Wyniki wyszukiwania - BazTech

1

High-Capacity Coherent WDM Networks Empowered by Probabilistic Shaping and End-to-End Deep Learning

Abbass Ayam M., Fyath Raad Sami

Journal of Telecommunications and Information Technology

|

2024

|

nr 2

71--81

EN

To optimize the functionality of coherent optical fiber communication (OFC) systems and enhance their capacity related to long-haul transmissions, wavelength-division multiplexing (WDM) and probabilistic constellation shaping (PCS) techniques have been used. This paper develops an end-to-end (E2E) deep learning (DL)-based PCS algorithm, i.e., autoencoder (AE) for a high-order modulation format WDM system that minimizes nonlinear effects while ensuring high capacity and considers system parameters, in particular those related to the OFC channel. Only the AE of the central channel is trained to meet the specified performance objective, as the system design employs identical AEs in each WDM channel. The simulation results show that the architecture should consist of two hidden layers, with thirty two nodes per hidden layer and a "32 × modulation order" batch size to obtain optimal system performance, when designing AE using a dense layer neural network. The behavior of the AE is examined to determine the optimum launch-power ranges that enhance the system's performance. The developed AE-based PCS-WDM provides a 0.4 shaping gain and outperforms conventional solutions.

2

Zwiększanie potencjału sztucznej inteligencji generatywnej dzięki prompt engineering

Bistroń Marta, Piotrowski Zbigniew

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

2023

|

nr 4

341--344

PL

W artykule opisano różne techniki stosowane w algorytmach sztucznej inteligencji generatywnej, takie jak modele oparte na rozkładach prawdopodobieństwa, modele wariancyjne oraz modele sekwencyjne. Wyjaśniono podstawy tych technik oraz omówiono ich zastosowania w generowaniu obrazów, muzyki, tekstu czy mowy. Artykuł podkreśla znaczenie algorytmów generative AI jako narzędzi do twórczego generowania treści oraz prezentuje możliwe sposoby zwiększenia efektywności generowania tych treści z wykorzystaniem techniki prompt engineering.

EN

The article describes various techniques used in generative artificial intelligence algorithms, such as models based on probability distributions, variance models and sequential models. The basics of these techniques are explained and their applications in generating images, music, text or speech are discussed. The article emphasizes the importance of generative AI algorithms as tools for creative content generation and presents possible ways to increase the efficiency of generating this content using the prompt engineering technique.

3

Deciphering Clinical Narratives - Augmented Intelligence for Decision Making in Healthcare Sector

Dey Lipika, Jana Sudeshna, Dasgupta Tirthankar, Gupta Tanay

Annals of Computer Science and Information Systems

|

2023

|

Vol. 35

11--24

EN

Clinical notes that describe details about diseases, symptoms, treatments and observed reactions of patients to them, are valuable resources to generate insights about the effectiveness of treatments. Their role in designing better clinical decision making systems is being increasingly acknowledged. However, availability of clinical notes is still an issue due to privacy violation concerns. Hence most of the work done are on small datasets and neither the power of machine learning is fully utilized, nor is it possible to vaidate the models properly. With the availability of Medical Information Mart for Intensive Care (MIMIC-III v1.4) dataset for researchers though, the problem has been somewhat eased. In this paper we have presented an overview of our earlier work on designing deep neural models for prediction of outcomes and hospital stay for patients using MIMIC data. We have also presented new work on patient stratification and explanation generation for patient cohorts. This is early work targeted towards studying trajectories for treatment for different cohorts of patients, which can ultimately lead to discovery of low-risk models for individual patients to ensure better outcomes.

4

Method of machining centre sliding system fault detection using torque signals and autoencoder

Augustyn Damian, Fidali Marek

Acta Mechanica et Automatica

|

2023

|

Vol. 17, no. 3

445--451

EN

The sliding system of machining centres often causes maintenance and process problems. Improper operation of the sliding system can result from wear of mechanical parts and drives faults. To detect the faulty operation of the sliding system, measurements of the torque of its servomotors can be used. Servomotor controllers can measure motor current, which can be used to calculate motor torque. For research purposes, the authors used a set of torque signals from the machining centre servomotors that were acquired over a long period. The signals were collected during a diagnostic test programmed in the machining centre controller and performed once per day. In this article, a method for detecting anomalies in torque signals was presented for the condition assessment of the machining centre sliding systems. During the research, an autoencoder was used to detect the anomaly, and the condition was assessed based on the value of the reconstruction error. The results indicate that the anomaly detection method using an autoencoder is an effective solution for detecting damage to the sliding system and can be easily used in a condition monitoring system.

5

Roller damage detection method based on the measurement of transverse vibrations of the conveyor belt

Bortnowski Piotr, Król Robert, Ozdoba Maksymilian

Eksploatacja i Niezawodność

|

2022

|

Vol. 24, no. 3

510--521

EN

The article presents the detection of damage to rollers based on the transverse vibration signal measured on the conveyor belt. A solution was proposed for a wireless measuring device that moves with the conveyor belt along of the route, which records the signal of transverse vibrations of the belt. In the first place, the research was conducted in laboratory conditions, where a roller with prepared damage was used. Subsequently, the process of validating the adopted test procedure under real conditions was performed. The approach allowed to verify the correctness of the adopted technical assumptions of the measuring device and to assess the reliability of the acquired test results. In addition, an LSTM neural network algorithm was proposed to automate the process of detecting anomalies of the recorded diagnostic signal based on designated time series. The adopted detection algorithm has proven itself in both laboratory and in-situ tests.

6

A nested autoencoder approach to automated defect inspection on textured surfaces

Oz Muhammed Ali Nur, Kaymakci Ozgur Turay, Mercimek Muharrem

International Journal of Applied Mathematics and Computer Science

|

2021

|

Vol. 31, no. 3

515--523

EN

In recent years, there has been a highly competitive pressure on industrial production. To keep ahead of the competition, emerging technologies must be developed and incorporated. Automated visual inspection systems, which improve the overall mass production quantity and quality in lines, are crucial. The modifications of the inspection system involve excessive time and money costs. Therefore, these systems should be flexible in terms of fulfilling the changing requirements of high capacity production support. A coherent defect detection model as a primary application to be used in a real-time intelligent visual surface inspection system is proposed in this paper. The method utilizes a new approach consisting of nested autoencoders trained with defect-free and defect injected samples to detect defects. Making use of two nested autoencoders, the proposed approach shows great performance in eliminating defects. The first autoencoder is used essentially for feature extraction and reconstructing the image from these features. The second one is employed to identify and fix defects in the feature code. Defects are detected by thresholding the difference between decoded feature code outputs of the first and the second autoencoder. The proposed model has a 96% detection rate and a relatively good segmentation performance while being able to inspect fabrics driven at high speeds.

7

AutoCovNet: Unsupervised feature learning using autoencoder and feature merging for detection of COVID-19 from chest X-ray images

Rashid Nayeeb, Hossain Md Adnan Faisal, Ali Mohammad, Islam Sukanya Mumtahina, Mahmud Tanvir, Fattah Shaikh Anowarul

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 4

1685--1701

EN

With the onset of the COVID-19 pandemic, the automated diagnosis has become one of the most trending topics of research for faster mass screening. Deep learning-based approaches have been established as the most promising methods in this regard. However, the limitation of the labeled data is the main bottleneck of the data-hungry deep learning methods. In this paper, a two-stage deep CNN based scheme is proposed to detect COVID-19 from chest X-ray images for achieving optimum performance with limited training images. In the first stage, an encoder-decoder based autoencoder network is proposed, trained on chest X-ray images in an unsupervised manner, and the network learns to reconstruct the X-ray images. An encoder-merging network is proposed for the second stage that consists of different layers of the encoder model followed by a merging network. Here the encoder model is initialized with the weights learned on the first stage and the outputs from different layers of the encoder model are used effectively by being connected to a proposed merging network. An intelligent feature merging scheme is introduced in the proposed merging network. Finally, the encoder-merging network is trained for feature extraction of the X-ray images in a supervised manner and resulting features are used in the classification layers of the proposed architecture. Considering the final classification task, an EfficientNet-B4 network is utilized in both stages. An end to end training is performed for datasets containing classes: COVID-19, Normal, Bacterial Pneumonia, Viral Pneumonia. The proposed method offers very satisfactory performances compared to the state of the art methods and achieves an accuracy of 90:13% on the 4-class, 96:45% on a 3-class, and 99:39% on 2-class classification.

8

Browser fingerprint coding methods increasing the effectiveness of user identification in the web traffic

Gabryel Marcin, Grzanek Konrad, Hayashi Yoichi

Journal of Artificial Intelligence and Soft Computing Research

|

2020

|

Vol. 10, No. 4

243--253

EN

Web-based browser fingerprint (or device fingerprint) is a tool used to identify and track user activity in web traffic. It is also used to identify computers that are abusing online advertising and also to prevent credit card fraud. A device fingerprint is created by extracting multiple parameter values from a browser API (e.g. operating system type or browser version). The acquired parameter values are then used to create a hash using the hash function. The disadvantage of using this method is too high susceptibility to small, normally occurring changes (e.g. when changing the browser version number or screen resolution). Minor changes in the input values generate a completely different fingerprint hash, making it impossible to find similar ones in the database. On the other hand, omitting these unstable values when creating a hash, significantly limits the ability of the fingerprint to distinguish between devices. This weak point is commonly exploited by fraudsters who knowingly evade this form of protection by deliberately changing the value of device parameters. The paper presents methods that significantly limit this type of activity. New algorithms for coding and comparing fingerprints are presented, in which the values of parameters with low stability and low entropy are especially taken into account. The fingerprint generation methods are based on popular Minhash, the LSH, and autoencoder methods. The effectiveness of coding and comparing each of the presented methods was also examined in comparison with the currently used hash generation method. Authentic data of the devices and browsers of users visiting 186 different websites were collected for the research.

9

Gear pitting fault diagnosis using raw acoustic emission signal based on deep learning

Li Xueyi, Li Jialin, He David, Qu Yongzhi

Eksploatacja i Niezawodność

|

2019

|

Vol. 21, no. 3

403--410

EN

Gear pitting fault is one of the most common faults in mechanical transmission. Acoustic emission (AE) signals have been effective for gear fault detection because they are less affected by ambient noise than traditional vibration signals. To overcome the problem of low gear pitting fault recognition rate using AE signals and convolutional neural networks, this paper proposes a new method named augmented convolution sparse autoencoder (ACSAE) for gear pitting fault diagnosis using raw AE signals. First, the proposed method combines sparse autoencoder and one-dimensional convolutional neural networks for unsupervised learning and then uses the reinforcement theory to enhance the adaptability and robustness of the network. The ACSAE method can automatically extract fault features directly from the original AE signals without time and frequency domain conversion of the AE signals. AE signals collected from gear test experiments are used to validate the ACSAE method. The analysis result of the gear pitting fault test shows that the proposed method can effectively performing recognition of the gear pitting faults, and the recognition rate reaches above 98%. The comparative analysis shows that in comparison with fully-connected neural networks, convolutional neural networks, and recurrent neural networks, the ACSAE method has achieved a better diagnostic accuracy for gear fitting faults.

PL

Pitting kół zębatych stanowi jedno z najczęstszych uszkodzeń przekładni mechanicznych. Do wykrywania takich uszkodzeń stosuje się sygnały emisji akustycznej (AE), które, ze względu na niższą wrażliwość na hałas otoczenia, stanowią skuteczniejsze narzędzie diagnostyczne niż tradycyjne sygnały wibracyjne. Wykrywalność zużycia guzełkowatego (pittingu) kół zębatych przy użyciu sygnałów AE i splotowych sieci neuronowych jest jednak niska. Aby rozwiązać ten problem, w niniejszym artykule zaproponowano nową metodę diagnozowania uszkodzeń kół zębatych za pomocą surowych sygnałów AE, którą nazwano augmented convolution sparse autoencoder (konwolucją rozszerzoną z wykorzystaniem autoenkodera rzadkiego, ACSAE). Jest to metoda samouczenia jednowymiarowych splotowych sieci neuronowych realizowanego za pomocą autoenkodera rzadkiego. Metoda ta wykorzystuje teorię wzmocnienia do zwiększania adaptacyjności i odporności sieci. Metoda ACSAE pozwala na automatyczne wyodrębnianie cech degradacji bezpośrednio z oryginalnych sygnałów AE bez konieczności ich konwersji do domeny czasu i częstotliwości. Walidację metody przeprowadzono na podstawie sygnałów AE otrzymanych w badaniach kół zębatych. Analiza wyników badań pittingu kół zębatych wskazuje, że proponowana metoda pozwala na skuteczną detekcję tego typu uszkodzeń, przy wskaźniku wykrywalności powyżej 98%. Analiza porównawcza pokazuje, że metoda ACSAE cechuje się większą trafnością diagnostyczną w wykrywaniu błędów montażowych kół zębatych w porównaniu z sieciami neuronowymi w pełni połączonymi, splotowymi i rekurencyjnymi.

10

Głębokie sieci neuronowe i ich zastosowania w eksploracji danych

Osowski S.

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

2018

|

nr 5

112--121

PL

Artykuł dotyczy podstaw działania typowych sieci neuronowych głębokich, do których zalicza się sieci konwolucyjne (CNN), autoenkoder czy sieć LSTM. Omówiono struktury tych sieci, ich algorytmy uczenia oraz dokonano przeglądu podstawowych zastosowań owych sieci w rozwiązywaniu różnego rodzaju zadań eksploracji danych, między innymi klasyfikacji, regresji, segmentacji danych, rekonstrukcji danych i wielu innych. Przedstawiono między innymi wyniki prac dotyczących bioinżynierii, w szczególności rozpoznawanie i klasyfikację obrazów mammograficznych.

EN

The paper presents the theoretical fundamentals of deep neural networks. The basic deep structures are discussed. They include convolutional neural networks (CNN), autoencoder (AE) and recurrent network called LSTM (Long short-term memory). This paper is concerned on presentation of their typical structures and learning algorithms. The review of some chosen applications of these solutions in such tasks as classification, regression, segmentation of data, reconstruction, text and speech recognition, etc., are discussed. Some chosen numerical results concerning classification problems will be also presented and discussed.