Search

The adoption of emerging machine learning (ML) techniques in sewer deterioration modelling remains limited. This is primarily due to a lack of comparisons with popular models to evaluate if they perform superiorly and the extensive datasets required for ML training, which many small- to medium-sized municipalities do not possess. This study compares an emerging ML technique, random survival forest (RSF), with two established models: support vector machine (SVM) and GompitZ. Additionally, it examines the transferability of RSF models to different municipalities. The results indicate that both RSF and GompitZ have unique strengths and weaknesses, suggesting parallel use with statistical models. RSF’s performance was comparable to, or better than, SVM. Furthermore, globally trained RSF models, which use aggregated datasets of multiple municipalities, perform similarly to locally trained models, which are trained on representative municipal data. However, globally trained models are promising for municipalities lacking data or expertise to develop their own models. [ABSTRACT FROM AUTHOR]

Deep neural networks have been used extensively for diverse visual tasks, including object detection, face recognition, and image classification. However, they face several security threats, such as adversarial attacks. To improve the resistance of neural networks to adversarial attacks, researchers have investigated the security issues of models from the perspectives of both attacks and defenses. Recently, the transferability of adversarial attacks has received extensive attention, which promotes the application of adversarial attacks in practical scenarios. However, existing transferable attacks tend to trap into a poor local optimum and significantly degrade the transferability because the production of adversarial samples lacks randomness. Therefore, we propose a self-ensemble-based feature-level adversarial attack (SEFA) to boost transferability by randomly disrupting salient features. We provide theoretical analysis to demonstrate the superiority of the proposed method. In particular, perturbing the refined feature importance weighted intermediate features suppresses positive features and encourages negative features to realize adversarial attacks. Subsequently, self-ensemble is introduced to solve the optimization problem, thus enhancing the diversity from an optimization perspective. The diverse orthogonal initial perturbations disrupt these features stochastically, searching the space of transferable perturbations exhaustively to avoid poor local optima and improve transferability effectively. Extensive experiments show the effectiveness and superiority of the proposed SEFA, i.e., the success rates against undefended models and defense models are improved by 7.7 % and 13.4 % , respectively, compared with existing transferable attacks. Our code is available at https://github.com/chengshuyan/SEFA. [ABSTRACT FROM AUTHOR]

Introduction: Although behavioural interventions have been found to help control type 2 diabetes (T2D), it is important to understand how the delivery context can influence implementation and outcomes. The NHS committed to testing a low‐calorie diet (LCD) programme designed to support people living with excess weight and T2D to lose weight and improve diabetes outcomes. Understanding what influenced implementation during the programme pilot is important in optimising rollout. This study explored the transferability of the NHS LCD Programme prior to wider adoption. Methods: Twenty‐five interviews were undertaken with stakeholders involved in implementing the LCD programme in pilot sites (health service leads, referring health professionals and programme deliverers). Interviews with programme participants (people living with T2D) were undertaken within a larger programme of work, exploring what worked, for whom and why, which is reported separately. The conceptual Population–Intervention–Environment–Transfer Model of Transferability (PIET‐T) guided study design and data collection. Constructs of the model were also used as a deductive coding frame during data analysis. Key themes were identified which informed recommendations to optimise programme transfer. Results: Population: Referral strategies in some areas lacked consideration of population characteristics. Many believed that offering a choice of delivery model would promote acceptability and accessibility of the eligible population. Intervention: Overall, stakeholders had confidence in the LCD programme due to the robust evidence base along with anecdotal evidence, but some felt the complex referral process hindered engagement from GP practices. Environment: Stakeholders described barriers to accessing the programme, including language and learning difficulties. Transferability: Multidisciplinary working and effective communication supported successful implementation. Conclusion: Referral strategies to reach underrepresented groups should be considered during programme transfer, along with timely data from service providers on access and programme benefits. A choice of delivery models may optimise uptake. Knowledge sharing between sites on good working practices is encouraged, including increasing engagement with key stakeholders. [ABSTRACT FROM AUTHOR]

This work is part of a program for the conservation and enhancement of Tunisian genetic resources of orchardgrass (Dactylis glomerata L.). This species is of great interest, especially from an agronomic point of view. However, little information is available regarding agronomic characterization and genetic variation in Tunisian orchardgrass. This study aims to evaluate the genetic diversity of nine natural populations of orchardgrass collected in the north of Tunisia through the analysis of 16 morpho-phenological traits and 14 simple sequence repeat (SSR) markers developed from different grass species. Our results showed that the analysis of variance and multivariate analyses of quantitative parameters revealed a significant morphological and phenological variation within and among the populations mainly relating to the precocity and vigor of the plants. Moreover, the population structure was independent from the geographic origin and bioclimatic stage. At the molecular level, the 14 selected SSR markers are highly transferable and exhibited amplification in Dactylis glomerata. An average of 5.27 alleles with a polymorphism information content (PIC) of 0.69 per locus set was detected among the populations studied. The average polymorphic rate for this species was 86.08%, suggesting a high degree of genetic diversity. A high level of genetic diversity (Gst = 65.49%) was observed among the populations. Bayesian clustering based on SSR data clearly segregated populations into two groups. The results of this study will be useful to identify suitable populations that could be used in breeding programs for the improvement of Tunisian orchardgrass. [ABSTRACT FROM AUTHOR]

AbstractIn this article, we study the transfer learning problem in functional classification, aiming to improve the classification accuracy of the target data by leveraging information from related source datasets. To facilitate transfer learning, we propose a novel transferability function tailored for classification problems, enabling a more accurate evaluation of the similarity between source and target dataset distributions. Interestingly, we find that a source dataset can offer more substantial benefits under certain conditions than another dataset with an identical distribution to the target dataset. This observation renders the commonly-used debiasing step in the parameter-based transfer learning algorithm unnecessary under some circumstances to the classification problem. In particular, we propose two adaptive transfer learning algorithms based on the functional Distance Weighted Discrimination (DWD) classifier for scenarios with and without prior knowledge regarding informative sources. Furthermore, we establish the upper bound on the excess risk of the proposed classifiers, providing the statistical gain via transfer learning mathematically provable. Simulation studies are conducted to thoroughly examine the finite-sample performance of the proposed algorithms. Finally, we implement the proposed method to Beijing air-quality data, and significantly improve the prediction of the PM 2.5 level of a target station by effectively incorporating information from source datasets. Supplementary materials for this article are available online, including a standardized description of the materials available for reproducing the work. [ABSTRACT FROM AUTHOR]

Innovative initiatives emerge in line with the recommendations of the United Nations Convention on the Rights of Persons with Disabilities. They are often place-based, context-dependent, and are not easily adapted for use in other contexts. It raises the question of their transferability. This concept has been studied in the field of public health. To explore the conditions surrounding the transfer of disability interventions, this study aims to determine the advances related to the transferability of complex interventions in public health. A review was conducted. Data were analyzed according to the concepts and terms used to describe the terminology related to transferability and the processes used to manage, assess, and report transferability. Fourteen papers fulfilled the inclusion criteria. The analysis shows that different terms and concepts are used. Numerous tools or frameworks have been developed to structure the identification of transferability factors or adaptations and usually require the involvement of stakeholders. Considering context is central. Finally, we identified a lack of reporting. This review provides a structured and operational framework for various concepts, including transferability as a form of knowledge generation, and implementation/adaptation as proactive actions. It emphasizes that a holistic approach to assessing transferability involves shifting the focus from transferability factors to understanding mechanisms of change and their interactions with the context. The review highlights the pivotal role of stakeholders in generating knowledge, capturing diverse contexts, and prioritizing information. Ultimately, this work will serve as a valuable foundation for guiding methodological developments on transferability in the field of disability. [ABSTRACT FROM AUTHOR]

Sport and physical activity is often utilized as a tool for engagement within interventions designed to support wider social and personal change for marginalized young people. The implicit discourse that underpins such interventions is the assumed transference of skills, qualities, and attributes acquired and developed through sport to broader societal contexts. However, there is a scarcity of studies that have critically examined this relationship. By way of correction, the purpose of this article is to examine the concept of transferability and explore how sport-based interventions might enable marginalized young people to thrive in other life domains. More precisely, the article calls for a rethink on what skills, attributes, and qualities might need to be transferred from sport-based interventions, while also outlining suggestions for how transfer might be facilitated. As a context for this discussion, the article draws upon empirical insights derived from a study of a youth-focused, golf-based intervention delivered in the south–west of England. Specifically, the article examines how providing opportunities for its youth participants to accumulate various forms of capital (rather than specific skills or qualifications) supported transfer, in combination with a pedagogical approach that resonated with notions of critical pedagogy. [ABSTRACT FROM AUTHOR]

Low temperatures and icing in winter are significant factors that severely affect highway safety and traffic mobility. To enhance the precision and reliability of real-time winter road surface temperature (RST) prediction, a short-term prediction model is developed that harnesses both feature selection and deep learning. Leveraging meteorological data from a mountain highway in Yunnan, China, the key environmental variables affecting road surface temperature were first extracted using a random forest (RF) model for feature selection. These features were then combined with RST data to construct multiple groups of input variable combinations for the prediction model. A short-term prediction model with a 10-minute update frequency was built using a long short-term memory neural network (LSTM), namely RF-LSTM. The best input variable combination and preset parameters for the prediction model were determined through comparative testing with prevalent machine learning models, and the transferability of the prediction model was verified. The results showed that the best input variable combination for the RF-LSTM prediction model was road surface temperature and air temperature. The model recognised that the short-term RST was affected by long and short-term memory characteristics within a two-hour timeframe. When compared to the RF model, backpropagation (BP) neural network model and the standard LSTM model, the proposed model reduces prediction errors by 59.15%, 31.10% and 20.26%, respectively, while the prediction accuracy is 99.13% within an error margin of ±0.5℃. On the verification dataset, the proposed model maintains its time transferability with an average prediction absolute error of 0.0478. In all, the proposed model not only achieves a higher level of precision in real-time RST predictions but also ensures a more consistent and reliable performance under the challenging conditions of high altitude and mountainous terrain, offering enhanced support for traffic safety and road maintenance decision-making.

Much has been written about the necessity for graduates to be aware of their skill set and transferability for the workplace. Degree programs in Scotland have long relied on guidance from the Quality Assurance Agency (QAA) on the taxonomy or wording of level learning outcomes (LLOs), which are the building blocks of degrees. More recently, a meta-skills framework created by Skills Development Scotland (SDS) offers clarity around meta-skills and suggests relevant wording, but these do not always align with academic taxonomies. The current research sought to explore the relationship between LLOs and meta-skills further from an academic and student perspective. A qualitative approach consisting of staff interviews and student focus groups from a range of creative business courses was adopted. A thematic analysis revealed gaps in staff and student understanding of LLOs and meta-skill terminology. The findings support the argument that skills should be linked more obviously to modular learning and recommendations are made as to how these could be communicated effectively to aid understanding around the transferability of university-acquired skills to the workplace.

Sport and physical activity is often utilized as a tool for engagement within interventions designed to support wider social and personal change for marginalized young people. The implicit discourse that underpins such interventions is the assumed transference of skills, qualities, and attributes acquired and developed through sport to broader societal contexts. However, there is a scarcity of studies that have critically examined this relationship. By way of correction, the purpose of this article is to examine the concept of transferability and explore how sport-based interventions might enable marginalized young people to thrive in other life domains. More precisely, the article calls for a rethink on what skills, attributes, and qualities might need to be transferred from sport-based interventions, while also outlining suggestions for how transfer might be facilitated. As a context for this discussion, the article draws upon empirical insights derived from a study of a youth-focused, golf-based intervention delivered in the south–west of England. Specifically, the article examines how providing opportunities for its youth participants to accumulate various forms of capital (rather than specific skills or qualifications) supported transfer, in combination with a pedagogical approach that resonated with notions of critical pedagogy.

Innovative initiatives emerge in line with the recommendations of the United Nations Convention on the Rights of Persons with Disabilities. They are often place-based, context-dependent, and are not easily adapted for use in other contexts. It raises the question of their transferability. This concept has been studied in the field of public health. To explore the conditions surrounding the transfer of disability interventions, this study aims to determine the advances related to the transferability of complex interventions in public health. A review was conducted. Data were analyzed according to the concepts and terms used to describe the terminology related to transferability and the processes used to manage, assess, and report transferability. Fourteen papers fulfilled the inclusion criteria. The analysis shows that different terms and concepts are used. Numerous tools or frameworks have been developed to structure the identification of transferability factors or adaptations and usually require the involvement of stakeholders. Considering context is central. Finally, we identified a lack of reporting. This review provides a structured and operational framework for various concepts, including transferability as a form of knowledge generation, and implementation/adaptation as proactive actions. It emphasizes that a holistic approach to assessing transferability involves shifting the focus from transferability factors to understanding mechanisms of change and their interactions with the context. The review highlights the pivotal role of stakeholders in generating knowledge, capturing diverse contexts, and prioritizing information. Ultimately, this work will serve as a valuable foundation for guiding methodological developments on transferability in the field of disability.

Deep learning plays a significant role in developing a robust and constructive framework for tackling complex learning tasks. Consequently, it is widely utilized in many security-critical contexts, such as Self-Driving and Biometric Systems. Due to their complex structure, Deep Neural Networks (DNN) are vulnerable to adversarial attacks. Adversaries can deploy attacks at training or testing time and can cause significant security risks in safety–critical applications. Therefore, it is essential to comprehend adversarial attacks, their crafting methods, and different defending strategies. Moreover, finding effective defenses to malicious attacks that can promote robustness and provide additional security in deep learning models is critical. Therefore, there is a need to analyze the different challenges concerning deep learning models' robustness. The proposed work aims to present a systematic review of primary studies that focuses on providing an efficient and robust framework against adversarial attacks. This work used a standard SLR (Systematic Literature Review) method to review the studies from different digital libraries. In the next step, this work designed and answered several research questions thoroughly. The study classified several defensive strategies and discussed the major conflicting factors that can enhance robustness and efficiency. Moreover, the impact of adversarial attacks and their perturbation metrics are also analyzed for different defensive approaches. The findings of this study assist researchers and practitioners in choosing an appropriate defensive strategy by incorporating the considerations of varying research issues and recommendations. Finally, relying upon reviewed studies, this work found future directions for researchers to design robust and innovative solutions against adversarial attacks. [ABSTRACT FROM AUTHOR]

Adversarial attacks pose a significant threat to real-world applications based on deep neural networks (DNNs), especially in security-critical applications. Research has shown that adversarial examples (AEs) generated on a surrogate model can also succeed on a target model, which is known as transferability. Feature-level transfer-based attacks improve the transferability of AEs by disrupting intermediate features. They target the intermediate layer of the model and use feature importance metrics to find these features. However, current methods overfit feature importance metrics to surrogate models, which results in poor sharing of the importance metrics across models and insufficient destruction of deep features. This work demonstrates the trade-off between feature importance metrics and feature corruption generalization, and categorizes feature destructive causes of misclassification. This work proposes a generative framework named PTNAA to guide the destruction of deep features across models, thus improving the transferability of AEs. Specifically, the method introduces path methods into integrated gradients. It selects path functions using only a priori knowledge and approximates neuron attribution using nonuniform sampling. In addition, it measures neurons based on the attribution results and performs feature-level attacks to remove inherent features of the image. Extensive experiments demonstrate the effectiveness of the proposed method. The code is available at https://github.com/lounwb/PTNAA. [ABSTRACT FROM AUTHOR]

Abstract A variety of complex socioeconomic phenomena, for example, migration, commuting, and trade can be abstracted by spatial interaction networks, where nodes represent geographic locations and weighted edges convey the interaction and its strength. However, obtaining fine-grained spatial interaction data is very challenging in practice due to limitations in collection methods and costs, so spatial interaction data such as transportation data and trade data are often only available at a coarse scale. Here, we propose a gravity downscaling (GD) method based on readily accessible socioeconomic data and the gravity law to infer fine-grained interactions from coarse-grained data. GD assumes that interactions of different spatial scales are governed by the similar gravity law and thus can transfer the parameters estimated from coarse-grained regions to fine-grained regions. Results show that GD has an average improvement of 24.6% in Mean Absolute Percentage Error over alternative downscaling methods (i.e., the areal-weighted method and machine learning models) across datasets with different spatial scales and in various regions. Using simple assumptions, GD enables accurate downscaling of spatial interactions, making it applicable to a wide range of fields, including human mobility, transportation, and trade.

Abstract To eliminate malaria, all populations must be included. For those who are not reached by the health care system, specific interventions must be tailor-made. An innovative Malakit strategy, based on the distribution of self-diagnosis and self-treatment kits, has been evaluated in the Suriname-French Guiana- Amapá (Brazil) region. The results showed effectiveness and good acceptability. The Malakit intervention is complex and has many components. Its transferability requires adaptation to other populations and regions, while retaining the main features of the intervention. This article provides the keys to adapting, implementing and evaluating it in other contexts facing residual malaria in hard-to-reach and/or mobile populations. The process of transferring this intervention includes: diagnosis of the situation (malaria epidemiology, characteristics of the population affected) to define the relevance of the strategy; determination of the stakeholders and the framework of the intervention (research project or public health intervention); adaptation modalities (adaptation of the kit, training, distribution strategy); the role of community health workers and their need for training and supervision. Finally, evaluation needs are specified in relation to prospects for geographical or temporal extension. Malaria elimination is likely to increasingly involve marginalized people due to climate change and displacement of populations. Evaluation of the transferability and effectiveness of the Malakit strategy in new contexts will be essential to increase and refine the evidence of its value, and to decide whether it could be an additional tool in the arsenal recommended in future WHO guidelines.

Writing is a challenging task for students in language learning. A key question in this challenge is how to exploit the potential of information technology and design effective learning strategies to promote quality writing. This is a question that Chinese teachers need to actively consider in the process of optimizing their writing instruction. Therefore, this study embedded problem-based scaffolds in an SVVR system and proposed a second-order progressive problem-based scaffold (SPPS-SVVR) strategy to enhance students' writing skills. To examine the effectiveness of the proposed strategy, a quasi-experiment was conducted in an elementary school in China. The experimental group (39 students) used the SPPS-SVVR writing strategy, while the control group (39 students) used the traditional SVVR writing strategy (T-SVVR). The study results showed that the SPPS-SVVR writing strategy not only significantly improved the students' writing performance, but also increased their learning engagement and transferability. In addition, the results of epistemic network structure analysis showed that students using the SPPS-SVVR writing strategy focused on writing in terms of internal, mental, and dynamic environments. Interviews revealed that the SPPS-SVVR writing strategy supported the experimental group students' grasp of writing ideas and verbal expressions, and they were more satisfied with this strategy. [ABSTRACT FROM AUTHOR]

Wireless Sensor Networks (WSNs) play a vital role in various applications, necessitating robust network security to protect sensitive data. Intrusion Detection Systems (IDSs) are crucial for preserving the integrity, availability, and confidentiality of WSNs by detecting and countering potential attacks. Despite significant research efforts, the existing IDS solutions still suffer from challenges related to detection accuracy and false alarms. To address these challenges, in this paper, we propose a Bayesian optimization-based Deep Learning (DL) model. However, the proposed optimized DL model, while showing promising results in enhancing security, encounters challenges such as data dependency, computational complexity, and the potential for overfitting. In the literature, researchers have employed Reinforcement Learning (RL) to address these issues. However, it also introduces its own concerns, including exploration, reward design, and prolonged training times. Consequently, to address these challenges, this paper proposes an Innovative Integrated RL-based Advanced DL Algorithm (IRADA) for attack detection in WSNs. IRADA leverages the convergence of DL and RL models to achieve superior intrusion detection performance. The performance analysis of IRADA reveals impressive results, including accuracy (99.50%), specificity (99.94%), sensitivity (99.48%), F1-Score (98.26%), Kappa statistics (99.42%), and area under the curve (99.38%). Additionally, we analyze IRADA's robustness against adversarial attacks, ensuring its applicability in real-world security scenarios. [ABSTRACT FROM AUTHOR]

Recently, there has been increasing concern about the vulnerability of deep neural network (DNN)-based synthetic aperture radar (SAR) automatic target recognition (ATR) to adversarial attacks, where a DNN could be easily deceived by clean input with imperceptible but aggressive perturbations. This paper studies the synthetic-to-measured (S2M) transfer setting, where an attacker generates adversarial perturbation based solely on synthetic data and transfers it against victim models trained with measured data. Compared with the current measured-to-measured (M2M) transfer setting, our approach does not need direct access to the victim model or the measured SAR data. We also propose the transferability estimation attack (TEA) to uncover the adversarial risks in this more challenging and practical scenario. The TEA makes full use of the limited similarity between the synthetic and measured data pairs for blind estimation and optimization of S2M transferability, leading to feasible surrogate model enhancement without mastering the victim model and data. Comprehensive evaluations based on the publicly available synthetic and measured paired labeled experiment (SAMPLE) dataset demonstrate that the TEA outperforms state-of-the-art methods and can significantly enhance various attack algorithms in computer vision and remote sensing applications. Codes and data are available at https://github.com/scenarri/S2M-TEA. [ABSTRACT FROM AUTHOR]

Context: One of the crucial issues related to machine learning potentials is the formation of representative dataset. For multicomponent systems, it is a general methodology to scan the composition range with a certain step. However, there is a lack of information on the compositional transferability of machine learning potentials. In this paper, we extend the knowledge in this area by studying the transferability of deep learning potential over the range of compositions of LiCl–KCl molten mixtures. The training dataset was formed using only the near-eutectic composition of 60% LiCl–40% KCl. Then, we tested the ability of the model to predict physicochemical properties of the melts far from the reference composition. It was found that for the composition range from 0 to 100% of LiCl, the calculated properties concur closely with those of other studies and ab initio calculations. Therefore, the model shows prominent non-intuitive compositional transferability. Moreover, the solid states and solid–liquid coexistence were reproduced. The calculated melting temperatures of LiCl and KCl show the errors of 6.6% and 0.4%, respectively. We argue that such good transferability stems from the local structure configurations that are typical both for pure LiCl and for pure KCl which are implicitly presented in the training dataset because of local fluctuations in composition. Methods: To collect the data for the initial dataset, density functional theory was employed. Then, the DeePMD package was used to train a neural network potential. To calculate the properties of the melts, standard equilibrium and non-equilibrium molecular dynamic approaches were utilized. [ABSTRACT FROM AUTHOR]

Relying on wide receptive fields, Vision Transformers (ViTs) are more robust than Convolutional Neural Networks (CNNs). Consequently, some transfer-based attack methods that perform well on CNNs perform poorly when attacking ViTs. To address the aforementioned issues, we propose dual-stage attack framework named DSA. More specifically, we introduce a dual spatial optimization strategy involving both decision space and feature space optimization to improve the transferability of adversarial examples across different ViTs. Adversarial perturbations are generated by our proposed semi self-integrated module in the first stage and optimized by the feature extractor in the second stage. During this process, our proposed integrated model makes full use of the discriminative information in the deep transformer blocks and achieves significant improvements in transferability. To further enhance the transferability, we design the random perturbation masking module to alleviate the over-fitting of adversarial examples to the surrogate model. We evaluate the transferability of attacks on state-of-the-art ViTs, CNNs, and robustly trained CNNs. Extensive experiments demonstrate that the proposed dual-stage attack can greatly boost transferability between ViTs and from ViTs to CNNs. [ABSTRACT FROM AUTHOR]

Forest fires result in significant damage, including the loss of critical ecosystems and individuals that depend on forests. Remote sensing provides efficient and reliable information for forest fire detection on various scales. The purposes of this study were to produce burned-area maps and to identify the applicability of transfer learning. We produced a burned-area (BA) maps using single post-fire PlanetScope images and a deep learning (DL)-based algorithm for three cases in the Republic of Korea and Greece. Publicly accessible Copernicus Emergency Management Service and land cover maps were used as reference data for classification and validation. The DL model was trained using six schemes, including three vegetation indicators, and the data were split into training, evaluation, and validation sets based on a specified ratio. In addition, the model was applied to another site and assessed for transferability. The performance of the model was assessed using its overall accuracy. The U-Net model used in this study produced an F1-score of 0.964–0.965 and an intersection-over-union score of 0.938–0.942 for BAs. When compared with other satellite images, unburned and non-forested areas were accurately identified using PlanetScope imagery with a spatial resolution of approximately 3 m. The structure and seasonality of the vegetation in each target area were also more accurately reflected because of the higher resolution, potentially lowering the transferability. These results indicate the possibility of efficiently identifying Bas using a method based on DL with single satellite images. [ABSTRACT FROM AUTHOR]

Recent research has revealed that the deep neural network (DNN)-based synthetic-aperture radar (SAR) automatic target recognition (ATR) techniques are vulnerable to adversarial examples, which poses significant security risks for their deployment in real-world systems. At the same time, the adversarial examples often exhibit transferability across DNN models, whereby when they are generated on the surrogate model they can also attack other target models. As the significant property in black-box scenarios, transferability has been enhanced by various methods, among which input transformations have demonstrated excellent effectiveness. However, we find that existing transformations suffer from limited enhancement of transferability due to the unique imaging mechanism and scattering characteristics of SAR images. To overcome this issue, we propose a novel method called intra-class transformations and inter-class nonlinear fusion attack (ITINFA). It enhances transferability from two perspectives: intra-class single image transformations and inter-class multiple images fusion. The intra-class transformations module utilizes a series of diverse transformations that align with the intrinsic characteristics of SAR images to obtain a more stable gradient update direction and prevent the adversarial examples from overfitting the surrogate model. The inter-class fusion strategy incorporates the information from other categories in a nonlinear manner, effectively enhances the feature fusion effect, and guides the misclassification of adversarial examples. Extensive experiments on the MSTAR dataset and SEN1-2 dataset demonstrate that ITINFA exhibits significantly better transferability than the existing transfer-based methods, with the average transfer attack success rate increases exceeding 8% for single models and over 4% for ensemble models. [ABSTRACT FROM AUTHOR]

Image classification models based on deep neural networks are vulnerable to adversarial examples. Existing studies have shown that white-box attacks have been able to achieve a high attack success rate, but the transferability of adversarial examples is low when attacking other models. In order to improve the transferability of adversarial attacks, this paper proposes a gradient aggregation method to enhance the transferability of adversarial examples. Firstly, the original image is mixed with other class images in a specific ratio to obtain a mixed image. By comprehensively considering the information of different categories of images and balancing the gradient contributions between categories, the influence of local oscillations can be avoided. Secondly, in the iterative process, the gradient information of other data points in the neighborhood of the current point is aggregated to optimize the gradient direction, avoiding excessive dependence on a single data point, and thus generating adversarial examples with stronger mobility. Experimental results on the ImageNet dataset show that the proposed method significantly improves the success rate of black-box attacks and the transferability of adversarial examples. On the single-model attack, the average attack success rate of the method in this paper is 88.5% in the four conventional training models, which is 2.7 percentage points higher than the Admix method; the average attack success rate on the integrated model attack reaches 92.7%. In addition, the proposed method can be integrated with the transformation-based adversarial attack method, and the average attack success rate on the three adversarial training models is 10.1 percentage points, higher than that of the Admix method, which enhances the transferability of adversarial attacks. [ABSTRACT FROM AUTHOR]

A variety of complex socioeconomic phenomena, for example, migration, commuting, and trade can be abstracted by spatial interaction networks, where nodes represent geographic locations and weighted edges convey the interaction and its strength. However, obtaining fine-grained spatial interaction data is very challenging in practice due to limitations in collection methods and costs, so spatial interaction data such as transportation data and trade data are often only available at a coarse scale. Here, we propose a gravity downscaling (GD) method based on readily accessible socioeconomic data and the gravity law to infer fine-grained interactions from coarse-grained data. GD assumes that interactions of different spatial scales are governed by the similar gravity law and thus can transfer the parameters estimated from coarse-grained regions to fine-grained regions. Results show that GD has an average improvement of 24.6% in Mean Absolute Percentage Error over alternative downscaling methods (i.e., the areal-weighted method and machine learning models) across datasets with different spatial scales and in various regions. Using simple assumptions, GD enables accurate downscaling of spatial interactions, making it applicable to a wide range of fields, including human mobility, transportation, and trade. [ABSTRACT FROM AUTHOR]

This study aimed to investigate the effects of Storytelling Narrated Videos (SNV) on students' knowledge retention and transferability. A total of 56 students from a university in Indonesia were randomly assigned to a quasi-experimental research design exposed to SNV and to Lecture Narrated Videos (LNV). Two videos were created to deliver content on Bloom's Taxonomy, one using a lecture-style format and the other adopting a storytelling approach. Data were collected through tests, questionnaires, and essays. The findings revealed that participants exposed to SNV had higher retention memory scores, indicating a positive impact on knowledge retention compared to those who watched LNV. Moreover, the storytelling videos facilitated cognitive skill progression, enhanced understanding through engaging visuals, and fostered a strong connection with a familiar narrator, resulting in a more dynamic and memorable learning experience. The study also examined knowledge transfer and found that participants who watched the storytelling videos performed better in applying Bloom's Taxonomy concepts to planning teaching objectives in the essay test. This suggests that the incorporation of storytelling narration and promoting transfer knowledge activities can enhance students' understanding, retention, and practical application of the learned material. Overall, the findings highlight the potential of incorporating storytelling in narrated videos to improve students' knowledge retention, transferability, and engagement in educational settings. Plain language summary: The impact of digital storytelling on students' learning and knowledge transfer This research aimed to explore how using Storytelling Narrated Videos (SNV) affects students' memory and ability to apply what they've learned. The study involved 56 students from an Indonesian university who were randomly assigned to either watch SNV or Lecture Narrated Videos (LNV). Two different videos were created to teach about Bloom's Taxonomy—one presented information in a traditional lecture style, while the other used storytelling. Data were collected through tests, questionnaires, and essays. Results showed that students who watched SNV had better memory scores, suggesting that storytelling videos helped them remember information better compared to those who watched LNV. Additionally, storytelling videos helped students improve their thinking skills, made the content more understandable with engaging visuals, and created a stronger connection with the narrator, resulting in a more interesting and memorable learning experience. The study also looked at whether students could use what they learned in practical situations, and found that those who watched storytelling videos performed better in applying Bloom's Taxonomy concepts in the essay test. This indicates that using storytelling in videos and encouraging students to apply what they learn can improve their understanding, memory, and ability to use the information in real-life scenarios. [ABSTRACT FROM AUTHOR]

Summary: Leaf traits are essential for understanding many physiological and ecological processes. Partial least squares regression (PLSR) models with leaf spectroscopy are widely applied for trait estimation, but their transferability across space, time, and plant functional types (PFTs) remains unclear.We compiled a novel dataset of paired leaf traits and spectra, with 47 393 records for > 700 species and eight PFTs at 101 globally distributed locations across multiple seasons. Using this dataset, we conducted an unprecedented comprehensive analysis to assess the transferability of PLSR models in estimating leaf traits.While PLSR models demonstrate commendable performance in predicting chlorophyll content, carotenoid, leaf water, and leaf mass per area prediction within their training data space, their efficacy diminishes when extrapolating to new contexts. Specifically, extrapolating to locations, seasons, and PFTs beyond the training data leads to reduced R2 (0.12–0.49, 0.15–0.42, and 0.25–0.56) and increased NRMSE (3.58–18.24%, 6.27–11.55%, and 7.0–33.12%) compared with nonspatial random cross‐validation. The results underscore the importance of incorporating greater spectral diversity in model training to boost its transferability.These findings highlight potential errors in estimating leaf traits across large spatial domains, diverse PFTs, and time due to biased validation schemes, and provide guidance for future field sampling strategies and remote sensing applications. [ABSTRACT FROM AUTHOR]

Recent works have demonstrated the great performance of forgery image forensics based on deep learning, but there is still a risk that detectors could be susceptible to unknown illegal attacks, raising growing security concerns. This paper starts from the perspective of reverse forensics and explores the vulnerabilities of current image manipulation detectors to achieve targeted attacks. We present a novel reverse decision aggregate gradient attack under low-frequency constraints (RevAggAL). Specifically, we first propose a novel pixel reverse content decision-making (PRevCDm) loss to optimize perturbation generation with a specific principle more suitable for segmenting manipulated regions. Then, we introduce the low-frequency component to constrain the perturbation into more imperceptible details, significantly avoiding the degradation of image quality. We also consider aggregating gradients on model-agnostic features to enhance the transferability of adversarial examples in black-box scenarios. We evaluate the effectiveness of our method on three representative detectors (ResFCN, MVSSNet, and OSN) with five widely used forgery datasets (COVERAGE, COLUMBIA, CASIA1, NIST 2016, and Realistic Tampering). Experimental results show that our method improves the attack success rate (ASR) while ensuring better image quality. [ABSTRACT FROM AUTHOR]

To eliminate malaria, all populations must be included. For those who are not reached by the health care system, specific interventions must be tailor-made. An innovative Malakit strategy, based on the distribution of self-diagnosis and self-treatment kits, has been evaluated in the Suriname-French Guiana- Amapá (Brazil) region. The results showed effectiveness and good acceptability. The Malakit intervention is complex and has many components. Its transferability requires adaptation to other populations and regions, while retaining the main features of the intervention. This article provides the keys to adapting, implementing and evaluating it in other contexts facing residual malaria in hard-to-reach and/or mobile populations. The process of transferring this intervention includes: diagnosis of the situation (malaria epidemiology, characteristics of the population affected) to define the relevance of the strategy; determination of the stakeholders and the framework of the intervention (research project or public health intervention); adaptation modalities (adaptation of the kit, training, distribution strategy); the role of community health workers and their need for training and supervision. Finally, evaluation needs are specified in relation to prospects for geographical or temporal extension. Malaria elimination is likely to increasingly involve marginalized people due to climate change and displacement of populations. Evaluation of the transferability and effectiveness of the Malakit strategy in new contexts will be essential to increase and refine the evidence of its value, and to decide whether it could be an additional tool in the arsenal recommended in future WHO guidelines. [ABSTRACT FROM AUTHOR]

Speaker recognition system (SRS) serves as the gatekeeper for secure access, using the unique vocal characteristics of individuals for identification and verification. SRS can be found several biometric security applications such as in banks, autonomous cars, military, and smart devices. However, as technology advances, so do the threats to these models. With the rise of adversarial attacks, these models have been put to the test. Adversarial machine learning (AML) techniques have been utilized to exploit vulnerabilities in SRS, threatening their reliability and security. In this study, we concentrate on transferability in AML within the realm of SRS. Transferability refers to the capability of adversarial examples generated for one model to outsmart another model. Our research centers on enhancing the transferability of adversarial attacks in SRS. Our innovative approach involves strategically skipping non-linear activation functions during the backpropagation process to achieve this goal. The proposed method yields promising results in enhancing the transferability of adversarial examples across diverse SRS architectures, parameters, features, and datasets. To validate the effectiveness of our proposed method, we conduct an evaluation using the state-of-the-art FoolHD attack, an attack designed specifically for exploiting SRS. By implementing our method in various scenarios, including cross-architecture, cross-parameter, cross-feature, and cross-dataset settings, we demonstrate its resilience and versatility. To evaluate the performance of the proposed method in improving transferability, we have introduced three novel metrics: enhanced transferability, relative transferability, and effort in enhancing transferability. Our experiments demonstrate a significant boost in the transferability of adversarial examples in SRS. This research contributes to the growing body of knowledge on AML for SRS and emphasizes the urgency of developing robust defenses to safeguard these critical biometric systems. [ABSTRACT FROM AUTHOR]

This paper describes how mixed methods can improve the value and policy relevance of impact evaluations, paying particular attention to how mixed methods can be used to address external validity and generalization issues. We briefly review the literature on the rationales for using mixed methods; provide documentation of the extent to which mixed methods have been used in impact evaluations in recent years; describe how we developed a list of recent impact evaluations using mixed methods and the process used to conduct full-text reviews of these articles; summarize the findings from our analysis of the articles; discuss three exemplars of using mixed methods in impact evaluations; and discuss how mixed methods have been used for studying and improving external validity and potential improvements that could be made in this area. We find that mixed methods are rarely used in impact evaluations, and we believe that increased use of mixed methods would be useful because they can reinforce findings from the quantitative analysis (triangulation), and they can also help us understand the mechanism by which programs have their impacts and the reasons why programs fail. [ABSTRACT FROM AUTHOR]

In a world marked by shifting climate patterns, a growing human population, and rising demand for ruminant-derived protein, producers face the need to implement strategies that enhance productivity, reduce greenhouse gas emissions (GHGs), promote adaptability, and improve the sustainability of milk and meat production while optimizing resource use. One promising strategy to address these challenges is the adoption of silvopastoral production systems, which combine livestock with trees and shrubs. These systems are widely used in Latin America due to their proven benefits in terms of production, reduced emission intensity, land utilization efficiency, and other ecosystem services. Transferring technology from one region to another necessitates adapting these techniques to suit the receiving environment. This review suggests that the successful silvopastoral systems employed in the Latin America context can be effectively introduced in Nigeria, offering potential advantages for livestock owners. The research encompassed in this review demonstrates that the utilization of silvopastoral systems in ruminant farming can contribute to achieving several sustainable development goals, including enhancing food security, increasing milk and meat yields, supporting conservation efforts, bolstering biodiversity, and reducing GHG emissions. At the level of individual farms, the adoption of silvopastoral systems (SPS) can enhance the stability and resilience of farmers' livelihoods, boost milk production, facilitate animal growth, and improve animal welfare. [ABSTRACT FROM AUTHOR]

The article "Downscaling investigations in Tree Physiology: mechanisms and context" published in Tree Physiology explores the methods used by tree physiologists to investigate the mechanisms driving biological phenomena. Through various studies, researchers have examined processes such as photosynthesis, carbon allocation, lignin deposition, and the production of anti-herbivory defenses in trees. The findings highlight the importance of context in understanding these mechanisms, as different species and environmental conditions can influence the outcomes of experiments. The research presented in the article demonstrates the progress being made in understanding tree physiology at different scales, from gene regulation to ecological implications. [Extracted from the article]

Implementation of different strategies on the demand and supply side to deal with potential water scarcity is based on a comparison of future water demand and availability of water resources based on different scenarios of climate change and population growth. Especially, the Alpine region is characterised by many small and medium water supply systems (WSSs) having neither human resources nor time for advanced planning, requiring simple methods for estimating future development. Therefore, the aim of this work is to provide future projections of water demand, resource availability, and drinking water quality for an Alpine area based on simple approaches with minimal data requirements. As the results of the case study show, linear and polynomial regression with precipitation and temperature data can illustrate the temporal variation of system input and drinking water temperature with sufficient accuracy and is suitable for an estimation of future development. The groundwater modelling, however, requires the consideration of a non-linear term depending on the depth to obtain reasonable results. Due to the usage of open-access data and the easy approaches developed and applied, a good transferability to other case studies is expected which can provide stakeholders a first assessment of the future need for action. HIGHLIGHTS Simple regression analyses are used for future projections for water resources.; Precipitation and temperature are utilised as input parameters.; Water demand increases by 25–125% due to climate change and population growth.; Increased availability of open-access data can help future planning.;

Objectives: This study aimed to delineate the ability of a plasmid, pS130–4, which harboured both hypervirulence and multidrug resistance genes, to disseminate within Klebsiella pneumoniae, as well as its potential formation mechanism. Methods: We employed whole-genome sequencing to decipher the genetic architecture of pS130–4. Its capability to conjugate and transfer was assessed through a series of experiments, including plasmid stability, competitive growth, and growth curve analysis. Its expression stability was further evaluated using drug sensitivity, larval survival, and biofilm formation tests. Results: pS130–4 contained four intact modules typical of self-transmissible plasmids. BLAST analysis revealed a sequence identity exceeding 90% with other plasmids from a variety of hosts, suggesting its broad prevalence. Our findings indicated the plasmid's formation resulted from IS26-mediated recombination, leading us to propose a model detailing the creation of this conjugative fusion plasmid housing both blaKPC-2 and hypervirulence genes. Our conjugation experiments established that pS130–4, when present in the clinical strain S130, was self-transmissible with an estimated efficiency between 10−5 and 10−4. Remarkably, pS130–4 showcased a 90% retention rate and did not impede the growth of host bacteria. Galleria mellonella larval infection assay demonstrated that S130 had pronounced toxicity when juxtaposed with high-virulence control strain NTUH-K2044 and low-toxicity control strain ATCC700603. Furthermore, pS130–4′s virulence remained intact postconjugation. Conclusion: A fusion plasmid, encompassing both hypervirulence and multidrug resistance genes, was viable within K. pneumoniae ST11-KL64 and incurred minimal fitness costs. These insights underscored the criticality of rigorous monitoring to pre-empt the escalation and distribution of this formidable super-plasmid.

Suspended particulate matter (SPM) in lakes exerts strong impact on light propagation, aquatic ecosystem productivity, which co-varies with nutrients, heavy metal and micro-pollutant in waters. In lakes, SPM exerts strong absorption and backscattering, ultimately affects water leaving signals that can be detected by satellite sensors. Simple regression models based on specific band or hand ratios have been widely used for SPM estimate in the past with moderate accuracy. There are still rooms for model accuracy improvements, and machine learning models may solve the non-linear relationships between spectral variable and SPM in waters. We assembled more than 16,400 in situ measured SPM in lakes from six continents (excluding the Antarctica continent), of which 9640 samples were matched with Landsat overpasses within ±7 days. Seven machine learning algorithms and two simple regression methods (linear and partial least squares models) were used to estimate SPM in lakes and the performance were compared. To overcome the problem of imbalance datasets in regression, a Synthetic Minority Over-Sampling technique for regression with Gaussian Noise (SMOGN) was adopted in this study. Through comparison, we found that gradient boosting decision tree (GBDT), random forest (RF), and extreme gradient boosting (XGBoost) models demonstrated good spatiotemporal transferability with SMOGN processed dataset, and has potential to map SPM at different year with good quality of Landsat land surface reflectance images. In all the tested modeling approaches, the GBDT model has accurate calibration (n = 6428, R2 = 0.95, MAPE = 29.8%) from SPM collected in 2235 lakes across the world, and the validation (n = 3214, R2 = 0.84, MAPE = 38.8%) also exhibited stable performance. Further, the good performances were also exhibited by RF model with calibration (R2 = 0.93) and validation (R2 = 0.86, MAPE = 24.2%) datasets. We applied GBDT and RF models to map SPM of typical lakes, and satisfactory result was obtained. In addition, the GBDT model was evaluated by historical SPM measurements coincident with different Landsat sensors (L5-TM, L7-ETM+, and L8-OLI), thus the model has the potential to map SPM of lakes for monitoring temporal variations, and tracks lake water SPM dynamics in approximately the past four decades (1984–2021) since Landsat-5/TM was launched in 1984.