Wyszukiwarka
Filtry
wszystkich: 57
Wyniki wyszukiwania dla: incremental learning
-
Intra-subject class-incremental deep learning approach for EEG-based imagined speech recognition
PublikacjaBrain–computer interfaces (BCIs) aim to decode brain signals and transform them into commands for device operation. The present study aimed to decode the brain activity during imagined speech. The BCI must identify imagined words within a given vocabulary and thus perform the requested action. A possible scenario when using this approach is the gradual addition of new words to the vocabulary using incremental learning methods....
-
MagMax: Leveraging Model Merging for Seamless Continual Learning
PublikacjaThis paper introduces a continual learning approach named MagMax, which utilizes model merging to enable large pre-trained models to continuously learn from new data without forgetting previously acquired knowledge. Distinct from traditional continual learning methods that aim to reduce forgetting during task training, MagMax combines sequential fine-tuning with a maximum magnitude weight selection for effective knowledge integration...
-
Adapt Your Teacher: Improving Knowledge Distillation for Exemplar-free Continual Learning
PublikacjaIn this work, we investigate exemplar-free class incremental learning (CIL) with knowledge distillation (KD) as a regularization strategy, aiming to prevent forgetting. KDbased methods are successfully used in CIL, but they often struggle to regularize the model without access to exemplars of the training data from previous tasks. Our analysis reveals that this issue originates from substantial representation shifts in the teacher...
-
Active Learning on Ensemble Machine-Learning Model to Retrofit Buildings Under Seismic Mainshock-Aftershock Sequence
PublikacjaThis research presents an efficient computational method for retrofitting of buildings by employing an active learning-based ensemble machine learning (AL-Ensemble ML) approach developed in OpenSees, Python and MATLAB. The results of the study shows that the AL-Ensemble ML model provides the most accurate estimations of interstory drift (ID) and residual interstory drift (RID) for steel structures using a dataset of 2-, to 9-story...
-
Divide and not forget: Ensemble of selectively trained experts in Continual Learning
PublikacjaClass-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a mixture-of-expert technique, where different models work together to solve the task. However, the experts are usually trained all at once using whole task data, which makes them all prone to forgetting and increasing computational burden. To address this limitation,...
-
Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery
Publikacja"Generalized Continual Category Discovery (GCCD) tackles learning from sequentially arriving, partially labeled datasets while uncovering new categories. Traditional methods depend on feature distillation to prevent forgetting the old knowledge. However, this strategy restricts the model’s ability to adapt and effectively distinguish new categories. To address this, we introduce a novel technique integrating a learnable projector...
-
Machine learning-based seismic fragility and seismic vulnerability assessment of reinforced concrete structures
PublikacjaMany studies have been performed to put quantifying uncertainties into the seismic risk assessment of reinforced concrete (RC) buildings. This paper provides a risk-assessment support tool for purpose of retrofitting and potential design strategies of RC buildings. Machine Learning (ML) algorithms were developed in Python software by innovative methods of hyperparameter optimization, such as halving search, grid search, random...
-
Machine learning-based seismic response and performance assessment of reinforced concrete buildings
PublikacjaComplexity and unpredictability nature of earthquakes makes them unique external loads that there is no unique formula used for the prediction of seismic responses. Hence, this research aims to implement the most well-known Machine Learning (ML) methods in Python software to propose a prediction model for seismic response and performance assessment of Reinforced Concrete Moment-Resisting Frames (RC MRFs). To prepare 92,400 data...
-
Seismic response and performance prediction of steel buckling-restrained braced frames using machine-learning methods
PublikacjaNowadays, Buckling-Restrained Brace Frames (BRBFs) have been used as lateral force-resisting systems for low-, to mid-rise buildings. Residual Interstory Drift (RID) of BRBFs plays a key role in deciding to retrofit buildings after seismic excitation; however, existing formulas have limitations and cannot effectively help civil engineers, e.g., FEMA P-58, which is a conservative estimation method. Therefore, there is a need to...
-
Machine learning-based prediction of seismic limit-state capacity of steel moment-resisting frames considering soil-structure interaction
PublikacjaRegarding the unpredictable and complex nature of seismic excitations, there is a need for vulnerability assessment of newly constructed or existing structures. Predicting the seismic limit-state capacity of steel Moment-Resisting Frames (MRFs) can help designers to have a preliminary estimation and improve their views about the seismic performance of the designed structure. This study improved data-driven decision techniques in...
-
Predicting seismic response of SMRFs founded on different soil types using machine learning techniques
PublikacjaPredicting the Maximum Interstory Drift Ratio (M-IDR) of Steel Moment-Resisting Frames (SMRFs) is a useful tool for designers to approximately evaluate the vulnerability of SMRFs. This study aims to explore supervised Machine Learning (ML) algorithms to build a surrogate prediction model for SMRFs to reduce the need for complex modeling. For this purpose, twenty well-known ML algorithms implemented in Python software are trained...
-
Optimization-based stacked machine-learning method for seismic probability and risk assessment of reinforced concrete shear walls
PublikacjaEfficient seismic risk assessment aids decision-makers in formulating citywide risk mitigation plans, providing insights into building performance and retrofitting costs. The complexity of modeling, analysis, and post-processing of the results makes it hard to fast-track the seismic probabilities, and there is a need to optimize the computational time. This research addresses seismic probability and risk assessment of reinforced...
-
Incremental Dynamic Analysis and Fragility Assessment of Buildings with Different Structural Arrangements Experiencing Earthquake-Induced Structural Pounding
PublikacjaStructural pounding is considered as one of the most critical phenomena occurring during earthquakes. This paper presents the incremental dynamic analysis and fragility assessment of buildings experiencing earthquake-induced pounding. Three 3-D buildings with different number of storeys and under different structural arrangements have been considered. Three pounding scenarios have been taken into account, i.e. pounding between...
-
Sampling-based novel heterogeneous multi-layer stacking ensemble method for telecom customer churn prediction
PublikacjaIn recent times, customer churn has become one of the most significant issues in business-oriented sectors with telecommunication being no exception. Maintaining current customers is particularly valuable due to the high degree of rivalry among telecommunication companies and the costs of acquiring new ones. The early prediction of churned customers may help telecommunication companies to identify the causes of churn and design...
-
Photovoltaic Maximum Power Point Technique based on Incremental Conductance (INCON) control algorithm
PublikacjaMaximum output power status can significantly improve the deployment rate of solar energy system. In order to get the maximum power output, issue of tracking maximum power point (MPP), reduced harmonics around MPP and improve efficiency of the solar power energy system, this paper presents the improved maximum power point tracking (MPPT) control...
-
Surface Structure of Components Created by Stereolitography
PublikacjaStereolithography is an additive rapid prototyping method. This method is based on the principle of solidifying a liquid photopolymer (resin) by laser radiation. Models obtained with this method are characterized by a specific surface structure called “stairstep effect”. It causes that, the surface should be processed by additional finishing (postprocessing). To minimize the additional machining process, the model should be set...
-
Elastoplastic material law in 6-parameter nonlinear shell theory
PublikacjaWe develop the elastoplastic constitutive relations for nonlinear exact 6-parameter shell theory. A J2-type theory with strain hardening is formulated that takes into account asymmetric membrane strain measures. The incremental equations are solved using implicit Euler scheme with closest point projection algorithm. The presented test example shows the correctness of the proposed approach. Influence of micropolar material parameters...
-
Switched-capacitor DC-DC converters in arbitrary switching mode - topologically derived resistive models based on incremental graph approach.
PublikacjaIn the preceding paper we reviewed some of modeling approaches aimed at systematic formulation and solution of switched capacitor DC-DC converters. In our review, special attention was paid to computationally efficient and mathematically elegant methods. In so doing we had tried to demonstrate the virtues of unified Incremental Graph (IG) approach. Incremental Graph is, in concept, a tool originally created for analysis and synthesis...
-
Uniform Model Interface for Assurance Case Integration with System Models
PublikacjaAssurance cases are developed and maintained in parallel with corresponding system models and therefore need to reference each other. Managing the correctness and consistency of interrelated safety argument and system models is essential for system dependability and is a nontrivial task. The model interface presented in this paper enables a uniform process of establishing and managing assurance case references to various types...
-
On modelling and non-linear elasto-plastic analysis of thin shells with deformable junctions
PublikacjaThe undeformed base surface of the irregular thin shell is modelled by the union of a finite number of regular smooth surface elements joined together along spatial curvilinear surface edges. The equilibrium conditions are formulated by postulating an appropriate form of the principle of virtual work, where also deformability of shell junctions is taken into account. The PVW is then discretised by C1 finite elements and the incremental-iterative...
-
Jamming and jamming mitigation for selected 5G military scenarios
PublikacjaThis paper presents jamming and jamming mitigation techniques, which can be used in relation to emerging military systems based on fifth-generation (5G) technology. Nowadays, 5G technology provides incremental improvements over Long Term Evolution (LTE) networks resulting in the enhancement of civilian communications. Considering enormous possible applications of this new technology, it is feasible to use them in military utilities....
-
Experience with instantiating an automated testing process in the context of incremental and evolutionary software development
PublikacjaThe purpose of this article is to present experiences from testing a complex AJAX-based Internet-system which is under development for more than five years. The development process follows incremental and evolutionary lifecycle model and the system is delivered in subsequent releases. Delivering a new release involves both, the new tests (related to the new and/or modified functionalities) and the regression tests (after their...
-
EXPERIMENTAL EVALUATION OF DLC/STEEL SLIDING CONTACTS’ OPERATIONAL ENVELOPE
PublikacjaIn an industrial project concerning sliding bearings, a sliding pair was selected of high alloy steel vs. industrial grade DLC coated high alloy steel as a basis for an innovative design of high performance sliding bearings lubricated with a synthetic oil for use in geared transmission units. The development process required credible data on the ultimate resistance of the sliding pair to very high contact stress. An experimental...
-
Improvement of Performance Level of Steel Moment-Resisting Frames Using Tuned Mass Damper System
PublikacjaIn this paper, parameters of the tuned mass dampers are optimized to improve the performance level of steel structures during earthquakes. In this regard, a six-story steel frame is modeled using a concentrated plasticity method. Then, the optimum parameters of the Tuned Mass Damper (TMD) are determined by minimizing the maximum drift ratio of the stories. The performance level of the structure is also forced to be located in a...
-
Predicting the seismic collapse capacity of adjacent structures prone to pounding
PublikacjaIn crowded cities, many structures are often constructed in a very close vicinity; therefore, during severe earthquakes, pounding phenomenon occurs due to out-of-phase vibrations of adjacent structures. In this study, pounding of adjacent structures is investigated up to the occurrence of total collapse. The novelty of this study is performing incremental dynamic analyses to compute the seismic collapse capacities of both pounding...
-
A perfect hashing incremental scheme for unranked trees using pseudo-minimal automata
PublikacjaWe describe a technique that maps unranked trees to arbitrary hash codes using a bottom-up deterministic tree automaton (DTA). In contrast to other hashing techniques based on automata, our procedure builds a pseudo-minimal DTA for this purpose. A pseudo-minimal automaton may be larger than the minimal one accepting the same language but, in turn, it contains proper elements (states or transitions that are unique) for every input...
-
Incremental construction of Minimal Tree Automata [online]
PublikacjaWe describe an algorithm that allows the incremental addition or removal of unranked ordered trees to minimal frontier-to-root deterministic tree automaton (DTA). The algorithm takes a tree t and a minimal DTA A as input; it outputs a minimal DTA A' which accepts the language L(A) accepted by A incremented (or decremented) with the tree t. The algorithm can be used to efficiently maintain dictionaries which store large collections...
-
SENSITIVITY OF PUBLIC PLACES IN GDAŃSK OSOWA DISTRICT
PublikacjaThis paper summarises the results of the research carried out at the University of Ljubljana, Faculty of Architecture, Slovenia, during the PhD visiting period of the first author from the Gdansk University of Technology, Poland, in the framework of the PhD course "Sensitive urban places", leaded by the second author. Focusing to the specific problems of the Gdansk Osowa district in Poland, this research develops the idea of sensitivity...
-
Evaluation of pounding effects between reinforced concrete frames subjected to far-field earthquakes in terms of damage index
PublikacjaIn this paper, three different damage indexes were used to detect nonlinear damages in two adjacent Reinforced Concrete (RC) structures considering pounding effects. 2-, 4- and 8-story benchmark RC Moment Resisting Frames (MRFs) were selected for this purpose with 60%, 75%, and 100% of minimum separation distance and also without any in-between separation gap. These structures were analyzed using the incremental dynamic analysis...
-
A new viscoelastic method of calculation of low-temperature thermal stresses in asphalt layers of pavements
PublikacjaThe paper presents a new method of calculation of thermal stresses in asphalt layers of pavements induced by cooling or heating. The method, developed by the author, is based on the analytical solution for the linear viscoelastic Burgers model extended numerically for the case of asphalt layers whose rheological parameters are strongly dependent on temperature. The coefficient of thermal expansion and Poisson’s ratio may optionally...
-
Introducing a Computational Method to Retrofit Damaged Buildings under Seismic Mainshock-Aftershock Sequence
PublikacjaRetrofitting damaged buildings is a challenge for engineers, since commercial software does not have the ability to consider the local damages and deformed shape of a building resulting from the mainshock record of an earthquake before applying the aftershock record. In this research, a computational method for retrofitting of damaged buildings under seismic mainshock-aftershock sequences is proposed, and proposed computational...
-
Non-Linear Analysis of Structures Utilizing Load-Discretization of Stiffness Matrix Method with Coordinate Update
PublikacjaThis paper proposes a stiffness method based structural analysis algorithm for geometrically non-linear structures. In this study, the applied load on the joints has been discretized to a sequence of a few loadings applied. Each loading step produces incremental external nodal displacements, which are added to the corresponding coordinates to get a new geometrical shape of the structure. This process is iteratively repeated until...
-
Evaluation the P-Delta Effect on Collapse Capacity of Adjacent Structures Subjected to Far-field Ground Motions
PublikacjaIn urban areas, adjacent structures can be seen in any insufficient distance from each other, because of economic reasons and refusal of acquired minimum separation distance according to seismic previsions. Collapse capacity assessment of structures is one of the important objectives of performance-based seismic engineering. The purpose of this study is to consider the pounding phenomenon and P-Delta effect in seismic collapse...
-
Damage of a post-tensioned concrete bridge – Unwanted cracks of the girders
PublikacjaThe cracking of a post-tensioned T-beam superstructure, which was built using the incremental launching method, is analyzed in the paper. The problem is studied in detail, as specific damage was observed in the form of longitudinal cracks, especially in the mid-height zone of the girder at the interface of two assembly sections. The paper is a case study. A detailed inspection is done and non-destructive testing results of the...
-
Enhancing seismic performance of steel buildings having semi-rigid connection with infill masonry walls considering soil type effects
PublikacjaUnpreventable constructional defects are the main issues in the case of steel Moment-Resisting Frames (MRFs) that mostly occur in the rigidities of beam-to-column connections. The present article aims to investigate the effects of different rigidities of structures and to propose Infill Masonry Walls (IMWs) as retrofitting strategy for the steel damaged buildings. A fault or failure to meet a certain consideration of the soil type...
-
Advanced Scalar-valued Intensity Measures for Residual Drift Prediction of SMRFs with Fluid Viscous Dampers
PublikacjaMaximum Residual Inter-story Drift Ratio (RIDRmax) plays an important role to specify the state of a structure after severe earthquake and the possibility of repairing the structure. Therefore, it is necessary to predict the RIDRmax of Steel Moment-Resisting Frames (SMRFs) with high reliability by employing powerful Intensity Measures (IMs). This study investigates the efficiency and sufficiency of scalar-valued IMs for predicting...
-
Investigating the effects of structural pounding on the seismic performance of adjacent RC and steel MRFs
PublikacjaAn insufficient separation distance between adjacent buildings is the main reason for structural pounding during severe earthquakes. The lateral load resistance system, fundamental natural period, mass, and stiffness are important factors having the influence on collisions between two adjacent structures. In this study, 3-, 5- and 9-story adjacent reinforced concrete and steel Moment Resisting Frames (MRFs) were considered to investigate...
-
The impact of institutions on innovation networks: empirical evidence from Poland
PublikacjaInnovation networks may accelerate and improve the innovation process, while institutional pathologies may hamper it. This study employs the Kruskal-Wallis H test and regression analysis to determine if the relationship between institutions and innovation networks does exist among the investigated variables. The purpose of the study was to find out whether cooperation with special local institutions influences the innovative behaviour...
-
Seismic damage diagnosis in adjacent steel and RC MRFs considering pounding effects through improved wavelet-based damage-sensitive feature
PublikacjaThis paper aims to propose complex Morlet (cmorfb-fc) wavelet-based refined damage-sensitive feature (rDSF) as a new and more precise damage indicator to diagnose seismic damages in adjacent steel and Reinforced Concrete (RC) Moment Resisting Frames (MRFs) assuming pounding conditions using acceleration responses. The considered structures include 6- and 9-story steel and 4- and 8-story RC benchmark MRFs that are assumed to have...
-
Enhancing Seismic Performance of Semi-rigid Connection Using Shape Memory Alloy Bolts Considering Nonlinear Soil–Structure Interaction
PublikacjaSteel Moment-Resisting Frames (SMRFs) have their lateral resistance for their rigid connections, while real conditions have shown that the rigidity of a connection depends on the bolts and the end-plate thickness, which may not provide the assumed rigidity in design process. In this research, the main goal is to enhance the semi-rigid connections using shape memory alloy (SMA) bolts and explore their effects on the seismic limit-state...
-
Applications of Additively Manufactured Tools in Abrasive Machining—A Literature Review
PublikacjaHigh requirements imposed by the competitive industrial environment determine the development directions of applied manufacturing methods. 3D printing technology, also known as additive manufacturing (AM), currently being one of the most dynamically developing production methods, is increasingly used in many different areas of industry. Nowadays, apart from the possibility of making prototypes of future products, AM is also used...
-
Performance of Vector-valued Intensity Measures for Estimating Residual Drift of Steel MRFs with Viscous Dampers
PublikacjaViscous Dampers (VDs) are widely used as passive energy dissipation system for improving seismic performance levels especially in retrofitting of buildings. Residual Inter-story Drift Ratio (R-IDR) is another important factor that specifies the condition of building after earthquake. The values of R-IDR illustrates the possibility of retrofitting and repairing of a building. Therefore, this study aims to explore the vector-valued...
-
Fragility analysis of structural pounding between adjacent structures arranged in series with various alignment configurations under near‑field earthquakes
PublikacjaA major cause of local to total damages is related to structural pounding in a large number of past earthquakes. In general, these collisions take place as a result of differences in the dynamic characteristics of the colliding structures. To acquire a better perception of the behavior of structures, in this paper, three structures featuring different heights are modeled in series and with various configurations next to each other...
-
Neural Architecture Search for Skin Lesion Classification
PublikacjaDeep neural networks have achieved great success in many domains. However, successful deployment of such systems is determined by proper manual selection of the neural architecture. This is a tedious and time-consuming process that requires expert knowledge. Different tasks need very different architectures to obtain satisfactory results. The group of methods called the neural architecture search (NAS) helps to find effective architecture...
-
Incremental dynamic analysis and fragility assessment of buildings founded on different soil types experiencing structural pounding during earthquakes
PublikacjaThe effect of the soil type on buildings experiencing pounding during earthquakes is investigated in this study using the incremental dynamic analysis and fragility assessment methods. Three 3-D structures with different number of storeys (4, 6 and 8) were considered in this study. Three pounding scenarios between these three buildings were taken into account, i.e. pounding between 4-storey and 6-storey buildings, between 4-storey...
-
Predicting the seismic collapse capacity of adjacent SMRFs retrofitted with fluid viscous dampers in pounding condition
PublikacjaSevere damages of adjacent structures due to structural pounding during earthquakes have emphasized the need to use some seismic retrofit strategy to enhance the structural performance. The purpose of this paper is to study the influence of using linear and nonlinear Fluid Viscous Dampers (FVDs) on the seismic collapse capacities of adjacent structures prone to pounding and proposing modification factors to modify the median...
-
Probabilistic assessment of SMRFs with infill masonry walls incorporating nonlinear soil-structure interaction
PublikacjaInfill Masonry Walls (IMWs) are used in the perimeter of a building to separate the inner and outer space. IMWs may affect the lateral behavior of buildings, while they are different from those partition walls that separate two inner spaces. This study focused on the seismic vulnerability assessment of Steel Moment-Resisting Frames (SMRFs) assuming different placement of IMWs incorporating nonlinear Soil-Structure Interaction (SSI)....
-
Seismic performance evaluation of steel buckling-restrained braced frames including SMA materials
PublikacjaThe permanent deformation of the building after seismic excitations can be determined by the Maximum Residual Interstory Drift Ratio (MR-IDR), which may be used for measuring the damage states. Low-post yield stiffness of the steel buckling-restrained braced frame (BRBF) makes this system vulnerable to large MR-IDR after a severe earthquake event. To overcome this issue, this paper investigates the seismic limit state performances...
-
Seismic Response Analysis of Knee-Braced Steel Frames Using Ni-Ti Shape Memory Alloys (SMAs)
PublikacjaShape Memory Alloys (SMAs) are known as active materials that can be widely used for structural purposes due to their flag-shape behavior under loading and reloading. Their unique characteristics provided a potential solution for civil engi-neers especially to model buildings with the capability of dissipating seismic en-ergy. In this study, the main purpose is to explore the seismic behavior of Knee-Braced Frames (KBFs) and...
-
Enhancing seismic performance of buckling-restrained brace frames equipped with innovative bracing systems
PublikacjaNowadays, to improve the performance of conventional bracing systems, in which, buckling in the pressure loads is the main disadvantage, the buckling-restrained brace (BRB) is introduced as a solution. In this study, the performance of the BRB system was improved with innovative lateral-resisting systems of double-stage yield buckling-restrained brace (DYB), and a combination of DYB improved with shape memory alloy (SMA) materials...