A Benchmark Dataset for the Validation of Phase-Based Motion Magnification-Based Experimental Modal Analysis

Editorial and News

Aim: In addition to affecting the individual sociologically and psychologically, heart disease also poses important problems in health systems. Evaluation of heart disease performances has gained great importance in terms of machine learning method. In the study, performances were compared with the machine learning method for risk methods that classify heart illness. Materials and Methods: The categorization process Throughout the research made use of the "Heart Disease Dataset," an open access dataset. F1-score, sensitivity, selectivity, accuracy, balanced accuracy, negative and positive predictive values were used to assess the performance of the categorisation model using the machine learning approach. Random forest method, one of the variable selection methods, was used. Results: According to the relational classification model's classification findings for heart disease, the accuracy, balanced accuracy, sensitivity, selectivity, positive predictive value, negative predictive value, and F1-score values were observed to be 0.997, 0.997, 0.995, 1, 1, and 0.995, respectively. Conclusion: The relational classification model proposed in the analysis obtained in the web-based open access dataset yielded distinctively successful results in classifying heart disease according to performance criteria.

Variable stiffness manipulators balance the trade-off between manipulation performance needing high stiffness and safe human-robot interaction desiring low stiffness. Variable stiffness compliant links provide a solution to enable this flexible manipulation function in human-robot co-working scenarios. In this paper, we propose a novel variable stiffness link based on discrete variable stiffness units (DSUs). A DSU is a parallel guided beam that can adjust stiffness discretely by changing the cross-sectional area properties of the hollow beam segments. The variable stiffness link (named Tri-DSU) consists of three tandem DSUs to achieve eight stiffness modes and a maximum stiffness change ratio of 31. To optimize the design, stiffness analysis of the DSU and Tri-DSU under various configurations and forces was performed by a derived theoretical model compared with finite element analysis (FEA). The analytical stiffness model is derived using the approach of serially connected beams and superposition combinations. It works not only for thin-walled flexure beams but also for general thick beam models. 3-D printed prototypes were built to verify the feature and performance of the Tri-DSU in comparison with the FEA and analytical model results. It’s demonstrated that our analytical model can accurately predict the stiffnesses of the DSU and Tri-DSU within a certain range of parameters. The developed variable stiffness link method and analytical model are extendable to multiple DSUs with different sizes and parameter configurations to achieve modularization and customization. The advantages of the stiffness change mechanism are rapid actuation, simple structure, and compact layout. These methods and results provide a new conceptual and theoretical basis for the development of new reconfigurable cobot manipulators, variable stiffness structures, and compliant mechanisms.

Here we present data from two studies, both of which had the purpose of investigating the potential of using electroencephalograms measured from the ear (’ear-EEG’) for sleep monitoring in a home environment. In total, 320 nights were recorded. All nights were recorded with ear-EEG, and some were also recorded using scalp-EEG and/or wristworn actigraphy. All subjects were recorded multiple times. To our knowledge, this is the most extensive open access data set available for mobile EEG development, and possibly also the best open access dataset for studying repeated sleep monitoring on individuals. We describe the details of each data set, including data quality measures, and compare the sleep scoring performance to a previously published dataset.

Artificial intelligence (AI) is being increasingly applied in the geosciences, particularly in fields like mineralogy, where it supports tasks such as mineral classification, automated thin‐section image analysis, or mineral exploration targeting. Such tasks require large structured and standardized data sets, which are currently not available. We build two databases to fill this gap: (i) MRMinerals contains a list of the 400 most common and geologically significant minerals, including major rock‐forming minerals, key accessory minerals, and economically important ore minerals with machine‐readable formulas as the key feature. (ii) MineralTD contains a large training data set with 10,000+ compositions for each of the 400 minerals in MRMinerals. MineralTD is split into two subdatasets: MineralTDMeasured and MineralTDSynthetic . MineralTDMeasured contains approximately 140,000 mineral compositions from the open‐access geochemical databases and repositories GEOROC, Pangaea, PetDB, RRUFF, and ESMD. MineralTDSynthetic contains synthetic mineral compositions, generated using machine‐readable formulas from MRMinerals, with at least 10,000 compositions per mineral. MineralTD is annotated with metadata, such as mineral frequency, rock classification, data source, and methods used to provide a full understanding of the individual data set. The MRMinerals and MineralTD are ready‐to‐use open access data sets that enable scalable, data‐driven research in mineralogy, e.g., ML applications.

For Variable Stiffness (VS) composites with steered curvilinear tow paths, the fiber orientation angle varies continuously throughout the laminate, and is not required to be straight, parallel and uniform within each ply as in conventional composite laminates. Hence, the thermal properties (conduction), as well as the structural stiffness and strength, vary as functions of location in the laminate, and the associated composite structure is often called a “variable stiffness” composite structure. The steered fibers lead not only to the alteration of mechanical load paths, but also to the alteration of thermal paths that may result in favorable temperature distributions within the laminate and improve the laminate performance. Evaluation of VS laminate performance under thermal loading is the focus of this chapter. Thermal performance evaluations require experimental and numerical analysis of VS laminates under different processing and loading conditions. One of the advantages of using composite materials in many applications is the tailoring capability of the laminate, not only during the design phase but also for manufacturing. Heat transfer through variable conduction and chemical reaction (degree of cure) occurring during manufacturing (curing) plays an important role in the final thermal and mechanical performance, and shape of composite structures. Three case studies are presented in this chapter to evaluate the thermal performance of VS laminates prior to and after manufacturing. The first case study is a numerical analysis that investigates the effect of variable conductivity within the VS laminate on the temperature and degree of cure distribution during its cure cycle. The second case study is a numerical analysis that investigates the transient thermal performance of a rectangular VS composite laminate. Variable thermal conductivity will affect the temperature profile and results are compared to a unidirectional composite. The effect of fiber steering on transient time and steady state solutions is compared to the effect of unidirectional fibers. The third case study is an experimental one that was conducted to evaluate the thermal performance of two variable stiffness panels fabricated using an Advanced Fiber Placement (AFP) Machine.

Brain-computer interfaces (BCIs) recognize specific features of a person's brain signal relating to his/her intent, and output a control command that controls the outside devices or computers. BCI systems facilitate the lives of patients who cannot move any muscles but have no cognitive disorder. The high dimensions of features represent a research challenge. In recent years, especially nature inspired heuristic optimization algorithms became popular in order to eliminate unnecessary features. This paper addresses a crucial factor for effective classification of motor imaginary based EEG signals that are an optimal selection of relevant EEG features using firefly algorithm. Firefly algorithm (FA) works on the principle of directing the less shiny than the light intensity emitted by fireflies in nature towards the bright. The algorithm can adaptively select the best subset of features and improve classification accuracy. In this study, following extracted Katz Fractal Dimension based features, effective feature(s) were selected by FA. The proposed method successfully applied on open access dataset which was collected from 29 subjects. We obtained an average 76.14% classification accuracy (CA) using k-nearest neighbor classifier. This is 4.4% higher than the CA calculated by using all features. These results proved that used method is robust for this dataset.

Comparison of total emitted solar-induced chlorophyll fluorescence (SIF) and top-of-canopy (TOC) SIF in estimating photosynthesis

Deep ensemble learning based probabilistic load forecasting in smart grids

With the exponential growth of high-quality fake images in social networks and media, it is necessary to develop recognition algorithms for this type of content. One of the most common types of image and video editing consists of duplicating areas of the image, known as the copy-move technique. Traditional image processing approaches manually look for patterns related to the duplicated content, limiting their use in mass data classification. In contrast, approaches based on deep learning have shown better performance and promising results, but they present generalization problems with a high dependence on training data and the need for appropriate selection of hyperparameters. To overcome this, we propose two approaches that use deep learning, a model by a custom architecture and a model by transfer learning. In each case, the impact of the depth of the network is analyzed in terms of precision (P), recall (R) and F1 score. Additionally, the problem of generalization is addressed with images from eight different open access datasets. Finally, the models are compared in terms of evaluation metrics, and training and inference times. The model by transfer learning of VGG-16 achieves metrics about 10% higher than the model by a custom architecture, however, it requires approximately twice as much inference time as the latter.

The HUPO Plasma Proteome Project (PPP) held its annual workshop at the 6th HUPO World Congress in Seoul, Korea, October 7, 2007. The agenda was organized around the aims of the next phase of the PPP. The pilot phase accomplished its goals of providing reference specimens of serum and plasma to a large international network of collaborating laboratories, comparing protein identifications with various fractionation and analytical technology platforms, introducing new technologies from vendor partners, generating extensive submissions to open source databases (www.peptideatlas. org/hupo/hppp (ISB); www.ebi.ac.uk/pride (EBI)) and bioinformatics insights, and laying a foundation for integration of plasma studies with organ proteome and disease biomarker projects. Results were published in a special issue of Proteomics (1), a Wiley book (2), and a special analysis in Nature Biotechnology (3). The specimens and databases have been utilized for many other studies. Participants at the PPP workshop in Long Beach, California, in November 2006 agreed to develop the current plans. The 2007 workshop was organized with panels of leading scientists in proteomics describing their commitments. The overriding principle is the sharing of data to advance the field and facilitate much needed comparative analyses. The first panel comprised laboratory leaders with advanced technology platforms. Ruedi Aebersold described the N-glycosite Nx(S/T) proteotypic peptide library approach for targeted analyses. Christie Hunter presented applications of multiple reaction monitoring with multiple transitions for each labeled peptide. Denis Hochstrasser emphasized the preanalytical variables and the advantages of starting from tissue, followed by the multiplex analyses of plasma (or serum, if immunoassays). Bill Hancock introduced multilectin affinity chromatography for glycoproteins, including glycan characterization. Ole Jensen introduced microparticles and phosphoprotein analyses. Richard Smith explained powerful ion mobility separation mass spectrometry and electrospray emitter design. And Rong Zeng presented label-free, integrated analyses after ethanol precipitation and pH elution of plasma proteins from diabetics. The second panel presented highly complementary bioinformatics and database resources already impressively connected with the PPP. Henry Lam announced that PeptideAtlas at the Institute for Systems Biology now has a human PPPspecific subatlas (see above); as the total resource has grown, more and more of the newly reported multiobserved peptides are confirmatory. PeptideAtlas applies to submitted datasets its uniform data analysis pipeline, including MS/MS spectral library searches with SpectraST (joint with the National Institute of Standards and Technology), which are much faster than Sequest. Lennart Martens described typical pitfalls in the analysis of mass spectrometry data obtained from serum or plasma samples along with tools that help resolve these problems. He reported that the PPP datasets were the first external data submitted to PRIDE at the European Bioinformatics Institute (see above); PRIDE assists data dissemination and links to EBI resources. Ron Beavis noted that the PPP was also one of the first datasets in the Global Proteome Machine, GPMdb (with the distinctive prefix 101). Martin McIntosh emphasized statistical variables, starting with variability among individuals and populations to be studied and discussed that follow-up analysis of the same individual minimizes genetic variation. Akhilesh Pandey described the Proteinpedia portal for sharing protein data and annotations. Both PRIDE and Proteinpedia use Tranche at ProteomeCommons.org, created by Philip Andrews of the University of Michigan, for storage of large volume raw datasets. Tranche provides encrypted file sharing among collaborators as well as open access datasets when made available. Contributors to the PPP should submit complex datasets with full experimental annotation specified by the HUPO Protein Standards. Users can find unaltered submissions at PRIDE, X!Tandem analyses at Global Proteome Machine, and TransProteomic Pipeline-processed datasets at PeptideAtlas. The final panel, moderated by John Bergeron as chair of HUPO Initiatives, demonstrated that the PPP and all other HUPO initiatives are complementary. EDTA-plasma specimens should be collected as part of organ-based studies for analysis in the same laboratories, followed by sharing of data on plasma and tissue findings with the PPP through the informatics resources just described. Helmut E. Meyer (Brain Proteome Project) reinforced the priority for starting from From ‡Human Genetics and Public Health, Center for Computational Medicine and Biology, University of Michigan, Ann Arbor, Michigan 48109, ¶Institute for Molecular Systems Biology, HPT E 76 ETH Honggerberg, CH-8093 ZAurich, Switzerland, and Department of Biochemistry, Yonsei Proteome Research Center & Biomedical Proteome Research Center, Room 423 Industry-University Building, Yonsei University, 134 Shinchon-dong, Sudaemoon-ku, Seoul, 120-749 Korea 1 The abbreviations used are: PPP, HUPO Plasma Proteome Project; PRIDE, Proteomics Identification Database. 2 This citation refers to just one of the articles used in this publication. HUPO Views

To help the clinicians to segment the borders of the left ventricle (LV) efficiently during measurement of the heart, the authors come up with a semi‐automatic approach in this study that is capable of identifying the endocardial borders robustly from cine magnetic resonance images. Firstly, the deformation flow is computed between the inputted boundary in the previous frame and the extracted edge of the LV in the current frame based on boundary minimum distance principle (BMDP). Then, the deformation flow is constrained by optical flow calculated by a partial differential equation model. A smooth deformation boundary is then formed by minimising the energy between the previously inputted boundary and the rough boundary obtained by BMDP and optical flow constraint. To extract edge of the LV as accurate as possible, a threshold selection method is used and improved based on the previous study. The proposed approach is tested on the open access dataset. The computed average perpendicular distance is 1.36 ± 0.24 mm and the computed Dice measure is 90.7% ± 0.15%. Experimental results show that the proposed approach is significantly more accurate than the referenced state of art methods.

: Prediction of electricity consumption is important for energy management and efficient use of energy resources. Accurate prediction of electricity consumption provides benefits to consumers and distribution companies in terms of correct management of electricity demand, electricity usage cost and waste control. This article proposes Temporal Convolutional Network (TCN) and Temporal Convolutional Network with Long Short-Term Memory (TCN-LSTM) models for medium-term electricity consumption prediction with an open access dataset in individual household electricity consumption prediction. An individual household’s 5000-hour electricity consumption prediction is made with the proposed models. The performance of the proposed models is compared with different prediction algorithms. The performance of all models used in the study is evaluated with three evaluation metrics commonly used in prediction model performance evaluation. When the prediction performances of TCN and TCN-LSTM models are compared with the performances of other prediction algorithms, it is seen that they have lower error rates and are more successful in medium-term electricity consumption prediction.

The article presents an empirical study of the global cryptocurrency market in the context of its evolution under the influence of macroeconomic, technological and geopolitical factors, as well as the broader framework of the global green transition. By analyzing market dynamics across several critical periods, including the pre COVID crisis phase, the COVID 19 pandemic, the full scale russian invasion of Ukraine and the most recent stage of partial recovery, the study characterizes the structural features of cryptocurrency volatility in comparison with traditional financial instruments, particularly the S&P 500 and USDX indices. The empirical component of the methodology is based on open access datasets from CoinMarketCap, TradingView and Investing.com, which enables a comparative assessment of cryptocurrency trends and stock market movements. The findings demonstrate that cryptocurrency markets remain highly sensitive to news flows, regulatory decisions and speculative activity by large investors, which complicates the application of conventional fundamental analysis methods. Special attention is devoted to the environmental dimension of crypto industry development. The high energy consumption of Bitcoin is identified as a major barrier to integrating blockchain technologies into sustainability oriented economic frameworks. The study also examines the potential of environmentally oriented tokens, most notably the Energy Web Token, which is positioned as a tool for supporting decarbonization processes in energy markets but continues to exhibit weak price performance and limited investor demand in comparison with green energy indices. The comparative analysis reveals a substantial gap between the conceptual value of green tokens and their actual market perception. Overall, the results confirm that despite the continuing expansion of the emergence of new technological solutions, the integration of cryptoassets into the green transition remains fragmented. Meaningful advancement in this direction requires clearer regulatory frameworks, technological improvements and stronger alignment between blockchain applications and measurable environmental outcomes.

Skull-removal is a standard preprocessing step for brain magnetic resonance image analysis. The gold standard of skull dissection are the anatomical templates of brain region after the manual removal of skull by experts. Manual segmentation is very time-consuming, but it is the evaluation basis of automatic brain extraction method. The existing skull stripping templates have some confused and unclear partitions around the brain marginal regions (sulci, gyrus) and skull base (brainstem). To this end, the study carried out three tasks: First, we proposed a brain extraction protocol that strictly followed human brain anatomy. Secondly, a more accurate skull stripping template was constructed on two open access datasets. Thirdly, we improved the commonly used segmentation evaluation metrics, such as Dice, Jaccard, sensitivity and precision, and proposed quantitative boundary-oriented evaluation indicators that accurately reflect the vulnerable error segmentation of sulci, gyrus and brainstem. The proposed brain template is widely compared with the existing segmentation template and various automatic brain extraction results.