Search

Federated Learning (FL), a burgeoning technology, has received increasing attention due to its privacy protection capability. However, the base algorithm FedAvg is vulnerable when it suffers from so-called backdoor attacks. Former researchers proposed several robust aggregation methods. Unfortunately, due to the hidden characteristic of backdoor attacks, many of these aggregation methods are unable to defend against backdoor attacks. What's more, the attackers recently have proposed some hiding methods that further improve backdoor attacks' stealthiness, making all the existing robust aggregation methods fail.To tackle the threat of backdoor attacks, we propose a new aggregation method, X-raying Models with A Matrix (XMAM), to reveal the malicious local model updates submitted by the backdoor attackers. Since we observe that the output of the Softmax layer exhibits distinguishable patterns between malicious and benign updates, unlike the existing aggregation algorithms, we focus on the Softmax layer's output in which the backdoor attackers are difficult to hide their malicious behavior. Specifically, like medical X-ray examinations, we investigate the collected local model updates by using a matrix as an input to get their Softmax layer's outputs. Then, we preclude updates whose outputs are abnormal by clustering. Without any training dataset in the server, the extensive evaluations show that our XMAM can effectively distinguish malicious local model updates from benign ones. For instance, when other methods fail to defend against the backdoor attacks at no more than 20% malicious clients, our method can tolerate 45% malicious clients in the black-box mode and about 30% in Projected Gradient Descent (PGD) mode. Besides, under adaptive attacks, the results demonstrate that XMAM can still complete the global model training task even when there are 40% malicious clients. Finally, we analyze our method's screening complexity and compare the real screening time with other methods. The results show that XMAM is about 10–10000 times faster than the existing methods.

Copyright of Duzce University Journal of Science & Technology is the property of Duzce University Journal of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This study addresses the issue of semantic similarity in sentences using the BERT model through various aggregation techniques, such as max-pooling, mean-pooling, and an LSTM network applied to the output of the BERT model. Subsequently, the linguistic interpretability of the BERT-Base transformer model is analyzed through the unsupervised learning approach, specifically through dimensionality reduction using autoencoders and clustering algorithms, utilizing the representation of the classification token CLS.The results highlight that the CLS classification token achieves better abstractions than the proposed methods. In terms of interpretability, it is observed that sequence length is relevant in the early layers, with a gradual decrease across the layers. Additionally, attention to semantic similarity is concentrated in the intermediate and upper layers, especially in layers 6, 8, 9, and 10. All these findings were obtained by addressing the semantic similarity task using the STS-Benchmark dataset. [ABSTRACT FROM AUTHOR]

Aggregation of species with similar ecological properties is one of the effective methods to simplify food web researches. However, species aggregation will affect not only the complexity of modeling process but also the accuracy of models' outputs. Selection of aggregation methods and the number of trophospecies are the keys to study the simplification of food web. In this study, three aggregation methods, including taxonomic aggregation (TA), structural equivalence aggregation (SEA), and self-organizing maps (SOM), were analyzed and compared with the linear inverse model–Markov Chain Monte Carlo (LIM-MCMC) model. Impacts of aggregation methods and trophospecies number on food webs were evaluated based on the robustness and unitless of ecological network indices. Results showed that aggregation method of SEA performed better than the other two methods in estimating food web structure and function indices. The effects of aggregation methods were driven by the differences in species aggregation principles, which will alter food web structure and function through the redistribution of energy flow. According to the results of mean absolute percentage error (MAPE) which can be applied to evaluate the accuracy of the model, we found that MAPE in food web indices will increase with the reducing trophospecies number, and MAPE in food web function indices were smaller and more stable than those in food web structure indices. Therefore, trade-off between simplifying food webs and reflecting the status of ecosystem should be considered in food web studies. These findings highlight the importance of aggregation methods and trophospecies number in the analysis of food web simplification. This study provided a framework to explore the extent to which food web models are affected by different species aggregation, and will provide scientific basis for the construction of food webs. [ABSTRACT FROM AUTHOR]

Agriculture is a basic activity of human survival and its sustainability is of the utmost importance. In this paper, we present a novel mathematical model for the assessment of agricultural sustainability, based on certain intuitive and fundamental postulates. The resulting mathematical framework generalizes most existing models. We then rank 148 countries according to their agricultural sustainability, using data from the period 1995 to 2022 and pinpoint those aspects with the highest potential of improving sustainability using sensitivity analysis. Our findings demonstrate that farming is mostly unsustainable worldwide. The most crucial factors are connected with bad water use, destruction of biodiversity, and the prevalence of conventional chemical farming. As expected, poor countries make the bottom of the sustainability list. Surprisingly, several advanced countries such as Belgium, Japan, the Netherlands and Norway also occupy the bottom of the list because of very high emissions and bad performance concerning land and biodiversity. Finally, the highest score worldwide is of the order of only 70% and the median 50%, which exhibit a rather unsatisfactory farming state of affairs. Such findings ought to guide immediate action to make agriculture more sustainable.

In this work we present a large-scale comparison of 21 learning and aggregation methods proposed in the ensemble learning, social choice theory (SCT), information fusion and uncertainty management (IF-UM) and collective intelligence (CI) fields, based on a large collection of 40 benchmark datasets. The results of this comparison show that Bagging-based approaches reported performances comparable with XGBoost, and significantly outperformed other Boosting methods. In particular, ExtraTree-based approaches were as accurate as both XGBoost and Decision Tree-based ones while also being more computationally efficient. We also show how standard Bagging-based and IF-UM-inspired approaches outperformed the approaches based on CI and SCT. IF-UM-inspired approaches, in particular, reported the best performance (together with standard ExtraTrees), as well as the strongest resistance to label noise (together with XGBoost). Based on our results, we provide useful indications on the practical effectiveness of different state-of-the-art ensemble and aggregation methods in general settings. • Large-scale comparison of fusion and aggregation methods in ensemble learning. • Uncertainty management methods had the best performance and noise robustness. • Extra-Trees were the most efficient and had excellent baseline performance. • XGBoost had excellent accuracy and robustness but was significantly less efficient. [ABSTRACT FROM AUTHOR]

Sustainable consumption and production strive for the rational management of natural resources, which implies a transition to the production of fewer goods with the greatest consumer value. Consequently, the consumer value assessment is a key task in the product and service design. However, a large number of applied practices for assessing consumer value is a challenge for researchers. Multiple heterogeneous solutions without a common classification and structure do not allow comparing methods with each other. Thus, there is a demand for some universal algorithm for assessing consumer value, which would be a model for the development of individual industry practices. Therefore, the present research aims to develop a universal algorithm for assessing consumer value, which is a unified sample. The work analyzes the current expertise in assessing consumer value. The paper provides a comparison of mathematical tools for aggregate indicators in order to develop a general formula for assessing consumer value. As a result, an algorithm for assessing consumer value has been developed, which includes the following stages: market segmentation by consumer groups, taking into account their personal characteristics and needs; product hierarchical division into groups according to indicators valuable to the consumer; selection of a scale for evaluating indicators; hierarchical convolution, calculation of the consumer value of selected indicators and their aggregation into a final assessment in accordance with coefficients obtained as a result of the initial data analysis. As part of the algorithm verification, an example of the implementation of the algorithm steps based on expert assessment of the tourist product characteristics is proposed. At the next stage of the study, a register of mathematical tools will be specified to ensure the implementation of the algorithm steps, and practical testing on real data on several products from different industries. [ABSTRACT FROM AUTHOR]

The reference point method (RPM) is based on the so-called augmented max-min aggregation where the worst individual achievement maximization process is additionally regularized with the average achievement. In order to avoid inconsistencies caused by the regularization, we replace it with the ordered weighted average (OWA) which combines all the individual achievements allocating the largest weight to the worst achievement, the second largest weight to the second worst achievement, and so on. Further following the concept of the weighted OWA (WOWA) we incorporate the importance weighting of several achievements into the RPM. Such a WOWA RPM approach uses importance weights to affect achievement importance by rescaling accordingly its measure within the distribution of achievements rather than by straightforward rescaling of achievement values. The recent progress in optimization methods for ordered averages allows us to implement the WOWA RPM quite effectively as extension of the original constraints and criteria with simple linear inequalities.

The problem of evaluation outcomes under several scenarios to form overall objective functions is of considerable importance in decision support under uncertainty. The fuzzy operator defined as the so-called weighted OWA (WOWA) aggregation offers a well-suited approach to this problem. The WOWA aggregation, similar to the classical ordered weighted averaging (OWA), uses the preferential weights assigned to the ordered values (i.e., to the worst value, the second worst and so on) rather than to the specific criteria. This allows one to model various preferences with respect to the risk. Simultaneously, importance weighting of scenarios can be introduced. In this paper we analyze solution procedures for optimization problems with the WOWA objective functions related to decisions under risk. Linear programming formulations are introduced for optimization of theWOWA objective representing risk averse preferences. Their computational efficiency is demonstrated.

Traditional machine learning projects have revolved around training the model with the help of previously observed data to be able to predict output for future unknown data. In the current scenario, when the data generated are huge, centralized training of the model becomes inefficient. Hence, distributed approach with client server model has to be used for training the models. This introduces data handling and critical data privacy issues. This paper concentrates on Federated learning (FL) which builds a model for the server by aggregating the parameters obtained from the local models of the client devices. The research work focuses on design and evaluation of three new FL algorithms against the average of the performances of the local models. The evolved approach considering weights of the local models proportional to accuracy of the local model is found to be the most accurate and better than the centralized approach. The evaluation is done using three different algorithms belonging to regression and classification on multiple datasets. It is observed that there is only one round of communication between the clients and server required in the federated learning setup to achieve the benchmarked accuracy set by the centralized setup. This is a considerable development and state-of-the-art approach to reduce communication and computation costs. [ABSTRACT FROM AUTHOR]

One of the problems in modern hydrology concerns the estimation of design events at sites with scarce or null data. This is a challenge for developing countries because they do not have monitoring networks as extensive and reliable as in developed nations. This situation has caused states in the Latin American and Caribbean region, in particular, to rely on hydrological regionalization techniques. These procedures implement clustering algorithms in combination with aggregation rules and metric distances to generate homogeneous groups from which hydrological information can be transferred. In addition, it has been proven that the analysis of spatial variables is sensitive to the magnitudes of extreme events; therefore, a mathematical formulation that adopts this fact into consideration must be included. For this purpose, the autocorrelation distance of the daily rainfall data series is proposed as an estimator of temporal variability. The fit parameters of the mixed Poisson-exponential probability distribution are operated as estimators of spatial variability. These spatio-temporal conditions are combined to obtain a mathematical relation of the autocorrelation as a measure of inertia for the classification of extreme events. This procedure is applied to Hydrologic Region 10 in northwestern Mexico from daily rainfall records. This zone has already been explored in terms of its regional homogeneity, which allows validating the results obtained. [ABSTRACT FROM AUTHOR]

Gaussian process regression is a flexible regression scheme but suffers from its high computational complexity regarding the inversion of a matrix with the same size as the training dataset. Aggregation method is one of the approximation techniques for reducing the complexity. In this paper, we propose a novel aggregation method, Nested Aggregation of Experts using Inducing Points (NAE-IP), which is an extension of a conventional method and enables dimensionality reduction by making use of the idea of linear sketching. There are some options for selecting inducing points in the proposed method. The options can introduce test points of interest as inducing points, albeit at the cost of slightly higher computational complexity. The other options exploiting less informative inducing points can yield a significant reduction of the computational complexity. The proposed NAE-IP is theoretically guaranteed to have consistency under certain conditions. Results of our computational experiments using synthetic and real data show that the proposed method achieves lower prediction error and even lower computing time than conventional methods. [ABSTRACT FROM AUTHOR]

One of the problems in modern hydrology concerns the estimation of design events at sites with scarce or null data. This is a challenge for developing countries because they do not have monitoring networks as extensive and reliable as in developed nations. This situation has caused states in the Latin American and Caribbean region, in particular, to rely on hydrological regionalization techniques. These procedures implement clustering algorithms in combination with aggregation rules and metric distances to generate homogeneous groups from which hydrological information can be transferred. In addition, it has been proven that the analysis of spatial variables is sensitive to the magnitudes of extreme events; therefore, a mathematical formulation that adopts this fact into consideration must be included. For this purpose, the autocorrelation distance of the daily rainfall data series is proposed as an estimator of temporal variability. The fit parameters of the mixed Poisson-exponential probability distribution are operated as estimators of spatial variability. These spatio-temporal conditions are combined to obtain a mathematical relation of the autocorrelation as a measure of inertia for the classification of extreme events. This procedure is applied to Hydrologic Region 10 in northwestern Mexico from daily rainfall records. This zone has already been explored in terms of its regional homogeneity, which allows validating the results obtained.

Composite indices of economic freedom may constitute a useful and practical guide and a significant source of information for experts in government policy, investors and market researchers across the world. Their high applicability and the important consequences of the relative position of the countries in a ranking of economic freedom, has led many practitioners and academic researchers to open a debate about some methodological aspects in the construction of these indices. In this paper, we will focus on the aggregation and normalization processes used to build the composite indicator, and we will make user of the data of the index of economic freedom published by the Heritage Foundation. In particular, we will propose a different more general and rich aggregation and normalization approach based on the Multiple Reference Point method. Rather than just providing a ranking, the resulting composite indicators will be able to show overall and particular strengths and weaknesses of the countries in terms of their economic freedom enriching therefore, the information provided by other indexes of economic freedom. Both, numerical scores and their correspondent graphical representation give the decision maker a full and detailed picture of the situation of the countries, informing in addition about the relative performance of the country with respect to other countries. [ABSTRACT FROM AUTHOR]

One of the most essential parts of every sentiment analysis application is the aggregation mechanism used to combine results obtained from a lower granularity level into an overall result. In this paper, the effects of the sentiment lexicon, aggregation level, and aggregation method on the sentiment polarity and rating classification of Persian reviews are investigated. To this aim, a new sentiment aggregation method based on the cross-ratio operator is proposed. The results on four Persian review data sets show that the review-level aggregation can improve rating classification, although this approach does not have a positive impact on polarity classification. [ABSTRACT FROM AUTHOR]

Various physical, chemical and biological variables are considered detrimental to the aquatic environment, especially if contained in excessive amounts. Such parameters originate from anthropogenic and natural sources. Though some might be essential in the aquatic ecosystem, they might pose a serious risk if present in excessive concentrations. Eventually, monitoring and assessing water resources becomes mandatory in order to trace the levels and effects of such physio-chemical and biological parameters. And the common practical method is through the application of water quality indices (WQIs). This prompts the need to further exploit the use of WQIs and continuously modify such important tools in order to become better, simpler and more appropriate toward water resource management needs; which needs are dynamic and forever changing. The current study focuses on developing a universal water quality model for South African river catchments. And as part of the study, this review work attempts to outline the objectives of establishing water quality monitoring tools, their classification and the basic procedure of developing WQIs. [ABSTRACT FROM AUTHOR]

Flooding is one of the most problematic natural events affecting urban areas. In this regard, developing flooding models plays a crucial role in reducing flood-induced losses and assists city managers to determine flooding-prone areas (FPAs). The aim of this study is to investigate on the prediction capability of fuzzy analytical hierarchy process (FAHP) and Mamdani fuzzy inference system (MFIS) methods as two completely and semi-knowledge-based models to identify FPAs in Tehran, Iran. Six flooding conditioning factors including density of channel, distance from channel, land use, elevation, slope, and water discharge were extracted from various geo-spatial datasets. A total of 62 flooding locations were identified in the study area based on the existing reports and field surveys. Of these, 44 (70%) floods were randomly selected as training data and the remaining 18 (30%) cases were used for the validation purposes. After the data preparation step, data were processed by means of two statistical (FAHP) and soft computing (MFIS) methods. Unlike most statistical and soft computing approaches which use flooding inventory data for both training and evaluation of models, only conditioning factor was involved in data processing and inventory data were used in the current study to assess models prediction accuracy. Also, the efficiency of two approaches was evaluated by pixel matching (PM) and area under curve to validate the prediction capability of models. The prediction rate for MFIS and FAHP was 89% and 84%, respectively. Moreover, according to the results obtained from PM, it was found out that about 90% of known flooding locations fell in high-risk areas, whereas it was 83% for FAHP, indicating that flooding susceptibility map of MFIS has higher performance. [ABSTRACT FROM AUTHOR]

Substantial progress has been made in assessing marine health in an integrative way. However, managers are still reluctant in undertaking such assessments, because: (i) lack of indicators; (ii) absence of targets; (iii) difficulty of aggregating indicators from different ecosystem components, habitats, and areas; (iv) absence of criteria on the number of indicators to be used; (v) discussion on the use of “one-out, all-out” (OOAO) principle in aggregating; and (vi) lack of traceability when integrating data. Our objective was, using open access databases with indicators across all the European seas with agreed targets, to demonstrate if the Nested Environmental status Assessment Tool (NEAT), can be used at the European scale, serving to managers and policy-makers as a tool to assess the environmental status under the Marine Strategy Framework Directive (MSFD). We have used MSFD Descriptor D3 (commercial fish) from 341 stocks, 119 species and two indicators from each of them (years 2013–2015); D5 (eutrophication) with 90th percentile of Chlorophyll-a (years 2009–2014); and D8 (contaminants), with Anthracene, Fluoranthene, Naphthalene, Cadmium, Nickel, and Lead as indicators (years 2009–2013). We have calculated the environmental status for each European subdivision, subregion, and regional sea, nested at different levels. The analyses include weighting and no-weighting by each assessment area; for ecosystem component (water column, phytoplankton, fish, crustaceans, and molluscs); descriptor (three), and habitat (pelagic, demersal/benthic), with the confidence value of the status. A sensitivity analysis was undertaken to determine a minimum number of indicators to include for a robust assessment. We demonstrated that using NEAT in assessing the status of large marine areas, by aggregating indicators, ecosystem components and descriptors, at different spatial scales, can remove at least four out of the six barriers that managers and policy-makers confront when undertaking such assessments. This can be done by using open-access databases and already established targets. Aggregating indicators of different origin is possible. Around 40 indicators seem to be enough to obtain robust assessments. It is better to integrate the assessment items using an ecosystem-based approach, rather than using the OOAO principle. Using NEAT, this approach supports identifying the problematic environmental issues needing management attention and measures.

We consider problem settings and methods of job-shop scheduling on mechanical engineering facilities whose production departments manufacture components, and the final products are assembled on conveyors. Job schedules are constructed both in terms of incoming orders for manufactured products and in terms of existing demand and storage costs at the company warehouses until the moment of sale. [ABSTRACT FROM AUTHOR]

Human gait or walking manner is a biometric feature that allows identification of a person when other biometric features such as the face or iris are not visible. In this study, the authors present a new pose‐based convolutional neural network model for gait recognition. Unlike many methods that consider the full‐height silhouette of a moving person, they consider the motion of points in the areas around human joints. To extract motion information, they estimate the optical flow between consecutive frames. They propose a deep convolutional model that computes pose‐based gait descriptors. They compare different network architectures and aggregation methods and experimentally assess various body parts to determine which are the most important for gait recognition. In addition, they investigate the generalisation ability of the developed algorithms by transferring them between datasets. The results of these experiments show that their approach outperforms state‐of‐the‐art methods. [ABSTRACT FROM AUTHOR]

In this work we consider the shortest path problem with uncertainty in arc lengths and convex risk measure objective.We explore efficient implementations of sample average approximation (SAA) methods to solve shortest path problems when the conditional value at risk and entropic risk measures are used and there is correlation present in the uncertain arc lengths. Ourwork explores the use of different decomposition techniques to achieve an efficient implementation of SAA methods for these nonlinear convex integer optimization problems. A computational study shows the effect of geometry, uncertainty correlation and variance, and risk measure parameters on efficiency and accuracy of the methods developed. [ABSTRACT FROM AUTHOR]

This work falls within the context of predicting the value of a real function at some input locations given a limited number of observations of this function. The Kriging interpolation technique (or Gaussian process regression) is often considered to tackle such a problem, but the method suffers from its computational burden when the number of observation points is large. We introduce in this article nested Kriging predictors which are constructed by aggregating sub-models based on subsets of observation points. This approach is proven to have better theoretical properties than other aggregation methods that can be found in the literature. Contrarily to some other methods it can be shown that the proposed aggregation method is consistent. Finally, the practical interest of the proposed method is illustrated on simulated datasets and on an industrial test case with 104 observations in a 6-dimensional space. [ABSTRACT FROM AUTHOR]

A Markov flow is a stationary measure, with the associated flows and mean first passage times, for a continuous-time regular jump homogeneous semi- Markov process on a discrete state space. Nodes in the state space can be eliminated to produce a smaller Markov flow which is a factor of the original one. Some improvements to the elimination methods of Wales are given. The main contribution of the paper is to present an alternative, namely a method to aggregate groups of nodes to produce a factor. The method can be iterated to make hierarchical aggregation schemes. The potential benefits are efficient computation, including recomputation to take into account local changes and insights into the macroscopic behaviour. This article is part of the theme issue 'Hilbert's sixth problem'. [ABSTRACT FROM AUTHOR]

This paper presents the development and performance testing of a modified bus-split method for aggregating interconnected distributed generation units (DGUs). The modified bus-split method is developed by introducing power-based models for interconnected DGUs. The introduced power-based models are used to replace admittance-based models used in the original bus-split method. The developed power-based models are generalized for DGUs that are interconnected to a $1\phi$ or a $3\phi$ distribution network. The modified bus-split aggregation method can be beneficial for determining possible offsets of conventional power generation, as well as improving the management of peak-demand conditions. The injected power-based bus-split aggregation method is implemented for performance testing using collected data from several wind and photovoltaic energy conversion systems, which are interconnected at different locations of the distribution network. Test results demonstrate accurate and reliable aggregation without sensitivity to the interface type, power ratings, location, voltage level at the interconnection node, and/or configuration ($1\phi$ or $3\phi$). [ABSTRACT FROM AUTHOR]

In this paper a novel hybrid ensemble method aiming at the improvement of models accuracy in regression tasks is presented. The basic idea of the approach is the creation of an ensemble learner composed by a strong learner which is trained by exploiting data belonging to the whole training dataset and a set of specialised weak learners trained by using data coming from limited regions of the input space determined by means of a self organising map based clustering. In this context, different methods have been tested for the design of the learners, including a hierarchical approach. In the simulation phase, the strong and weak learners operate according to their punctual self-estimated reliabilities so as to exploit their strengths and overcome their weaknesses. The method has been tested on literature and real world datasets achieving competitive results by outperforming other ensemble methods on most of the tested datasets and reducing the average absolute error by up to 10%. [ABSTRACT FROM AUTHOR]