Benchmark Methods Research Articles

Financial performance evaluation of firms in BIST 100 index with ITARA and COBRA methods

Evaluating firms’ financial performance is important for survival in the competitive environment arising from technological advancements and gaining a competitive advantage. This study aims to assess the financial performances of firms traded on the Istanbul Stock Exchange 100 Index (Borsa Istanbul (BIST) 100 Index) between 2018 and 2022 using an integrated multi-criteria decision-making (MCDM) method. This is the first study to use a new combined approach proposed based on the indifference threshold-based attribute ratio analysis (ITARA) and cost estimation, benchmarking, and risk assessment (COBRA) methods, which have not been applied to corporate performance assessment. The ITARA method is used to find the weights of the criteria, and the ranking of the firms in terms of financial performance is obtained using the COBRA method. The results show that the firms with the highest financial performance are ISMEN, ALGYO, PGSUS, KOZAA, and IPEKE. The companies with the lowest financial performance are AKFGY, BAGFS, MGROS, KOZAL, and GOZDE. The results of this ranking provide important information for firms to recognize their position and for investors who want to invest in firms in the BIST 100 Index. Additionally, sensitivity analyses are performed to assess the impact of changes in the criteria on the ranking of the firms and to validate the results of the proposed method. A comparative analysis is made with different MCDM methods like the technique for order preference by similarity to ideal solution (TOPSIS), and combined compromise solution (CoCoSo) methods and Spearman’s rank correlation test results are presented. This approach leads to the conclusion that the proposed approach can be a useful and effective tool for assessing the financial performance of firms.

Estimating the Hawkes process from a discretely observed sample path

Estimating the Hawkes process from a discretely observed sample path is challenging due to the intractability of the likelihood in such cases. To overcome this, we employ a state-space representation of the incomplete data problem and use the sequential Monte Carlo (SMC, aka particle filters) to approximate the likelihood function. The resulting estimator of the likelihood function is unbiased and, therefore, can be used along with the Metropolis-Hastings algorithm to construct Markov Chains to approximate the likelihood distribution and, more generally, the posterior distribution of model parameters. The performance of our methodology is assessed using simulation experiments and compared with other recently published methods. The proposed estimator exhibits a smaller mean square error compared to two benchmark estimators. Furthermore, an advantage of our method compared to existing methods is that confidence intervals for the parameters are readily computable. Finally, we apply the proposed estimator to the analysis of weekly count data on measles cases in Tokyo, Japan, and compare the results to one of the benchmark methods. The online supplementary materials contain a Julia package that implements our methodology, along with the technical proofs for two propositions.

Risk Stratification Using Tree-Based Models for Recurrence-Free Survival in Breast Cancer

PURPOSE An accurate risk model is critical for risk-stratified cancer care and delivery. We developed a survival decision tree (SDT) model as a risk stratification tool to categorize patients into distinct groups and compared the model performance with other methods through a benchmarking design. METHODS Data were obtained from the Northwell Health cancer registry for patients with breast cancer who were initially diagnosed and first seen at one of the nine Northwell facilities between 2018 and 2021. The SDT model was constructed to segment patients into different risk groups, and their recurrence-free survival (RFS) probabilities were compared using the log-rank test. We compared the SDT with the Cox proportional hazards model and random survival forest (RSF). Model performance was assessed using the c-index, calibration intercept and slope, and integrated Brier score. RESULTS A total of 5,919 patients diagnosed with invasive breast cancer were analyzed, and four risk groups were identified: low risk, medium risk, high risk, and very high risk. There was a significant difference in RFS across groups ( P < .001). The pruned SDT model showed similar or better performance than the benchmarking methods; however, the RSF may be useful in the subgroup of patients with two or more comorbidities, where a more complex relationship may exist. CONCLUSION Risk stratification can be accurately modeled via a tree-based method. Future research should layer in other outcomes, such as comorbidity, ongoing treatment toxicities, or risk of delayed treatment, to improve risk-stratified care and effective use of health care resources.

Postfire Estimation of Heating Temperatures Experienced by Fire Retardant Coatings Using Smartphone Videos and Machine Learning

ABSTRACTAccurate estimation of heating temperatures experienced by fire retardant coatings (FRCs) is crucial in identifying the ignition source during fire investigations. While traditional methods, such as spectroscopy, effectively capture the compositional changes in FRC at various heating temperatures, they are typically bulky, costly, and unsuitable for rapid field analysis. This study proposes the use of smartphone and machine learning to predict the heating temperatures of FRC. A smartphone is employed to capture short videos of FRC samples illuminated by its color‐changing screen. Video frames are then decomposed into color images and converted into spectral data for further processing. Linear and nonlinear regression models are applied to identify key variables and enhance predictive accuracy. The performance of smartphone‐based temperature estimation is compared to that of hyperspectral imaging and laser‐induced breakdown spectroscopy. In the test phase, the coefficient of determination for smartphone‐based estimation ranges from 0.946 to 0.962, often surpassing that of benchmark methods. These results indicate that smartphones can provide a low‐cost, effective means for estimating heating temperatures of FRC in fire investigations.

Optimization of microwave components using machine learning and rapid sensitivity analysis

Recent years have witnessed a tremendous popularity growth of optimization methods in high-frequency electronics, including microwave design. With the increasing complexity of passive microwave components, meticulous tuning of their geometry parameters has become imperative to fulfill demands imposed by the diverse application areas. More and more often, achieving the best possible performance requires global optimization. Unfortunately, global search is an intricate undertaking. To begin with, reliable assessment of microwave components involves electromagnetic (EM) analysis entailing significant CPU expenses. On the other hand, the most widely used nature-inspired algorithms require large numbers of system simulations to yield a satisfactory design. The associated costs are impractically high if not prohibitive. The use of available mitigation methods, primarily surrogate-based approaches, is impeded by dimensionality-related problems and the complexity in microwave circuit characteristics. This research introduces a procedure for expedited globalized parameter adjustment of microwave passives. The search process is embedded in a surrogate-assisted machine learning framework that operates in a dimensionality-restricted domain, spanned by the parameter space directions being of importance in terms of their effects on the circuit characteristic variability. These directions are established using a fast global sensitivity analysis procedure developed for this purpose. Domain confinement reduces the cost of surrogate model establishment and improves its predictive power. The global optimization phase is complemented by local tuning. Verification experiments demonstrate the remarkable efficacy of the presented approach and its advantages over the benchmark methods that include machine learning in full-dimensionality space and population-based metaheuristics.

A New Tensor Summary Statistic for Real-Time Detection of Stealthy Anomaly in Avatar Interaction

Avatar is one of the most intuitive central components in Metaverse and faces serious security problems, particularly during the interaction with each other. In this article, we consider the problem of timely detecting the stealthy anomaly in the avatar interaction, which is crucial for security and privacy in Metaverse. With this goal, a new tensor summary statistic is proposed first to well depict the statistical discrepancy between normal and anomalous interaction volume samples, even when anomalies are stealthy. The proposed tensor summary statistic is established from the tensor linear representation residual, which naturally implies the statistical probability that an interaction volume sample lies within or deviates from the tensor lateral space. Moreover, a convex optimization programme is introduced to robustly recover the tensor lateral space in the presence of anomalous samples, thereby enhancing the robustness of our tensor summary statistic. On the basis of the tensor summary statistic, a non-parametric statistic framework is developed for the real-time detection of the stealthy interaction volume anomaly. We also provide theoretical analysis concerning its detection performance and parameter selection. Extensive experiments using synthetic and real-world datasets verify our effectiveness and superiority. Compared with benchmark methods, the proposed detection scheme achieves significantly lower detection delay and higher false alarm period, particularly in the detection of stealthy anomalies with a low change rate.

A Sentiment Analysis and Semantic Comprehension-Integrated Automatic Abstraction Model for English Texts

Automatic abstraction has been a more prevalent technical demand in text analysis. However, due to the complex relationship between sentence structure and semantics, current automatic abstraction models in English texts still suffer from some challenges. Therefore, this paper explores a new type of English text automatic abstraction model that combines sentiment analysis and semantic perception technology. First, it is supposed to make serialization and extraction of English texts, resulting in multi-level sequential text. Then, a hierarchical multihead attention mechanism is introduced to achieve dynamic word vectorization. Finally, it is input into a multi-angle convolutional network, in which each token-level vector in the sentence is input for multiangle sentiment analysis and double-layer semantic perception. Hence, the automatic abstract result for long texts can be achieved. After that, experiments are conducted on multiple English text datasets to compare the proposal with other benchmark methods. The results show that the model has achieved significant improvement in the generation of text summaries, which can more effectively generate text summaries with rich emotions and accurate semantics.

A robust adaptive meta-sample generation method for few-shot time series prediction

The research and exploration of time series prediction (TSP) have attracted much attention recently. Researchers can achieve effective TSP based on the deep learning model and a large amount of data. However, when sufficient high-quality data are not available, the performance of prediction models based on deep learning techniques may degrade. Therefore, this paper focuses on few-shot time series prediction (FTSP) and plans to combine meta-learning and generative models to alleviate the problems caused by insufficient training data. When using meta-learning techniques to process FTSP tasks, researchers set the meta-parameter in model-agnostic meta-learning (MAML) as a meta-sample and construct meta-sample generation methods based on advanced generative modeling theory to achieve better uncertainty coding. The existing meta-sample generation methods in FTSP scenes have an inherent limitation: With the increase of the complexity of prediction tasks, samples based on Gaussian distribution may be sensitive to noise and outliers in the meta-learning environment and lack of uncertainty expression, thus affecting the robustness and accuracy of prediction. Therefore, this paper proposes an adaptive sample generation method called JLSG-Diffusion. Based on the Jensen constraint framework and Laplace modeling theory, this method constructs a sample adapter with reasonable adaptive steps and fast convergence for specific tasks. The advantage is to realize fast adaptive convergence of samples to new tasks at lower cost, effectively control the overall generalization error, and improve the robustness and non-Gaussian generalization of sample posterior reasoning. Moreover, the meta sampler of JLSG-Diffusion embeds meta-learning from the implicit probability measure level of Denoising Diffusion Probabilistic Models (DDPM), which makes the meta-sample distribution directly establish a function mapping with the new task and effectively quantifies the uncertainty of spatiotemporal dimension. Experimental results on three real datasets prove the efficiency and effectiveness of JLSG-Diffusion. Compared with the benchmark methods, the prediction model combined with JLSG-Diffusion shows better accuracy.

Deep learning-based prediction approaches of binary star parameters

The precise computation of binary star parameters is crucial for understanding their formation, evolution, and dynamics. However, large datasets of available astronomical measurements require substantial effort for computing using classic astronomical methods. Deep learning (DL) is a promising approach that can provide a proper solution for estimating the parameters and reducing the burden of the lengthy procedures of astronomical computations. This study proposes two DL-based models for estimating binary star parameters. The first is the well-known multi-layer perceptron (MLP) model, whereas the second is based on long short-term memory (LSTM). We rely on databases, such as large sky multi-object fiber spectroscopic telescope area (LAMOST), to train the proposed models. In addition, we verify the training ratio showing that the performance of both models at a low training ratio of 30%, based on the mean square error (MSE), results in acceptable performance. Furthermore, the LSTM-based DL model outperforms the conventional MLP for different training ratios. Eventually, the two models have superiority compared to the benchmark methods.

Short-Term Photovoltaic Power Forecasting Using PV Data and Sky Images in an Auto Cross Modal Correlation Attention Multimodal Framework

The accurate prediction of photovoltaic (PV) power generation is crucial for improving virtual power plant (VPP) efficiency and power system stability. However, short-term PV power forecasting remains highly challenging due to the significant impact of weather changes, especially the complexity of cloud motion. To this end, this paper proposes an end-to-end innovative deep learning framework for data fusion based on multimodal learning, which utilizes a new auto cross modal correlation attention (ACMCA) mechanism designed in this paper for feature extraction and fusion by combining historical PV power generation time-series data and sky image data, thereby enhancing the model’s prediction performance under complex weather conditions. In this paper, the effectiveness of the proposed model was verified through a large number of experiments, and the experimental results showed that the model’s forecast skill (FS) reached 24.2% under all weather conditions 15 min in advance, and 24.32% under cloudy conditions with the largest fluctuations. This paper also compared the model with a variety of existing unimodal and multimodal models, respectively. The experimental results showed that the model in this paper outperformed other benchmark methods in all indices under different weather conditions, demonstrating stronger adaptability and robustness.

A unified multi‐class anomaly detection model based on reverse distillation

AbstractThe multi‐class single‐model detection paradigm is a prevalent design for industrial anomaly detection, exhibiting suitability for varying industrial classes and dynamic, flexible production scenarios. This approach not only enhances model adaptability but also minimizes maintenance costs. However, the current popular methods are susceptible to the ‘copying shortcut’ phenomenon, which constrains their performance on benchmark datasets. To overcome this limitation, this article proposes a multi‐class anomaly detection model: UniRD, based on the reverse distillation method. This model creates an image corruptor that expands the dataset and generates ‘normal‐corrupt’ image pairs. During the training process, their correspondence is used to optimize the reverse distillation. This process greatly exploits and releases the potential of the student decoder. Furthermore, a teacher feature adaptation module is devised to enhance the compatibility between the pre‐trained model and the anomaly detection task. This has the effect of reducing the discrepancy between teacher and student features while ensuring the consistency of normal sample features. The comprehensive evaluation results in two mainstream datasets, MVTec and VisA, and demonstrates that the proposed method exhibits improvement in all indicators compared to benchmark methods. The proposed method attains the state‐of‐the‐art, substantiating its effectiveness and advancement.

Fischer-Speier Esterification and Beyond: Recent Mechanicistic Advances

Over the past 130 years, Fischer-Speier esterification has been established as the benchmark method for synthesizing esters from organic acids and alcohols. The reaction’s versatility, arising from the vast combinations of starting materials and the numerous catalytic alternatives to the traditional H2SO4, has maintained its relevance, with a steady flow of publications addressing new developments. This review highlights the most significant contributions to Fischer-Speier esterification over the past five years, with a particular emphasis on mechanistic advancements and innovative catalytic systems. Both homogeneous and heterogeneous catalytic approaches are discussed, including novel catalysts leveraging hydrogen-bonding interactions and systems offering fresh insights into specific reaction mechanisms and atypical methodologies. Some of these catalytic systems, as ionic liquids or sulfonated heterogeneous catalytic precursors, reached excellent yields (>90%), e.g., in the synthesis of fatty acids methyl esters. Also, classic catalysts such as H2SO4 and para-toluen sulfonic acid were optimized for quantitative conversions (e.g., in the esterification of trans-cinnamic acid with methanol). A consistent number of catalysts was studied with model substrates (as benzoic acid in combination with methanol, ethanol, and ethylene glycol), and new activation pathways were presented.

Community Detection Framework Using Deep Learning in Social Media Analysis

Social media analysis aims to collect and analyze social media user information and communication content. When people communicate through messages, phone calls, emails, and social media platforms, they leave various records on their devices and the Internet, forming a huge social network. Community detection can help investigators analyze group leaders and community structure, which is significant to further crime control, identifying coordinated campaigns, and analyzing social network dynamics. This paper proposes the application of deep learning methods for community detection. Our main idea is to utilize social network topology and social network communication content to construct user features. The proposed end-to-end community detection framework is the implementation of Graph Convolution Network and can display the social network topology, locate the core members of the community, and show the connections between users. We evaluate our framework on the Enron email dataset. Experimental results indicate that our proposed model achieves a 1.1% higher modularity score than the unsupervised benchmark methods. We also concluded that the community detection framework should be able to analyze social networks, enabling investigators to reveal connections between people.

Enhancing Swift and Socially-Aware Navigation with Continuous Spatial-Temporal Routing

AbstractRouting for autonomous robots in dynamic human environments requires paths that are collision-free, efficient, and socially considerate. This article introduces an optimization-based routing method that operates in continuous space using a spatial-temporal model of crowd dynamics. Our approach anticipates future crowd changes and adjusts routes by considering potential speed variations due to local motion planning. It optimizes navigation speed while avoiding densely crowded areas, ensuring efficient and socially-aware navigation. Simulations in three scenarios demonstrate superior performance compared to benchmark methods in terms of navigation efficiency and adaptability in crowded, dynamic environments.

MOLA: Enhancing Industrial Process Monitoring Using a Multi-Block Orthogonal Long Short-Term Memory Autoencoder

In this work, we introduce MOLA, a multi-block orthogonal long short-term memory autoencoder paradigm, to conduct accurate, reliable fault detection of industrial processes. To achieve this, MOLA effectively extracts dynamic orthogonal features by introducing an orthogonality-based loss function to constrain the latent space output. This helps eliminate the redundancy in the features identified, thereby improving the overall monitoring performance. On top of this, a multi-block monitoring structure is proposed, which categorizes the process variables into multiple blocks by leveraging expert process knowledge about their associations with the overall process. Each block is associated with its specific orthogonal long short-term memory autoencoder model, whose extracted dynamic orthogonal features are monitored by distance-based Hotelling’s T2 statistics and quantile-based cumulative sum (CUSUM) designed for multivariate data streams that are nonparametric and heterogeneous. Compared to having a single model accounting for all process variables, such a multi-block structure significantly improves overall process monitoring performance, especially for large-scale industrial processes. Finally, we propose an adaptive weight-based Bayesian fusion (W-BF) framework to aggregate all block-wise monitoring statistics into a global statistic that we monitor for faults. Fault detection speed and accuracy are improved by assigning and adjusting weights to blocks based on the sequential order in which alarms are raised. We demonstrate the efficiency and effectiveness of our MOLA framework by applying it to the Tennessee Eastman process and comparing the performance with various benchmark methods.

Sum computation rate maximization for wireless powered OFDMA-based mobile edge computing network

The wireless power transfer (WPT) and mobile edge computing (MEC) technologies have been advocated as the prospective effective solution for future wireless networks. This paper introduces a multi-user WPT-MEC system, where a sum computation rate (SCR) maximization design by jointly optimizing the WPT duration, the allocation of the subcarrier selection indicator of each user, each user’s transmit power, and the parameters related to different offload modes at each user is considered. In such a system, the hybrid access point (AP) broadcasts radio frequency (RF) energy intended for users to harvest, subsequently enabling users to transmit their computation tasks to the MEC server via the orthogonal frequency division multiple access (OFDMA) protocol. To address this non-convexity SCR maximization problem, a decomposition optimization is proposed. In the top-problem, the DRL-based deep neural network (DNN) model is applied to realize the computation selection indicator and subcarrier selection indicator among each user. In the sub-problem, for the binary offloading mode, an efficient two-stage algorithm with golden section search and intrinsic properties is utilized to determine the optimal values of remaining parameters. For the partial offloading mode, the problem is reformulated by introducing new variables and then the convex optimization techniques are utilized to efficiently obtain the corresponding solutions. Simulation results demonstrate the proposed approach outperforms the benchmark methods considered in both binary and partial offloading modes.

Multi-agent modeling for energy storage charging station scheduling strategies in the electricity market: A cooperative learning approach

With integration of an energy storage system (ESS), an energy storage charging station serves as pivotal intermediaries between the smart grid and electric vehicles (EVs). This station utilizes the ESS to enhance grid stability and facilitate energy management. Participation in electricity market transactions offers revenue opportunities for charging stations, but it also introduces operational challenges, due to fluctuating electricity market prices and diverse energy demands and supplies. In this paper, we study the operation strategy optimization problem for the charging station, addressing economic and service challenges influenced by market volatility and energy diversity. The optimization objective considers not only maximizing economic benefits from the electricity market and EV services but also minimizing penalties associated with EV service quality. We propose a model that accounts for the dynamics of the electricity market, uncertainties from EV demands, and disturbances from green power generation, optimizing the power scheduling of the ESS and multiple charging piles (CPs) to determine transaction power in the market. The cooperative scheduling strategies for the ESS and CPs are learned using the proposed heterogeneous Multi-agent Deep Deterministic Policy Gradient method. This approach features distributed agents learning to determine decision variables for both the ESS and CPs, while a joint critic network assesses the station’s overall objectives to guide their cooperative learning. The proposed method was tested against three state-of-the-art benchmark methods, which showed our method achieves better results.

The Matrix‐Free Macro‐Element Hybridized Discontinuous Galerkin Method for Steady and Unsteady Compressible Flows

ABSTRACTThe macro‐element variant of the hybridized discontinuous Galerkin (HDG) method combines advantages of continuous and discontinuous finite element discretization. In this paper, we investigate the performance of the macro‐element HDG method for the analysis of compressible flow problems at moderate Reynolds numbers. To efficiently handle the corresponding large systems of equations, we explore several strategies at the solver level. On the one hand, we utilize a second‐layer static condensation approach that reduces the size of the local system matrix in each macro‐element and hence the factorization time of the local solver. On the other hand, we employ a multi‐level preconditioner based on the FGMRES solver for the global system that integrates well within a matrix‐free implementation. In addition, we integrate a standard diagonally implicit Runge–Kutta scheme for time integration. We test the matrix‐free macro‐element HDG method for compressible flow benchmarks, including Couette flow, flow past a sphere, and the Taylor–Green vortex. Our results show that unlike standard HDG, the macro‐element HDG method can operate efficiently for moderate polynomial degrees, as the local computational load can be flexibly increased via mesh refinement within a macro‐element. Our results also show that due to the balance of local and global operations, the reduction in degrees of freedom, and the reduction of the global problem size and the number of iterations for its solution, the macro‐element HDG method can be a competitive option for the analysis of compressible flow problems.

Satellite Fingerprinting Methods for GNSS Spoofing Detection.

Spoofing attacks pose a significant security risk for organizations and systems relying on global navigation satellite systems (GNSS) for their operations. While the existing spoofing detection methods have shown some effectiveness, these can be vulnerable to certain attacks, such as secure code estimation and replay (SCER) attacks, among others.This paper analyzes the potential of satellite fingerprinting methods for GNSS spoofing detection and benchmarks their performance using real (in realistic scenarios by using GPS and Galileo signals generated and recorded in the advanced GNSS simulation facility of DLR) GNSS signals and scenarios. Our results show that our proposed fingerprinting methods can improve the detection accuracy of the existing methods and can be coupled with other techniques to enhance the overall performance of the detection systems, all based on relatively simple metrics. In this paper, we compare the performance of several fingerprinting methods, including those from the existing literature (based on signal Gaussian properties of the signal complex envelope, energy and in-phase symbol dispersion) and one proposed in this paper, based on the satellite instrumental delay. The innovation of this work is a new jamming and spoofing complementary detection technique, based on fingerprinting and machine learning, including a new fingerprinting metric (based on the satellite instrumental delay).

Joint Short-term Power Forecasting of Hydro-Wind-Photovoltaic Considering Spatiotemporal Delay of Weather Processes

Regional integrated energy systems (RIES) represented by hydro, wind, and solar energy are crucial avenues for future clean energy development, fully leveraging their complementarity can facilitate the orderly supply of renewable energy, significantly enhance the level of new energy consumption, and make outstanding contributions to achieving carbon neutrality goals. However, run-of-river hydropower (RHP), wind power (WP), and photovoltaic (PV) are affected by the chaotic characteristics of the weather system, with significant random fluctuations, and their output characteristics have significant heterogeneity, which brings a big challenge for the complementary coordinated scheduling. The high-accuracy power prediction of RHP, WP, and PV in the region is one of the key means for solving the above problems. To meet this challenge, by analyzing the spatio-temporal correlation properties between weather processes and station output, a novel joint prediction framework for short-term power forecasting (STPF) of regional hydro-wind-PV clusters is proposed. Firstly, to solve the problem of significant heterogeneity of water, wind, and solar, a Differentiated Spatio-Temporal Mixture Network (DSTMN) is proposed, which differentially encodes the weather and power information at multiple locations, enabling the extraction of common features while preserving their specificities, which addresses the difficulty of representing the inherent correlation patterns between wide-area meteorological information and heterogeneous energy sources. Secondly, to further explore the spatio-temporal correlation between meteorological information and power information, to improve the forecasting performance of the model, a spatio-temporal-lagged correlation (STLC) that can quantify their spatio-temporal delays is proposed. By analyzing the correlation characteristics between regional grid numerical weather prediction (NWP) information and station output at different spatial and temporal scales, the optimal spatial location and delay time of NWP inputs under the current scenario are determined for each station. Based on this, the best NWP scene probabilistic transfer model is established based on the Rank Bayesian Ensemble (RBE) method. By fitting the conditional probability distribution of the current best NWP spatiotemporal location and the 2nd day’s best NWP spatiotemporal location, providing a reliable input for the STPF model. Finally, a case study with 164 hydro-wind-solar stations in China demonstrates the effectiveness of the proposed method. Specifically, we achieved an accuracy improvement of 0.46% — 11.03% on the 2nd day of forecasting compared to benchmark methods.