Institute of Electron Technology
Biblioteka Cyfrowa Instytutu Łączności / National Institute of Telecomunications: Digital LibraryNot a member yet
2189 research outputs found
Sort by
Analysis of an LSTM-based NOMA Detector Over Time Selective Nakagami-m Fading Channel Conditions, Journal of Telecommunications and Information Technology, 2022, nr 3
Full text linkThis work examines the efficacy of deep learning (DL) based non-orthogonal multiple access (NOMA) receivers in vehicular communications (VC). Analytical formulations for the outage probability (OP), symbol error rate (SER), and ergodic sum rate for the researched vehicle networks are established Rusing i.i.d. Nakagami-m fading links. Standard receivers, such as least square (LS) and minimum mean square error (MMSE), are outperformed by the stacked long-short term memory (S-LSTM) based DL-NOMA receiver. Under real time propagation circumstances, including the cyclic prefix (CP) and clipping distortion, the simulation curves compare the performance of MMSE and LS receivers with that of the DL-NOMA receiver. According to numerical statistics, NOMA outperforms conventional orthogonal multiple access (OMA) by roughly 20% and has a high sum rate when considering i.i.d. fading links
Ranging and PositioningAccuracy for Selected Correlatorsunder VHF Maritime PropagationConditions, Journal of Telecommunications and Information Technology, 2022, nr 3
Full text linkThe article presents an analysis of the features of selected correlators impacting the accuracy of determining the receiver’s range and position in VHF marine environment. The paper introduces the concept of various correlators – including the double delta correlator – and describes the proposed measurement scenarios that have been designed to demonstrate the effectiveness of those components. The entire work was performed as part of the R-Mode Baltic and R-Mode Baltic 2 projects, with our goals including analyzing the impact of multipath phenomena, changes in the sampling frequency or Signac type on the determination of the received signal delay at the receiver. The measured data were processed in a signal correlation application and in a TOA-based tool in order to determine the receiver’s position. This process made it possible to compare the selected correlating devices. The results presented in this article are to be used by IALA in developing a current version of the VHF data exchange system’s (VDES) specification
Convolutional Neural Networks for C. Elegans Muscle Age Classification Using Only Self-learned Features, Journal of Telecommunications and Information Technology, 2022, nr 4
Full text linkNematodes Caenorhabditis elegans (C. elegans) have been used as model organisms in a wide variety of biological studies, especially those intended to obtain a better understanding of aging and age-associated diseases. This paper focuses on automating the analysis of C. elegans imagery to classify the muscle age of nematodes based on the known and well established IICBU dataset. Unlike many modern classification methods, the proposed approach relies on deep learning techniques, specifically on convolutional neural networks (CNNs), to solve the problem and achieve high classification accuracy by focusing on non-handcrafted self-learned features. Various networks known from the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) have been investigated and adapted for the purposes of the C. elegans muscle aging dataset by applying transfer learning and data augmentation techniques. The proposed approach of unfreezing different numbers of convolutional layers at the feature extraction stage and introducing different structures of newly trained fully connected layers at the classification stage, enable to better fine-tune the selected networks. The adjusted CNNs, as featured in this paper, have been compared with other state-of-art methods. In anti-aging drug research, the proposed CNNs would serve as a very fast and effective age determination method, thus leading to reductions in time and costs of laboratory research
Preliminary Evaluation of Convolutional Neural Network Acoustic Model for Iban Language Using NVIDIA NeMo, Journal of Telecommunications and Information Technology, 20022, nr 1
Full text linkFor the past few years, artificial neural networks (ANNs) have been one of the most common solutions relied upon while developing automated speech recognition (ASR) acoustic models. There are several variants of ANNs, such as deep neural networks (DNNs), recurrent neural networks (RNNs), and convolutional neural networks (CNNs). A CNN model is widely used as a method for improving image processing performance. In recent years, CNNs have also been utilized in ASR techniques, and this paper investigates the preliminary result of an end-to-end CNN-based ASR using NVIDIA NeMo on the Iban corpus, an under-resourced language. Studies have shown that CNNs have also managed to produce excellent word error (WER) rates for the acoustic model on ASR for speech data. Conversely, results and studies concerned with under-resourced languages remain unsatisfactory. Hence, by using NVIDIA NeMo, a new ASR engine developed by NVIDIA, the viability and the potential of this alternative approach are evaluated in this paper. Two experiments were conducted: the number of resources used in the works of our ASR’s training was manipulated, as was the internal parameter of the engine used, namely the epochs. The results of those experiments are then analyzed and compared with the results shown in existing papers
How to Model an Engaging Online Quiz? The Emotion Modeling Approach, Journal of Telecommunications and Information Technology, 2022, nr 1
Full text linkThe article focuses on software technology used to provide a more engaging and exciting learning environment for students by introducing a variety of quizzes. Presently, quiz development can range from simple multiple-choice questions, true or false, drag-and-drop, dropdown menu selections, to 3D interactive techniques. This study introduces a systematic way of creating an engaging application using emotion modeling. Emotion models are being introduced in order to collect and model the systems’ meaningful emotional needs. According to the findings, agent-oriented modeling is capable of modeling the emotional requirements of a system and of transforming these into a specific solution enabling to rapidly prototype an engaging system. A quantitative study has been performed on the novel approach to determine the feasibility of the proposed methodology in terms of analyzing, designing, and developing engaging applications
An Extended Version of the Proportional Adaptive Algorithm Based on Kernel Methods for Channel Identification with Binary Measurements, Journal of Telecommunications and Information Technology, 2022, nr 3
Full text linkIn recent years, kernel methods have provided an important alternative solution, as they offer a simple way of expanding linear algorithms to cover the non-linear mode as well. In this paper, we propose a novel recursive kernel approach allowing to identify the finite impulse response (FIR) in non-linear systems, with binary value output observations. This approach employs a kernel function to perform implicit data mapping. The transformation is performed by changing the basis of the data In a high-dimensional feature space in which the relations between the different variables become linearized. To assess the performance of the proposed approach, we have compared it with two other algorithms, such as proportionate normalized least-meansquare (PNLMS) and improved PNLMS (IPNLMS). For this purpose, we used three measurable frequency-selective fading radio channels, known as the broadband radio access Network (BRAN C, BRAN D, and BRAN E), which are standardized by the European Telecommunications Standards Institute (ETSI), and one theoretical frequency selective channel, known as the Macchi’s channel. Simulation results show that the proposed algorithm offers better results, even in high noise environments, and generates a lower mean square error (MSE) compared with PNLMS and IPNLMS
Multi-operator Differential Evolution with MOEA/D for Solving Multi-objective Optimization Problems, Journal of Telecommunications and Information Technology, 2022, nr3
Full text linkIn this paper, we propose a multi-operator differentia evolution variant that incorporates three diverse mutation strategies in MOEA/D. Instead of exploiting the local region, the proposed approach continues to search for optimal solutions in the entire objective space. It explicitly maintains diversity of the population by relying on the benefit of clustering. To promowe convergence, the solutions close to the ideal position, in the objective space are given preference in the evolutionary process. The core idea is to ensure diversity of the population by applying multiple mutation schemes and a faster convergence rate, giving preference to solutions based on their proximity to the ideal position in the MOEA/D paradigm. The performance of the proposed algorithm is evaluated by two popular test suites. The experimental results demonstrate that the proposed approach outperforms other MOEA/D algorithms
Shallow Layer Convolutional Features with Correlation Filters for UAV Object Tracking, Journal of Telecommunications and Information Technology, 2022, nr 2
Full text linkIn this paper, convolutional shallow features are proposed for unmanned aerial vehicle (UAV) tracking. These convolutional shallow features are generated by pre-trained convolutional neural networks (CNN) and are used to represent the target objects. Furthermore, to estimate the location of the target objects, an adaptive correlation filter based on the Fourier transform is used. This filter is multiplied with the convolutional shallow features by using pixel-wise multiplication in the Fourier domain. Then, the inverse of Fourier is performed to estimate the location of the target object, where its location is represented by the maximum value of the response map. Unfortunately, the target object always changes its appearance during tracking. Therefore, we proposed an updated model to address this issue. The proposed method is evaluated by using the UAV123 10fps benchmark dataset. Based on the comprehensive experimental results, the proposed method performs favorably against state-of-the-art tracking algorithm
Unequally Spaced Antenna Array Synthesis Using Accelerating Gaussian Mutated Cat Swarm Optimization, Journal of Telecommunications and Information Technology, 2022, nr 1
Full text linkLow peak sidelobe level (PSLL) and antenna arrays with high directivity are needed nowadays for reliable wireless communication systems. Controlling the PSLL is a major issue in designing effective antenna array systems. In this paper, a nature inspired technique, namely accelerating Gaussian mutated cat swarm optimization (AGMCSO) that attributes global search abilities, is proposed to control PSLL in the radiation pattern. In AGM-SCO, Gaussian mutation with an acceleration parameter is used in the position-updated equation, which allows the algorithm to search in a systematic way to prevent premature convergence and to enhance the speed of convergence. Experiments concerning several benchmark multimodal problems have been conducted and the obtained results illustrate that AGMCSO shows excellent performance concerning evolutionary speed and accuracy. To validate the overall efficacy of the algorithm, a sensitivity analysis was performed for different AGMCSO parameters. AGMCSO was researched on numerous linear, unequally spaced antenna arrays and the results show that in terms of generating low PSLL with a narrow first null beamwidth (FNBW), AGMCSO outperforms conventional algorithms
Multimodal Sarcasm Detection via Hybrid Classifier with Optimistic Logic, Journal of Telecommunications and Information Technology, 2022, nr 3
Full text linkThis work aims to provide a novel multimodal sarcasm detection model that includes four stages: pre-processing, feature extraction, feature level fusion, and classification. The pre-processing uses multimodal data that includes text, video, and audio. Here, text is pre-processed using tokenization and stemming, video is pre-processed during the face detection phase, and audio is pre-processed using the filtering technique. During the feature extraction stage, such text features as TF-IDF, improved bag of visual words, n-gram, and emojis as well on the video features using improved SLBT, and constraint local model (CLM) are extraction. Similarly the audio features like MFCC, chroma, spectral features, and jitter are extracted. Then, the extracted features are transferred to the feature level fusion stage, wherein an improved multilevel canonical correlation analysis (CCA) fusion technique is performed. The classification is performer using a hybrid classifier (HC), e.g. bidirectional gated recurrent unit (Bi-GRU) and LSTM. The outcomes of Bi-GRU and LSTM are averaged to obtain an effective output. To make the detection results more accurate, the weight of LSTM will be optimally tuned by the proposed opposition learning-based aquila optimization (OLAO) model. The MUStARD dataset is a multimodal video corpus used for automated sarcasm Discovery studies. Finally, the effectiveness of the proposed approach is proved based on various metrics