Random pulse width modulation techniques are used in AC motors powered by two-level three-phase inverters, which cause a broadband spectrum of voltage, current, and electromagnetic force. The voltage distribution across a wide range of frequencies may increase the vibration and acoustic noise of motors. This study proposes two selective noise suppression (SNS) methods to eliminate voltage harmonics for specified frequencies. In the first method, the switching frequency is constant. The pulse position is calculated by the duty cycle of the current switching cycle. Both the pulse position and switching frequency are randomized in the second method. This involves creating a unique relationship among the switching frequency, pulse position, and duty cycle to shape the noise spectrum. Computer simulation and experimental results show that both methods effectively perform selective noise suppression at a specific frequency. The power spectrum density (PSD) using the second SNS method is more uniform near integer multiples of the switching frequency than that using random pulse width modulation techniques or the first SNS method. These methods provide a valuable reference for eliminating electromagnetic and acoustic noises at resonant frequencies in motors.
There has been a recent surge of interest in introducing transformers to 3D human pose estimation (HPE) due to their powerful capabilities in modeling long-term dependencies. However, existing transformer-based methods treat body joints as equally important inputs and ignore the prior knowledge of human skeleton topology in the self-attention mechanism. To tackle this issue, in this paper, we propose a Pose-Oriented Transformer (POT) with uncertainty guided refinement for 3D HPE. Specifically, we first develop novel pose-oriented self-attention mechanism and distance-related position embedding for POT to explicitly exploit the human skeleton topology. The pose-oriented self-attention mechanism explicitly models the topological interactions between body joints, whereas the distance-related position embedding encodes the distance of joints to the root joint to distinguish groups of joints with different difficulties in regression. Furthermore, we present an Uncertainty-Guided Refinement Network (UGRN) to refine pose predictions from POT, especially for the difficult joints, by considering the estimated uncertainty of each joint with uncertainty-guided sampling strategy and self-attention mechanism. Extensive experiments demonstrate that our method significantly outperforms the state-of-the-art methods with reduced model parameters on 3D HPE benchmarks such as Human3.6M and MPI-INF-3DHP
A new era of space exploration and exploitation is fast approaching. A multitude of spacecraft will flow in the future decades under the propulsive momentum of the new space economy. Yet, the flourishing proliferation of deep-space assets will make it unsustainable to pilot them from ground with standard radiometric tracking. The adoption of autonomous navigation alternatives is crucial to overcoming these limitations. Among these, optical navigation is an affordable and fully ground-independent approach. Probes can triangulate their position by observing visible beacons, e.g., planets or asteroids, by acquiring their line-of-sight in deep space. To do so, developing efficient and robust image processing algorithms providing information to navigation filters is a necessary action. This paper proposes an innovative pipeline for unresolved beacon recognition and line-of-sight extraction from images for autonomous interplanetary navigation. The developed algorithm exploits the k-vector method for the non-stellar object identification and statistical likelihood to detect whether any beacon projection is visible in the image. Statistical results show that the accuracy in detecting the planet position projection is independent of the spacecraft position uncertainty. Whereas, the planet detection success rate is higher than 95% when the spacecraft position is known with a 3sigma accuracy up to 10^5 km.
Recent work has shown the possibility of training generative models of 3D content from 2D image collections on small datasets corresponding to a single object class, such as human faces, animal faces, or cars. However, these models struggle on larger, more complex datasets. To model diverse and unconstrained image collections such as ImageNet, we present VQ3D, which introduces a NeRF-based decoder into a two-stage vector-quantized autoencoder. Our Stage 1 allows for the reconstruction of an input image and the ability to change the camera position around the image, and our Stage 2 allows for the generation of new 3D scenes. VQ3D is capable of generating and reconstructing 3D-aware images from the 1000-class ImageNet dataset of 1.2 million training images. We achieve an ImageNet generation FID score of 16.8, compared to 69.8 for the next best baseline method.
In this paper, we address the vehicle scheduling problem for improving passenger safety in bus rapid transit systems. Our focus is on passengers waiting at street stops to enter terminal stations. To enhance their safety, we minimize deviations from the proposed timetable, thereby minimizing passengers' initial waiting time. We formulate an optimization problem considering the position, speed deviation, and passenger count at each stop, solved using dynamic programming. Numerical simulations validate the effectiveness of our approach in enhancing passenger safety. Our work is the first attempt to minimize waiting time for improved safety and the first to utilize position tracking for departure time matching.
Context-aware translation can be achieved by processing a concatenation of consecutive sentences with the standard Transformer architecture. This paper investigates the intuitive idea of providing the model with explicit information about the position of the sentences contained in the concatenation window. We compare various methods to encode sentence positions into token representations, including novel methods. Our results show that the Transformer benefits from certain sentence position encoding methods on English to Russian translation if trained with a context-discounted loss (Lupo et al., 2022). However, the same benefits are not observed in English to German. Further empirical efforts are necessary to define the conditions under which the proposed approach is beneficial.
Text generation from Abstract Meaning Representation (AMR) has substantially benefited from the popularized Pretrained Language Models (PLMs). Myriad approaches have linearized the input graph as a sequence of tokens to fit the PLM tokenization requirements. Nevertheless, this transformation jeopardizes the structural integrity of the graph and is therefore detrimental to its resulting representation. To overcome this issue, Ribeiro et al. have recently proposed StructAdapt, a structure-aware adapter which injects the input graph connectivity within PLMs using Graph Neural Networks (GNNs). In this paper, we investigate the influence of Relative Position Embeddings (RPE) on AMR-to-Text, and, in parallel, we examine the robustness of StructAdapt. Through ablation studies, graph attack and link prediction, we reveal that RPE might be partially encoding input graphs. We suggest further research regarding the role of RPE will provide valuable insights for Graph-to-Text generation.
This work proposes a novel approach that uses a semantic segmentation mask to obtain a 2D spatial layout of the segmentation-categories across the scene, designated by segmentation-based semantic features (SSFs). These features represent, per segmentation-category, the pixel count, as well as the 2D average position and respective standard deviation values. Moreover, a two-branch network, GS2F2App, that exploits CNN-based global features extracted from RGB images and the segmentation-based features extracted from the proposed SSFs, is also proposed. GS2F2App was evaluated in two indoor scene benchmark datasets: the SUN RGB-D and the NYU Depth V2, achieving state-of-the-art results on both datasets.
For the stable optimization of deep neural networks, regularization methods such as dropout and batch normalization have been used in various tasks. Nevertheless, the correct position to apply dropout has rarely been discussed, and different positions have been employed depending on the practitioners. In this study, we investigate the correct position to apply dropout. We demonstrate that for a residual network with batch normalization, applying dropout at certain positions increases the performance, whereas applying dropout at other positions decreases the performance. Based on theoretical analysis, we provide the following guideline for the correct position to apply dropout: apply one dropout after the last batch normalization but before the last weight layer in the residual branch. We provide detailed theoretical explanations to support this claim and demonstrate them through module tests. In addition, we investigate the correct position of dropout in the head that produces the final prediction. Although the current consensus is to apply dropout after global average pooling, we prove that applying dropout before global average pooling leads to a more stable output. The proposed guidelines are validated through experiments using different datasets and models.
With the power of large pretrained language models, various research works have integrated knowledge into dialogue systems. The traditional techniques treat knowledge as part of the input sequence for the dialogue system, prepending a set of knowledge statements in front of dialogue history. However, such a mechanism forces knowledge sets to be concatenated in an ordered manner, making models implicitly pay imbalanced attention to the sets during training. In this paper, we first investigate how the order of the knowledge set can influence autoregressive dialogue systems' responses. We conduct experiments on two commonly used dialogue datasets with two types of transformer-based models and find that models view the input knowledge unequally. To this end, we propose a simple and novel technique to alleviate the order effect by modifying the position embeddings of knowledge input in these models. With the proposed position embedding method, the experimental results show that each knowledge statement is uniformly considered to generate responses.
In recent years, deep learning technology has developed rapidly, and the application of deep neural networks in the medical image processing field has become the focus of the spotlight. This paper aims to achieve needle position detection in medical retinal surgery by adopting the target detection algorithm based on YOLOv5 as the basic deep neural network model. The state-of-the-art needle detection approaches for medical surgery mainly focus on needle structure segmentation. Instead of the needle segmentation, the proposed method in this paper contains the angle examination during the needle detection process. This approach also adopts a novel classification method based on the different positions of the needle to improve the model. The experiments demonstrate that the proposed network can accurately detect the needle position and measure the needle angle. The performance test of the proposed method achieves 4.80 for the average Euclidean distance between the detected tip position and the actual tip position. It also obtains an average error of 0.85 degrees for the tip angle across all test sets.
Deep Neural Network (DNN) Inference in Edge Computing, often called Edge Intelligence, requires solutions to insure that sensitive data confidentiality and intellectual property are not revealed in the process. Privacy-preserving Edge Intelligence is only emerging, despite the growing prevalence of Edge Computing as a context of Machine-Learning-as-a-Service. Solutions are yet to be applied, and possibly adapted, to state-of-the-art DNNs. This position paper provides an original assessment of the compatibility of existing techniques for privacy-preserving DNN Inference with the characteristics of an Edge Computing setup, highlighting the appropriateness of secret sharing in this context. We then address the future role of model compression methods in the research towards secret sharing on DNNs with state-of-the-art performance.
In this paper, we investigate the problem of estimating the position and the angle of rotation of a mobile station (MS) in a millimeter wave (mmWave) multiple-input-multiple-output (MIMO) system aided by a reconfigurable intelligent surface (RIS). The virtual line-of-sight (VLoS) link created by the RIS and the non-line-of-sight (NLoS) links that originate from scatterers in the considered environment are utilized to facilitate the estimation. A two-step positioning scheme is exploited, where the channel parameters are first acquired, and the position-related parameters are then estimated. The channel parameters are obtained through a coarser and a subsequent finer estimation processes. As for the coarse estimation, the distributed compressed sensing orthogonal simultaneous matching pursuit (DCS-SOMP) algorithm, the maximum likelihood (ML) algorithm, and the discrete Fourier transform (DFT) are utilized to separately estimate the channel parameters. The obtained channel parameters are then jointly refined by using the space-alternating generalized expectation maximization (SAGE) algorithm, which circumvents the high-dimensional optimization issue of ML estimation. Departing from the estimated channel parameters, the positioning-related parameters are estimated. The performance of estimating the channel-related and position-related parameters is theoretically quantified by using the Cramer-Rao lower bound (CRLB). Simulation results demonstrate the superior performance of the proposed positioning algorithms.
Across the legal profession, statistics related to the numbers of women and other underrepresented groups in leadership roles continue to paint a bleak picture of diversity and inclusion. Some approaches to closing this gap have focused on the cause; some have devised and applied solutions. Questions about the efficacy of many of these solutions remain essentially unanswered. This empirical study represents one of the first of its kind. Studies of the legal profession have not focused on the dynamics of supply and demand in the context of leadership positions (counsel and partner (equity and non-equity)). Neither have they examined the interrelationships of these dynamics to race and gender demographic factors (white female and minorities (male and female)). This research seeks to determine the supply-demand position of leadership in the legal profession and establish market equilibrium for these counsel and partner roles.
This paper considers an integrated sensing and communication system, where some radar targets also serve as communication scatterers. A location domain channel modeling method is proposed based on the position of targets and scatterers in the scattering environment, and the resulting radar and communication channels exhibit a two-dimensional (2-D) joint burst sparsity. We propose a joint scattering environment sensing and channel estimation scheme to enhance the target/scatterer localization and channel estimation performance simultaneously, where a spatially non-stationary Markov random field (MRF) model is proposed to capture the 2-D joint burst sparsity. An expectation maximization (EM) based method is designed to solve the joint estimation problem, where the E-step obtains the Bayesian estimation of the radar and communication channels and the M-step automatically learns the dynamic position grid and prior parameters in the MRF. However, the existing sparse Bayesian inference methods used in the E-step involve a high-complexity matrix inverse per iteration. Moreover, due to the complicated non-stationary MRF prior, the complexity of M-step is exponentially large. To address these difficulties, we propose an inverse-free variational Bayesian inference algorithm for the E-step and a low-complexity method based on pseudo-likelihood approximation for the M-step. In the simulations, the proposed scheme can achieve a better performance than the state-of-the-art method while reducing the computational overhead significantly.
Construction Grammar (CxG) has recently been used as the basis for probing studies that have investigated the performance of large pretrained language models (PLMs) with respect to the structure and meaning of constructions. In this position paper, we make suggestions for the continuation and augmentation of this line of research. We look at probing methodology that was not designed with CxG in mind, as well as probing methodology that was designed for specific constructions. We analyse selected previous work in detail, and provide our view of the most important challenges and research questions that this promising new field faces.
In nearest-neighbor classification, a training set $P$ of points in $\mathbb{R}^d$ with given classification is used to classify every point in $\mathbb{R}^d$: Every point gets the same classification as its nearest neighbor in $P$. Recently, Eppstein [SOSA'22] developed an algorithm to detect the relevant training points, those points $p\in P$, such that $P$ and $P\setminus\{p\}$ induce different classifications. We investigate the problem of finding the minimum cardinality reduced training set $P'\subseteq P$ such that $P$ and $P'$ induce the same classification. We show that the set of relevant points is such a minimum cardinality reduced training set if $P$ is in general position. Furthermore, we show that finding a minimum cardinality reduced training set for possibly degenerate $P$ is in P for $d=1$, and NP-complete for $d\geq 2$.
Image-based environment perception is an important component especially for driver assistance systems or autonomous driving. In this scope, modern neuronal networks are used to identify multiple objects as well as the according position and size information within a single frame. The performance of such an object detection model is important for the overall performance of the whole system. However, a detection model might also predict these objects under a certain degree of uncertainty. [...] In this work, we examine the semantic uncertainty (which object type?) as well as the spatial uncertainty (where is the object and how large is it?). We evaluate if the predicted uncertainties of an object detection model match with the observed error that is achieved on real-world data. In the first part of this work, we introduce the definition for confidence calibration of the semantic uncertainty in the context of object detection, instance segmentation, and semantic segmentation. We integrate additional position information in our examinations to evaluate the effect of the object's position on the semantic calibration properties. Besides measuring calibration, it is also possible to perform a post-hoc recalibration of semantic uncertainty that might have turned out to be miscalibrated. [...] The second part of this work deals with the spatial uncertainty obtained by a probabilistic detection model. [...] We review and extend common calibration methods so that it is possible to obtain parametric uncertainty distributions for the position information in a more flexible way. In the last part, we demonstrate a possible use-case for our derived calibration methods in the context of object tracking. [...] We integrate our previously proposed calibration techniques and demonstrate the usefulness of semantic and spatial uncertainty calibration in a subsequent process. [...]
We develop a method to decompose the PnL of a portfolio of assets into four parts: (a) PnL due to FX rate changes, (b) PnL due to interest rate changes, (c) carry gain due to time passing, (d) PnL due to residual market risk changes (credit risk, liquidity risk, volatility risk etc.). We demonstrate the usefulness of our approach by decomposing the performance of an FX- and interest rate-hedged negative basis position in our fund XAIA Credit Basis II, and we apply the methodology to decompose the performance of our fund XAIA Credit Debt Capital in the first quarter of 2022 into PnL contributions of the single positions.
This paper presents a data-driven interpretable machine learning algorithm for semi-static hedging of Exchange Traded options, considering transaction costs with efficient run-time. Further, we provide empirical evidence on the performance of hedging longer-term National Stock Exchange (NSE) Index options using a self-replicating portfolio of shorter-term options and cash position, achieved by the automated algorithm, under different modeling assumptions and market conditions, including Covid period. We also systematically assess the model's performance using the Superior Predictive Ability (SPA) test by benchmarking against the static hedge proposed by Peter Carr and Liuren Wu and industry-standard dynamic hedging. We finally perform a thorough Profit and Loss (PnL) attribution analysis on the target option and hedge portfolios (dynamic and static) to discern the factors explaining the superior performance of static hedging.