Search
Search results for: FEATURE IMPORTANCE
-
Feature Importance of Stabilised Rammed Earth Components Affecting the Compressive Strength Calculated with Explainable Artificial Intelligence Tools
Publication -
Audio Feature Analysis for Precise Vocalic Segments Classification in English
PublicationAn approach to identifying the most meaningful Mel-Frequency Cepstral Coefficients representing selected allophones and vocalic segments for their classification is presented in the paper. For this purpose, experiments were carried out using algorithms such as Principal Component Analysis, Feature Importance, and Recursive Parameter Elimination. The data used were recordings made within the ALOFON corpus containing audio signal...
-
Optimization-Based Robustness Enhancement of Compact Microwave Component Designs with Response Feature Regression Surrogates
PublicationThe ability to evaluate the effects of fabrication tolerances and other types of uncertainties is a critical part of microwave design process. Improving the immunity of the device to parameter deviations is equally important, especially when the performance specifications are stringent and can barely be met even assuming a perfect manufacturing process. In the case of modern miniaturized microwave components of complex topologies,...
-
Evaluating the risk of endometriosis based on patients’ self-assessment questionnaires
PublicationBackground Endometriosis is a condition that significantly affects the quality of life of about 10 % of reproductive-aged women. It is characterized by the presence of tissue similar to the uterine lining (endometrium) outside the uterus, which can lead lead scarring, adhesions, pain, and fertility issues. While numerous factors associated with endometriosis are documented, a wide range of symptoms may still be undiscovered. Methods In...
-
Machine learning for the management of biochar yield and properties of biomass sources for sustainable energy
PublicationBiochar is emerging as a potential solution for biomass conversion to meet the ever increasing demand for sustainable energy. Efficient management systems are needed in order to exploit fully the potential of biochar. Modern machine learning (ML) techniques, and in particular ensemble approaches and explainable AI methods, are valuable for forecasting the properties and efficiency of biochar properly. Machine-learning-based forecasts,...
-
Modern remote sensing and the challenges facing education systems in terms of its teaching
PublicationCurrently the fastest growing area of geodesy is undoubtedly remote sensing. The importance that it has recently conducted on the effectiveness of worldwide research determines its huge success. Examination of the specific characteristics of objects without direct contact with them is a key feature has opened the way to the new very interesting areas of contemporary research. In this light, it seems reasonable to say that there...
-
Feature extraction in detection and recognition of graphical objects
PublicationDetection and recognition of graphic objects in images are of great and growing importance in many areas, such as medical and industrial diagnostics, control systems in automation and robotics, or various types of security systems, including biometric security systems related to the recognition of the face or iris of the eye. In addition, there are all systems that facilitate the personal life of the blind people, visually impaired...
-
Application of gas chromatographic data and 2D molecular descriptors for accurate global mobility potential prediction
PublicationMobility is a key feature affecting the environmental fate, which is of particular importance in the case of persistent organic pollutants (POPs) and emerging pollutants (EPs). In this study, the global mobility classification artificial neural networks-based models employing GC retention times (RT) and 2D molecular descriptors were constructed and validated. The high usability of RT was confirmed based on the feature selection...
-
Revisiting Supervision for Continual Representation Learning
Publication"In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, there is a growing interest in unsupervised continual learning, which makes use of the vast amounts of unlabeled data. Recent studies have highlighted the strengths of unsupervised methods, particularly self-supervised learning, in providing robust representations. The improved...
-
Methodology of generation of CFD meshes and 4D shape reconstruction of coronary arteries from patient-specific dynamic CT
PublicationDue to the difficulties in retrieving both the time‑dependent shapes of the vessels and the generation of numerical meshes for such cases, most of the simulations of blood flow in the cardiac arteries use static geometry. The article describes a methodology for generating a sequence of time‑dependent 3D shapes based on images of different resolutions and qualities acquired from ECG‑gated coronary artery CT angiography. The precision...
-
Systems of General Grants for Local Governments in Selected EU Countries Against the Background of the General Theory of Fiscal Policy
PublicationFiscal policy, including its expenditure aspect, is often discussed and analysed from a variety of angles in the literature on public finances, undoubtedly due to the major importance of this topic. However, not all areas of the expenditure part of fiscal policy have been subjected to in-depth analysis. One of the less discussed tools of fiscal policy consists of general purpose transfers, which are a certain type of expenditure...
-
Creating a Realible Music Discovery and Recomendation System
PublicationThe aim of this paper is to show problems related to creating a reliable music dis-covery system. The SYNAT database that contains audio files is used for the purpose of experiments. The files are divided into 22 classes corresponding to music genres with different cardinality. Of utmost importance for a reliable music recommendation system are the assignment of audio files to their appropriate gen-res and optimum parameterization...
-
Forewarned Is Forearmed: Machine Learning Algorithms for the Prediction of Catheter-Induced Coronary and Aortic Injuries
PublicationCatheter-induced dissections (CID) of coronary arteries and/or the aorta are among the most dangerous complications of percutaneous coronary procedures, yet the data on their risk factors are anecdotal. Logistic regression and five more advanced machine learning techniques were applied to determine the most significant predictors of dissection. Model performance comparison and feature importance ranking were evaluated. We identified...
-
Modelling the time-dependent behaviour of soft soils
PublicationTime-dependence of soft soils has already been thoroughly investigated. The knowledge on creep and relaxation phenomena is generally available in the literature. However, it is still rarely applied in practice. Regarding the organic soils, geotechnical engineers mostly base their calculations on the simple assumptions. Yet, as presented within this paper, the rate-dependent behaviour of soft soils is a very special and important...
-
Fusion-based Representation Learning Model for Multimode User-generated Social Network Content
PublicationAs mobile networks and APPs are developed, user-generated content (UGC), which includes multi-source heterogeneous data like user reviews, tags, scores, images, and videos, has become an essential basis for improving the quality of personalized services. Due to the multi-source heterogeneous nature of the data, big data fusion offers both promise and drawbacks. With the rise of mobile networks and applications, UGC, which includes...
-
Tacit Knowledge Sharing and Personal Branding. How to Derive Innovation From Project Teams?
PublicationInnovation, relationships, cooperation, and knowledge are key factors which determine a competitive advantage in the networked economy. A network serves as a contemporary form of market process coordination. Network economy, according to the idea of prosumerism, is founded on collaboration of individual creators based on a network of values instead of hierarchical dependencies. Another feature of a network is that it imposes symmetry...
-
The role of isolated farmsteads in the open landscape protection on the example of Kashubia
PublicationAs a result of the social and economic transformation of rural areas, open landscapes are disappearing. Former farmsteads are being devastated or beginning to lose their landscape context due to the spread of residential building development. At the same time, in many places, the farmstead form is clearly legible and remains an element with which the view is structured and enriched. The article was aimed at drawing attention to...
-
Is Digitalization Improving Governance Quality? Correlating Analog and Digital Benchmarks
PublicationThe digitalization of public governance and the resulting concept of electronic governance is a characteristic feature of contemporary information society. Both can be defined as the process and outcome of digital transformation: transformation of the “analog” version of governance into “digital” governance. Measuring both versions of governance against typical performance measures of efficiency, effectiveness, equity, openness...