryption for modulated signals are provided and proved. Then, we provide a detailed process of the scheme in the wireless system. Since the plaintext is the modulated signal rather than the bit sequence, we use high-level quantized channel estimation samples as secret keys and design encryption functions for QAM and PSK signals. The theoretical proof and Monte Carlo simulation results show that the proposed scheme can achieve perfect secrecy by designing the ciphertext signal independent of the plaintext signal. Furthermore, the simulation shows that the error probability of the proposed scheme is lower than that of the current mainstream physical layer encryption scheme because  the quantization level is optimized according to the signal-to noise ratio.

According to new discovery of law of moving photon does create force, we can know the reason why the photon become to electron-positron pair and can get that the elementary particle in Nature is photon, from this we can know the basic composition of matter is photon, in other words: the matter of producing gravitation and electromagnetic force is based on the same matter: photon. Meanwhile here show the Millikan’s elementary charge is not universal law, reveal the essence of matter wave is due to force.

In the Indian court system, pending cases have long been a problem. There are more than 4 crore cases outstanding. Manually summarising hundreds of documents is a time-consuming and tedious task for legal stakeholders. Many state-of-the-art models for text summarization have emerged as machine learning has progressed. Domain-independent models don't do well with legal texts, and fine-tuning those models for the Indian Legal System is problematic due to a lack of publicly available datasets. To improve the performance of domain-independent models, the authors have proposed a methodology for normalising legal texts in the Indian context. The authors experimented with two state-of-the-art domain-independent models for legal text summarization, namely BART and PEGASUS. BART and PEGASUS are put through their paces in terms of extractive and abstractive summarization to understand the effectiveness of the text normalisation approach. Summarised texts are evaluated by domain experts on multiple parameters and using ROUGE metrics. It shows the proposed text normalisation approach is effective in legal texts with domain-independent models.

In this paper, we investigate the maximum size of a minimal dictionary of a binary prefix-code string. We develop exact formulas for the maximum number of codewords of a minimal dictionary, which belongs to a binary string of some length. Further, we elaborate on the computational complexity of our approach and its relation to the Lambert function. We also present a way, how this information enables us to efficiently construct a Huffman code in the case of uniform probability distribution of codewords. The paper is of mathematical nature, i.e. all the methodology used in the paper is based on mathematical proofs.

The electrical sector has been facing a wide-scale transformation with renewable energy, distributed energy resources, information, and communication technology such as distributed ledger technologies. This paper presents a methodology for analyzing a blockchain-based solution applied to energy trading in Brazil. The proposed methodology applies for a proof of concept based on blockchain and other applications. Although the proof of concept in this study addresses the free-energy market, we also developed the methodology for the regulated energy market, net metering energy market, and decentralized energy market---peer-to-peer. We developed the methodology creating energy market metrics, researching electrical sector regulation and blockchain, and validating the case study. In this paper, we presented the validation of this case study through testing a proof of concept. We presented and tested the energy methodology through analysis of the free energy market. We concluded that proof of concept and methodology developed are precise and reliable for their applications. Our methodology may have a huge impact on the Brazilian energy market and may open peer-to-peer trading after law regulation.

This paper focuses on the issue of network connectedness (NC) in security-constrained optimal transmission switching problems, which is complicated by branch contingencies and corrective line switching. Two criteria are firstly proposed with the principle of preserving NC as much as possible within reasonable limits. By extending the electrical flow based NC constraints, a proposition is derived to associate different cases of NC with the optimum of a linear program, yielding the mathematical formulation of the NC criteria. By Karush-Kuhn-Tucker conditions, this formulation is further transformed into a tractable version which can be incorporated with existing SCOTS models without affecting the applicability of original solution approaches. Finally, case studies on various networks and SCOTS models demonstrate the efficacy of the proposed approach.

While the literature on RF fingerprinting-based authentication and key distillation is vast, the two topics have customarily been studied separately. In this paper, starting from the observation that the wireless channel is a composite, deterministic / stochastic process, we propose a power domain decomposition that allows performing the two tasks simultaneously. We devise intelligent pre-processing schemes to decompose channel state information (CSI) observation vectors into “predictable’‘ and “unpredictable’‘ components. The former, primarily due to large-scale fading, can be used for node authentication through RF fingerprinting. The latter, primarily due to small-scale fading, could be used for semantically secure secret key generation (SKG). To perform the decomposition, we propose: (i) a fingerprint “separability” criterion, expressed through the maximisation of the total variation distance between the empirical fingerprint measures; (ii) a statistical independence metric for observations collected at different users, expressed through a normalised version of the $d$-dimensional Hilbert Schmidt independence criterion (dHSIC) test statistic. We propose both explicit implementations, using principal component analysis (PCA) and kernel PCA and black-box, unsupervised learning, using autoencoders. Our experiments on synthetic and real CSI datasets showcase that the incorporation of RF fingerprinting and SKG, with explicit security guarantees, is tangible in future generations of wireless.

In this work, we have aimed at developing a new source location privacy preserving protocols to achieve uniform privacy privacy irrespective of the location of the source in the network with enhanced privacy and network lifetime. This is done without the use of fake packets and fake source. The proposed technique falls under the category of Phantom-based Random Walk Technicues.

Reducing Emotion to Mere ‘Information’A Phenomenological Critique of a Partial Understandingof Emotion in Affective ComputingNithin Monteiro SJAbstract —Affective computing, a growing field in human-computer interaction aims to create computers that have the ability to sense, recognize, express and in some cases ‘have’ emotions/affect. Affective computing manipulates the physiological modulations felt during emotional experiences to infer the supposed corresponding ‘affective states’ in human beings. The empirical approach to affective computing emphasizes the physical and cognitive aspects of affective experiences. However, it lacks a discrimination in the treatment of affectivity. Furthermore, affective computational models consider emotion as ‘information’ that can be extracted from the human ‘body’ in isolation to the complex relations that human beings share with others and the world against a backdrop of an overall network of interpersonal emotions and moods. I argue that an empirical approach to affective computing misses the existential significance of emotions because it considers ‘emotion’ derivative rather than constitutive of human existence. In this essay, I shall offer a phenomenological account of ‘emotion’ inspired by the accounts of Martin Heidegger, Jean-Paul Sartre and Edward Casey. I contend that a dialogue with phenomenology and philosophy in general, can help computational scientists to define specific affective experiences that they are investigating. A cross-disciplinary dialogue offers insights into the ethical design of affective computing technologies.Index Terms : Interaction; Affectivity; Emotion; Phenomenology; Interembodiment—————————— ——————————

Human language expression is based on the subjective construal of the situation instead of the objective truth conditions, which means that speakers’ personalities and emotions after cognitive processing have an important influence on conversation. However, most existing datasets for conversational AI ignore human personalities and emotions, or only consider part of them. It’s difficult for dialogue systems to understand speakers’ personalities and emotions although large-scale pre-training language models have been widely used. In order to consider both personalities and emotions in the process of conversation generation, we propose CPED, a large-scale Chinese personalized and emotional dialogue dataset, which consists of multi-source knowledge related to empathy and personal characteristic. These knowledge covers gender, Big Five personality traits, 13 emotions, 19 dialogue acts and 10 scenes. CPED contains more than 12K dialogues of 392 speakers from 40 TV shows. We release the textual dataset with audio features and video features according to the copyright claims, privacy issues, terms of service of video platforms. We provide detailed description of the CPED construction process and introduce three tasks for conversational AI, including personality recognition, emotion recognition in conversations as well as personalized and emotional conversation generation. Finally, we provide baseline systems for these tasks and consider the function of speakers’ personalities and emotions on conversation. Our motivation is to propose a dataset to be widely adopted by the NLP community as a new open benchmark for conversational AI research. The full dataset is available at https://github.com/scutcyr/CPED.

Overheating of battery packs in electrified vehicles is detrimental to their lifetime and performance. Unfortunately, designing a control strategy that ensures battery protection without jeopardizing fuel economy is not a straightforward task. In this paper, we investigate battery temperature-sensitive optimal energy management for a 48V mild-hybrid electric vehicle to prevent overheating with minimal fuel consumption increase. Indeed, this family of hybrid architectures is challenging due to the absence of an active cooling system. In particular, we modeled a p0 parallel-hybrid with a 48V battery pack and we employed dynamic programming to numerically investigate the fuel economy capability while tracking the battery pack temperature. First, we tuned a battery current-constrained powertrain control strategy in order to avoid battery overheating, which could be easily implemented on-board. Then, we implemented a predictive temperature-constrained strategy that exploits the a priori knowledge of driving conditions and temperature constraints to maximize fuel economy. Results show that both strategies are able to meet the battery temperature constraints, although the predictive temperature-constrained control strategy outperforms the current-constrained strategy in terms of fuel economy. This case study demonstrates the theoretical benefits of a predictive battery thermal management for 48V mild hybrids.

It is well-known that the optimality of the Kalman filter relies on the Gaussian distribution of the process and observation model errors, which in many situations is well justified [1, 2, 3]. However, its optimality is useless in applications that the distribution assumptions of the model errors do not hold in practice. Even minor deviation from the assumed (or nominal) distribution may cause the Kalman filter’s performance to drastically degrade or to completely breakdown. In particular, when dealing with perceptually important signals such as speech, images, medical, campaign and ocean engineering, the measurements have confirmed the presence of non-Gaussian impulsive (heavy tailed) or Laplace noises [4]. Therefore, the classical Kalman filter which is derived under nominal Gaussian probability model is biased or even breaks down in such situations. This article presents a simple modification approach to overcome this limitation of the Kalman filter. We show that in the smoothing Wiener filter, the estimated state is chosen to minimize the ℓ2-norm of the variation of the system model error. The ℓ2-norm, however, corresponds to Gaussian priors. It confirms the optimality of Wiener filter and Kalman filter in linear Gaussian systems and explains why they suffer from the sensitivity to Laplase or impulsive error statistics. To address this limitation, we propose a variation on smoothing Wiener filter which substitutes a sum of absolute values (i.e., ℓ1-norm) for the sum of squares used in ℓ2 smoothing Wiener filter to penalize variations in the system model error. The proposed ℓ1 smoothing Wiener filter is suitable for analyzing systems with impulsive or Laplace model errors. The idea of ℓ1 smoothing Wiener filter is then used to recast and correct the system (or process) model equation. The modified model puts a Laplace or a sparse distribution on the system model error to enforce the sparsity on the states of the system. Based on the fact that the formulations of the optimum filter by Wiener and Kalman are equivalent in discrete time steady state [5], the Kalman filter can be used to estimate the desired states using the modified model.

Virtual synchronous machines (VSM) are inverters that behave towards the power grid like synchronous generators. Hence, they can be used as grid forming inverters and they can support the grid with inertia, droops, fault ride-through and more. Synchronverters are a much studied type of VSM. In this paper we present several improvements and innovations to the synchronverter control algorithm. We offer a complete design procedure for this algorithm. One change is meant to mitigate the fact that earlier designs are very sensitive to grid voltage measurement errors and processing delay, which may cause harmonic distortion and fluctuating amplitude of the grid-side currents. We propose to include a fast current controller as the internal control loop of the inverter. The design of this current controller involves delicate issues of compensating the delays and eliminating the DC components of the currents. The new design enables also a natural way for distortion-less current limitation. We present a smooth start?up procedure. Our simulations and experiments show that the current controller leads to a dramatic reduction of the sensitivity of the VSM to measurement errors, processing delay and grid voltage imbalance.