Search
Search results for: DEEP NEURAL NETWORK TRAINING
-
Video of LEGO bricks on conveyor belt - Technic Brics
Open Research DataThe set contains videos of LEGO bricks (Technic bricks) moving on a white conveyor belt. The videos were prepared for training neural network for recognition of LEGO bricks. The bricks were separated as much as possible and in most cases they should not overlap. The images were taken from different sides by stationary camera located over the final conveyor...
-
Video of LEGO bricks on conveyor belt - Technic axles
Open Research DataThe set contains videos of LEGO bricks (Technic axles) moving on a white conveyor belt. The videos were prepared for training neural network for recognition of LEGO bricks. The bricks were separated as much as possible and in most cases they should not overlap. The images were taken from different sides by stationary camera located over the final conveyor...
-
Using Long-Short term Memory networks with Genetic Algorithm to predict engine condition
PublicationPredictive maintenance (PdM) is a type of approach for maintenance processes, allowing maintenance actions to be managed depending on the machine's current condition. Maintenance is therefore carried out before failures occur. The approach doesn’t only help avoid abrupt failures but also helps lower maintenance cost and provides possibilities to manufacturers to manage maintenance budgets in a more efficient way. A new deep neural...
-
Open-Set Speaker Identification Using Closed-Set Pretrained Embeddings
PublicationThe paper proposes an approach for extending deep neural networks-based solutions to closed-set speaker identification toward the open-set problem. The idea is built on the characteristics of deep neural networks trained for the classification tasks, where there is a layer consisting of a set of deep features extracted from the analyzed inputs. By extracting this vector and performing anomaly detection against the set of known...
-
Playback detection using machine learning with spectrogram features approach
PublicationThis paper presents 2D image processing approach to playback detection in automatic speaker verification (ASV) systems using spectrograms as speech signal representation. Three feature extraction and classification methods: histograms of oriented gradients (HOG) with support vector machines (SVM), HAAR wavelets with AdaBoost classifier and deep convolutional neural networks (CNN) were compared on different data partitions in respect...
-
Video of LEGO bricks on conveyor belt - Special Brics
Open Research DataThe set contains videos of LEGO bricks (special bricks, with additional connectors etc.) moving on a white conveyor belt. The videos were prepared for training neural network for recognition of LEGO bricks. The bricks were separated as much as possible and in most cases they should not overlap. The images were taken from different sides by stationary...
-
Video of LEGO bricks on conveyor belt - Wide Brics
Open Research DataThe set contains videos of LEGO bricks (wide bricks, with each side having more than 1 stud) moving on a white conveyor belt. The videos were prepared for training neural network for recognition of LEGO bricks. The bricks were separated as much as possible and in most cases they should not overlap. The images were taken from different sides by stationary...
-
Video of LEGO bricks on conveyor belt - minifigures, animals, plants and accessories
Open Research DataThe set contains videos of LEGO bricks (minifigures, animals, plants and accessories) moving on a white conveyor belt. The images were prepared for training neural network for recognition of LEGO bricks. The bricks were separated as much as possible and in most cases they should not overlap. The images were taken from different sides by stationary camera...
-
Video of LEGO bricks on conveyor belt - Narrow Brics
Open Research DataThe set contains videos of LEGO bricks (narrow bricks, with on side no wider than 1 stud) moving on a white conveyor belt. The videos were prepared for training neural network for recognition of LEGO bricks. The bricks were separated as much as possible and in most cases they should not overlap. The images were taken from different sides by stationary...
-
When Neural Networks Meet Decisional DNA: A Promising New Perspective for Knowledge Representation and Sharing
PublicationABSTRACT In this article, we introduce a novel concept combining neural network technology and Decisional DNA for knowledge representation and sharing. Instead of using traditional machine learning and knowledge discovery methods, this approach explores the way of knowledge extraction through deep learning processes based on a domain’s past decisional events captured by Decisional DNA. We compare our approach with kNN (k-nearest...
-
LSTM-based method for LOS/NLOS identification in an indoor environment
PublicationDue to the multipath propagation, harsh indoor environment significantly impacts transmitted signals which may adversely affect the quality of the radiocommunication services, with focus on the real-time ones. This negative effect may be significantly reduced (e.g. resources management and allocation) or compensated (e.g. correction of position estimation in radiolocalisation) by the LOS/NLOS identification algorithm. This paper...
-
Deep Learning: A Case Study for Image Recognition Using Transfer Learning
PublicationDeep learning (DL) is a rising star of machine learning (ML) and artificial intelligence (AI) domains. Until 2006, many researchers had attempted to build deep neural networks (DNN), but most of them failed. In 2006, it was proven that deep neural networks are one of the most crucial inventions for the 21st century. Nowadays, DNN are being used as a key technology for many different domains: self-driven vehicles, smart cities,...
-
Deep Learning
PublicationDeep learning (DL) is a rising star of machine learning (ML) and artificial intelligence (AI) domains. Until 2006, many researchers had attempted to build deep neural networks (DNN), but most of them failed. In 2006, it was proven that deep neural networks are one of the most crucial inventions for the 21st century. Nowadays, DNN are being used as a key technology for many different domains: self-driven vehicles, smart cities,...
-
Olgun Aydin dr
PeopleOlgun Aydin finished his PhD by publishing a thesis about Deep Neural Networks. He works as a Principal Machine Learning Engineer in Nike, and works as Assistant Professor in Gdansk University of Technology in Poland. Dr. Aydin is part of editorial board of "Journal of Artificial Intelligence and Data Science" Dr. Aydin served as Vice-Chairman of Why R? Foundation and is member of Polish Artificial Intelligence Society. Olgun is...
-
CNN Architectures for Human Pose Estimation from a Very Low Resolution Depth Image
PublicationThe paper is dedicated to proposing and evaluating a number of convolutional neural network architectures for calculating a multiple regression on 3D coordinates of human body joints tracked in a single low resolution depth image. The main challenge was to obtain a high precision in case of a noisy and coarse scan of the body, as observed by a depth sensor from a large distance. The regression network was expected to reason about...
-
Video of LEGO bricks on conveyor belt - wheels, tires and caterpillars
Open Research DataThe set contains videos of LEGO bricks (wheels, tires and caterpillars) moving on a white conveyor belt. The images were prepared for training neural network for recognition of LEGO bricks. The bricks were separated as much as possible and in most cases they should not overlap. The images were taken from different sides by stationary camera located...
-
TensorHive: Management of Exclusive GPU Access for Distributed Machine Learning Workloads
PublicationTensorHive is a tool for organizing work of research and engineering teams that use servers with GPUs for machine learning workloads. In a comprehensive web interface, it supports reservation of GPUs for exclusive usage, hardware monitoring, as well as configuring, executing and queuing distributed computational jobs. Focusing on easy installation and simple configuration, the tool automatically detects the available computing...
-
Deep learning techniques for biometric security: A systematic review of presentation attack detection systems
PublicationBiometric technology, including finger vein, fingerprint, iris, and face recognition, is widely used to enhance security in various devices. In the past decade, significant progress has been made in improving biometric sys- tems, thanks to advancements in deep convolutional neural networks (DCNN) and computer vision (CV), along with large-scale training datasets. However, these systems have become targets of various attacks, with...
-
Physics-guided neural networks (PGNNs) to solve differential equations for spatial analysis
PublicationNumerous examples of physically unjustified neural networks, despite satisfactory performance, generate contradictions with logic and lead to many inaccuracies in the final applications. One of the methods to justify the typical black-box model already at the training stage and lead to many inaccuracies in the final applications. One of the methods to justify the typical black-box model already at the training stage involves extending...
-
Deep learning-enabled integration of renewable energy sources through photovoltaics in buildings
PublicationInstalling photovoltaic (PV) systems in buildings is one of the most effective strategies for achieving sustainable energy goals and reducing carbon emissions. However, the requirement for efficient energy management, the fluctuating energy demands, and the intermittent nature of solar power are a few of the obstacles to the seamless integration of PV systems into buildings. These complexities surpass the capabilities of rule-based...
-
OBTAINING FLUID FLOW PATTERN FOR TURBINE STAGE WITH NEURAL MODEL.
PublicationIn the paper possibility of applying neural model to obtaining patterns of proper operation for fluid flow in turbine stage for fluid-flow diagnostics is discussed. Main differences between Computational Fluid Dynamics (CFD) solvers and neural model is given, also limitations and advantages of both are considered. Time of calculations of both methods was given, also possibilities of shortening that time with preserving the accuracy...
-
Investigating Feature Spaces for Isolated Word Recognition
PublicationMuch attention is given by researchers to the speech processing task in automatic speech recognition (ASR) over the past decades. The study addresses the issue related to the investigation of the appropriateness of a two-dimensional representation of speech feature spaces for speech recognition tasks based on deep learning techniques. The approach combines Convolutional Neural Networks (CNNs) and timefrequency signal representation...
-
Gesture Recognition With the Linear Optical Sensor and Recurrent Neural Networks
PublicationIn this paper, the optical linear sensor, a representative of low-resolution sensors, was investigated in the multiclass recognition of near-field hand gestures. The recurrent neural network (RNN) with a gated recurrent unit (GRU) memory cell was utilized as a gestures classifier. A set of 27 gestures was collected from a group of volunteers. The 27 000 sequences obtained were divided into training, validation, and test subsets....
-
Adaptive CAD-Model Construction Schemes
PublicationTwo advanced surrogate model construction techniques are discussed in this paper. The models employ radial basis function (RBF)interpolation scheme or artificial neural networks (ANN) with a new training algorithm. Adaptive sampling technique is applied withrespect to all variables. Histograms showing the quality of the models are presented. While the quality of RBF models is satisfactory, theperformance of the ANN models obtained...
-
Deep-Learning-Based Precise Characterization of Microwave Transistors Using Fully-Automated Regression Surrogates
PublicationAccurate models of scattering and noise parameters of transistors are instrumental in facilitating design procedures of microwave devices such as low-noise amplifiers. Yet, data-driven modeling of transistors is a challenging endeavor due to complex relationships between transistor characteristics and its designable parameters, biasing conditions, and frequency. Artificial neural network (ANN)-based methods, including deep learning...
-
Neural Modelling of Steam Turbine Control Stage
PublicationThe paper describes possibility of steam turbine control stage neural model creation. It is of great importance because wider application of green energy causes severe conditions for control of energy generation systems operation Results of chosen steam turbine of 200 MW power measurements are applied as an example showing way of neural model creation. They serve as training and testing data of such neural model. Relatively simple...
-
Deep Learning-Based Intrusion System for Vehicular Ad Hoc Networks
PublicationThe increasing use of the Internet with vehicles has made travel more convenient. However, hackers can attack intelligent vehicles through various technical loopholes, resulting in a range of security issues. Due to these security issues, the safety protection technology of the in-vehicle system has become a focus of research. Using the advanced autoencoder network and recurrent neural network in deep learning, we investigated...
-
Deep learning for recommending subscription-limited documents
PublicationDocuments recommendation for a commercial, subscription-based online platform is important due to the difficulty in navigation through a large volume and diversity of content available to clients. However, this is also a challenging task due to the number of new documents added every day and decreasing relevance of older contents. To solve this problem, we propose deep neural network architecture that combines autoencoder with...
-
Underground Water Level Prediction in Remote Sensing Images Using Improved Hydro Index Value with Ensemble Classifier
PublicationThe economic sustainability of aquifers across the world relies on accurate and rapid estimates of groundwater storage changes, but this becomes difficult due to the absence of insitu groundwater surveys in most areas. By closing the water balance, hydrologic remote sensing measures offer a possible method for quantifying changes in groundwater storage. However, it is uncertain to what extent remote sensing data can provide an...
-
Iterative Global Sensitivity Analysis Algorithm with Neural Network Surrogate Modeling
PublicationGlobal sensitivity analysis (GSA) is a method to quantify the effect of the input parameters on outputs of physics-based systems. Performing GSA can be challenging due to the combined effect of the high computational cost of each individual physics-based model, a large number of input parameters, and the need to perform repetitive model evaluations. To reduce this cost, neural networks (NNs) are used to replace the expensive physics-based...
-
Optimal selection of input features and an acompanying neural network structure for the classification purposes - skin lesions case study
PublicationMalignant melanomas are the most deadly type of skin cancers however detected early enough give a high chances for successful treatment. The last years saw the dynamic growth of interest of automatic computer-aided skin cancer diagnosis. Every month brings new research results on new approaches to this problem, new methods of preprocessing, new classifiers, new ideas to follow etc. In particular, the rapid development of dermatoscopy,...
-
Recognition of Emotions in Speech Using Convolutional Neural Networks on Different Datasets
PublicationArtificial Neural Network (ANN) models, specifically Convolutional Neural Networks (CNN), were applied to extract emotions based on spectrograms and mel-spectrograms. This study uses spectrograms and mel-spectrograms to investigate which feature extraction method better represents emotions and how big the differences in efficiency are in this context. The conducted studies demonstrated that mel-spectrograms are a better-suited...
-
Federated Learning in Healthcare Industry: Mammography Case Study
PublicationThe paper focuses on the role of federated learning in a healthcare environment. The experimental setup involved different healthcare providers, each with their datasets. A comparison was made between training a deep learning model using traditional methods, where all the data is stored in one place, and using federated learning, where the data is distributed among the workers. The experiment aimed to identify possible challenges...
-
IFE: NN-aided Instantaneous Pitch Estimation
PublicationPitch estimation is still an open issue in contemporary signal processing research. Nowadays, growing momentum of machine learning techniques application in the data-driven society allows for tackling this problem from a new perspective. This work leverages such an opportunity to propose a refined Instantaneous Frequency and power based pitch Estimator method called IFE. It incorporates deep neural network based pitch estimation...
-
An automated learning model for twitter sentiment analysis using Ranger AdaBelief optimizer based Bidirectional Long Short Term Memory
PublicationSentiment analysis is an automated approach which is utilized in process of analysing textual data to describe public opinion. The sentiment analysis has major role in creating impact in the day-to-day life of individuals. However, a precise interpretation of text still relies as a major concern in classifying sentiment. So, this research introduced Bidirectional Long Short Term Memory with Ranger AdaBelief Optimizer (Bi-LSTM RAO)...
-
Study of Statistical Text Representation Methods for Performance Improvement of a Hierarchical Attention Network
PublicationTo effectively process textual data, many approaches have been proposed to create text representations. The transformation of a text into a form of numbers that can be computed using computers is crucial for further applications in downstream tasks such as document classification, document summarization, and so forth. In our work, we study the quality of text representations using statistical methods and compare them to approaches...
-
Smart Approach for Glioma Segmentation in Magnetic Resonance Imaging using Modified Convolutional Network Architecture (U-NET)
PublicationSegmentation of a brain tumor from magnetic resonance multimodal images is a challenging task in the field of medical imaging. The vast diversity in potential target regions, appearance and multifarious intensity threshold levels of various tumor types are few of the major factors that affect segmentation results. An accurate diagnosis and its treatment demand strict delineation of the tumor affected tissues. Herein, we focus on...
-
Vehicle detector training with labels derived from background subtraction algorithms in video surveillance
PublicationVehicle detection in video from a miniature station- ary closed-circuit television (CCTV) camera is discussed in the paper. The camera provides one of components of the intelligent road sign developed in the project concerning the traffic control with the use of autonomous devices being developed. Modern Convolutional Neural Network (CNN) based detectors need big data input, usually demanding their manual labeling. In the presented...
-
Ranking Speech Features for Their Usage in Singing Emotion Classification
PublicationThis paper aims to retrieve speech descriptors that may be useful for the classification of emotions in singing. For this purpose, Mel Frequency Cepstral Coefficients (MFCC) and selected Low-Level MPEG 7 descriptors were calculated based on the RAVDESS dataset. The database contains recordings of emotional speech and singing of professional actors presenting six different emotions. Employing the algorithm of Feature Selection based...
-
Automated detection of pronunciation errors in non-native English speech employing deep learning
PublicationDespite significant advances in recent years, the existing Computer-Assisted Pronunciation Training (CAPT) methods detect pronunciation errors with a relatively low accuracy (precision of 60% at 40%-80% recall). This Ph.D. work proposes novel deep learning methods for detecting pronunciation errors in non-native (L2) English speech, outperforming the state-of-the-art method in AUC metric (Area under the Curve) by 41%, i.e., from...
-
Automated hearing loss type classification based on pure tone audiometry data
PublicationHearing problems are commonly diagnosed with the use of tonal audiometry, which measures a patient’s hearing threshold in both air and bone conduction at various frequencies. Results of audiometry tests, usually represented graphically in the form of an audiogram, need to be interpreted by a professional audiologist in order to determine the exact type of hearing loss and administer proper treatment. However, the small number of...
-
Architectural Modifications to Enhance Steganalysis with Convolutional Neural Networks
PublicationThis paper investigates the impact of various modifications introduced to current state-of-the-art Convolutional Neural Network (CNN) architectures specifically designed for the steganalysis of digital images. Usage of deep learning methods has consistently demonstrated improved results in this field over the past few years, primarily due to the development of newer architectures with higher classification accuracy compared to...
-
Detecting Objects of Various Categories in Optical Remote Sensing Imagery Using Neural Networks
PublicationThe effective detection of objects in remote sensing images is of great research importance, so recent years have seen a significant progress in deep learning techniques in this field. However, despite much valuable research being conducted, many challenges still remain. A lot of research projects focus on detecting objects of a single category (class), while correctly detecting objects of different categories is much harder. The...
-
Machine Learning and Deep Learning Methods for Fast and Accurate Assessment of Transthoracic Echocardiogram Image Quality
PublicationHigh-quality echocardiogram images are the cornerstone of accurate and reliable measurements of the heart. Therefore, this study aimed to develop, validate and compare machine learning and deep learning algorithms for accurate and automated assessment of transthoracic echocardiogram image quality. In total, 4090 single-frame two-dimensional transthoracic echocardiogram...
-
Toward Intelligent Recommendations Using the Neural Knowledge DNA
PublicationIn this paper we propose a novel recommendation approach using past news click data and the Neural Knowledge DNA (NK-DNA). The Neural Knowledge DNA is a novel knowledge representation method designed to support discovering, storing, reusing, improving, and sharing knowledge among machines and computing systems. We examine our approach for news recommendation tasks on the MIND benchmark dataset. By taking advantages of NK-DNA, deep...
-
Abdominal Aortic Aneurysm segmentation from contrast-enhanced computed tomography angiography using deep convolutional networks
PublicationOne of the most common imaging methods for diagnosing an abdominal aortic aneurysm, and an endoleak detection is computed tomography angiography. In this paper, we address the problem of aorta and thrombus semantic segmentation, what is a mandatory step to estimate aortic aneurysm diameter. Three end-to-end convolutional neural networks were trained and evaluated. Finally, we proposed an ensemble of deep neural networks with underlying...
-
Using Convolutional Neural Networks for Corneal Arcus Detection Towards Familial Hypercholesterolemia Screening
PublicationFamilial hypercholesterolemia (FH) is a highly undiagnosed disease. Among FH patients, the onset of premature coronary artery disease is 13 times higher than in the general population. Early diagnosis and treatment is essential to prevent cardiovascular diseases and their complications, and to prolong life. One of the clinical criteria of FH is the occurrence of a corneal arcus (CA) among patients, especially those under 45 years...
-
Deep neural networks for data analysis
e-Learning CoursesThe aim of the course is to familiarize students with the methods of deep learning for advanced data analysis. Typical areas of application of these types of methods include: image classification, speech recognition and natural language understanding. Celem przedmiotu jest zapoznanie studentów z metodami głębokiego uczenia maszynowego na potrzeby zaawansowanej analizy danych. Do typowych obszarów zastosowań tego typu metod należą:...
-
Equal Baseline Camera Array—Calibration, Testbed and Applications
PublicationThis paper presents research on 3D scanning by taking advantage of a camera array consisting of up to five adjacent cameras. Such an array makes it possible to make a disparity map with a higher precision than a stereo camera, however it preserves the advantages of a stereo camera such as a possibility to operate in wide range of distances and in highly illuminated areas. In an outdoor environment, the array is a competitive alternative...
-
Mask Detection and Classification in Thermal Face Images
PublicationFace masks are recommended to reduce the transmission of many viruses, especially SARS-CoV-2. Therefore, the automatic detection of whether there is a mask on the face, what type of mask is worn, and how it is worn is an important research topic. In this work, the use of thermal imaging was considered to analyze the possibility of detecting (localizing) a mask on the face, as well as to check whether it is possible to classify...