Search
Search results for: SEMANTIC SEGMENTATION, NOISY ANNOTATIONS, LOSS MASKING, DEEP NEURAL NETWORKS
-
Conference on Artificial Neural Networks and Expert systems
Conferences -
International Conference on Engineering Applications of Neural Networks
Conferences -
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,...
-
Speech Analytics Based on Machine Learning
PublicationIn this chapter, the process of speech data preparation for machine learning is discussed in detail. Examples of speech analytics methods applied to phonemes and allophones are shown. Further, an approach to automatic phoneme recognition involving optimized parametrization and a classifier belonging to machine learning algorithms is discussed. Feature vectors are built on the basis of descriptors coming from the music information...
-
Optimized Deep Learning Model for Flood Detection Using Satellite Images
PublicationThe increasing amount of rain produces a number of issues in Kerala, particularly in urban regions where the drainage system is frequently unable to handle a significant amount of water in such a short duration. Meanwhile, standard flood detection results are inaccurate for complex phenomena and cannot handle enormous quantities of data. In order to overcome those drawbacks and enhance the outcomes of conventional flood detection...
-
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...
-
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...
-
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...
-
Robust Object Detection with Multi-input Multi-output Faster R-CNN
PublicationRecent years have seen impressive progress in visual recognition on many benchmarks, however, generalization to the out-of-distribution setting remains a significant challenge. A state-of-the-art method for robust visual recognition is model ensembling. However, recently it was shown that similarly competitive results could be achieved with a much smaller cost, by using multi-input multi-output architecture (MIMO). In this work,...
-
Robust Object Detection with Multi-input Multi-output Faster R-CNN
PublicationRecent years have seen impressive progress in visual recognition on many benchmarks, however, generalization to the out-of-distribution setting remains a significant challenge. A state-of-the-art method for robust visual recognition is model ensembling. However, recently it was shown that similarly competitive results could be achieved with a much smaller cost, by using multi-input multi-output architecture (MIMO). In this work,...
-
Predicting emotion from color present in images and video excerpts by machine learning
PublicationThis work aims at predicting emotion based on the colors present in images and video excerpts using a machine-learning approach. The purpose of this paper is threefold: (a) to develop a machine-learning algorithm that classifies emotions based on the color present in an image, (b) to select the best-performing algorithm from the first phase and apply it to film excerpt emotion analysis based on colors, (c) to design an online survey...
-
Language Models in Speech Recognition
PublicationThis chapter describes language models used in speech recognition, It starts by indicating the role and the place of language models in speech recognition. Mesures used to compare language models follow. An overview of n-gram, syntactic, semantic, and neural models is given. It is accompanied by a list of popular software.
-
Detecting type of hearing loss with different AI classification methods: a performance review
PublicationHearing is one of the most crucial senses for all humans. It allows people to hear and connect with the environment, the people they can meet and the knowledge they need to live their lives to the fullest. Hearing loss can have a detrimental impact on a person's quality of life in a variety of ways, ranging from fewer educational and job opportunities due to impaired communication to social withdrawal in severe situations. Early...
-
International Conference on Artificial Neural Networks and Genetic Algorithms
Conferences -
International Work-Conference on Artificial and Natural Neural Networks
Conferences -
IEEE International Workshop on Neural Networks for Signal Processing
Conferences -
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...
-
Shape Optimisation of Kaplan Turbine Blades Using Genetic Algorithms
PublicationThis monograph is a comprehensive guide to a method of blade profile optimisation for Kaplan-type turbines. This method is based on modelling the interaction between rotor and stator blades. Additionally, the shape of the draft tube is investigated. The influence of the periodic boundary condition vs. full geometry is also discussed. Evolutionary algorithms (EA) are used as an optimisation method together with artificial neural...
-
Neural Network Subgraphs Correlation with Trained Model Accuracy
PublicationNeural Architecture Search (NAS) is a computationally demanding process of finding optimal neural network architecture for a given task. Conceptually, NAS comprises applying a search strategy on a predefined search space accompanied by a performance evaluation method. The design of search space alone is expected to substantially impact NAS efficiency. We consider neural networks as graphs and find a correlation between the presence...
-
Exergy and Energy Analyses of Microwave Dryer for Cantaloupe Slice and Prediction of Thermodynamic Parameters Using ANN and ANFIS Algorithms
PublicationThe study targeted towards drying of cantaloupe slices with various thicknesses in a microwave dryer. The experiments were carried out at three microwave powers of 180, 360, and 540 W and three thicknesses of 2, 4, and 6 mm for cantaloupe drying, and the weight variations were determined. Artificial neural networks (ANN) and adaptive neuro-fuzzy inference systems (ANFIS) were exploited to investigate energy and exergy indices of...
-
Detection of Alzheimer's disease using Otsu thresholding with tunicate swarm algorithm and deep belief network
PublicationIntroduction: Alzheimer’s Disease (AD) is a degenerative brain disorder characterized by cognitive and memory dysfunctions. The early detection of AD is necessary to reduce the mortality rate through slowing down its progression. The prevention and detection of AD is the emerging research topic for many researchers. The structural Magnetic Resonance Imaging (sMRI) is an extensively used imaging technique in detection of AD, because...
-
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...
-
Interpretable Deep Learning Model for the Detection and Reconstruction of Dysarthric Speech
PublicationWe present a novel deep learning model for the detection and reconstruction of dysarthric speech. We train the model with a multi-task learning technique to jointly solve dysarthria detection and speech reconstruction tasks. The model key feature is a low-dimensional latent space that is meant to encode the properties of dysarthric speech. It is commonly believed that neural networks are black boxes that solve problems but do not...
-
A repeated game formulation of network embedded coding for multicast resilience in extreme conditions
PublicationComputer networks and data sharing applications are vital for our current society and fundamental for any available ICT solution, so that networking is considered as one of the key critical infrastructures and its correct behavior should be always enforced, even in case of disasters or severe execution conditions. Resilience is a strongly demanding nonfunctional requirement for current computer networks, and one of the key factors...
-
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...
-
Development of an AI-based audiogram classification method for patient referral
PublicationHearing loss is one of the most significant sensory disabilities. It can have various negative effects on a person's quality of life, ranging from impeded school and academic performance to total social isolation in severe cases. It is therefore vital that early symptoms of hearing loss are diagnosed quickly and accurately. Audiology tests are commonly performed with the use of tonal audiometry, which measures a patient's hearing...
-
Identyfikacja instrumentu muzycznego z nagrania fonicznego za pomocą sztucznych sieci neuronowych
PublicationCelem rozprawy jest zbadanie algorytmów do identyfikacji instrumentów występujących w sygnale polifonicznym z wykorzystaniem sztucznych sieci neuronowych. W części teoretycznej przywołano podstawy przetwarzania sygnałów fonicznych w kontekście ekstrakcji parametrów sygnałów wykorzystywanych w treningu sieci neuronowych. Dodatkowo dokonano analizy rozwoju metod uczenia maszynowego z uwzględnieniem podziału na sieci neuronowe pierwszej,...
-
Selection of an artificial pre-training neural network for the classification of inland vessels based on their images
PublicationArtificial neural networks (ANN) are the most commonly used algorithms for image classification problems. An image classifier takes an image or video as input and classifies it into one of the possible categories that it was trained to identify. They are applied in various areas such as security, defense, healthcare, biology, forensics, communication, etc. There is no need to create one’s own ANN because there are several pre-trained...
-
Society 4.0: Issues, Challenges, Approaches, and Enabling Technologies
PublicationThis guest edition of Cybernetics and Systems is a broadening continuation of our last year edition titled “Intelligence Augmentation and Amplification: Approaches, Tools, and Case Studies”. This time we cover research perspective extending towards what is known as Society 4.0. Bob de Vit brought the concept of Society 4.0 to life in his book “Society 4.0 – resolving eight key issues to build a citizens society”. From the Systems...
-
Neural Architecture Search for Skin Lesion Classification
PublicationDeep 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...
-
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...
-
Detection of the Oocyte Orientation for the ICSI Method Automation
PublicationAutomation or even computer assistance of the popular infertility treatment method: ICSI (Intracytoplasmic Sperm Injection) would speed up the whole process and improve the control of the results. This paper introduces a preliminary research for automatic spermatozoon injection into the oocyte cytoplasm. Here, the method for detection a correct orientation of the polar body of the oocyte is presented. Proposed method uses deep...
-
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...
-
Rotor Blade Geometry Optimisation in Kaplan Turbine
PublicationThe paper presents the description of method and results of rotor blade shape optimisation. The rotor blading constitutes a part ofturbine flow path. Optimisation consists in selection of the shape that minimises ratio of polytrophic loss. Shape of the blade isdefined by the mean camber line and thickness of the airfoil. Thickness is distributed around the camber line based on the ratio ofdistribution. Global optimisation was done...
-
Deep learning in the fog
PublicationIn the era of a ubiquitous Internet of Things and fast artificial intelligence advance, especially thanks to deep learning networks and hardware acceleration, we face rapid growth of highly decentralized and intelligent solutions that offer functionality of data processing closer to the end user. Internet of Things usually produces a huge amount of data that to be effectively analyzed, especially with neural networks, demands high...
-
Improvement of speech intelligibility in the presence of noise interference using the Lombard effect and an automatic noise interference profiling based on deep learning
PublicationThe Lombard effect is a phenomenon that results in speech intelligibility improvement when applied to noise. There are many distinctive features of Lombard speech that were recalled in this dissertation. This work proposes the creation of a system capable of improving speech quality and intelligibility in real-time measured by objective metrics and subjective tests. This system consists of three main components: speech type detection,...
-
Global Surrogate Modeling by Neural Network-Based Model Uncertainty
PublicationThis work proposes a novel adaptive global surrogate modeling algorithm which uses two neural networks, one for prediction and the other for the model uncertainty. Specifically, the algorithm proceeds in cycles and adaptively enhances the neural network-based surrogate model by selecting the next sampling points guided by an auxiliary neural network approximation of the spatial error. The proposed algorithm is tested numerically...
-
Preprocessing of Document Images Based on the GGD and GMM for Binarization of Degraded Ancient Papyri Images
PublicationThresholding of document images is one of the most relevant operations that influence the final results of their further analysis. Although many image binarization methods have been proposed during recent several years, starting from global thresholding, through local and adaptive methods, to more sophisticated multi-stage algorithms and the use of deep convolutional neural networks, proper thresholding of degraded historical...
-
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...
-
Bio-inspired Decisional DNA in Machinas and other Man-made Systems: The Way Forward
PublicationArtificial bio-inspired intelligent techniques and systems supporting smart, knowledge-based solutions of real world problems which are currently researched very extensively by research teams around the world, have enormous potential to enhance automation of decision making and problem solving for a number of diverse areas including design, manufacturing, Information Technology (IT), social communities of practice, and economics...
-
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...
-
Deep learning-based waste detection in natural and urban environments
PublicationWaste pollution is one of the most significant environmental issues in the modern world. The importance of recycling is well known, both for economic and ecological reasons, and the industry demands high efficiency. Current studies towards automatic waste detection are hardly comparable due to the lack of benchmarks and widely accepted standards regarding the used metrics and data. Those problems are addressed in this article by...
-
Towards neural knowledge DNA
PublicationIn this paper, we propose the Neural Knowledge DNA, a framework that tailors the ideas underlying the success of neural networks to the scope of knowledge representation. Knowledge representation is a fundamental field that dedicates to representing information about the world in a form that computer systems can utilize to solve complex tasks. The proposed Neural Knowledge DNA is designed to support discovering, storing, reusing,...
-
Real-Time Facial Features Detection from Low Resolution Thermal Images with Deep Classification Models
PublicationDeep networks have already shown a spectacular success for object classification and detection for various applications from everyday use cases to advanced medical problems. The main advantage of the classification models over the detection models is less time and effort needed for dataset preparation, because classification networks do not require bounding box annotations, but labels at the image level only. Yet, after passing...
-
Comparison of image pre-processing methods in liver segmentation task
PublicationAutomatic liver segmentation of Computed Tomography (CT) images is becoming increasingly important. Although there are many publications in this field there is little explanation why certain pre-processing methods were utilised. This paper presents a comparison of the commonly used approach of Hounsfield Units (HU) windowing, histogram equalisation, and a combination of these methods to try to ascertain what are the differences...
-
KEMR-Net: A Knowledge-Enhanced Mask Refinement Network for Chromosome Instance Segmentation
PublicationThis article proposes a mask refinement method for chromosome instance segmentation. The proposed method exploits the knowledge representation capability of Neural Knowledge DNA (NK-DNA) to capture the semantics of the chromosome’s shape, texture, and key points, and then it uses the captured knowledge to improve the accuracy and smoothness of the masks. We validate the method’s effectiveness on our latest high-resolution chromosome...
-
Automated Parking Management for Urban Efficiency: A Comprehensive Approach
PublicationEffective parking management is essential for ad-dressing the challenges of traffic congestion, city logistics, and air pollution in densely populated urban areas. This paper presents an algorithm designed to optimize parking management within city environments. The proposed system leverages deep learning models to accurately detect and classify street elements and events. Various algorithms, including automatic segmentation of...
-
Controlling computer by lip gestures employing neural network
PublicationResults of experiments regarding lip gesture recognition with an artificial neural network are discussed. The neural network module forms the core element of a multimodal human-computer interface called LipMouse. This solution allows a user to work on a computer using lip movements and gestures. A user face is detected in a video stream from a standard web camera using a cascade of boosted classifiers working with Haar-like features....
-
Rediscovering Automatic Detection of Stuttering and Its Subclasses through Machine Learning—The Impact of Changing Deep Model Architecture and Amount of Data in the Training Set
PublicationThis work deals with automatically detecting stuttering and its subclasses. An effective classification of stuttering along with its subclasses could find wide application in determining the severity of stuttering by speech therapists, preliminary patient diagnosis, and enabling communication with the previously mentioned voice assistants. The first part of this work provides an overview of examples of classical and deep learning...
-
Assessment of the Effectiveness of a Short-term Hearing Aid Use in Patients with Different Degrees of Hearing Loss
PublicationThe study presents evaluating the effectiveness of the hearing aid fitting process in the short-term use (7 days). The evaluation method consists of a survey based on the APHAB (Abbreviated Profile of Hearing Aid Benefit) questionnaire. Additional criteria such as a degree of hearing loss, number of hours and days of hearing aid use as well as the user’s experience were also taken into consideration. The outcomes of the benefit...