Search

Mobility-as-a-service (MaaS) integrates different transport modalities and can support more personalization of travelers’ journey planning based on their individual preferences, behaviors and wishes. To fully achieve the potential of MaaS, a range of artificial intelligence (AI) (including machine learning and data mining) algorithms are needed to learn personal requirements and needs to optimize the journey planning of each traveler and all travelers as a whole, to help transport service operators and relevant governmental bodies to operate and plan their services, and to detect and prevent cyberattacks from various threat actors, including dishonest and malicious travelers and transport operators. The increasing use of different AI and data processing algorithms in both centralized and distributed settings opens the MaaS ecosystem up to diverse cyber and privacy attacks at both the AI algorithm level and the connectivity surfaces. In this article, we present the first comprehensive review on the coupling between AI-driven MaaS design and the diverse cybersecurity challenges related to cyberattacks and countermeasures. In particular, we focus on how current and emerging AI-facilitated privacy risks (profiling, inference, and third-party threats) and adversarial AI attacks (evasion, extraction, and gamification) may impact the MaaS ecosystem. These risks often combine novel attacks (e.g., inverse learning) with traditional attack vectors (e.g., man-in-the-middle attacks), exacerbating the risks for the wider participation actors and the emergence of new business models. [ABSTRACT FROM AUTHOR]

Replicating neural responses observed in biological systems using artificial neural networks holds significant promise in the fields of medicine and engineering. In this study, we employ ultra-fast artificial neurons based on antiferromagnetic (AFM) spin Hall oscillators to emulate the biological withdrawal reflex responsible for self-preservation against noxious stimuli, such as pain or temperature. As a result of utilizing the dynamics of AFM neurons, we are able to construct an artificial neural network that can mimic the functionality and organization of the biological neural network responsible for this reflex. The unique features of AFM neurons, such as inhibition that stems from an effective AFM inertia, allow for the creation of biologically realistic neural network components, like the interneurons in the spinal cord and antagonist motor neurons. To showcase the effectiveness of AFM neuron modeling, we conduct simulations of various scenarios that define the withdrawal reflex, including responses to both weak and strong sensory stimuli, as well as voluntary suppression of the reflex. [ABSTRACT FROM AUTHOR]

As social robots and other intelligent machines enter the home, artificial emotional intelligence (AEI) is taking center stage to address users’ desire for deeper, more meaningful human-machine interaction. To accomplish such efficacious interaction, the next-generation AEI needs comprehensive human emotion models for training. Unlike theory of emotion, which has been the historical focus in psychology, emotion models are a descriptive tool. In practice, the strongest models need robust coverage, which means defining the smallest core set of emotions from which all others can be derived. To achieve the desired coverage, we turn to word embeddings from natural language processing. Using unsupervised clustering techniques, our experiments show that with as few as 15 discrete emotion categories, we can provide maximum coverage across six major languages–Arabic, Chinese, English, French, Spanish, and Russian. In support of our findings, we also examine annotations from two large-scale emotion recognition datasets to assess the validity of existing emotion models compared to human perception at scale. Because robust, comprehensive emotion models are foundational for developing real-world affective computing applications, this work has broad implications in social robotics, human-machine interaction, mental healthcare, computational psychology, and entertainment. [ABSTRACT FROM AUTHOR]

Emotion elicitation using emotional film clips is one of the most common and ecologically valid methods in Affective Computing. However, selecting and validating appropriate materials that evoke a range of emotions is challenging. Here, we present EmoStim: A Database of Emotional Film Clips as a film library with rich and varied content. EmoStim is designed for researchers interested in studying emotions in relation to either discrete or componential models of emotion. To create the database, 139 film clips were selected from literature and then annotated by 638 participants through the CrowdFlower platform. We selected 99 film clips based on the distribution of subjective ratings that effectively distinguished between emotions defined by the discrete model. We show that the selected film clips reliably induce a range of specific emotions according to the discrete model. Further, we describe relationships between emotions, emotion organization in the componential space, and underlying dimensions representing emotional experience. The EmoStim database and participant annotations are freely available for research purposes. The database can be used to enrich our understanding of emotions further and serve as a guide to select or creating additional materials. [ABSTRACT FROM AUTHOR]

Diabetes Mellitus (DM) is emerging as a global concern, affecting people from early ages to adulthood and positioning itself as one of the leading causes of mortality worldwide. The post-COVID-19 era has been characterized by notable progress in the domains of medicine, science, and engineering, creating a favorable atmosphere for the investigation of innovative solutions. The present manuscript aims to investigate the problem of glucose regulation in adults diagnosed with Type 1 Diabetes mellitus (T1D) using a two-degree-of-freedom robust controller technique. A physiological mathematical model involving individuals with T1D serves as the foundation for the proposed closed-loop technique. The control algorithm approach successfully maintains safe glycemic levels in a virtual population of 10 adults using a sophisticated, well-known physiological T1D simulator. We evaluated this with continuous 24-hour simulations. Simulation results support the practicality of the presented approach, and we further validate it using a statistical analysis that incorporates a probability density function and control variability grid analysis (CVGA). Despite being a theoretical and simulation-based methodology, the results of this study demonstrate promise, offering promising opportunities for developments in the field of artificial pancreas technology using Mexican technology.

The concept of Digital Twins (DTs), software models that mimic the behavior and interactions of physical or conceptual objects within their environments, has gained traction in recent years, particularly in medicine and healthcare research. DTs technology emerges as a pivotal tool in disease modeling, integrating diverse data sources to computationally model dynamic biological systems. This narrative review explores potential DT applications in medicine, from defining DTs and their history to constructing DTs, modeling biologically relevant systems, as well as discussing the benefits, risks, and challenges in their application. The influence of DTs extends beyond healthcare and can revolutionize healthcare management, drug development, clinical trials, and various biomedical research fields

In this Article, we will introduce several interrelated problems present in municipal solid waste recycling efforts, both globally and locally. The introduction serves to demonstrate how the lack of adequate global waste tracking and community-level waste contamination are related issues. This article elaborates on how these issues could be addressed with the Internet of Things (IoT), artificial intelligence (AI), and open data technology deployment. We will investigate the existing and possible applicability of this solution in resource-constrained environments, as opposed to exclusive use in the typical “smart city” context. Finally, we will discuss the risks and limitations of this approach. [ABSTRACT FROM AUTHOR]

Neuron-on-chip (NoC) systems—microfluidic devices in which neurons are cultured—have become a promising alternative to replace or minimize the use of animal models and have greatly facilitated in vitro research. Here, we review and discuss current developments in neuron-on-chip platforms, with a particular emphasis on existing biological models, culturing techniques, biomaterials, and topologies. We also discuss how the architecture, flow, and gradients affect neuronal growth, differentiation, and development. Finally, we discuss some of the most recent applications of NoCs in fundamental research (i.e., studies on the effects of electrical, mechanical/topological, or chemical stimuli) and in disease modeling. [ABSTRACT FROM AUTHOR]

Cardiovascular disease (CVD) is the leading cause of mortality worldwide and its incidence is rising due to an aging population. The development and progression of CVD is directly linked to adverse vascular hemodynamics and biomechanics, whose in-vivo measurement remains challenging but can be simulated numerically and experimentally. The ability to evaluate these parameters in patient-specific CVD cases is crucial to better predict future disease progression, risk of adverse events, and treatment efficacy. While significant progress has been made toward patient-specific hemodynamic simulations, blood vessels are often assumed to be rigid, which does not consider the compliant mechanical properties of vessels whose malfunction is implicated in disease. In an effort to simulate the biomechanics of flexible vessels, fluid-structure interaction (FSI) simulations have emerged as promising tools for the characterization of hemodynamics within patient-specific cardiovascular anatomies. Since FSI simulations combine the blood's fluid domain with the arterial structural domain, they pose novel challenges for their experimental validation. This paper reviews the scientific work related to FSI simulations for patient-specific arterial geometries and the current standard of FSI model validation including the use of compliant arterial phantoms, which offer novel potential for the experimental validation of FSI results. [ABSTRACT FROM AUTHOR]

Precision agriculture (PA), also known as smart farming, has emerged as an innovative solution to address contemporary challenges in agricultural sustainability. A particular sector within PA, precision viticulture (PV), is specifically tailored for vineyards. The advent of the Internet of Things (IoT) has facilitated the acquisition of higher resolution meteorological and soil data obtained through in situ sensing. The integration of machine learning (ML) with IoT-enabled farm machinery stands at the forefront of the forthcoming agricultural revolution. These data allow ML-based forecasting as an alternative to conventional approaches, providing agronomists with predictive tools essential for improved land productivity and crop quality. This study conducts a thorough examination of vineyards with a specific focus on three key aspects of PV: mitigating frost damage, analyzing soil moisture levels, and addressing grapevine diseases. In this context, several ML-based models are proposed in a real-world scenario involving a vineyard located in Southern Italy. The test results affirm the feasibility and efficacy of the ML models, demonstrating their potential to revolutionize vineyard management and contribute to sustainable agricultural practices. [ABSTRACT FROM AUTHOR]

In the context of global warming, the lake surface water temperature (LSWT) exhibits a general upward trend. As an indicator of climate change, the surface water temperature of plateau lakes is particularly sensitive to climate warming. In this study, the machine learning model and physical process model are combined to predict water temperature in lake systems: The Air2water model and the long short term memory (LSTM) model are combined to form a prediction model for the inversion and prediction of 11 typical plateau lakes in the Yunnan–Guizhou Plateau. The modeling results show that the Air2water model performs best, followed by the LSTM model. Overall, the Air2water model and the LSTM model effectively reproduce the monthly, seasonal, and interannual variations of LSWT dynamics in the 11 lakes. The research results show that the LSWT dataset from 2021 to 2025 is constructed based on the forecast result, and it is found that six lakes, including Caohai, Dianchi, Erhai, Qionghai, Xingyun Lake, and Yangzonghai, showed significant warming in the next five years (the maximum warming rate was less than +0.2 °C/year), while the remaining five lakes showed no significant changes, and the size classification of LSWT data in different spaces on the interannual scale was consistent with the classification of altitudes. By conducting extensive exploration and research on the inversion of LSWT using physical process models and machine learning models, this study offers novel solutions for LSWT prediction and inversion. The study also provides a solid theoretical and practical foundation for future LSWT research, thereby holding practical significance and research value. [ABSTRACT FROM AUTHOR]

Aiming at achieving artificial general intelligence (AGI) for the metaverse, pretrained foundation models (PFMs), e.g., generative pretrained transformers (GPTs), can effectively provide various artificial intelligence (AI) services, such as autonomous driving, digital twins (DTs), and AI-generated content (AIGC) for extended reality (XR). With the advantages of low latency and privacy-preserving, serving PFMs of mobile AI services in edge intelligence is a viable solution for caching and executing PFMs on edge servers with limited computing resources and GPU memory. However, PFMs typically consist of billions of parameters that are computation- and memory-intensive for edge servers during loading and execution. In this article, we investigate edge PFM serving problems for mobile AIGC services of the metaverse. First, we introduce the fundamentals of PFMs and discuss their characteristic fine-tuning and inference methods in edge intelligence. Then, we propose a novel framework of joint model caching and inference for managing models and allocating resources to satisfy users’ requests efficiently. Furthermore, considering the in-context learning ability of PFMs, we propose a new metric to evaluate the freshness and relevance between examples in demonstrations and executing tasks, namely the Age of Context (AoC). Finally, we propose a least-context (LC) algorithm for managing cached models at edge servers by balancing the tradeoff among latency, energy consumption, and accuracy. [ABSTRACT FROM AUTHOR]

Advancements in machine learning algorithms have had a beneficial impact on representation learning, classification, and prediction models built using electronic health record (EHR) data. Effort has been put both on increasing models' overall performance as well as improving their interpretability, particularly regarding the decision-making process. In this study, we present a temporal deep learning model to perform bidirectional representation learning on EHR sequences with a transformer architecture to predict future diagnosis of depression. This model is able to aggregate five heterogenous and high-dimensional data sources from the EHR and process them in a temporal manner for chronic disease prediction at various prediction windows. We applied the current trend of pretraining and fine-tuning on EHR data to outperform the current state-of-the-art in chronic disease prediction, and to demonstrate the underlying relation between EHR codes in the sequence. The model generated the highest increases of precision-recall area under the curve (PRAUC) from 0.70 to 0.76 in depression prediction compared to the best baseline model. Furthermore, the self-attention weights in each sequence quantitatively demonstrated the inner relationship between various codes, which improved the model's interpretability. These results demonstrate the model's ability to utilize heterogeneous EHR data to predict depression while achieving high accuracy and interpretability, which may facilitate constructing clinical decision support systems in the future for chronic disease screening and early detection.

Cardiovascular disease (CVD) threatens the lives of many and affects their productivity. Wearable sensors can enable continuous monitoring of hemodynamic parameters to improve the diagnosis and management of CVD. Bio-Impedance (Bio-Z) is an effective non-invasive sensor for arterial pulse wave monitoring based on blood volume changes in the artery due to the deep penetration of its current signal inside the tissue. However, the measured data are significantly affected by the placement of electrodes relative to the artery and the electrode configuration. In this work, we created a Bio-Z simulation platform that models the tissue, arterial pulse wave, and Bio-Z sensing configuration using a 3D circuit model based on a time-varying impedance grid. A new method is proposed to accurately simulate the different tissue types such as blood, fat, muscles, and bones in a 3D circuit model in addition to the pulsatile activity of the arteries through a variable impedance model. This circuit model is simulated in SPICE and can be used to guide design decisions (i.e. electrode placement relative to the artery and electrode configuration) to optimize the monitoring of pulse wave prior to experimentation. We present extensive simulations of the arterial pulse waveform for different sensor locations, electrode sizes, current injection frequencies, and artery depths. These simulations are validated by experimental Bio-Z measurements.

Photoplethysmography (PPG) is a noninvasive way to monitor various aspects of the circulatory system, and is becoming more and more widespread in biomedical processing. Recently, deep learning methods for analyzing PPG have also become prevalent, achieving state of the art results on heart rate estimation, atrial fibrillation detection, and motion artifact identification. Consequently, a need for interpretable deep learning has arisen within the field of biomedical signal processing. In this paper, we pioneer novel explanatory metrics which leverage domain-expert knowledge to validate a deep learning model. We visualize model attention over a whole testset using saliency methods and compare it to human expert annotations. Congruence, our first metric, measures the proportion of model attention within expert-annotated regions. Our second metric, Annotation Classification, measures how much of the expert annotations our deep learning model pays attention to. Finally, we apply our metrics to compare between a signal based model and an image based model for PPG signal quality classification. Both models are deep convolutional networks based on the ResNet architectures. We show that our signal-based one dimensional model acts in a more explainable manner than our image based model; on average 50.78% of the one dimensional model's attention are within expert annotations, whereas 36.03% of the two dimensional model's attention are within expert annotations. Similarly, when thresholding the one dimensional model attention, one can more accurately predict if each pixel of the PPG is annotated as artifactual by an expert. Through this testcase, we demonstrate how our metrics can provide a quantitative and dataset-wide analysis of how explainable the model is.

Until relatively recently, basic biomedical research was almost exclusively conducted with male human, animal, and cell models. It was widely assumed that the research findings and medical treatments developed from these studies could be generalized to the whole population. However, there are sex differences in key biological pathways and processes that can influence a person’s disease risk, experience of symptoms, and response to treatment. The lack of female representation in preclinical biomedical research has resulted in gaps in our medical knowledge, with important consequences for women’s health. In the past decade, efforts to remedy this historic exclusion have increased, but opportunities remain to make basic biomedical research more equitable, reproducible, and applicable to all people. [ABSTRACT FROM AUTHOR]

This letter examines how the principal component analysis (PCA) affects the performance of the deep forest 2021 (DF21) model for the hyperspectral inversion. To this end, the spectra contaminated by eight types of heavy metals are applied and processed by PCA. Subsequently, various retained principal components (PCs) are devoted to establish the inversion model in line with the DF21. Two typical heavy metal elements, i.e., zinc (Zn) and chromium (Cr), are used for instance; it explores the accuracies of the DF21 model for inverting their concentrations under different PCs. The findings reveal that the DF21 model’s performance fluctuates with varying retained PCs. Furthermore, the fluctuations are influenced by the heavy metal’s type and its concentration distribution. As a result, the optimal performances for inverting the Zn and Cr concentrations appear at the first nine PCs and first eight PCs, respectively. Hence, it might not be feasible to improve the accuracy by retaining more PCs in hyperspectral inversion, at least not for the DF21 model. [ABSTRACT FROM AUTHOR]

By combining a multitask deep learning method and a nitrogen PROSPECT and scattering by arbitrarily inclined leaves (N-PROSAILs) model, we proposed a multitask learning-based hybrid model (ML-HM) for leaf nitrogen content (LNC) prediction in a previous study. To provide an optimal ML-HM design for LNC prediction, this study focused on analyzing how factors, such as the simulated data distribution and sample size and the simulated and measured data batch sizes, affect the ML-HM accuracy. For this purpose, different scenarios for the above three factors were generated. ML-HMs were designed under these scenarios, and the performance was evaluated. The results showed that the simulated data distribution affects the ML-HM inversion accuracy, and it is better to use a priori knowledge to set the range and sampling strategy for the N-PROSAIL input variables to obtain a generated simulated data distribution that is similar to that of the measured data. The ML-HM accuracy increases with increasing measured sample size, but it does not change in an obvious manner once a certain threshold is reached. Thus, it is better to apply the sample size determination method based on simple random sampling to calculate the required sample size. The simulated and measured data batch sizes significantly affect the ML-HM accuracy, and we recommended creating a model for ML-HM accuracy prediction based on a certain number of batch size scenarios and using it to estimate suitable batch sizes of simulated and measured data to design an ML-HM. [ABSTRACT FROM AUTHOR]

Cotton is under the threat of climate and ecosystem change and has an essential role in the global textile industry. This makes its yield prediction essential for both economics and sustainability. The potential cotton yield can be predicted by integrating climatic factors, soil parameters, and biophysical parameters observed by high temporal and spatial resolution remote sensing satellites. This study used a multisource dataset to create an explainable and accurate predictive model for cotton yield prediction over the continental United States (CONUS). A recently proposed glass-box method called explainable boosting machine (EBM), which provides transparency, reliability, and ease of interpretation, was implemented. Accuracy performance was compared with the common machine learning (ML) methods for predicting cotton yields. The EBM showed higher accuracy against other glass-box methods and competitive results with black-box models. With the help of the EBM, the importance of individual features and their pairwise interactions was revealed without applying any post hoc methods. The study findings showed that precipitation (P), enhanced vegetation index (EVI), and leaf area index (LAI) are the three most important dynamic features. The dynamic features are the driver of the created model with 78% of the overall feature importance, followed by pairwise interactions of the features with 16% contribution. Finally, static features contribute 6% to the overall feature importance. The study highlights the importance of using multisource data and interactions of the input features and providing an interpretable model to understand the inner dynamics of cotton yield predictions. [ABSTRACT FROM AUTHOR]

The carbon dioxide (CO2) fertilization effect has captured worldwide attention, owing to its tremendous potential to challenge existing predictions of future climate. However, quantifying the CO2 fertilization effect (CFE) has proven to be challenging, given that it is closely entangled with other ecological and environmental processes. Recent years have witnessed significant advances with breakthroughs using theoretical methods to infer the CFE from eddy covariance tower measurements. Building on earlier findings, this study presents an innovative approach that utilizes explainable machine-learning techniques—describing the partial dependence of the response variable to each explanatory variable—to quantify the global CFE from remote-sensing platforms with an averaged $R ^{2}$ of 0.85. This study provides the first data-driven evidence of the global CFE and confirms the potential for extrapolation to the globe. The findings suggest that: 1) the employment of satellite vegetation proxies contributed to more than 50% of the fitting of gross primary productivity (GPP) and 2) the manifestation of the CO2 fertilization impact demonstrated heterogeneity among various types of ecosystems, and in some cases, an adverse effect was detected in broadleaf forests. Our results have significant implications for the preservation and protection of terrestrial ecosystems, particularly for a carbon-neutral future. This study, therefore, provides a valuable contribution to the growing body of knowledge in this area and highlights the potential of innovative analytical techniques to address complex ecological challenges. [ABSTRACT FROM AUTHOR]

For the predominant classification performance, the convolutional neural network (CNN) is becoming quite popular in the hyperspectral image (HSI) classification. However, quite a few parameters must be updated in the training procedure. The overfitting problem is also exacerbated by HSI’s high dimensionality and limited training samples. Therefore, an end-to-end model DWTCNN that deeply integrates 3-D discrete wavelet transform (DWT) and CNN is proposed. The 3-D DWT is introduced for the intrinsic feature collection in multiresolution, and the 3-D DWT modulated kernel with predefined parameters will not increase the trainable parameters of DWTCNN. The impact of 3D-DWT at different scale levels on classification performance is also studied. The amalgamation of 3-D DWT reduces the feature extraction burden of 3-D CNN while increasing the feature extraction capacity of the network. With a compact and light structure, our model is easier to train with less memory and limited training samples. Compared with other methods, our model has a considerable advantage in computational efficiency while maintaining good classification accuracy and clear physical meaning interpretability. Experimental results on three public datasets also demonstrate the superiority of our approach in the training process and classification performance. [ABSTRACT FROM AUTHOR]

Forest inventory forms the foundation of forest management. Remote sensing (RS) is an efficient means of measuring forest parameters at scale. Remotely sensed species classification can be used to estimate species abundances, distributions, and to better approximate metrics such as aboveground biomass. State-of-the-art methods of RS species classification rely on deep-learning models such as convolutional neural networks (CNNs). These models have two major drawbacks: they require large samples of each species to classify well and they lack explainability. Therefore, rare species are poorly classified causing poor approximations of their associated parameters. We show that the classification of rare species can be improved by as much as eight F1-points using a neuro-symbolic (NS) approach that combines CNNs with an NS framework. The framework allows for the incorporation of domain knowledge into the model through the use of mathematically represented rules, improving model explainability. [ABSTRACT FROM AUTHOR]

Visual explanation of “black-box” models allows researchers in explainable artificial intelligence (XAI) to interpret the model’s decisions in a human-understandable manner. In this letter, we propose interpretable class activation mapping for tree crown detection (Crown-CAM) that overcomes inaccurate localization and computational complexity of previous methods while generating reliable visual explanations for the challenging and dynamic problem of tree crown detection in aerial images. It consists of an unsupervised selection of activation maps, computation of local score maps, and noncontextual background suppression to efficiently provide fine-grain localization of tree crowns in scenarios with dense forest trees or scenes without tree crowns. In addition, two intersection over union (IoU)-based metrics are introduced to effectively quantify both the accuracy and inaccuracy of generated explanations with respect to regions with or even without tree crowns in the image. Empirical evaluations demonstrate that the proposed Crown-CAM outperforms the Score-CAM, Augmented Score-CAM, and Eigen-CAM methods by an average IoU margin of 8.7, 5.3, and 21.7 (and 3.3, 9.8, and 16.5), respectively, in improving the accuracy (and decreasing inaccuracy) of visual explanations on the challenging NEON tree crown dataset. [ABSTRACT FROM AUTHOR]

Quantifying and monitoring land surface evapotranspiration (ET) is an essential task for understanding the earth’s water, energy, and carbon cycles. ET, specifically plant transpiration ($T$), is closely linked to the photosynthesis, which is coupled through stomatal function. However, the mechanistic links between sun-induced chlorophyll fluorescence (SIF) information indicating canopy photosynthetic activity and $T$ are complex and difficult to derive empirically. An empirical SIF- $T$ relationship at ecosystem scale was developed and coupled to the two-source energy balance model (TSEB-SIF) to estimate the ET and its components, $T$ and soil evaporation, $E$. By comparing model predictions with observations from an irrigated cropland site located in a semiarid region, the TSEB-SIF model shows a slightly better performance to the TSEB model in estimating ET, especially under water deficit conditions. Moreover, the TSEB-SIF model more reliably partitioned the $T$ from ET, while the TSEB model tended to overestimate the contribution of $T$ to ET. [ABSTRACT FROM AUTHOR]

Emotion analysis based on peripheral physiological signals has attracted increasing attention recently in affective computing. Previous works usually predict emotional states using a single emotion label for each discrete time. However, in real-world scenarios, it is not sufficient due to the fact that the real-world emotional state is usually a mixture of basic emotions. In this paper, we formulate the emotion analysis as an emotion distribution learning (EDL) problem and make two contributions. First, we establish a standardised dataset containing four negative emotions (anger, disgust, sadness, fear) and three positive emotions (tenderness, joy, amusement), which could be a useful benchmark for the EDL task. Second, we propose an emotion distribution prediction system which has the following distinct characteristics: (1) after processing raw peripheral physiological signals, we compute totally 89 representative features from four channels, i.e., GSR, SKT, ECG and HR, (2) an adaptive feature selection strategy based on recursive feature elimination (RFE) is used to select the most significant features in our EDL task, and (3) we design a dedicated EDL model based on convolution neural networks that takes information from both the feature correlation and the time domain into consideration. Experiments were conducted to validate our proposed system, and the results indicated that (1) the proposed feature selection strategy effectively selects significant features and improves algorithmic performance, and (2) the proposed EDL model can obtain good results in terms of six evaluation measures and outperform existing methods. [ABSTRACT FROM AUTHOR]

Cross-domain sentiment analysis aims to adapt sentiment classification models trained on one or more source domains to the target domain, which can effectively alleviate the problem of insufficient labelled data in specific domains. Unlike most previous methods of adjusting models based on observed data, we propose a novel counterfactual representation augmentation (CRA) method, which aims to improve target-domain generalization by constructing new counterfactual representations for training. Specifically, we train a domain discriminator to learn the domain discrepancy between the source and target domains on unlabeled data, and use a gradient editing method to directly construct counterfactual representations, which reduces the inductive bias of the source domain and augments the training data. Moreover, we further leverage an ensemble-based training method to indirectly encourage the target-domain classifier to rely more on robust features for prediction. Extensive experiments on a widely-used cross-domain sentiment classification benchmark dataset show that our method consistently surpasses different baseline methods on different tasks, demonstrating the strong ability to improve domain generalization. We also find that our model can effectively adjust the decision boundary to make the classifier more robust and generalized, through extensive qualitative and quantitative analysis. [ABSTRACT FROM AUTHOR]

Secret-key agreement using physical identifiers is a promising security protocol for the authentication of users and devices with small chips, owing to its lightweight security. In the previous studies, the fundamental limits of such a protocol were analyzed, and the results showed that two auxiliary random variables were involved in the capacity region expressions. However, with two auxiliary random variables, it is difficult to directly apply the expressions to derive the computable forms of the capacity regions for certain information sources such as binary and Gaussian sources, which hold importance in practical applications. In this paper, we explore the structure of authentication channels and reveal that for the classes of degraded and less noisy authentication channels, a single auxiliary random variable is sufficient to express the capacity regions. As specific examples, we use the expressions with one auxiliary random variable to derive the computable forms for binary and Gaussian sources. Numerical calculations for the Gaussian case show the trade-off between secret-key and privacy-leakage rates under a given storage rate, which illustrates how the noise in the enrollment phase affects the capacity region. [ABSTRACT FROM AUTHOR]

Recent advances in the fingerprinting of deep neural networks are able to detect specific instances of models, placed in a black-box interaction scheme. Inputs used by the fingerprinting protocols are specifically crafted for each precise model to be checked for. While efficient in such a scenario, this nevertheless results in a lack of guarantee after a mere modification of a model (e.g. finetuning, quantization of the parameters). This article generalizes fingerprinting to the notion of model families and their variants and extends the task-encompassing scenarios where one wants to fingerprint not only a precise model (previously referred to as a detection task) but also to identify which model or family is in the black-box (identification task). The main contribution is the proposal of fingerprinting schemes that are resilient to significant modifications of the models. We achieve these goals by demonstrating that benign inputs, that are unmodified images, are sufficient material for both tasks. We leverage an information-theoretic scheme for the identification task. We devise a greedy discrimination algorithm for the detection task. Both approaches are experimentally validated over an unprecedented set of more than 1,000 networks. [ABSTRACT FROM AUTHOR]

Recognition of ovarian-cancer biomarker (HE4) in serum using dual-material In0.53Ga0.47As/Si hetero-structure charge-plasma-based extended gate TFET biosensor (DCE-HTFET) has been depicted in this article. The virtual fabrication flow for the configuration has been mentioned here. Silvaco ATLAS TCAD device simulator is used to optimize the device for better sensitivity. The sensitivity of the proposed model in the serum biosphere for different HE4 concentrations in histological subgroups of ovarian cancer has been investigated. An optimum ON-current to OFF-current sensitivity (SION/IOFF) of 18.2 × 106 and sensitivity regarding sub-threshold swing (SSS) of 95% have been achieved for the “Mucinous” type histological sub-group of ovarian-cancer biomarker having 74 pmol/L concentration. The proposed biosensor has been compared with the state-of-the-art literature to highlight its efficacy. [ABSTRACT FROM AUTHOR]

There are a lack of quantitative measures for clinically assessing upper limb function. Conventional biomechanical performance measures are restricted to specialist labs due to hardware cost and complexity, while the resulting measurements require specialists for analysis. Depth cameras are low cost and portable systems that can track surrogate joint positions. However, these motions may not be biologically consistent, which can result in noisy, inaccurate movements. This paper introduces a rigid body modelling method to enforce biological feasibility of the recovered motions. This method is evaluated on an existing depth camera assessment: the reachable workspace (RW) measure for assessing gross shoulder function. As a rigid body model is used, position estimates of new proximal targets can be added, resulting in a proximal function (PF) measure for assessing a subject's ability to touch specific body landmarks. The accuracy, and repeatability of these measures is assessed on ten asymptomatic subjects, with and without rigid body constraints. This analysis is performed both on a low-cost depth camera system and a gold-standard active motion capture system. The addition of rigid body constraints was found to improve accuracy and concordance of the depth camera system, particularly in lateral reaching movements. Both RW and PF measures were found to be feasible candidates for clinical assessment, with future analysis needed to determine their ability to detect changes within specific patient populations.

The efficacy of deep brain stimulation (DBS) depends on electrode placement accuracy, which can be jeopardized by brain shift due to burr hole and dura opening during surgery. Brain shift violates assumed rigid alignment between preoperative image and intraoperative anatomy, negatively impacting therapy.ObjectiveThis study presents a deformation-atlas biomechanical model-based approach to address shift.MethodsSix patients, who underwent interventional magnetic resonance (iMR) image-guided DBS burr hole surgery, were studied. A patient-specific model was employed under varying surgical conditions, generating a collection of possible intraoperative shift estimations or a 'deformation atlas.' An inverse problem was driven by sparse measurements derived from iMR to determine an optimal fit of solutions of the atlas. This fit was then used to obtain a volumetric deformation field, which was utilized to update preoperative MR and estimate shift at surgical target region localized on iMR. Model performance was examined by quantitatively comparing intraoperative subsurface measurements to their model-predicted counterparts, and qualitatively comparing iMR, preoperative MR, and model updated MR. A nonrigid image registration was introduced as a comparator.ResultsModel-based approach reduced general parenchyma shift from 8.2 ± 2.2 to 2.7 ± 1.1 mm (∼66.8% correction), and produced updated MR with better agreement to iMR than that of preoperative MR. The average model estimated shift at target region was 1.2 mm.ConclusionsThis study demonstrates the feasibility of a model-based shift correction strategy in DBS surgery with only sparse data.SignificanceThe developed strategy has the potential to complement and/or enhance current clinical approaches in addressing shift.

In this article, we analyze the performance of an agent developed according to a well-accepted appraisal theory of human emotion with respect to how it modulates play in the context of a social dilemma. We ask if the agent will be capable of generating interactions that are considered to be more human-like than machine-like. We conducted an experiment with 117 participants and show how participants rated our agent on dimensions of human-uniqueness (separating humans from animals) and human-nature (separating humans from machines). We show that our appraisal theoretic agent is perceived to be more human-like than the baseline models, by significantly improving both human-nature and human-uniqueness aspects of the intelligent agent. We also show that perception of humanness positively affects enjoyment and cooperation in the social dilemma, and discuss consequences for the task duration recall. [ABSTRACT FROM AUTHOR]

Practical affect recognition needs to be efficient and unobtrusive in interactive contexts. One approach to a robust realtime system is to sense and automatically integrate multiple nonverbal sources. We investigated how users’ touch, and secondarily gaze, perform as affect-encoding modalities during physical interaction with a robot pet, in comparison to more-studied biometric channels. To elicit authentically experienced emotions, participants recounted two intense memories of opposing polarity in Stressed-Relaxed or Depressed-Excited conditions. We collected data (N=30) from a touch sensor embedded under robot fur (force magnitude and location), a robot-adjacent gaze tracker (location), and biometric sensors (skin conductance, blood volume pulse, respiration rate). Cross-validation of Random Forest classifiers achieved best-case accuracy for combined touch-with-gaze approaching that of biometric results: where training and test sets include adjacent temporal windows, subject-dependent prediction was 94% accurate. In contrast, subject-independent Leave-One-participant-Out predictions resulted in 30% accuracy (chance 25%). Performance was best where participant information was available in both training and test sets. Addressing computational robustness for dynamic, adaptive realtime interactions, we analyzed subsets of our multimodal feature set, varying sample rates and window sizes. We summarize design directions based on these parameters for this touch-based, affective, and hard, realtime robot interaction application. [ABSTRACT FROM AUTHOR]

There has been an encouraging progress in the affective states recognition models based on the single-modality signals as electroencephalogram (EEG) signals or peripheral physiological signals in recent years. However, multimodal physiological signals-based affective states recognition methods have not been thoroughly exploited yet. Here we propose Multiscale Convolutional Neural Networks (Multiscale CNNs) and a biologically inspired decision fusion model for multimodal affective states recognition. First, the raw signals are pre-processed with baseline signals. Then, the High Scale CNN and Low Scale CNN in Multiscale CNNs are utilized to predict the probability of affective states output for EEG and each peripheral physiological signal respectively. Finally, the fusion model calculates the reliability of each single-modality signals by the euclidean distance between various class labels and the classification probability from Multiscale CNNs, and the decision is made by the more reliable modality information while other modalities information is retained. We use this model to classify four affective states from the arousal valence plane in the DEAP and AMIGOS dataset. The results show that the fusion model improves the accuracy of affective states recognition significantly compared with the result on single-modality signals, and the recognition accuracy of the fusion result achieve 98.52 and 99.89 percent in the DEAP and AMIGOS dataset respectively. [ABSTRACT FROM AUTHOR]

Kinetic and dynamic motion analysis provides quantitative, functional assessments of human ability that are unobtainable through static imaging methods or subjective surveys. While biomechanics facilities are equipped to perform this measurement and analysis, the clinical translation of these methods is limited by the specialized skills and equipment needed. This paper presents and validates a method for estimating dynamic effects such as joint torques and body momenta using a single depth camera. An allometrically scaled, sagittal plane dynamic model is used to estimate the joint torques at the ankles, knees, hips, and low back, as well as the torso momenta, and shear and normal loads at the L5-S1 disk. These dynamic metrics are applied to the sit-to-stand motion and validated against a gold-standard biomechanical system consisting of full-body active motion-capture and force-sensing systems. The metrics obtained from the proposed method were found to have excellent concordance with peak metrics that are consistent with prior biomechanical studies. This suggests the feasibility of using this system for rapid clinical assessment, with applications in diagnostics, longitudinal tracking, and quantifying patient recovery.

The aim of the article is to examine the possibilities of modeling electrical properties of cardiac cell membrane using the Cole impedance model containing a fractional-order capacitor. A method is presented to determine the parameters of the model based on the current transient response to a voltage step applied to the membrane. The method is based on the numerical minimization of the least squares error between the recorded and calculated transient response of the model using the MATLAB function fminsearch. The use of a fractional-order capacitor in the membrane model is found to result in a reduction in the modeling error compared to that of the classic capacitor.

Recently, brain-inspired hyperdimensional computing (HDC) becomes an emerging computational scheme that has achieved success in various domains, such as human activity recognition, voice recognition, and bio-medical signal classification. HDC mimics the brain cognition and leverages high-dimensional vectors (e.g., 10 000 dimensions) with fully distributed holographic representation and (pseudo-)randomness. Ensemble learning is a classical learning method utilizing a group of weak learners to form a strong learner, which aims to increase the accuracy of the model. This letter presents a systematic effort in exploring ensemble learning in the context of HDC and proposes an ensemble HDC model referred to as EnHDC. EnHDC uses a majority voting-based mechanism to synergistically integrate the prediction outcomes of multiple base HDC classifiers. To enhance the diversity of base classifiers, we vary the encoding mechanisms, dimensions, and data width settings among base classifiers. By applying EnHDC on a wide range of applications, results show that EnHDC can achieve on average 3.2% accuracy improvement over a single HDC classifier. Further, we show that EnHDC with reduced dimensionality can achieve similar or even surpass the accuracy of baseline HDC with higher dimensionality. This leads to a 20% reduction of storage requirement of the HDC model, which can enhance the efficiency of HDC enabled on low-power computing platforms. [ABSTRACT FROM AUTHOR]

Semiconductor intellectual property (SIP) represents a crucial component of integrated circuit design activities. However, many small SIP firms fail to create value and adopt a viable business model. This article aims to investigate the value creation mechanism within the SIP business by drawing on the business model and dynamic capabilities views of the firm. First, the authors classify the forms and types of SIP from a technology and market perspective. Analyzing ten leading SIP firms, three SIP business models based on resources, competencies, and strategies are then identified. Dynamic capabilities are then linked to the selection and implementation of classified business models. Findings of the study suggest that existing SIP business models primarily favor large vendors. Keystone business model is proposed as a possible successful business model for small vendors. Consequently, this article provides insights and opportunities for leveraging the SIP ecosystem and business model innovation for small firms in the industry. [ABSTRACT FROM AUTHOR]

Measuring and improving the efficiency of a sustainable supply chain in an effective way for strategic decision making is important in the business world. In this article, an alternative coherent data envelopment analysis (CoDEA) with a representation of the intramural structure is established for evaluating the efficiency of a sustainable supply chain. The proposed CoDEA model not only maintains the traditional value of data envelopment analysis (DEA) in its “black box” approach, which avoids the intermediate measures among different nodes in the supply chain, but also overcomes some main pitfalls in previously developed DEA models. The usefulness of the proposed model is illustrated in both simple and complex supply chain situations, yielding reasonable efficiency scores as compared with those from the existing methods. Moreover, the dummy decision-making unit (DMU) introduced in CoDEA offers additional benefits in the scenario of a small supply chain. The approach allows the implicit rule that requires three times the ratio between the total measurement factors and total DMUs to be always satisfied, providing a higher discriminatory power of CoDEA. Based on the case studies covering both simple and complex supply chains, the results and sensitivity analysis ascertain that the proposed CoDEA model is a flexible and reasonable alternative with a good efficiency evaluation, contributing toward an efficient and sustainable supply chain management process pertaining to sustainable strategy or policy recommendations. [ABSTRACT FROM AUTHOR]

To achieve a fully automatic artificial pancreas (AP), i.e., an AP without the need for meal announcements, the intraperitoneal (IP) route is explored. This route has faster dynamics than the typical subcutaneous (SC) route. Model predictive control (MPC) is the most promising control algorithm, but it requires a predictive and identifiable model. This paper presents the design of such a model for MPC-based dual hormone IP APs. This model is trained and tested on recorded data from anesthetized pigs. Animal experiments show that the saturation of the hepatic first-pass effect is essential in how IP insulin and IP glucagon affect glucose levels. These physiological phenomena must be modeled to estimate the system behavior for various conditions. This, in turn, increases the number of parameters and complicates system identification. The availability of rich experimental data from 26 animal trials motivated the design of a technique to exploit this prior information to ensure the identifiability of our model. Through this technique, most parameters were either modeled as body weight functions or common among animals. The correlation between parameter values and body weight is discovered utilizing prior data from various animal experiments, such as blood glucose, plasma insulin, and glucagon levels, in which hormones were administered intraperitoneally or intravenously. This method simplifies the system identification for every new subject while keeping the model's essential details that improve the prediction capability relative to comparable models. The model can be exploited in MPC or any other model-based controller of a bi-hormonal IP AP. It can also be used as a simulator to develop control approaches for single and bi-hormonal IP APs. • A nonlinear model of blood glucose level in type 1 diabetes, developed for closed loop control. • Includes intraperitoneal insulin and glucagon infusion. • Includes dynamics of the hepatic first-pass effect. • Improved identifiability using prior information, to fit the model to animal experiments. • Improved prediction compared to other models suggested in literature. [ABSTRACT FROM AUTHOR]

In regions with complex terrain, high-spatial-resolution downward surface shortwave radiation (DSSR) is critical for monitoring mountain ecological processes and for environmental management. However, currently available DSSR products are often too coarse (from a kilometer to tens of kilometers) to capture the spatial heterogeneity of DSSR in topographically complex regions. To address this issue, this study proposes a new downscaling method for all-sky instantaneous DSSR, employing a machine learning (ML) method, top-of-atmosphere reflectance, and topographic data. The method is used to downscale the 5-km Himawari-8 (H-8) DSSR product to the Sentinel 10 m scale. A region of Southwest China was chosen as a case study. Validated by field measurements from nine stations in 2020, the downscaled DSSR showed improvements in the mean bias error (MBE), mean absolute error (MAE), and root-mean-square error (RMSE) of 32.74%, 9.31%, and 6.34%, respectively, when compared with the original product. The downscaled DSSR can be generated in all-sky conditions. In general, this method successfully captures high-resolution DSSR over complex terrain and should be helpful for related studies. [ABSTRACT FROM AUTHOR]

In this study, we improve the existing model for force distribution over the muscles by considering reflex excitation as a nonvoluntary mechanism of our neuromuscular system. The improved model can explain the large difference between biological torque and experimentally optimized assistive torque profiles. Accordingly, we hypothesize that the “nonvoluntary nature of reflexive excitation highly restricts biological torque compensation”. The proposed model can also potentially characterize co-activation behavior in antagonistic muscles. Using our improved model, we introduce a well-posed framework to optimize the exoskeleton torque profile by metabolic rate minimization. Methods: To support our hypothesis and the proposed method, we utilize two experimental datasets for exoskeleton torque optimization; passive and active ankle exoskeletons. First, we use the passive exoskeleton dataset to identify the parameters of our model; i.e., reflex gains. Then, to validate the proposed model, the identified parameters are used to optimize the exoskeleton torque profile for the second experimental study. Limitations: It is assumed that joint kinematic and reflex gains are fixed with and without exoskeleton. Results: 74% of biological torque at the ankle joint cannot be experimentally compensated and the existing models can only explain that 17% of the biological torque is uncompensable. Our improved model can explain that 58% of biological torque is uncompensable (but still 16% remains unexplained). This achievement provides support for our hypothesis and shows undeniable contribution of reflex excitation for exoskeleton torque profile optimization. [ABSTRACT FROM AUTHOR]

Human finger joints are conventionally simplified as rigid joints in robotic hand design and biomechanical hand modelling, due to their anatomic and morphologic complexity. However, our understanding of the effect of the finger joint configuration on the resulting hand performance is still primitive. In this study, we systematically investigate the grasping performance of the hands with the conventional rigid joints and the biomechanical flexible joints based on a computational human hand model. The measured muscle electromyography (EMG) and hand kinematic data during grasping are used as inputs for the grasping simulations. The results show that the rigid joint configuration currently used in most robotic hands leads to large reductions in hand contact force, contact pressure and contact area, compared to the flexible joint configuration. The grasping quality could be reduced up to 40% and 36% by the rigid joint configuration in terms of algebraic properties of grasping matrix and finger force limit respectively. Further investigation reveals that these reductions are caused by the weak rotational stiffness of the rigid joint configuration. This study implies that robotic/prosthetic hand performance could be improved by exploiting flexible finger joint design. Hand contact parameters and grasping performance may be underestimated by the rigid joint simplification in human hand modelling. [ABSTRACT FROM AUTHOR]

Prosthetic discrete controller relies on finite state machines to switch between a set of predefined task-specific controllers. Therefore the prosthesis can only perform a limited number of discrete locomotion tasks and need hours to tune the parameters for each user. In contrast, the continuous controller treats a gait cycle in a unified way. Thus it is expected to better facilitate normative biomechanics by providing a gait predictive model to contribute a non-switching controller that supports a continuum of tasks. Furthermore, a better method is to train a personalized trajectory prediction model suitable for personal characteristics according to personal walking data. This paper proposes a Gaussian process enhanced Fourier series (GPEFS) method to construct a gait prediction model that represents the human locomotion as a continuous function of phase, speed and slope. Firstly the joint trajectories are transformed into the Fourier coefficient space by least square method. Then the relationship between each Fourier coefficient and task input can be learned by multiple Gaussian process regression (GPRs) model respectively. Compared with directly using GPR to fit the joint trajectory under multi task, our method greatly reduces the computational burden, so as to meet the real-time application scenario. In addition, in Fourier coefficient space, the difference in all tasks between the Fourier coefficient of personal data and the one of statistical data follows the same trend. Therefore, a personalized prediction model is built to predict an individual’s kinematics over a continuous range of slopes and speeds given only one personalized task at level ground and normal speed. The experimental results show that the gait prediction model and the personalized prediction model are feasible and effective. [ABSTRACT FROM AUTHOR]

Due to the close relevance to the reliability and efficiency of power systems, network parameters such as branch admittance have been the target of various cyberattacks. However, existing attack models are generally based on the impractical assumption that attackers can directly modify the data of network parameter stored in well-secured control centers. This article proposes a practical attack model and designs an optimal strategy to detect malicious modification of critical network parameters. Specifically, the vulnerability of network parameter error processing is discovered and exploited to indirectly modify the data of network parameter without accessing to the well-secured control center. A model of false-data-injection-enabled network parameter modification is proposed, which significantly reduces the requirements on attackers’ capability and system information. An optimal detection strategy is designed based on the analysis of the minimal protection set at a single branch, which can significantly reduce the number of protected measurements in detecting malicious modification of critical network parameters. Finally, numerical simulations are carried out on the PJM 5-bus and the IEEE 118-bus test systems to validate the theoretical results. [ABSTRACT FROM AUTHOR]

The high proliferation of electric vehicles has intensified the interdependency between traffic networks (TNs) and power distribution networks (PDNs). Accordingly, this article proposes a decentralized optimization framework for the multiarea optimal traffic-power flow (OTPF) problem, in which the models of PDNs and TNs are established separately in a distributed manner. A multistage distributionally robust optimization (MDRO) model is formulated for PDNs to address wind power uncertainty, with the introduction of a traffic assignment problem to describe the distribution of traffic flows in TNs. Furthermore, an improved alternative direction method of multipliers (I-ADMM) algorithm is developed to solve the multiarea OTPF problem. Numerical results from a three-area traffic-power coupled system demonstrate that the proposed MDRO model bears a cost $89.50 lower than that of the multistage robust optimization model, while the I-ADMM algorithm yields a solving time only one-third that of the traditional ADMM. [ABSTRACT FROM AUTHOR]

Given the prevalence of depression worldwide and its major impact on society, several studies employed artificial intelligence modelling to automatically detect and assess depression. However, interpretation of these models and cues are rarely discussed in detail in the AI community, but have received increased attention lately. In this article, we aim to analyse the commonly selected features using a proposed framework of several feature selection methods and their effect on the classification results, which will provide an interpretation of the depression detection model. The developed framework aggregates and selects the most promising features for modelling depression detection from 38 feature selection algorithms of different categories. Using three real-world depression datasets, 902 behavioural cues were extracted from speech behaviour, speech prosody, eye movement and head pose. To verify the generalisability of the proposed framework, we applied the entire process to depression datasets individually and when combined. The results from the proposed framework showed that speech behaviour features (e.g. pauses) are the most distinctive features of the depression detection model. From the speech prosody modality, the strongest feature groups were F0, HNR, formants, and MFCC, while for the eye activity modality they were left-right eye movement and gaze direction, and for the head modality it was yaw head movement. Modelling depression detection using the selected features (even though there are only 9 features) outperformed using all features in all the individual and combined datasets. Our feature selection framework did not only provide an interpretation of the model, but was also able to produce a higher accuracy of depression detection with a small number of features in varied datasets. This could help to reduce the processing time needed to extract features and creating the model. [ABSTRACT FROM AUTHOR]

Despite the myriad peer-reviewed papers demonstrating novel Artificial Intelligence (AI)-based solutions to COVID-19 challenges during the pandemic, few have made a significant clinical impact, especially in diagnosis and disease precision staging. One major cause for such low impact is the lack of model transparency, significantly limiting the AI adoption in real clinical practice. To solve this problem, AI models need to be explained to users. Thus, we have conducted a comprehensive study of Explainable Artificial Intelligence (XAI) using PRISMA technology. Our findings suggest that XAI can improve model performance, instill trust in the users, and assist users in decision-making. In this systematic review, we introduce common XAI techniques and their utility with specific examples of their application. We discuss the evaluation of XAI results because it is an important step for maximizing the value of AI-based clinical decision support systems. Additionally, we present the traditional, modern, and advanced XAI models to demonstrate the evolution of novel techniques. Finally, we provide a best practice guideline that developers can refer to during the model experimentation. We also offer potential solutions with specific examples for common challenges in AI model experimentation. This comprehensive review, hopefully, can promote AI adoption in biomedicine and healthcare. [ABSTRACT FROM AUTHOR]