Phase Tracking Sequences for 5G NR in 52.6-71 GHz Band: Design and Analysis

This paper presents a novel approach to the phase tracking reference signal (PTRS) design for phase noise impact compensation in the 5G NR communication systems intended to work in a new 52.6 GHz to 71 GHz frequency band. For detailed problem illustration, the phase noise compensation algorithms are discussed and explained, from the basic common phase error (CPE) compensation to the MMSE-base inter-carrier interference (ICI) filtering. Performance of the different phase noise compensation algorithms is investigated for the baseline PTRS accepted in the current 5G NR specification and compared with the newly proposed approach to the PTRS design. This approach is based on nulling the subcarriers adjacent to the reference signals to minimize influence of the ICI on the estimation process. It was shown that new nulling PTRS design outperforms currently used distributed PTRS structure. In addition, numerical results represent a trade-off between the filter size and the amount of the allocated training resources to achieve better performance. It was shown that proposed PTRS structures and processing algorithms give ICI compensation level very close to optimal scheme and thus, different approaches (such as time domain compensation) may be required for further progress.

Analysing the Correlation between Convolutional Filter Sizes and Classification Accuracy Using MNIST

Handwriting recognition is the process of automatically converting handwritten text into electronic text (letter codes) usable by a computer. The increase in technology reliance during an international pandemic caused by COVID-19 has showcased the importance of ensuring the information stored and digitised is done accurately and efficiently. Interpreting handwriting remains complex for both humans and computers due to the various styles and skewed characters. In this study, we conducted a correlational analysis on the association between filter sizes and the convolutional neural networks (CNN’s) classification accuracy. The testing has been conducted from the publicly available MNIST database of handwritten digits (LeCun and Cortes, 2010). The dataset consists of a training set (N=60,000) and a testing set (N=10,000). Using ANOVA, our results indicate a strong correlation (.000,P≤0.05) between filter size and classification accuracy. However, this significance is only present when increasing the filter size from 1x1 to 2x2. Larger filter sizes were insignificant therefore, a filter size above 2x2 cannot be recommended.

Design of a compact reconfigurable bandpass filter using interdigital capacitor, DMS slots and varactor diode for wireless RF systems

This paper proposes a new design of a reconfigurable bandpass filter based on an interdigital capacitor and varactor diode for wireless and mobile applications. The designed reconfigurable bandpass filter has been implemented on an RT 6010 substrate with a relative dielectric constant of 10.2, thickness of 1.27 mm, and loss tangent of 0.0023. In order to reduce the filter size, the defected microstrip structure (DMS) is used due to its easy design, high compactness, high quality factor and easy integration with other RF devices. The suggested reconfigurable filter has a simple structure with a very attractive compact size of 4.7 × 8.4 mm2, low insertion loss than -1 dB, and tuning range (2–2.6 GHz).

A Precision Agricultural Application: Manggis Fruit Classification Using Hybrid Deep Learning

Fruits come in different variants and subspecies. While some subspecies of fruits can be easily differentiated, others may require an expertness to differentiate them. Although farmers rely on the traditional methods to identify and classify fruit types, the methods are prone to so many challenges. Training a machine to identify and classify fruit types in place of traditional methods can ensure precision fruit classification. By taking advantage of the state-of-the-art image recognition techniques, we approach fruits classification from another perspective by proposing a high performing hybrid deep learning which could ensure precision mangosteen fruit classification. This involves a proposed optimized Convolutional Neural Network (CNN) model compared to other optimized models such as Xception, VGG16, and ResNet50 using Adam, RMSprop, Adagrad, and Stochastic Gradient Descent (SGD) optimizers on specified dense layers and filters numbers. The proposed CNN model has three types of layers that make up its model, they are: 1) the convolutional layers, 2) the pooling layers, and 3) the fully connected (FC) layers. The first convolution layer uses convolution filters with a filter size of 3x3 used for initializing the neural network with some weights prior to updating to a better value for each iteration. The CNN architecture is formed from stacking these layers. Our self-acquired dataset which is composed of four different types of Malaysian mangosteen fruit, namely Manggis Hutan, Manggis Mesta, Manggis Putih and Manggis Ungu was employed for the training and testing of the proposed CNN model. The proposed CNN model achieved 94.99% classification accuracy higher than the optimized Xception model which achieved 90.62% accuracy in the second position.

Layer contour characterization in additive manufacturing through image binarization

On-Machine Measurement adoption will be key to dimensional and geometrical improvement of additively manufactured parts. One possible approach based on OMM aims at using digital images of manufactured layers to characterize actual contour deviations with respect to their theoretical profile. This strategy would also allow for in-process corrective actions. This work describes a layer-contour characterization procedure based on binarization of digital images acquired with a flat-bed scanner. This procedure has been tested off-line to evaluate the influence of two of the parameters for image treatment, the median filter size (S f ) and the threshold value (T), on the dimensional/geometrical reliability of the contour characterization. Results showed that an appropriate selection of configuration parameters allowed to characterize the proposed test-target with excellent coverage and reasonable accuracy.

A Novel Handwritten Digit Classification System Based on Convolutional Neural Network Approach

An enormous number of CNN classification algorithms have been proposed in the literature. Nevertheless, in these algorithms, appropriate filter size selection, data preparation, limitations in datasets, and noise have not been taken into consideration. As a consequence, most of the algorithms have failed to make a noticeable improvement in classification accuracy. To address the shortcomings of these algorithms, our paper presents the following contributions: Firstly, after taking the domain knowledge into consideration, the size of the effective receptive field (ERF) is calculated. Calculating the size of the ERF helps us to select a typical filter size which leads to enhancing the classification accuracy of our CNN. Secondly, unnecessary data leads to misleading results and this, in turn, negatively affects classification accuracy. To guarantee the dataset is free from any redundant or irrelevant variables to the target variable, data preparation is applied before implementing the data classification mission. Thirdly, to decrease the errors of training and validation, and avoid the limitation of datasets, data augmentation has been proposed. Fourthly, to simulate the real-world natural influences that can affect image quality, we propose to add an additive white Gaussian noise with σ = 0.5 to the MNIST dataset. As a result, our CNN algorithm achieves state-of-the-art results in handwritten digit recognition, with a recognition accuracy of 99.98%, and 99.40% with 50% noise.

Compact Size of an Interdigital Band-Pass Filter with Flexible Bandwidth and Low Insertion-Loss Using a Folded Spiral and Stepped Impedance Resonant Structure

A conventional interdigital bandpass filter (BPF) is characterized by coupled and tapped lines and affords low insertion loss (IL) and easy fractional bandwidth (FBW) adjustment. However, the maximum FBW of the filter is limited to 30%, beyond that, its gap size increases, thereby rendering filter fabrication impractical on a standard printed circuit board. In addition, the filter size cannot be changed because it dictates the operational frequency of the filter. Hence, in this study, we propose a compact interdigital BPF based on a spiral and folded stepped impedance resonator (SIR), which affords low IL and excellent group delay. The spiral, folded structure facilitates drastic FBW adjustment: the center frequency and adjustable range of the FBW of the designed BPF are 800 MHz and 80 to 180%, respectively. Additionally, the proposed BPF can adjust the FBW by k-factor which can adjust from 80 to 180%. The insertion and return losses of the proposed filter are 0.043 dB and 17.1 dB, respectively, and the group delay is 0.098 ns. The total filter size is only 13.8 mm × 5.98 mm, which corresponds to a size reduction by factors of >2/8 relative to a conventional filter and 2.1 relative to the latest BPF design. The group delay difference between the BPF and other filters is 0.15 ns. In addition, the range of adjustable FBW for the filter is 1.36 times different than for other filters.

Generalization Capability of Convolutional Neural Networks for Progress Variable Variance and Reaction Rate Subgrid-Scale Modeling

Deep learning has recently emerged as a successful approach to produce accurate subgrid-scale (SGS) models for Large Eddy Simulations (LES) in combustion. However, the ability of these models to generalize to configurations far from their training distribution is still mainly unexplored, thus impeding their application to practical configurations. In this work, a convolutional neural network (CNN) model for the progress-variable SGS variance field is trained on a canonical premixed turbulent flame and evaluated a priori on a significantly more complex slot burner jet flame. Despite the extensive differences between the two configurations, the CNN generalizes well and outperforms existing algebraic models. Conditions for this successful generalization are discussed, including the effect of the filter size and flame–turbulence interaction parameters. The CNN is then integrated into an analytical reaction rate closure relying on a single-step chemical source term formulation and a presumed beta PDF (probability density function) approach. The proposed closure is able to accurately recover filtered reaction rate values on both training and generalization flames.

P–260 Towards better explainable deep learning models for embryo selection in ART

Study question Can heatmaps generated by occlusion explain the patterns learned by deep learning (DL) models classifying the embryo viability in ART? Summary answer Occlusion experiments generate heatmaps that reveal which regions in frames of time-lapse video (TLV) are more discriminative for classification and prediction by the DL models. What is known already DL has widely been explored in ART for embryo selection. Depending upon input (video or image), different DL models classifying embryo viability are developed. However, whether the prediction is based on actual input features or random guessing is unknown. The embryo selection in ART is subjective. If the intention is using DL models’ prediction to transfer, freeze or discard the embryo, explanations of how they interpret embryonic development features brings transparency and trust. In other areas, heatmaps are used for explaining DL predictions. The heatmaps can be a tool to understand patterns learned by DL models for embryo selection. Study design, size, duration We trained two separate DL models for predicting the presence of fetal heartbeat for the transferred embryos. We further used occlusion generated heatmaps to explain the predictions. For training, retrospective data was used. The input dataset consisted of 136 TLVs and corresponding patient data for 132 participants (128: single embryo transfers and 8: double embryo transfer) from both IVF and ICSI treatment. Each video was assessed by an embryologist. Participants/materials, setting, methods DL models (A as ResNet–18, B as VGG16) are trained for predicting the presence of fetal heartbeat on a single frame extracted from TLV after day three or later. Model A has a better recall (0.7) compared to B (0.5). Heatmaps explain the reason behind models’ recall rate by visually representing patterns learned by them. Using occlusion filter size 30*30 with stride 14 and size 50*50 with stride 25, we generate heatmaps for both models. Main results and the role of chance The heatmaps generated using occlusion can represent visually the patterns discovered by the DL models when predicting the presence of a fetal heartbeat. Using occlusion filter size 30*30 with stride 14, we verified that Model B has lower recall because the heatmaps show that the model finds redundant features present outside the embryo region in many input frames. It could be interpreted that either the model has not learned relevant patterns or is more robust to noise. This representation of DL models equips us in better decision-making, whether to consider or discard the prediction or rather train the model further, preprocess training data or change network architecture. The heatmaps revealed that for frames where significant patterns learned by the models are within the embryo region, more weight was given to specific features like the inner cell mass, trophectoderm and some parts within the zona pellucida. Moreover, the heat maps generated using occlusion are independent of the underlying model’s architecture as the same experiment settings were used for both models. For occlusion filter size 50*50 with stride 25, the expanse of input regions (in or outside the embryo) considered relevant could be visualized for both models A and B. Limitations, reasons for caution Heatmaps generated by occluding input regions give a visual representation of features in individual frames not directly on videos. Explaining DL models by heatmaps besides occlusion, other techniques (Grad-Cam) exist but were not evaluated. Furthermore, there is no quantitative measure for evaluating whether heatmaps are a good explanation or not. Wider implications of the findings: The heatmaps make the patterns discovered by DL models visually recognized and bring forth the prominent portions of embryo regions. This will again improve understanding and trust in DL models’ predictions. Visual representation of DL models using heatmaps enables interpreting a prediction, performing model analysis and determining scope for improvement. Trial registration number Not applicable