Filters
total: 582
filtered: 531
Search results for: deep-learning, neural networks
-
Experience-Based Cognition for Driving Behavioral Fingerprint Extraction
PublicationABSTRACT With the rapid progress of information technologies, cars have been made increasingly intelligent. This allows cars to act as cognitive agents, i.e., to acquire knowledge and understanding of the driving habits and behavioral characteristics of drivers (i.e., driving behavioral fingerprint) through experience. Such knowledge can be then reused to facilitate the interaction between a car and its driver, and to develop better and...
-
Age Prediction from Low Resolution, Dual-Energy X-ray Images Using Convolutional Neural Networks
PublicationAge prediction from X-rays is an interesting research topic important for clinical applications such as biological maturity assessment. It is also useful in many other practical applications, including sports or forensic investigations for age verification purposes. Research on these issues is usually carried out using high-resolution X-ray scans of parts of the body, such as images of the hands or images of the chest. In this...
-
Speaker Recognition Using Convolutional Neural Network with Minimal Training Data for Smart Home Solutions
PublicationWith the technology advancements in smart home sector, voice control and automation are key components that can make a real difference in people's lives. The voice recognition technology market continues to involve rapidly as almost all smart home devices are providing speaker recognition capability today. However, most of them provide cloud-based solutions or use very deep Neural Networks for speaker recognition task, which are...
-
Impact of Visual Image Quality on Lymphocyte Detection Using YOLOv5 and RetinaNet Algorithms
PublicationLymphocytes, a type of leukocytes, play a vital role in the immune system. The precise quantification, spatial arrangement and phenotypic characterization of lymphocytes within haematological or histopathological images can serve as a diagnostic indicator of a particular lesion. Artificial neural networks, employed for the detection of lymphocytes, not only can provide support to the work of histopathologists but also enable better...
-
Explainable machine learning for diffraction patterns
PublicationSerial crystallography experiments at X-ray free-electron laser facilities produce massive amounts of data but only a fraction of these data are useful for downstream analysis. Thus, it is essential to differentiate between acceptable and unacceptable data, generally known as ‘hit’ and ‘miss’, respectively. Image classification methods from artificial intelligence, or more specifically convolutional neural networks (CNNs), classify...
-
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...
-
WYKORZYSTANIE SIECI NEURONOWYCH DO SYNTEZY MOWY WYRAŻAJĄCEJ EMOCJE
PublicationW niniejszym artykule przedstawiono analizę rozwiązań do rozpoznawania emocji opartych na mowie i możliwości ich wykorzystania w syntezie mowy z emocjami, wykorzystując do tego celu sieci neuronowe. Przedstawiono aktualne rozwiązania dotyczące rozpoznawania emocji w mowie i metod syntezy mowy za pomocą sieci neuronowych. Obecnie obserwuje się znaczny wzrost zainteresowania i wykorzystania uczenia głębokiego w aplikacjach związanych...
-
Musical Instrument Identification Using Deep Learning Approach
PublicationThe work aims to propose a novel approach for automatically identifying all instruments present in an audio excerpt using sets of individual convolutional neural networks (CNNs) per tested instrument. The paper starts with a review of tasks related to musical instrument identification. It focuses on tasks performed, input type, algorithms employed, and metrics used. The paper starts with the background presentation, i.e., metadata...
-
Investigating Feature Spaces for Isolated Word Recognition
PublicationThe study addresses the issues related to the appropriateness of a two-dimensional representation of speech signal for speech recognition tasks based on deep learning techniques. The approach combines Convolutional Neural Networks (CNNs) and time-frequency signal representation converted to the investigated feature spaces. In particular, waveforms and fractal dimension features of the signal were chosen for the time domain, and...
-
Using deep learning to increase accuracy of gaze controlled prosthetic arm
PublicationThis paper presents how neural networks can be utilized to improve the accuracy of reach and grab functionality of hybrid prosthetic arm with eye tracing interface. The LSTM based Autoencoder was introduced to overcome the problem of lack of accuracy of the gaze tracking modality in this hybrid interface. The gaze based interaction strongly depends on the eye tracking hardware. In this paper it was presented how the overall the...
-
Detecting Lombard Speech Using Deep Learning Approach
PublicationRobust Lombard speech-in-noise detecting is challenging. This study proposes a strategy to detect Lombard speech using a machine learning approach for applications such as public address systems that work in near real time. The paper starts with the background concerning the Lombard effect. Then, assumptions of the work performed for Lombard speech detection are outlined. The framework proposed combines convolutional neural networks...
-
Deep learning approach on surface EEG based Brain Computer Interface
PublicationIn this work we analysed the application of con-volutional neural networks in motor imagery classification for the Brain Computer Interface (BCI) purposes. To increase the accuracy of classification we proposed the solution that combines the Common Spatial Pattern (CSP) with convolutional network (ConvNet). The electroencephalography (EEG) is one of the modalities we try to use for controlling the prosthetic arm. Therefor in this...
-
Poprawa jakości klasyfikacji głębokich sieci neuronowych poprzez optymalizację ich struktury i dwuetapowy proces uczenia
PublicationW pracy doktorskiej podjęto problem realizacji algorytmów głębokiego uczenia w warunkach deficytu danych uczących. Głównym celem było opracowanie podejścia optymalizującego strukturę sieci neuronowej oraz zastosowanie uczeniu dwuetapowym, w celu uzyskania mniejszych struktur, zachowując przy tym dokładności. Proponowane rozwiązania poddano testom na zadaniu klasyfikacji znamion skórnych na znamiona złośliwe i łagodne. W pierwszym...
-
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...
-
Autonomous pick-and-place system based on multiple 3Dsensors and deep learning
PublicationGrasping objects and manipulating them is the main way the robot interacts with its environment. However, for robots to operate in a dynamic environment, a system for determining the gripping position for objects in the scene is also required. For this purpose, neural networks segmenting the point cloud are usually applied. However, training such networks is very complex and their results are unsatisfactory. Therefore, we propose...
-
Analysis of the Capability of Deep Learning Algorithms for EEG-based Brain-Computer Interface Implementation
PublicationMachine learning models have received significant attention for their exceptional performance in classifying electroencephalography (EEG) data. They have proven to be highly effective in extracting intricate patterns and features from the raw signal data, thereby contributing to their success in EEG classification tasks. In this study, we explore the possibilities of utilizing contemporary machine learning algorithms in decoding...
-
DEEP LEARNING BASED ON X-RAY IMAGING IMPROVES COXARTHROSIS DETECTION
PublicationObjective: The purpose of the study was to create an Artificial Neural Network (ANN) based on X-ray images of the pelvis, as an additional tool to automate and improve the diagnosis of coxarthrosis. The research is focused on joint space narrowing, which is a radiological symptom showing the thinning of the articular cartilage layer, which is translucent to X-rays. It is the first and the most important of the radiological signs...
-
Autonomous Perception and Grasp Generation Based on Multiple 3D Sensors and Deep Learning
PublicationGrasping objects and manipulating them is the main way the robot interacts with its environment. However, for robots to operate in a dynamic environment, a system for determining the gripping position for objects in the scene is also required. For this purpose, neural networks segmenting the point cloud are usually applied. However, training such networks is very complex and their results are unsatisfactory. Therefore, we propose...
-
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...
-
Data Acquisition and Processing for GeoAI Models to Support Sustainable Agricultural Practices
PublicationThere are growing opportunities to leverage new technologies and data sources to address global problems related to sustainability, climate change, and biodiversity loss. The emerging discipline of GeoAI resulting from the convergence of AI and Geospatial science (Geo-AI) is enabling the possibility to harness the increasingly available open Earth Observation data collected from different constellations of satellites and sensors...
-
Deep neural network architecture search using network morphism
PublicationThe paper presents the results of the research on neural architecture search (NAS) algorithm. We utilized the hill climbing algorithm to search for well-performing structures of deep convolutional neural network. Moreover, we used the function preserving transformations which enabled the effective operation of the algorithm in a short period of time. The network obtained with the advantage of NAS was validated on skin lesion classification...
-
Solvent Screening for Solubility Enhancement of Theophylline in Neat, Binary and Ternary NADES Solvents: New Measurements and Ensemble Machine Learning
PublicationTheophylline, a typical representative of active pharmaceutical ingredients, was selected to study the characteristics of experimental and theoretical solubility measured at 25 °C in a broad range of solvents, including neat, binary mixtures and ternary natural deep eutectics (NADES) prepared with choline chloride, polyols and water. There was a strong synergistic effect of organic solvents mixed with water, and among the experimentally...
-
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...
-
Pedestrian detection in low-resolution thermal images
PublicationOver one million people die in car accidents worldwide each year. A solution that will be able to reduce situations in which pedestrian safety is at risk has been sought for a long time. One of the techniques for detecting pedestrians on the road is the use of artificial intelligence in connection with thermal imaging. The purpose of this work was to design a system to assist the safety of people and car intelligence with the use...
-
Employing Subjective Tests and Deep Learning for Discovering the Relationship between Personality Types and Preferred Music Genres
PublicationThe purpose of this research is two-fold: (a) to explore the relationship between the listeners’ personality trait, i.e., extraverts and introverts and their preferred music genres, and (b) to predict the personality trait of potential listeners on the basis of a musical excerpt by employing several classification algorithms. We assume that this may help match songs according to the listener’s personality in social music networks....
-
Interpretable deep learning approach for classification of breast cancer - a comparative analysis of multiple instance learning models
PublicationBreast cancer is the most frequent female cancer. Its early diagnosis increases the chances of a complete cure for the patient. Suitably designed deep learning algorithms can be an excellent tool for quick screening analysis and support radiologists and oncologists in diagnosing breast cancer.The design of a deep learning-based system for automated breast cancer diagnosis is not easy due to the lack of annotated data, especially...
-
Thermal Images Analysis Methods using Deep Learning Techniques for the Needs of Remote Medical Diagnostics
PublicationRemote medical diagnostic solutions have recently gained more importance due to global demographic shifts and play a key role in evaluation of health status during epidemic. Contactless estimation of vital signs with image processing techniques is especially important since it allows for obtaining health status without the use of additional sensors. Thermography enables us to reveal additional details, imperceptible in images acquired...
-
Evaluation of Facial Pulse Signals Using Deep Neural Net Models
PublicationThe reliable measurement of the pulse rate using remote photoplethysmography (PPG) is very important for many medical applications. In this paper we present how deep neural networks (DNNs) models can be used in the problem of PPG signal classification and pulse rate estimation. In particular, we show that the DNN-based classification results correspond to parameters describing the PPG signals (e.g. peak energy in the frequency...
-
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...
-
Comparative study on the effectiveness of various types of road traffic intensity detectors
PublicationVehicle detection and speed measurements are crucial tasks in traffic monitoring systems. In this work, we focus on several types of electronic sensors, operating on different physical principles in order to compare their effectiveness in real traffic conditions. Commercial solutions are based on road tubes, microwave sensors, LiDARs, and video cameras. Distributed traffic monitoring systems require a high number of monitoring...
-
The impact of the AC922 Architecture on Performance of Deep Neural Network Training
PublicationPractical deep learning applications require more and more computing power. New computing architectures emerge, specifically designed for the artificial intelligence applications, including the IBM Power System AC922. In this paper we confront an AC922 (8335-GTG) server equipped with 4 NVIDIA Volta V100 GPUs with selected deep neural network training applications, including four convolutional and one recurrent model. We report...
-
Segmentation Quality Refinement in Large-Scale Medical Image Dataset with Crowd-Sourced Annotations
PublicationDeployment of different techniques of deep learning including Convolutional Neural Networks (CNN) in image classification systems has accomplished outstanding results. However, the advantages and potential impact of such a system can be completely negated if it does not reach a target accuracy. To achieve high classification accuracy with low variance in medical image classification system, there is needed the large size of the...
-
Self-Supervised Learning to Increase the Performance of Skin Lesion Classification
PublicationTo successfully train a deep neural network, a large amount of human-labeled data is required. Unfortunately, in many areas, collecting and labeling data is a difficult and tedious task. Several ways have been developed to mitigate the problem associated with the shortage of data, the most common of which is transfer learning. However, in many cases, the use of transfer learning as the only remedy is insufficient. In this study,...
-
Robustness in Compressed Neural Networks for Object Detection
PublicationModel compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a large effect on noisy cases or objects belonging to less frequent classes. It is a crucial problem from the perspective of the models' safety, especially for object detection in the autonomous driving...
-
Performance and Energy Aware Training of a Deep Neural Network in a Multi-GPU Environment with Power Capping
PublicationIn this paper we demonstrate that it is possible to obtain considerable improvement of performance and energy aware metrics for training of deep neural networks using a modern parallel multi-GPU system, by enforcing selected, non-default power caps on the GPUs. We measure the power and energy consumption of the whole node using a professional, certified hardware power meter. For a high performance workstation with 8 GPUs, we were...
-
Analysis of 2D Feature Spaces for Deep Learning-based Speech Recognition
Publicationconvolutional neural network (CNN) which is a class of deep, feed-forward artificial neural network. We decided to analyze audio signal feature maps, namely spectrograms, linear and Mel-scale cepstrograms, and chromagrams. The choice was made upon the fact that CNN performs well in 2D data-oriented processing contexts. Feature maps were employed in the Lithuanian word recognition task. The spectral analysis led to the highest word...
-
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...
-
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...
-
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...
-
Assessing the attractiveness of human face based on machine learning
PublicationThe attractiveness of the face plays an important role in everyday life, especially in the modern world where social media and the Internet surround us. In this study, an attempt to assess the attractiveness of a face by machine learning is shown. Attractiveness is determined by three deep models whose sum of predictions is the final score. Two annotated datasets available in the literature are employed for training and testing...
-
Modeling and Simulation for Exploring Power/Time Trade-off of Parallel Deep Neural Network Training
PublicationIn the paper we tackle bi-objective execution time and power consumption optimization problem concerning execution of parallel applications. We propose using a discrete-event simulation environment for exploring this power/time trade-off in the form of a Pareto front. The solution is verified by a case study based on a real deep neural network training application for automatic speech recognition. A simulation lasting over 2 hours...
-
Inteligentne systemy agentowe w systemach zdalnego nauczania
PublicationW pracy omówiono inteligentne systemy agentowe w systemach zdalnego nauczania. Po krótkim przedstawieniu ewolucji systemów zdalnego nauczania i ich wybranych zastosowań, scharakteryzowano inteligentne agenty edukacyjne. Omówiono wykorzystanie programowania genetycznego oraz algorytmów neuro-ewolucyjnych do implementacji oprogramowania tej klasy. Ponadto, nawiązano do modelu Map-Reduce, który efektywnie wspiera architekturę nowoczesnego...
-
Towards Knowledge Sharing Oriented Adaptive Control
PublicationIn this paper, we propose a knowledge sharing oriented approach to enable a robot to reuse other robots' knowledge by adapting itself to the inverse dynamics model of the knowledge-sharing robot. The purpose of this work is to remove the heavy fine-tuning procedure required before using a new robot for a task via reusing other robots' knowledge. We use the Neural Knowledge DNA (NK-DNA) to help robots gain empirical knowledge and...
-
Diagnostyka łożysk silnika indukcyjnego na podstawie prądu zasilającego przy użyciu sztucznych sieci neuronowych
PublicationW artykule zawarto wyniki badań dotyczące diagnostyki łożysk silnika indukcyjnego na podstawie pomiarów prądu zasilającego z wykorzystaniem sztucznych sieci neuronowych. Zaprezentowano wyniki uczenia sieci oraz rezultaty testów przeprowadzonych na danych spoza zbioru uczącego. Badania wykonane zostały na obiektach z celowo wprowadzonymi uszkodzeniami łożysk. Przedstawiona nowa koncepcja zakłada użycie zestawu sieci neuronowych...
-
Comparison of the Ability of Neural Network Model and Humans to Detect a Cloned Voice
PublicationThe vulnerability of the speaker identity verification system to attacks using voice cloning was examined. The research project assumed creating a model for verifying the speaker’s identity based on voice biometrics and then testing its resistance to potential attacks using voice cloning. The Deep Speaker Neural Speaker Embedding System was trained, and the Real-Time Voice Cloning system was employed based on the SV2TTS, Tacotron,...
-
Resource constrained neural network training
PublicationModern applications of neural-network-based AI solutions tend to move from datacenter backends to low-power edge devices. Environmental, computational, and power constraints are inevitable consequences of such a shift. Limiting the bit count of neural network parameters proved to be a valid technique for speeding up and increasing efficiency of the inference process. Hence, it is understandable that a similar approach is gaining...
-
Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention
PublicationThis paper describes two novel complementary techniques that improve the detection of lexical stress errors in non-native (L2) English speech: attention-based feature extraction and data augmentation based on Neural Text-To-Speech (TTS). In a classical approach, audio features are usually extracted from fixed regions of speech such as the syllable nucleus. We propose an attention-based deep learning model that automatically de...
-
MP3vec: A Reusable Machine-Constructed Feature Representation for Protein Sequences
Publication—Machine Learning (ML) methods have been used with varying degrees of success on protein prediction tasks, with two inherent limitations. First, prediction performance often depends upon the features extracted from the proteins. Second, experimental data may be insufficient to construct reliable ML models. Here we introduce MP3vec, a transferable representation for protein sequences that is designed to be used specifically for sequence-to-sequence...
-
Minimizing Distribution and Data Loading Overheads in Parallel Training of DNN Acoustic Models with Frequent Parameter Averaging
PublicationIn the paper we investigate the performance of parallel deep neural network training with parameter averaging for acoustic modeling in Kaldi, a popular automatic speech recognition toolkit. We describe experiments based on training a recurrent neural network with 4 layers of 800 LSTM hidden states on a 100-hour corpora of annotated Polish speech data. We propose a MPI-based modification of the training program which minimizes the...
-
Method for Clustering of Brain Activity Data Derived from EEG Signals
PublicationA method for assessing separability of EEG signals associated with three classes of brain activity is proposed. The EEG signals are acquired from 23 subjects, gathered from a headset consisting of 14 electrodes. Data are processed by applying Discrete Wavelet Transform (DWT) for the signal analysis and an autoencoder neural network for the brain activity separation. Processing involves 74 wavelets from 3 DWT families: Coiflets,...