Robust flight navigation out of distribution with liquid neural networks

Autonomous robots can learn to perform visual navigation tasks from offline human demonstrations and generalize well to online and unseen scenarios within the same environment they have been trained on. It is challenging for these agents to take a step further and robustly generalize to new environments with drastic scenery changes that they have never encountered. Here, we present a method to create robust flight navigation agents that successfully perform vision-based fly-to-target tasks beyond their training environment under drastic distribution shifts. To this end, we designed an imitation learning framework using liquid neural networks, a brain-inspired class of continuous-time neural models that are causal and adapt to changing conditions. We observed that liquid agents learn to distill the task they are given from visual inputs and drop irrelevant features. Thus, their learned navigation skills transferred to new environments. When compared with several other state-of-the-art deep agents, experiments showed that this level of robustness in decision-making is exclusive to liquid networks, both in their differential equation and closed-form representations.

Re-assessing human mortality risks attributed to PM2.5-mediated effects of agricultural ammonia

How can and should epidemiologists and risk assessors assemble and present evidence for causation of mortality or morbidities by identified agents such as fine particulate matter or other air pollutants? As a motivating example, some scientists have warned recently that ammonia from the production of meat significantly increases human mortality rates in exposed populations by increasing the ambient concentration of fine particulate matter (PM2.5) in air. We reexamine the support for such conclusions, including quantitative calculations that attribute deaths to PM2.5 air pollution by applying associational results such as relative risks, odds ratios, or slope coefficients from regression models to predict the effects on mortality or morbidity of reducing PM2.5 exposures. Taking an outside perspective from the field of causal artificial intelligence (CAI), we conclude that these attribution calculations are methodologically unsound. They produce unreliable conclusions because they ignore an essential distinction between differences in outcomes observed at different levels of exposure and changes in outcomes caused by changing exposure. We find that multiple studies that have examined associations between changes over time in particulate exposure and mortality risk instead of differences in exposures and corresponding mortality risks have found no clear evidence that observed changes in exposure help to predict or explain subsequent changes in mortality risks. We conclude that there is no sound theoretical or empirical reason to believe that reducing ammonia emissions from farms has reduced or would reduce human mortality risks. More generally, applying CAI principles and methods can potentially improve current widespread practices of unsound causal inferences and policy-relevant causal claims that are made without the benefit of formal causal analysis in air pollution health effects research and in other areas of applied epidemiology and public health risk assessment.

Transport of Microplastic and Dispersed Oil Co-contaminants in the Marine Environment

Microplastics (MPs) and oil pollution are major concerns in oceans. Although their coexistence in oceans and the associated MP-oil-dispersant agglomerates (MODAs) have been reported, limited attention is given to the behavior of the co-contaminants. This study investigated MODA transport in a simulated ocean system and explored related mechanisms under various oil types, salinities, and mineral concentrations. We found that more than 90% of the heavy oil-formed MODAs stayed at the seawater surface, while the light oil-formed MODAs were widely distributed throughout the seawater column. The increased salinity promoted MODAs formed by 7 and 90 μm MPs to transport from the seawater surface to the column. This was elucidated by the Derjaguin-Landau-Verwey-Overbeek theory as more MODAs formed under higher salinities and dispersants kept them stable in the seawater column. Minerals facilitated the sinking of large MP-formed MODAs (e.g., 40 μm) as minerals were adsorbed on the MODA surface, but their impact on small MP-formed MODAs (e.g., 7 μm) was negligible. A MODA-mineral system was proposed to explain their interaction. Rubey's equation was recommended to predict the sinking velocity of MODAs. This study is the first attempt to reveal MODA transport. Findings will contribute to the model development to facilitate their environmental risk evaluation in oceans.

Prediction of morning fatigue severity in outpatients receiving chemotherapy: less may still be more

INTRODUCTION

Fatigue is the most common and debilitating symptom experienced by cancer patients undergoing chemotherapy (CTX). Prediction of symptom severity can assist clinicians to identify high-risk patients and provide education to decrease symptom severity. The purpose of this study was to predict the severity of morning fatigue in the week following the administration of CTX.

METHODS

Outpatients (n = 1217) completed questionnaires 1 week prior to and 1 week following administration of CTX. Morning fatigue was measured using the Lee Fatigue Scale (LFS). Separate prediction models for morning fatigue severity were created using 157 demographic, clinical, symptom, and psychosocial adjustment characteristics and either morning fatigue scores or individual fatigue item scores. Prediction models were created using two regression and five machine learning approaches.

RESULTS

Elastic net models provided the best fit across all models. For the EN model using individual LFS item scores, two of the 13 individual LFS items (i.e., "worn out," "exhausted") were the strongest predictors.

CONCLUSIONS

This study is the first to use machine learning techniques to accurately predict the severity of morning fatigue from prior to through the week following the administration of CTX using total and individual item scores from the Lee Fatigue Scale (LFS). Our findings suggest that the language used to assess clinical fatigue in oncology patients is important and that two simple questions may be used to predict morning fatigue severity.

Income raises human well-being indefinitely, but age consistently slashes it

The relationships among human well-being, income, and age have long been debated. The association between human well-being and income is believed to be U-shaped, although the reasons remain elusive. A recent study shows a turning point in the link between human well-being and income; that is, increased income does not always improve well-being. However, the mechanisms of the effects of income and age on human well-being are unknown. Here, we illustrate the total cumulative effects of income and age on evaluated well-being through all observed causal pathways based on a 1.6-million-observation global dataset and the structural causal model. This is the first study to investigate those casual relationships globally. We find that an increase in age always reduces evaluated well-being, and the adverse effects are aggravated with age. Furthermore, increased income continuously improves human well-being, but the impacts gradually become marginal with higher income. Our results demonstrate that physical health improvement in older people is the most effective way to intervene against the harmful effects of age on well-being. Moreover, increased income may dramatically enhance the well-being of people living close to the poverty line.

An integrated analysis of air pollution and meteorological conditions in Jakarta

Air pollution and climate change are general problems for society. This paper proposes an integrated analysis of the Air Quality Index (AQI) and meteorological conditions in Jakarta. The column-based data integration model is applied to create integrated data of the Air Quality Index and meteorological conditions. The integrated data is then used to generate a causal graph using the PC algorithm. The causal graph reveals that there exist causal relationships between pollutants and meteorological conditions, e.g, humidity, rainfall, wind speed, and duration of sunshine affect particulate matter 10 (PM[Formula: see text]); wind speed affects sulfur dioxide (SO[Formula: see text]); temperature affects ozone (O[Formula: see text]). The historical data records that the average wind speed is decreased and the number of unhealthy days has risen. Ozone and particulate matter are two pollutants that mainly influence poor air quality in Jakarta. The integrated data is also used to train Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) for forecasting. Experimental results show that LSTM using integrated data produces smaller errors for forecasting AQI and meteorological conditions.

A systematic review and repeatability study on the use of deep learning for classifying and detecting tuberculosis bacilli in microscopic images

Tuberculosis (TB) is among the leading causes of death worldwide from a single infectious agent. This disease usually affects the lungs (pulmonary TB) and can be cured in most cases with a quick diagnosis and proper treatment. Microscopic sputum smear is widely used to diagnose and manage pulmonary TB. Despite being relatively fast and low cost, it can be exhausting because it depends on manually counting TB bacilli (Mycobacterium tuberculosis) in microscope images. In this context, different Deep Learning (DL) techniques are proposed in the literature to assist in performing smear microscopy. This article presents a systematic review based on the PRISMA procedure, which investigates which DL techniques can contribute to classifying TB bacilli in microscopic images of sputum smears using the Ziehl-Nielsen method. After an extensive search and a careful inclusion/exclusion procedure, 28 papers were selected from a total of 400 papers retrieved from nine databases. Based on these articles, the DL techniques are presented as possible solutions to improve smear microscopy. The main concepts necessary to understand how such techniques are proposed and used are also presented. In addition, replication work is also carried out, verifying reproducibility and comparing different works in the literature. In this review, we look at how DL techniques can be a partner to make sputum smear microscopy faster and more efficient. We also identify some gaps in the literature that can guide which issues can be addressed in other works to contribute to the practical use of these methods in laboratories.

How effective is reducing traffic speed for safer work zones? Methodology and a case study in Pennsylvania

Transportation agencies post and enforce reduced speed limits in work zones to ensure work zone safety, since traffic speed is found to be associated with work zone crash risks. However, prior findings on the relationship between speed and crash rate in work zones are inconsistent. This may be attributed to the methods of statistical associations between traffic speed and crash risks that do not necessarily discover true causal relations. In fact, work zone presence could lead to the reduction of actual traffic speed that influences crash risks, where it may also directly impose effects on crash risks as a result of work zone configurations. The actual traffic speed (not posted speed limit) is also known as a "mediator" where work zones can indirectly impact the crash risks. It is challenging to rigorously separate the causal effect of traffic speed on work zone crash risk from that directly caused by work zones. The underlying causal relation could help to determine what reduced post speed limit (with enforcement) is necessary to ensure work zone safety under the most desired "actual traffic speed". This study proposes to use the sequential g-estimation and the regression discontinuity design to estimate the controlled direct effect of traffic speed on work zone crashes. Two research gaps are identified and filled: inaccurate inferences of the effect of reduced speed limit in work zones as a result of ignoring (1) potential post-treatment bias since traffic speed is a mediator; and (2) potential confounding bias caused by unobservable roadway characteristics. The proposed methodology was applied to 4008 work zones in Pennsylvania from 2015 to 2017, and the results were validated through a series of robustness tests. The results indicate that the direct causal effect of the presence of work zones on crash risk is significantly positive when the traffic speed is relatively low (i.e., lower than 55 mph in this case study), while traffic speed has a positive causal effect on crash occurrences when the actual traffic speed is high (i.e., greater or equal to 55 mph). It suggests that strictly enforcing reduced posted speed limits in work zones is particularly effective when the actual traffic speed is greater than 55 mph. This is particularly true on roadways with high traffic volume (i.e., AADT > 20,000 vehicles per day), long, and daytime work zones (i.e., > 3000 m). On the other hand, the effect of enforcing reduced speed on work zone safety is unclear when the actual speed is already low. In this case, improving work zone configurations and driving behaviors may be more effective in reducing crash risks.

Error Consistency for Machine Learning Evaluation and Validation with Application to Biomedical Diagnostics

Supervised machine learning classification is the most common example of artificial intelligence (AI) in industry and in academic research. These technologies predict whether a series of measurements belong to one of multiple groups of examples on which the machine was previously trained. Prior to real-world deployment, all implementations need to be carefully evaluated with hold-out validation, where the algorithm is tested on different samples than it was provided for training, in order to ensure the generalizability and reliability of AI models. However, established methods for performing hold-out validation do not assess the consistency of the mistakes that the AI model makes during hold-out validation. Here, we show that in addition to standard methods, an enhanced technique for performing hold-out validation—that also assesses the consistency of the sample-wise mistakes made by the learning algorithm—can assist in the evaluation and design of reliable and predictable AI models. The technique can be applied to the validation of any supervised learning classification application, and we demonstrate the use of the technique on a variety of example biomedical diagnostic applications, which help illustrate the importance of producing reliable AI models. The validation software created is made publicly available, assisting anyone developing AI models for any supervised classification application in the creation of more reliable and predictable technologies.

Seeking innovation: The research protocol for SMEs' networking

The paper aims to state the research protocol for the innovation-seeking behavior of Small- to Medium-sized Enterprises (SMEs), related to the classification of knowledge needs expressed in the networking databases. The dataset of 9301 networking offers as the outcome of proactive attitudes represents the content of the Enterprise Europe Network (EEN) database. The data set has been semi-automatically obtained using the rvest R package, and then analyzed using static word embedding neural network architecture: Continuous Bag-of-Words (CBoW), predictive model Skip-Gram, and Global Vectors for Word Representation (GloVe) considered the state-of-the-art models, to create topic-specific lexicons. The proportion of offers labeled as Exploitative innovation to Explorative innovation is balanced with a 51%-49% proportion. The prediction rates show good performance with an AUC score of 0.887, and the prediction rates for exploratory innovation 0.878 and explorative innovation 0.857. The performance of predictions with the frequency-inverse document frequency (TF-IDF) technique shows that the research protocol is sufficient to categorize the innovation-seeking behavior of SMEs using static word embedding based on the description of knowledge needs and text classification, but it is not perfect due to the general entropy related to the outcome of networking. In the context of networking, SMEs place a greater emphasis on explorative innovation in their innovation-seeking behavior. They prioritize smart technologies and global business cooperation, whereas current information technologies and software are more of interest to SMEs that adopt an exploitative innovation approach.

Predicting the HIV/AIDS Knowledge among the Adolescent and Young Adult Population in Peru: Application of Quasi-Binomial Logistic Regression and Machine Learning Algorithms

Inadequate knowledge is one of the principal obstacles for preventing HIV/AIDS spread. Worldwide, it is reported that adolescents and young people have a higher vulnerability of being infected. Thus, the need to understand youths' knowledge towards HIV/AIDS becomes crucial. This study aimed to identify the determinants and develop a predictive model to estimate HIV/AIDS knowledge among this target population in Peru. Data from the 2019 DHS Survey were used. The software RStudio and RapidMiner were used for quasi-binomial logistic regression and computational model building, respectively. Five classification algorithms were considered for model development and their performance was assessed using accuracy, sensitivity, specificity, FPR, FNR, Cohen's kappa, F1 score and AUC. The results revealed an association between 14 socio-demographic, economic and health factors and HIV/AIDS knowledge. The accuracy levels were estimated between 59.47 and 64.30%, with the random forest model showing the best performance (64.30%). Additionally, the best classifier showed that the gender of the respondent, area of residence, wealth index, region of residence, interviewee's age, highest educational level, ethnic self-perception, having heard about HIV/AIDS in the past, the performance of an HIV/AIDS screening test and mass media access have a major influence on HIV/AIDS knowledge prediction. The results suggest the usefulness of the associations found and the random forest model as a predictor of knowledge of HIV/AIDS and may aid policy makers to guide and reinforce the planning and implementation of healthcare strategies.

A New ECG Data Processing Approach to Developing an Accurate Driving Fatigue Detection Framework with Heart Rate Variability Analysis and Ensemble Learning

More than 1.3 million people are killed in traffic accidents annually. Road traffic accidents are mostly caused by human error. Therefore, an accurate driving fatigue detection system is required for drivers. Most driving fatigue detection studies concentrated on improving feature engineering and classification methods. We propose a novel driving fatigue detection framework concentrating on the development of the preprocessing, feature extraction, and classification stages to improve the classification accuracy of fatigue states. The proposed driving fatigue detection framework measures fatigue using a two-electrode ECG. The resampling method and heart rate variability analysis were used to extract features from the ECG data, and an ensemble learning model was utilized to classify fatigue states. To achieve the best model performance, 40 possible scenarios were applied: a combination of 5 resampling scenarios, 2 feature extraction scenarios, and 4 classification model scenarios. It was discovered that the combination of a resampling method with a window duration of 300 s and an overlap of 270 s, 54 extracted features, and AdaBoost yielded an optimum accuracy of 98.82% for the training dataset and 81.82% for the testing dataset. Furthermore, the preprocessing resampling method had the greatest impact on the model’s performance; it is a new approach presented in this study.

Real-Time Monitoring Using Multiplexed Multi-Electrode Bioelectrical Impedance Spectroscopy for the Stratification of Vascularized Composite Allografts: A Perspective on Predictive Analytics

Vascularized composite allotransplantation addresses injuries to complex anatomical structures such as the face, hand, and abdominal wall. Prolonged static cold storage of vascularized composite allografts (VCA) incurs damage and imposes transportation limits to their viability and availability. Tissue ischemia, the major clinical indication, is strongly correlated with negative transplantation outcomes. Machine perfusion and normothermia can extend preservation times. This perspective introduces multiplexed multi-electrode bioimpedance spectroscopy (MMBIS), an established bioanalytical method to quantify the interaction of the electrical current with tissue components, capable of measuring tissue edema, as a quantitative, noninvasive, real-time, continuous monitoring technique to provide crucially needed assessment of graft preservation efficacy and viability. MMBIS must be developed, and appropriate models explored to address the highly complex multi-tissue structures and time-temperature changes of VCA. Combined with artificial intelligence (AI), MMBIS can serve to stratify allografts for improvement in transplantation outcomes.

Development of a Physical Activity and Sedentary Behaviour Policy for Canadian Childcare Settings: A Delphi Study

This study aimed to obtain consensus on physical activity (PA) and sedentary behaviour (SB) policy items for use in Canadian childcare settings. Purposeful sampling of Canadian experts in PA/SB (n = 19) and Early Childhood Education (ECE; n = 20) was used to form two distinct (i.e., PA/SB and ECE) panels for a 3-round Delphi study. In round 1, the PA/SB experts suggested their top 10 items for a Canadian childcare PA/SB policy. Policy items were then pooled to generate a list of 24 unique items. In round 2, experts in both panels rated the importance of the 24 policy items using a 7-point Likert scale (i.e., 1 = Not at all important to 7 = Extremely important). The ECE panel was also asked to report on the feasibility of the policy items using a 4-point Likert scale (i.e., 1 = Not at all feasible to 4 = Very feasible). Policy items that received an interquartile deviation (IQD) score of ≤ 1 (indicating consensus) and a median score of ≥ 6 (indicating importance) in both panels were considered shared priorities. In round 3, members of both panels re-rated the importance of the policy items that did not achieve consensus among their respective panel in round 2 and were asked to order items based on importance. Descriptive statistics were used to assess feasibility of policy items, and differences in panel ratings were quantified using Mann Whitney U tests. Consensus was achieved for 23 policy items in the PA/SB panel and 17 items in the ECE panel. Overall, 15 shared priorities were identified (e.g., provide 120 min of outdoor time per day, sedentary behaviour should not be used as a punishment), and six policy items exhibited a statistical difference in ratings across panels. Members of the ECE panel indicated that the policy item, "children should be permitted to go outside whenever they want, for as long as they want" (M = 1.78; SD = 0.65) was lowest in terms of feasibility, and the policy item, "children should receive opportunities to engage in both unstructured and structured physical activity opportunities daily" (M = 3.89; SD = 0.32) was the most feasible for daily implementation. Findings from this study can inform the development of an expert-generated and feasibility-informed institutional PA/SB policy for use in Canadian childcare settings.

Supplementary Information

The online version contains supplementary material available at 10.1007/s10643-023-01473-z.

Evaluation of Kidney Donor Risk Index/Kidney Donor Profile Index as Predictor Tools of Deceased-Donor Kidney Transplant Outcomes in a Greek Cohort

The Kidney Donor Risk Index (KDRI) and Kidney Donor Profile Index (KDPI) have been developed to assess deceased-donor graft quality, although validation of their utility outside the USA remains limited. This single-center retrospective cohort study evaluated the ability of KDRI and KDPI to predict transplant outcomes in a Greek cohort. The efficacy of KDRI, KDPI, and donor's age in predicting death-censored graft failure was primarily assessed. Overall, 394 donors and 456 recipients were included. Death-censored graft survival was significantly worse with increasing KDRI (hazard ratio-HR: 2.21, 95% confidence intervals-CI: 1.16-4.22), KDPI (HR: 1.01, 95% CI: 1.00-1.02), and donor's age (HR: 1.03, 95% CI: 1.00-1.05). The unadjusted discriminative ability was similar for KDPI (C-statistic: 0.54) and donor's age (C-statistic: 0.52). The KDPI threshold of 85 was not predictive of graft failure (p-value: 0.19). Higher KDPI was linked to delayed graft function and worse kidney function, but not among expanded-criteria donor transplantations. No significant association was found between KDRI, KDPI, and patient survival. In conclusion, increasing KDRI and KDPI are linked to worse graft function, although their ability to discriminate long-term graft failure remains limited.

Quantum Computing Approaches for Vector Quantization-Current Perspectives and Developments

In the field of machine learning, vector quantization is a category of low-complexity approaches that are nonetheless powerful for data representation and clustering or classification tasks. Vector quantization is based on the idea of representing a data or a class distribution using a small set of prototypes, and hence, it belongs to interpretable models in machine learning. Further, the low complexity of vector quantizers makes them interesting for the application of quantum concepts for their implementation. This is especially true for current and upcoming generations of quantum devices, which only allow the execution of simple and restricted algorithms. Motivated by different adaptation and optimization paradigms for vector quantizers, we provide an overview of respective existing quantum algorithms and routines to realize vector quantization concepts, maybe only partially, on quantum devices. Thus, the reader can infer the current state-of-the-art when considering quantum computing approaches for vector quantization.

How I Would have been Differently Treated. Discrimination Through the Lens of Counterfactual Fairness

The widespread use of algorithms for prediction-based decisions urges us to consider the question of what it means for a given act or practice to be discriminatory. Building upon work by Kusner and colleagues in the field of machine learning, we propose a counterfactual condition as a necessary requirement on discrimination. To demonstrate the philosophical relevance of the proposed condition, we consider two prominent accounts of discrimination in the recent literature, by Lippert-Rasmussen and Hellman respectively, that do not logically imply our condition and show that they face important objections. Specifically, Lippert-Rasmussen's definition proves to be over-inclusive, as it classifies some acts or practices as discriminatory when they are not, whereas Hellman's account turns out to lack explanatory power precisely insofar as it does not countenance a counterfactual condition on discrimination. By defending the necessity of our counterfactual condition, we set the conceptual limits for justified claims about the occurrence of discriminatory acts or practices in society, with immediate applications to the ethics of algorithmic decision-making.

TorchLens: A Python package for extracting and visualizing hidden activations of PyTorch models

Deep neural network models (DNNs) are essential to modern AI and provide powerful models of information processing in biological neural networks. Researchers in both neuroscience and engineering are pursuing a better understanding of the internal representations and operations that undergird the successes and failures of DNNs. Neuroscientists additionally evaluate DNNs as models of brain computation by comparing their internal representations to those found in brains. It is therefore essential to have a method to easily and exhaustively extract and characterize the results of the internal operations of any DNN. Many models are implemented in PyTorch, the leading framework for building DNN models. Here we introduce TorchLens , a new open-source Python package for extracting and characterizing hidden-layer activations in PyTorch models. Uniquely among existing approaches to this problem, TorchLens has the following features: (1) it exhaustively extracts the results of all intermediate operations, not just those associated with PyTorch module objects, yielding a full record of every step in the model's computational graph, (2) it provides an intuitive visualization of the model's complete computational graph along with metadata about each computational step in a model's forward pass for further analysis, (3) it contains a built-in validation procedure to algorithmically verify the accuracy of all saved hidden-layer activations, and (4) the approach it uses can be automatically applied to any PyTorch model with no modifications, including models with conditional (if-then) logic in their forward pass, recurrent models, branching models where layer outputs are fed into multiple subsequent layers in parallel, and models with internally generated tensors (e.g., injections of noise). Furthermore, using TorchLens requires minimal additional code, making it easy to incorporate into existing pipelines for model development and analysis, and useful as a pedagogical aid when teaching deep learning concepts. We hope this contribution will help researchers in AI and neuroscience understand the internal representations of DNNs.

Eating smart: Free-ranging dogs follow an optimal foraging strategy while scavenging in groups

Foraging and acquiring of food is a delicate balance between managing the costs (both energy and social) and individual preferences. Previous research on solitarily foraging free-ranging dogs showed that they prioritise the nutritionally highest valued food, but do not ignore other less valuable food either, displaying typical scavenger behaviour. We conducted a similar experiment on 136 groups of dogs with the same set-up to see the change in foraging strategies, if any, under the influence of social cost like intra-group competition. We found multiple differences between the strategies of dogs foraging alone versus in groups with competition playing an implicit role in the dogs’ decision making when foraging in groups. Dogs continually assessed and evaluated the available resources in a “patch,” transitioning from random foraging to systematic foraging with time and more information. Dogs in groups used an, “eat first, sample afterwards” strategy whereas individual dogs sampled thoroughly before eating. Additionally, dogs in groups were quicker and more likely to respond to the experimental set-up and eat from it. The dogs adjusted their behaviour in terms of effort and time allocated according to the quality of the “patch.” Foraging in groups also provided benefits of reduced individual vigilance. The various decisions and choices made lend support to the optimal foraging theory wherein the dogs harvested the nutritionally richest patch possible with the least risk and cost involved but were willing to compromise if that was not possible. This underscores the cognitive, quick decision-making abilities and adaptable behaviour of these dogs, which is likely to have influenced the process of dog domestication.

Data-Driven Quantitative Intrinsic Hazard Criteria for Nanoproduct Development in a Safe-by-Design Paradigm: A Case Study of Silver Nanoforms

The current European (EU) policies, that is, the Green Deal, envisage safe and sustainable practices for chemicals, which include nanoforms (NFs), at the earliest stages of innovation. A theoretically safe and sustainable by design (SSbD) framework has been established from EU collaborative efforts toward the definition of quantitative criteria in each SSbD dimension, namely, the human and environmental safety dimension and the environmental, social, and economic sustainability dimensions. In this study, we target the safety dimension, and we demonstrate the journey toward quantitative intrinsic hazard criteria derived from findable, accessible, interoperable, and reusable data. Data were curated and merged for the development of new approach methodologies, that is, quantitative structure-activity relationship models based on regression and classification machine learning algorithms, with the intent to predict a hazard class. The models utilize system (i.e., hydrodynamic size and polydispersity index) and non-system (i.e., elemental composition and core size)-dependent nanoscale features in combination with biological in vitro attributes and experimental conditions for various silver NFs, functional antimicrobial textiles, and cosmetics applications. In a second step, interpretable rules (criteria) followed by a certainty factor were obtained by exploiting a Bayesian network structure crafted by expert reasoning. The probabilistic model shows a predictive capability of ≈78% (average accuracy across all hazard classes). In this work, we show how we shifted from the conceptualization of the SSbD framework toward the realistic implementation with pragmatic instances. This study reveals (i) quantitative intrinsic hazard criteria to be considered in the safety aspects during synthesis stage, (ii) the challenges within, and (iii) the future directions for the generation and distillation of such criteria that can feed SSbD paradigms. Specifically, the criteria can guide material engineers to synthesize NFs that are inherently safer from alternative nanoformulations, at the earliest stages of innovation, while the models enable a fast and cost-efficient in silico toxicological screening of previously synthesized and hypothetical scenarios of yet-to-be synthesized NFs.

A Federated Learning-Inspired Evolutionary Algorithm: Application to Glucose Prediction

In this paper, we propose an innovative Federated Learning-inspired evolutionary framework. Its main novelty is that this is the first time that an Evolutionary Algorithm is employed on its own to directly perform Federated Learning activity. A further novelty resides in the fact that, differently from the other Federated Learning frameworks in the literature, ours can efficiently deal at the same time with two relevant issues in Machine Learning, i.e., data privacy and interpretability of the solutions. Our framework consists of a master/slave approach in which each slave contains local data, protecting sensible private data, and exploits an evolutionary algorithm to generate prediction models. The master shares through the slaves the locally learned models that emerge on each slave. Sharing these local models results in global models. Being that data privacy and interpretability are very significant in the medical domain, the algorithm is tested to forecast future glucose values for diabetic patients by exploiting a Grammatical Evolution algorithm. The effectiveness of this knowledge-sharing process is assessed experimentally by comparing the proposed framework with another where no exchange of local models occurs. The results show that the performance of the proposed approach is better and demonstrate the validity of its sharing process for the emergence of local models for personal diabetes management, usable as efficient global models. When further subjects not involved in the learning process are considered, the models discovered by our framework show higher generalization capability than those achieved without knowledge sharing: the improvement provided by knowledge sharing is equal to about 3.03% for precision, 1.56% for recall, 3.17% for F1, and 1.56% for accuracy. Moreover, statistical analysis reveals the statistical superiority of model exchange with respect to the case of no exchange taking place.

Crosstalk in Facial EMG and Its Reduction Using ICA

There is ample evidence that electromyography (EMG) signals from the corrugator supercilii and zygomatic major muscles can provide valuable information for the assessment of subjective emotional experiences. Although previous research suggested that facial EMG data could be affected by crosstalk from adjacent facial muscles, it remains unproven whether such crosstalk occurs and, if so, how it can be reduced. To investigate this, we instructed participants (n = 29) to perform the facial actions of frowning, smiling, chewing, and speaking, in isolation and combination. During these actions, we measured facial EMG signals from the corrugator supercilii, zygomatic major, masseter, and suprahyoid muscles. We performed an independent component analysis (ICA) of the EMG data and removed crosstalk components. Speaking and chewing induced EMG activity in the masseter and suprahyoid muscles, as well as the zygomatic major muscle. The ICA-reconstructed EMG signals reduced the effects of speaking and chewing on zygomatic major activity, compared with the original signals. These data suggest that: (1) mouth actions could induce crosstalk in zygomatic major EMG signals, and (2) ICA can reduce the effects of such crosstalk.

On joint parameterizations of linear and nonlinear functionals in neural networks

The paper proposes a new class of nonlinear operators and a dual learning paradigm where optimization jointly concerns both linear convolutional weights and the parameters of these nonlinear operators. The nonlinear class proposed to perform a rich functional representation is composed by functions called rectified parametric sigmoid units. This class is constructed to benefit from the advantages of both sigmoid and rectified linear unit functions, while rejecting their respective drawbacks. Moreover, the analytic form of this new neural class involves scale, shift and shape parameters to obtain a wide range of activation shapes, including the standard rectified linear unit as a limit case. Parameters of this neural transfer class are considered as learnable for the sake of discovering the complex shapes that can contribute to solving machine learning issues. Performance achieved by the joint learning of convolutional and rectified parametric sigmoid learnable parameters are shown to be outstanding in both shallow and deep learning frameworks. This class opens new prospects with respect to machine learning in the sense that main learnable parameters are attached not only to linear transformations, but also to a wide range of nonlinear operators.

Four-Year Nutritional Outcomes in Single-Anastomosis Duodeno-Ileal Bypass with Sleeve Gastrectomy Patients: an Australian Experience

Nutritional deficiencies following malabsorptive surgeries are a major concern.

PURPOSE

To present clinical-based, mid-term nutritional outcomes in single-anastomosis duodeno-ileal bypass with sleeve gastrectomy (SADI-S) patients using a nutritional supplement based on the American Society for Metabolic & Bariatric Surgery (ASMBS) guidelines.

SETTING

Single private institute, Australia.

MATERIALS AND METHODS

Data from 196 patients who underwent a primary SADI-S by a single surgeon from January 2017 through March 2022 were retrospectively analysed. All patients received either original or altered formulated nutritional supplementation throughout the study. In total, three formulae, slightly different from each other, were used at three different time points to formulate the supplement.

RESULTS

In total, 196 patients were included. The average age and preoperative body mass index were 44.9 ± 6.7 years and 43.6 ± 22.5 kg/m², respectively. Nutritional follow-up was available on 77.5%, 73.2%, 73.4%, and 59.7% of patients at 12, 24, 36, and 48 months, respectively. At baseline, 48.3%, 30%, 14.9%, 13.3%, 12.4%, 3.8%, 2.3%, and 0.5% of the patients had vitamin D, calcium, folic acid, total protein, iron, vitamin B12, copper, and vitamin A deficiencies, respectively. Postoperatively, mild to moderate vitamin deficiencies were noted in 14.2% of the patients in the first 18 months; however, at 4 years, the cohort had zero nutritional deficiencies. There were no long-term complications, revisions/conversions, or mortalities related to nutritional deficiencies.

CONCLUSION

Factors, like preoperative and postoperative early, aggressive correction of nutritional deficiencies, regular laboratory monitoring and follow-ups with the multidisciplinary team, and adherence to our formulated nutritional supplement, have contributed to favourable nutritional outcomes at 4 years.

Impact assessment of human activities on resources of juvenile horseshoe crabs in Hainan coastal areas, China

The booming coastal zone economy poses increasing anthropogenic threats to marine life and habitats. Using the endangered living fossil horseshoe crab (HSC) as an example, we quantified the intensity of various anthropogenic pressures along the coast of Hainan Island, China, and for the first time assessed their impact on the distribution of juvenile HSCs through a field survey, remote sensing, spatial geographic modeling, and machine learning methods. The results indicate that the Danzhou Bay needs to be protected as a priority based on species and anthropogenic pressure information. Aquaculture and port activities dramatically impact the density of HSCs and therefore be managed priority. Finally, a threshold effect between total, coastal residential, and beach pressure and the density of juvenile HSCs were detected, which indicates the need for a balance between development and conservation as well as the designation of suitable sites for the construction of marine protected areas.

Brain Network Analysis: A Review on Multivariate Analytical Methods

Despite the explosive growth of neuroimaging studies aimed at analyzing the brain as a complex system, critical methodological gaps remain to be addressed. Most tools currently used for analyzing network data of the brain are univariate in nature and are based on assumptions borne out of previous techniques not directly related to the big and complex data of the brain. Although graph-based methods have shown great promise, the development of principled multivariate models to address inherent limitations of graph-based methods, such as their dependence on network size and degree distributions, and to allow assessing the effects of multiple phenotypes on the brain and simulating brain networks has largely lagged behind. Although some studies have been made in developing multivariate frameworks to fill this gap, in the absence of a "gold-standard" method or guidelines, choosing the most appropriate method for each study can be another critical challenge for investigators in this multidisciplinary field. Here, we briefly introduce important multivariate methods for brain network analyses in two main categories: data-driven and model-based methods. We discuss whether/how such methods are suited for examining connectivity (edge-level), topology (system-level), or both. This review will aid in choosing an appropriate multivariate method with respect to variables such as network type, number of subjects and brain regions included, and the interest in connectivity, topology, or both. This review is aimed to be accessible to investigators from different backgrounds, with a focus on applications in brain network studies, though the methods may be applicable in other areas too. Impact statement As the U.S. National Institute of Health notes, the rich biomedical data can greatly improve our knowledge of human health if new analytical tools are developed, and their applications are broadly disseminated. A major challenge in analyzing the brain as a complex system is about developing parsimonious multivariate methods, and particularly choosing the most appropriate one among the existing methods with respect to the study variables in this multidisciplinary field. This study provides a review on the most important multivariate methods to aid in helping the most appropriate ones with respect to the desired variables for each study.

An effective brain connectivity technique to predict repetitive transcranial magnetic stimulation outcome for major depressive disorder patients using EEG signals

One of the most effective treatments for drug-resistant Major depressive disorder (MDD) patients is repetitive transcranial magnetic stimulation (rTMS). To improve treatment efficacy and reduce health care costs, it is necessary to predict the treatment response. In this study, we intend to predict the rTMS treatment response in MDD patients from electroencephalogram (EEG) signals before starting the treatment using machine learning approaches. Effective brain connectivity of 19-channel EEG data of MDD patients was calculated by the direct directed transfer function (dDTF) method. Then, using three feature selection methods, the best features were selected and patients were classified as responders or non-responders to rTMS treatment by using the support vector machine (SVM). Results on the 34 MDD patients indicated that the Fp2 region in the delta and theta frequency bands has a significant difference between the two groups and can be used as a significant brain biomarker to assess the rTMS treatment response. Also, the highest accuracy (89.6%) using the SVM classifier for the best features of the dDTF method based on the area under the receiver operating characteristic curve (AUC-ROC) criteria was obtained by combining the delta and theta frequency bands. Consequently, the proposed method can accurately detect the rTMS treatment response in MDD patients before starting treatment on the EEG signal to avoid financial and time costs to patients and medical centers.

Beyond one-size-fits-all: Consumers react differently to packaging colors and names of cultured meat in Italy

Cultured meat, also known as "in-vitro meat," "clean meat," "synthetic meat," "lab-grown meat" and many other nomenclatures, represents one of the most recent controversial food technologies, even with its environmental benefits. Although the market success of cultured meat depends on consumers' acceptance, specific characteristics such as name and packaging color can influence consumers' perceptions and acceptance of the food product. This study assessed the impact of the name and packaging color of cultured meat on consumers' behavioral intentions toward its consumption in Italy. With the assumption that names and packaging colors affect consumers' acceptance differently, according to their characteristics and food neophobia, this study used a finite mixture model to analyze the stimulus impacts across different groups of consumers. The results showed that food neophobia plays a relevant role in individual response to name and packaging color of cultured meat. Less neophobic consumers are more likely to be positively affected in their intentions by green color packaging and nomenclatures that least emphasize the unnaturalness of the product, such as "clean meat," whereas neophobic consumers are more likely to be positively affected only by green color.

A case study on genomic imprinting facilitates student learning

Problem-based learning encourages students to deepen their understanding of a concept by working through a real-world example of course content. Case studies represent a form of problem-based learning that engages students in realistic scenarios to achieve a deeper understanding of concepts. Case studies have been shown to facilitate the learning of challenging subject matter. We hypothesized that the use of a case study would help students better learn the topic of genomic imprinting, an abstract phenomenon in molecular biology and genetics. We wrote an interrupted case study that focused on genomic imprinting. The case study consists of three short popular news articles that relate to genomic imprinting. Each article is followed by a set of two to four questions. Students read each article and discuss its associated questions in small groups and then with the entire class before moving on to the next article. We deployed the case study in an intermediate-level molecular biology course at a small, liberal arts university. We assessed student learning and attitudes toward the case study (50 pre/postmatched pairs). In four true/false assessment questions, our results showed that the students' performance on the assessment after the case study was significantly higher than their performance before the case study. Students also self-reported increased knowledge of concepts related to genomic imprinting. Finally, students were likely to agree that the case study was beneficial to their learning and was an enjoyable classroom activity. We conclude that the case study is an effective way to instruct students about the topic of genomic imprinting.NEW & NOTEWORTHY Students often struggle with the concept of genomic imprinting, in part because it violates Mendelian rules of inheritance. Students learned about genomic imprinting, and enjoyed doing it when completing this case study.

Water Quality Predictions Through Linear Regression - A Brute Force Algorithm Approach

Linear regression is one of the oldest statistical modeling approaches. Still, it is a valuable tool, particularly when it is necessary to create forecast models with low sample sizes. When researchers use this method and have numerous potential regressors, choosing the group of regressors for a model that fulfills all the required assumptions can be challenging. In this sense, the authors developed an open-source Python script that automatically tests all the combinations of regressors under a brute-force approach. The output displays the best linear regression models, regarding the thresholds set by users for the required assumptions: statistical significance of the estimations, multicollinearity, error normality, and homoscedasticity. Further, the script allows the selection of linear regressions with regression coefficients according to the user's expectations. This script was tested with an environmental dataset to predict surface water quality parameters based on landscape metrics and contaminant loads. Among millions of possible combinations, less than 0.1 % of the regressor combinations fulfilled the requirements. The resulting combinations were also tested in geographically weighted regression, with similar results to linear regression. The model's performance was higher for pH and total nitrate and lower for total alkalinity and electrical conductivity.•A Python script was developed to find the best linear regressions within a dataset.•Output regressions are automatically selected based on regression coefficient expectations set by the user and the linear regression assumptions.•The algorithm was successfully validated through an environmental dataset.

High-Dimensional Survival Analysis: Methods and Applications

In the era of precision medicine, time-to-event outcomes such as time to death or progression are routinely collected, along with high-throughput covariates. These high-dimensional data defy classical survival regression models, which are either infeasible to fit or likely to incur low predictability due to over-fitting. To overcome this, recent emphasis has been placed on developing novel approaches for feature selection and survival prognostication. We will review various cutting-edge methods that handle survival outcome data with high-dimensional predictors, highlighting recent innovations in machine learning approaches for survival prediction. We will cover the statistical intuitions and principles behind these methods and conclude with extensions to more complex settings, where competing events are observed. We exemplify these methods with applications to the Boston Lung Cancer Survival Cohort study, one of the largest cancer epidemiology cohorts investigating the complex mechanisms of lung cancer.

Airtightness evaluation of Canadian dwellings and influencing factors based on measured data and predictive models

The airtightness of buildings has a significant impact on buildings' energy efficiency, maintenance and occupant comfort. The main goal of this study is to provide an evaluation of the air leakage characteristics of dwellings in different regions in Canada. This study evaluated the key influencing factors on airtightness performance based on a large set of measured data (73,450 dwellings located in Canada with 11 measurement parameters for each). Machine learning models based on multivariate regression (MVR) and Random Forest Ensemble (RFE) were developed to predict the air leakage value. The RFE model, which shows better results than MVR, was used to evaluate the effect of the ageing of buildings. Results showed that the maximum increase in air leakage occurs during the first year after construction - approximately 25%, and then 3.7% in the second year, after which the increase rate becomes insignificant and relatively constant - approximately 0.3% per year. The findings from this study can provide significant information for building designs, building performance simulations and strengthening standards and guidelines policies on indoor environmental quality.

Optimizing multivariate pattern classification in rapid event-related designs

BACKGROUND

Multivariate pattern analysis (MVPA or pattern decoding) has attracted considerable attention as a sensitive analytic tool for investigations using functional magnetic resonance imaging (fMRI) data. With the introduction of MVPA, however, has come a proliferation of methodological choices confronting the researcher, with few studies to date offering guidance from the vantage point of controlled datasets detached from specific experimental hypotheses.

NEW METHOD

We investigated the impact of four data processing steps on support vector machine (SVM) classification performance aimed at maximizing information capture in the presence of common noise sources. The four techniques included: trial averaging (classifying on separate trial estimates versus condition-based averages), within-run mean centering (centering the data or not), method of cost selection (using a fixed or tuned cost value), and motion-related denoising approach (comparing no denoising versus a variety of nuisance regressions capturing motion-related reference signals). The impact of these approaches was evaluated on real fMRI data from two control ROIs, as well as on simulated pattern data constructed with carefully controlled voxel- and trial-level noise components.

RESULTS

We find significant improvements in classification performance across both real and simulated datasets with run-wise trial averaging and mean centering. When averaging trials within conditions of each run, we note a simultaneous increase in the between-subject variability of SVM classification accuracies which we attribute to the reduced size of the test set used to assess the classifier's prediction error. Therefore, we propose a hybrid technique whereby randomly sampled subsets of trials are averaged per run and demonstrate that it helps mitigate the tradeoff between improving signal-to-noise ratio by averaging and losing exemplars in the test set.

COMPARISON WITH EXISTING METHODS

Though a handful of empirical studies have employed run-based trial averaging, mean centering, or their combination, such studies have done so without theoretical justification or rigorous testing using control ROIs.

CONCLUSIONS

Therefore, we intend this study to serve as a practical guide for researchers wishing to optimize pattern decoding without risk of introducing spurious results.

Radiogenomic classification for MGMT promoter methylation status using multi-omics fused feature space for least invasive diagnosis through mpMRI scans

Accurate radiogenomic classification of brain tumors is important to improve the standard of diagnosis, prognosis, and treatment planning for patients with glioblastoma. In this study, we propose a novel two-stage MGMT Promoter Methylation Prediction (MGMT-PMP) system that extracts latent features fused with radiomic features predicting the genetic subtype of glioblastoma. A novel fine-tuned deep learning architecture, namely Deep Learning Radiomic Feature Extraction (DLRFE) module, is proposed for latent feature extraction that fuses the quantitative knowledge to the spatial distribution and the size of tumorous structure through radiomic features: (GLCM, HOG, and LBP). The application of the novice rejection algorithm has been found significantly effective in selecting and isolating the negative training instances out of the original dataset. The fused feature vectors are then used for training and testing by k-NN and SVM classifiers. The 2021 RSNA Brain Tumor challenge dataset (BraTS-2021) consists of four structural mpMRIs, viz. fluid-attenuated inversion-recovery, T1-weighted, T1-weighted contrast enhancement, and T2-weighted. We evaluated the classification performance, for the very first time in published form, in terms of measures like accuracy, F₁-score, and Matthews correlation coefficient. The Jackknife tenfold cross-validation was used for training and testing BraTS-2021 dataset validation. The highest classification performance is (96.84 ± 0.09)%, (96.08 ± 0.10)%, and (97.44 ± 0.14)% as accuracy, sensitivity, and specificity respectively to detect MGMT methylation status for patients suffering from glioblastoma. Deep learning feature extraction with radiogenomic features, fusing imaging phenotypes and molecular structure, using rejection algorithm has been found to perform outclass capable of detecting MGMT methylation status of glioblastoma patients. The approach relates the genomic variation with radiomic features forming a bridge between two areas of research that may prove useful for clinical treatment planning leading to better outcomes.

Active Learning for Efficient Soil Monitoring in Large Terrain with Heterogeneous Sensor Network

Soils are a complex ecosystem that provides critical services, such as growing food, supplying antibiotics, filtering wastes, and maintaining biodiversity; hence monitoring soil health and domestication is required for sustainable human development. Low-cost and high-resolution soil monitoring systems are challenging to design and build. Compounded by the sheer size of the monitoring area of interest and the variety of biological, chemical, and physical parameters to monitor, naive approaches to adding or scheduling more sensors will suffer from cost and scalability problems. We investigate a multi-robot sensing system integrated with an active learning-based predictive modeling technique. Taking advantage of advances in machine learning, the predictive model allows us to interpolate and predict soil attributes of interest from the data collected by sensors and soil surveys. The system provides high-resolution prediction when the modeling output is calibrated with static land-based sensors. The active learning modeling technique allows our system to be adaptive in data collection strategy for time-varying data fields, utilizing aerial and land robots for new sensor data. We evaluated our approach using numerical experiments with a soil dataset focusing on heavy metal concentration in a flooded area. The experimental results demonstrate that our algorithms can reduce sensor deployment costs via optimized sensing locations and paths while providing high-fidelity data prediction and interpolation. More importantly, the results verify the adapting behavior of the system to the spatial and temporal variations of soil conditions.

Reconsidering Read and Spontaneous Speech: Causal Perspectives on the Generation of Training Data for Automatic Speech Recognition

Superficially, read and spontaneous speech—the two main kinds of training data for automatic speech recognition—appear as complementary, but are equal: pairs of texts and acoustic signals. Yet, spontaneous speech is typically harder for recognition. This is usually explained by different kinds of variation and noise, but there is a more fundamental deviation at play: for read speech, the audio signal is produced by recitation of the given text, whereas in spontaneous speech, the text is transcribed from a given signal. In this review, we embrace this difference by presenting a first introduction of causal reasoning into automatic speech recognition, and describing causality as a tool to study speaking styles and training data. After breaking down the data generation processes of read and spontaneous speech and analysing the domain from a causal perspective, we highlight how data generation by annotation must affect the interpretation of inference and performance. Our work discusses how various results from the causality literature regarding the impact of the direction of data generation mechanisms on learning and prediction apply to speech data. Finally, we argue how a causal perspective can support the understanding of models in speech processing regarding their behaviour, capabilities, and limitations.

Effects of Charge Traps on Hysteresis in Organic Field-Effect Transistors and Their Charge Trap Cause Analysis through Causal Inference Techniques

Hysteresis in organic field-effect transistors is attributed to the well-known bias stress effects. This is a phenomenon in which the measured drain-source current varies when sweeping the gate voltage from on to off or from off to on. Hysteresis is caused by various factors, and one of the most common is charge trapping. A charge trap is a defect that occurs in an interface state or part of a semiconductor, and it refers to an electronic state that appears distributed in the semiconductor's energy band gap. Extensive research has been conducted recently on obtaining a better understanding of charge traps for hysteresis. However, it is still difficult to accurately measure or characterize them, and their effects on the hysteresis of organic transistors remain largely unknown. In this study, we conduct a literature survey on the hysteresis caused by charge traps from various perspectives. We first analyze the driving principle of organic transistors and introduce various types of hysteresis. Subsequently, we analyze charge traps and determine their influence on hysteresis. In particular, we analyze various estimation models for the traps and the dynamics of the hysteresis generated through these traps. Lastly, we conclude this study by explaining the causal inference approach, which is a machine learning technique typically used for current data analysis, and its implementation for the quantitative analysis of the causal relationship between the hysteresis and the traps.

Wideband Spectrum Sensing Using Modulated Wideband Converter and Data Reduction Invariant Algorithms

Wideband spectrum sensing is a challenging problem in the framework of cognitive radio and spectrum surveillance, mainly because of the high sampling rates required by standard approaches. In this paper, a compressed sensing approach was considered to solve this problem, relying on a sub-Nyquist or Xsampling scheme, known as a modulated wideband converter. First, the data reduction at its output is performed in order to enable a highly effective processing scheme for spectrum reconstruction. The impact of this data transformation on the behavior of the most popular sparse reconstruction algorithms is then analyzed. A new mathematical approach is proposed to demonstrate that greedy reconstruction algorithms, such as Orthogonal Matching Pursuit, are invariant with respect to the proposed data reduction. Relying on the same formalism, a data reduction invariant version of the LASSO (least absolute shrinkage and selection operator) reconstruction algorithm was also introduced. It is finally demonstrated that the proposed algorithm provides good reconstruction results in a wideband spectrum sensing scenario, using both synthetic and measured data.