Search

The paper explores a new extremality model involving collections of arbitrary families of sets. We demonstrate its applicability to set-valued optimization problems with general preferences, weakening the assumptions of the known results and streamlining their proofs., Comment: 15 pages. Formerly appeared as part of arXiv:2403.16511v2

This research presents an enhanced approach for precise segmentation of brain tumor masses in magnetic resonance imaging (MRI) using an advanced 3D-UNet model combined with a Context Transformer (CoT). By architectural expansion CoT, the proposed model extends its architecture to a 3D format, integrates it smoothly with the base model to utilize the complex contextual information found in MRI scans, emphasizing how elements rely on each other across an extended spatial range. The proposed model synchronizes tumor mass characteristics from CoT, mutually reinforcing feature extraction, facilitating the precise capture of detailed tumor mass structures, including location, size, and boundaries. Several experimental results present the outstanding segmentation performance of the proposed method in comparison to current state-of-the-art approaches, achieving Dice score of 82.0%, 81.5%, 89.0% for Enhancing Tumor, Tumor Core and Whole Tumor, respectively, on BraTS2019., Comment: 6 pages, 7 figures

We introduce HouseCrafter, a novel approach that can lift a floorplan into a complete large 3D indoor scene (e.g., a house). Our key insight is to adapt a 2D diffusion model, which is trained on web-scale images, to generate consistent multi-view color (RGB) and depth (D) images across different locations of the scene. Specifically, the RGB-D images are generated autoregressively in a batch-wise manner along sampled locations based on the floorplan, where previously generated images are used as condition to the diffusion model to produce images at nearby locations. The global floorplan and attention design in the diffusion model ensures the consistency of the generated images, from which a 3D scene can be reconstructed. Through extensive evaluation on the 3D-Front dataset, we demonstrate that HouseCraft can generate high-quality house-scale 3D scenes. Ablation studies also validate the effectiveness of different design choices. We will release our code and model weights. Project page: https://neu-vi.github.io/houseCrafter/

Intrinsic capability to continuously learn a changing data stream is a desideratum of deep neural networks (DNNs). However, current DNNs suffer from catastrophic forgetting, which hinders remembering past knowledge. To mitigate this issue, existing Continual Learning (CL) approaches either retain exemplars for replay, regularize learning, or allocate dedicated capacity for new tasks. This paper investigates an unexplored CL direction for incremental learning called Incremental Latent Rectification or ILR. In a nutshell, ILR learns to propagate with correction (or rectify) the representation from the current trained DNN backward to the representation space of the old task, where performing predictive decisions is easier. This rectification process only employs a chain of small representation mapping networks, called rectifier units. Empirical experiments on several continual learning benchmarks, including CIFAR10, CIFAR100, and Tiny ImageNet, demonstrate the effectiveness and potential of this novel CL direction compared to existing representative CL methods.

Many recent studies have investigated social biases in LLMs but brand bias has received little attention. This research examines the biases exhibited by LLMs towards different brands, a significant concern given the widespread use of LLMs in affected use cases such as product recommendation and market analysis. Biased models may perpetuate societal inequalities, unfairly favoring established global brands while marginalizing local ones. Using a curated dataset across four brand categories, we probe the behavior of LLMs in this space. We find a consistent pattern of bias in this space -- both in terms of disproportionately associating global brands with positive attributes and disproportionately recommending luxury gifts for individuals in high-income countries. We also find LLMs are subject to country-of-origin effects which may boost local brand preference in LLM outputs in specific contexts.

Learning conditional distributions is challenging because the desired outcome is not a single distribution but multiple distributions that correspond to multiple instances of the covariates. We introduce a novel neural entropic optimal transport method designed to effectively learn generative models of conditional distributions, particularly in scenarios characterized by limited sample sizes. Our method relies on the minimax training of two neural networks: a generative network parametrizing the inverse cumulative distribution functions of the conditional distributions and another network parametrizing the conditional Kantorovich potential. To prevent overfitting, we regularize the objective function by penalizing the Lipschitz constant of the network output. Our experiments on real-world datasets show the effectiveness of our algorithm compared to state-of-the-art conditional distribution learning techniques. Our implementation can be found at https://github.com/nguyenngocbaocmt02/GENTLE., Comment: 15 pages, 8 figures

Rating elicitation is a success element for recommender systems to perform well at cold-starting, in which the systems need to recommend items to a newly arrived user with no prior knowledge about the user's preference. Existing elicitation methods employ a fixed set of items to learn the user's preference and then infer the users' preferences on the remaining items. Using a fixed seed set can limit the performance of the recommendation system since the seed set is unlikely optimal for all new users with potentially diverse preferences. This paper addresses this challenge using a 2-phase, personalized elicitation scheme. First, the elicitation scheme asks users to rate a small set of popular items in a ``burn-in'' phase. Second, it sequentially asks the user to rate adaptive items to refine the preference and the user's representation. Throughout the process, the system represents the user's embedding value not by a point estimate but by a region estimate. The value of information obtained by asking the user's rating on an item is quantified by the distance from the region center embedding space that contains with high confidence the true embedding value of the user. Finally, the recommendations are successively generated by considering the preference region of the user. We show that each subproblem in the elicitation scheme can be efficiently implemented. Further, we empirically demonstrate the effectiveness of the proposed method against existing rating-elicitation methods on several prominent datasets., Comment: Accepted at UAI 2024

The Shapley value is a prominent tool for interpreting black-box machine learning models thanks to its strong theoretical foundation. However, for models with structured inputs, such as graph neural networks, existing Shapley-based explainability approaches either focus solely on node-wise importance or neglect the graph structure when perturbing the input instance. This paper introduces the Myerson-Taylor interaction index that internalizes the graph structure into attributing the node values and the interaction values among nodes. Unlike the Shapley-based methods, the Myerson-Taylor index decomposes coalitions into components satisfying a pre-chosen connectivity criterion. We prove that the Myerson-Taylor index is the unique one that satisfies a system of five natural axioms accounting for graph structure and high-order interaction among nodes. Leveraging these properties, we propose Myerson-Taylor Structure-Aware Graph Explainer (MAGE), a novel explainer that uses the second-order Myerson-Taylor index to identify the most important motifs influencing the model prediction, both positively and negatively. Extensive experiments on various graph datasets and models demonstrate that our method consistently provides superior subgraph explanations compared to state-of-the-art methods., Comment: 30 pages, ICML'24

Interpretability techniques are valuable for helping humans understand and oversee AI systems. The SaTML 2024 CNN Interpretability Competition solicited novel methods for studying convolutional neural networks (CNNs) at the ImageNet scale. The objective of the competition was to help human crowd-workers identify trojans in CNNs. This report showcases the methods and results of four featured competition entries. It remains challenging to help humans reliably diagnose trojans via interpretability tools. However, the competition's entries have contributed new techniques and set a new record on the benchmark from Casper et al., 2023., Comment: Competition for SaTML 2024

This paper presents a simple yet efficient ensemble learning framework for Vietnamese scene text spotting. Leveraging the power of ensemble learning, which combines multiple models to yield more accurate predictions, our approach aims to significantly enhance the performance of scene text spotting in challenging urban settings. Through experimental evaluations on the VinText dataset, our proposed method achieves a significant improvement in accuracy compared to existing methods with an impressive accuracy of 5%. These results unequivocally demonstrate the efficacy of ensemble learning in the context of Vietnamese scene text spotting in urban environments, highlighting its potential for real world applications, such as text detection and recognition in urban signage, advertisements, and various text-rich urban scenes., Comment: RIVF 2023

The paper proposes another extension of the extremal principle. A new extremality model involving collections of arbitrary families of sets is studied. It generalizes the conventional model based on linear translations of given sets as well as its set-valued extensions. This approach leads to a more general and simpler version of fuzzy separation. The new model is capable of treating a wider range of optimization and variational problems., Comment: 12 pages

The ability to extract material parameters of perovskite from quantitative experimental analysis is essential for rational design of photovoltaic and optoelectronic applications. However, the difficulty of this analysis increases significantly with the complexity of the theoretical model and the number of material parameters for perovskite. Here we use Bayesian optimization to develop an analysis platform that can extract up to 8 fundamental material parameters of an organometallic perovskite semiconductor from a transient photoluminescence experiment, based on a complex full physics model that includes drift-diffusion of carriers and dynamic defect occupation. An example study of thermal degradation reveals that the carrier mobility and trap-assisted recombination coefficient are reduced noticeably, while the defect energy level remains nearly unchanged. The reduced carrier mobility can dominate the overall effect on thermal degradation of perovskite solar cells by reducing the fill factor, despite the opposite effect of the reduced trap-assisted recombination coefficient on increasing the fill factor. In future, this platform can be conveniently applied to other experiments or to combinations of experiments, accelerating materials discovery and optimization of semiconductor materials for photovoltaics and other applications., Comment: The work is published in Energy & Environmental Science (DOI: 10.1039/D4EE00911H). This work is supported by the Australian Centre for Advanced Photovoltaics (ACAP) and received funding from the Australian Renewable Energy Agency (ARENA). H.Z. acknowledges the support of the ACAP Fellowship. H.Z. thanks Pawsey for providing the Nimbus Research Cloud Service

Recent advances in AI and intelligent vehicle technology hold promise to revolutionize mobility and transportation, in the form of advanced driving assistance (ADAS) interfaces. Although it is widely recognized that certain cognitive factors, such as impulsivity and inhibitory control, are related to risky driving behavior, play a significant role in on-road risk-taking, existing systems fail to leverage such factors. Varying levels of these cognitive factors could influence the effectiveness and acceptance of driver safety interfaces. We demonstrate an approach for personalizing driver interaction via driver safety interfaces that are triggered based on a learned recurrent neural network. The network is trained from a population of human drivers to infer impulsivity and inhibitory control from recent driving behavior. Using a high-fidelity vehicle motion simulator, we demonstrate the ability to deduce these factors from driver behavior. We then use these inferred factors to make instantaneous determinations on whether or not to engage a driver safety interface. This interface aims to decrease a driver's speed during yellow lights and reduce their inclination to run through them., Comment: 12 pages, 7 figures

In recent years, scientific machine learning, particularly physic-informed neural networks (PINNs), has introduced new innovative methods to understanding the differential equations that describe power system dynamics, providing a more efficient alternative to traditional methods. However, using a single neural network to capture patterns of all variables requires a large enough size of networks, leading to a long time of training and still high computational costs. In this paper, we utilize the interfacing of PINNs with symbolic techniques to construct multiple single-output neural networks by taking the loss function apart and integrating it over the relevant domain. Also, we reweigh the factors of the components in the loss function to improve the performance of the network for instability systems. Our results show that the symbolic PINNs provide higher accuracy with significantly fewer parameters and faster training time. By using the adaptive weight method, the symbolic PINNs can avoid the vanishing gradient problem and numerical instability.

Macro placement is a critical phase in chip design, which becomes more intricate when involving general rectilinear macros and layout areas. Furthermore, macro placement that incorporates human-like constraints, such as design hierarchy and peripheral bias, has the potential to significantly reduce the amount of additional manual labor required from designers. This study proposes a methodology that leverages an approach suggested by Google's Circuit Training (G-CT) to provide a learning-based macro placer that not only supports placing rectilinear cases, but also adheres to crucial human-like design principles. Our experimental results demonstrate the effectiveness of our framework in achieving power-performance-area (PPA) metrics and in obtaining placements of high quality, comparable to those produced with human intervention. Additionally, our methodology shows potential as a generalized model to address diverse macro shapes and layout areas., Comment: Fast ML for Science @ ICCAD 2023

Navigating in unseen environments is crucial for mobile robots. Enhancing them with the ability to follow instructions in natural language will further improve navigation efficiency in unseen cases. However, state-of-the-art (SOTA) vision-and-language navigation (VLN) methods are mainly evaluated in simulation, neglecting the complex and noisy real world. Directly transferring SOTA navigation policies trained in simulation to the real world is challenging due to the visual domain gap and the absence of prior knowledge about unseen environments. In this work, we propose a novel navigation framework to address the VLN task in the real world. Utilizing the powerful foundation models, the proposed framework includes four key components: (1) an LLMs-based instruction parser that converts the language instruction into a sequence of pre-defined macro-action descriptions, (2) an online visual-language mapper that builds a real-time visual-language map to maintain a spatial and semantic understanding of the unseen environment, (3) a language indexing-based localizer that grounds each macro-action description into a waypoint location on the map, and (4) a DD-PPO-based local controller that predicts the action. We evaluate the proposed pipeline on an Interbotix LoCoBot WX250 in an unseen lab environment. Without any fine-tuning, our pipeline significantly outperforms the SOTA VLN baseline in the real world.

This research project aims to develop a real-time traffic sign detection system using the YOLOv5 architecture and deploy it for efficient traffic sign recognition during a drive in a suburban neighborhood. The project's primary objectives are to train the YOLOv5 model on a diverse dataset of traffic sign images and deploy the model on a suitable hardware platform capable of real-time inference. The project will involve collecting a comprehensive dataset of traffic sign images. By leveraging the trained YOLOv5 model, the system will detect and classify traffic signs from a real-time camera on a dashboard inside a vehicle. The performance of the deployed system will be evaluated based on its accuracy in detecting traffic signs, real-time processing speed, and overall reliability. During a case study in a suburban neighborhood, the system demonstrated a notable 96% accuracy in detecting traffic signs. This research's findings have the potential to improve road safety and traffic management by providing timely and accurate real-time information about traffic signs and can pave the way for further research into autonomous driving.

We consider unmanned aerial vehicle (UAV)-enabled wireless systems where downlink communications between a multi-antenna UAV and multiple users are assisted by a hybrid active-passive reconfigurable intelligent surface (RIS). We aim at a fairness design of two typical UAV-enabled networks, namely the static-UAV network where the UAV is deployed at a fixed location to serve all users at the same time, and the mobile-UAV network which employs the time division multiple access protocol. In both networks, our goal is to maximize the minimum rate among users through jointly optimizing the UAV's location/trajectory, transmit beamformer, and RIS coefficients. The resulting problems are highly nonconvex due to a strong coupling between the involved variables. We develop efficient algorithms based on block coordinate ascend and successive convex approximation to effectively solve these problems in an iterative manner. In particular, in the optimization of the mobile-UAV network, closed-form solutions to the transmit beamformer and RIS passive coefficients are derived. Numerical results show that a hybrid RIS equipped with only 4 active elements and a power budget of 0 dBm offers an improvement of 38%-63% in minimum rate, while that achieved by a passive RIS is only about 15%, with the same total number of elements., Comment: This paper has been submitted to IEEE Transaction on Wireless Communications

Power system dynamics are generally modeled by high dimensional nonlinear differential-algebraic equations (DAEs) given a large number of components forming the network. These DAEs' complexity can grow exponentially due to the increasing penetration of distributed energy resources, whereas their computation time becomes sensitive due to the increasing interconnection of the power grid with other energy systems. This paper demonstrates the use of quantum computing algorithms to solve DAEs for power system dynamic analysis. We leverage a symbolic programming framework to equivalently convert the power system's DAEs into ordinary differential equations (ODEs) using index reduction methods and then encode their data into qubits using amplitude encoding. The system nonlinearity is captured by Hamiltonian simulation with truncated Taylor expansion so that state variables can be updated by a quantum linear equation solver. Our results show that quantum computing can solve the power system's DAEs accurately with a computational complexity polynomial in the logarithm of the system dimension. We also illustrate the use of recent advanced tools in scientific machine learning for implementing complex computing concepts, i.e. Taylor expansion, DAEs/ODEs transformation, and quantum computing solver with abstract representation for power engineering applications., Comment: 10 pages, 17 figures, Journal

Machine learning model weights and activations are represented in full-precision during training. This leads to performance degradation in runtime when deployed on neural network accelerator (NNA) chips, which leverage highly parallelized fixed-point arithmetic to improve runtime memory and latency. In this work, we replicate the NNA operators during the training phase, accounting for the degradation due to low-precision inference on the NNA in back-propagation. Our proposed method efficiently emulates NNA operations, thus foregoing the need to transfer quantization error-prone data to the Central Processing Unit (CPU), ultimately reducing the user perceived latency (UPL). We apply our approach to Recurrent Neural Network-Transducer (RNN-T), an attractive architecture for on-device streaming speech recognition tasks. We train and evaluate models on 270K hours of English data and show a 5-7% improvement in engine latency while saving up to 10% relative degradation in WER., Comment: Accepted to SLT 2022

Influence functions (IFs) are a powerful tool for detecting anomalous examples in large scale datasets. However, they are unstable when applied to deep networks. In this paper, we provide an explanation for the instability of IFs and develop a solution to this problem. We show that IFs are unreliable when the two data points belong to two different classes. Our solution leverages class information to improve the stability of IFs. Extensive experiments show that our modification significantly improves the performance and stability of IFs while incurring no additional computational cost., Comment: Thang Nguyen-Duc, Hoang Thanh-Tung, and Quan Hung Tran are co-first authors of this paper. 12 pages, 12 figures. Accepted to ACL 2023

We conducted a prospective study to measure the clinical impact of an explainable machine learning system on interobserver agreement in chest radiograph interpretation. The AI system, which we call as it VinDr-CXR when used as a diagnosis-supporting tool, significantly improved the agreement between six radiologists with an increase of 1.5% in mean Fleiss' Kappa. In addition, we also observed that, after the radiologists consulted AI's suggestions, the agreement between each radiologist and the system was remarkably increased by 3.3% in mean Cohen's Kappa. This work has been accepted for publication in IEEE Access and this paper is our short version submitted to the Midwest Machine Learning Symposium (MMLS 2023), Chicago, IL, USA., Comment: This work has been accepted for publication in IEEE Access. This is a short version submitted to the Midwest Machine Learning Symposium (MMLS 2023), Chicago, IL, USA

The trajectory planning problem for a swarm of multiple UAVs is known as a challenging nonconvex optimization problem, particularly due to a large number of collision avoidance constraints required for individual pairs of UAVs in the swarm. In this paper, we tackle this nonconvexity by leveraging the difference of convex function (DC) programming. We introduce the slack variables to relax and reformulate the collision avoidance conditions and employ the penalty function term to equivalently convert the problem into a DC form. Consequently, we construct a penalty DC algorithm in which we sequentially solve a set of convex optimization problems obtained by linearizing the collision avoidance constraint. The algorithm iteratively tightens the safety condition and reduces the objective cost of the planning problem and the additional penalty term. Numerical results demonstrate the effectiveness of the proposed approach in planning a large number of UAVs in congested space., Comment: This paper has been accepted for presentation at the 62nd IEEE Conference on Decision and Control (CDC 2023)

Given the high power density low discharge rate and decreasing cost rechargeable lithium-ion batteries LiBs have found a wide range of applications such as power grid level storage systems electric vehicles and mobile devices. Developing a framework to accurately model the nonlinear degradation process of LiBs which is indeed a supervised learning problem becomes an important research topic. This paper presents a classical-quantum hybrid machine learning approach to capture the LiB degradation model that assesses battery cell life loss from operating profiles. Our work is motivated by recent advances in quantum computers as well as the similarity between neural networks and quantum circuits. Similar to adjusting weight parameters in conventional neural networks the parameters of the quantum circuit namely the qubits degree of freedom can be tuned to learn a nonlinear function in a supervised learning fashion. As a proof of concept paper our obtained numerical results with the battery dataset provided by NASA demonstrate the ability of the quantum neural networks in modeling the nonlinear relationship between the degraded capacity and the operating cycles. We also discuss the potential advantage of the quantum approach compared to conventional neural networks in classical computers in dealing with massive data especially in the context of future penetration of EVs and energy storage., Comment: Accepted for 2023 IEEE Green Technology Conference, Denver, Colorado, USA

Wireless jamming attacks have plagued wireless communication systems and will continue to do so going forward with technological advances. These attacks fall under the category of Electronic Warfare (EW), a continuously growing area in both attack and defense of the electromagnetic spectrum, with one subcategory being electronic attacks. Jamming attacks fall under this specific subcategory of EW as they comprise adversarial signals that attempt to disrupt, deny, degrade, destroy, or deceive legitimate signals in the electromagnetic spectrum. While jamming is not going away, recent research advances have started to get the upper hand against these attacks by leveraging new methods and techniques, such as machine learning. However, testing such jamming solutions on a wide and realistic scale is a daunting task due to strict regulations on spectrum emissions. In this paper, we introduce eSWORD, the first large-scale framework that allows users to safely conduct real-time and controlled jamming experiments with hardware-in-the-loop. This is done by integrating eSWORD into the Colosseum wireless network emulator that enables large-scale experiments with up to 50 software-defined radio nodes. We compare the performance of eSWORD with that of real-world jamming systems by using an over-the-air wireless testbed (ensuring safe measures were taken when conducting experiments). Our experimental results demonstrate that eSWORD follows similar patterns in throughput, signal-to-noise ratio, and link status to real-world jamming experiments, testifying to the high accuracy of the emulated eSWORD setup., Comment: 6 pages, 7 figures, 1 table. IEEE Wireless Communications and Networking Conference (WCNC), Glasgow, Scotland, March 2023

During the COVID-19 pandemic, the U.S. power sector witnessed remarkable electricity demand changes in many geographical regions. these changes were evident in population-dense cities. This paper incorporates a techno-economic analysis of energy storage systems to investigate the pandemic's influence on ESS development, In particular, we employ a linear program-based revenue maximization model to capture the revenues of ESS from participating in the electricity market, by performing arbitrage on energy trading, and regulation market, by providing regulation services to stabilize the grid's frequency. We consider five dominant energy storage technologies in the U.S., namely, Lithium-ion, Advanced Lead Acid, Flywheel, Vanadium Redox Flow, and Lithium-Iron Phosphate storage technologies. Extensive numerical results conducted on the case of New York City allow us to highlight the negative impact that COVID-19 had on the NYC power sector.

Inverse medium scattering solvers generally reconstruct a single solution without an associated measure of uncertainty. This is true both for the classical iterative solvers and for the emerging deep learning methods. But ill-posedness and noise can make this single estimate inaccurate or misleading. While deep networks such as conditional normalizing flows can be used to sample posteriors in inverse problems, they often yield low-quality samples and uncertainty estimates. In this paper, we propose U-Flow, a Bayesian U-Net based on conditional normalizing flows, which generates high-quality posterior samples and estimates physically-meaningful uncertainty. We show that the proposed model significantly outperforms the recent normalizing flows in terms of posterior sample quality while having comparable performance with the U-Net in point estimation., Comment: 5 pages, 5 figures

For on-device automatic speech recognition (ASR), quantization aware training (QAT) is ubiquitous to achieve the trade-off between model predictive performance and efficiency. Among existing QAT methods, one major drawback is that the quantization centroids have to be predetermined and fixed. To overcome this limitation, we introduce a regularization-free, "soft-to-hard" compression mechanism with self-adjustable centroids in a mu-Law constrained space, resulting in a simpler yet more versatile quantization scheme, called General Quantizer (GQ). We apply GQ to ASR tasks using Recurrent Neural Network Transducer (RNN-T) and Conformer architectures on both LibriSpeech and de-identified far-field datasets. Without accuracy degradation, GQ can compress both RNN-T and Conformer into sub-8-bit, and for some RNN-T layers, to 1-bit for fast and accurate inference. We observe a 30.73% memory footprint saving and 31.75% user-perceived latency reduction compared to 8-bit QAT via physical device benchmarking., Comment: Accepted for publication at IEEE SLT'22

The pricing of housing properties is determined by a variety of factors. However, post-pandemic markets have experienced volatility in the Chicago suburb area, which have affected house prices greatly. In this study, analysis was done on the Naperville/Bolingbrook real estate market to predict property prices based on these housing attributes through machine learning models, and to evaluate the effectiveness of such models in a volatile market space. Gathering data from Redfin, a real estate website, sales data from 2018 up until the summer season of 2022 were collected for research. By analyzing these sales in this range of time, we can also look at the state of the housing market and identify trends in price. For modeling the data, the models used were linear regression, support vector regression, decision tree regression, random forest regression, and XGBoost regression. To analyze results, comparison was made on the MAE, RMSE, and R-squared values for each model. It was found that the XGBoost model performs the best in predicting house prices despite the additional volatility sponsored by post-pandemic conditions. After modeling, Shapley Values (SHAP) were used to evaluate the weights of the variables in constructing models.

We introduce MTet, the largest publicly available parallel corpus for English-Vietnamese translation. MTet consists of 4.2M high-quality training sentence pairs and a multi-domain test set refined by the Vietnamese research community. Combining with previous works on English-Vietnamese translation, we grow the existing parallel dataset to 6.2M sentence pairs. We also release the first pretrained model EnViT5 for English and Vietnamese languages. Combining both resources, our model significantly outperforms previous state-of-the-art results by up to 2 points in translation BLEU score, while being 1.6 times smaller.

This paper aims to implement and evaluate the performance of quantum computing on solving combinatorial optimization problems arising from the operations of the power grid. To this end, we construct a novel mixed integer conic programming formulation for the reconfiguration of radial distribution network in response to faults in distribution lines. Comparing to existing bus injection model in the literature, our formulation based the branch flows model is theoretically equivalent without needing non-explainable variables, thus being more numerically stable. The network reconfiguration model is then used as a benchmark to evaluate the performance of quantum computing algorithms in real quantum computers. It shows that while current quantum computing algorithms with fast execution time in quantum computers can be a promising solution candidate, its heuristic nature stem from its theoretical foundation should be considered carefully when applying into power grid optimization problems., Comment: Accepted for presentation at the 54th North American Power Symposium (NAPS 2022)

Recent artificial intelligence (AI) algorithms have achieved radiologist-level performance on various medical classification tasks. However, only a few studies addressed the localization of abnormal findings from CXR scans, which is essential in explaining the image-level classification to radiologists. We introduce in this paper an explainable deep learning system called VinDr-CXR that can classify a CXR scan into multiple thoracic diseases and, at the same time, localize most types of critical findings on the image. VinDr-CXR was trained on 51,485 CXR scans with radiologist-provided bounding box annotations. It demonstrated a comparable performance to experienced radiologists in classifying 6 common thoracic diseases on a retrospective validation set of 3,000 CXR scans, with a mean area under the receiver operating characteristic curve (AUROC) of 0.967 (95% confidence interval [CI]: 0.958-0.975). The VinDr-CXR was also externally validated in independent patient cohorts and showed its robustness. For the localization task with 14 types of lesions, our free-response receiver operating characteristic (FROC) analysis showed that the VinDr-CXR achieved a sensitivity of 80.2% at the rate of 1.0 false-positive lesion identified per scan. A prospective study was also conducted to measure the clinical impact of the VinDr-CXR in assisting six experienced radiologists. The results indicated that the proposed system, when used as a diagnosis supporting tool, significantly improved the agreement between radiologists themselves with an increase of 1.5% in mean Fleiss' Kappa. We also observed that, after the radiologists consulted VinDr-CXR's suggestions, the agreement between each of them and the system was remarkably increased by 3.3% in mean Cohen's Kappa.

The rapid development in representation learning techniques such as deep neural networks and the availability of large-scale, well-annotated medical imaging datasets have to a rapid increase in the use of supervised machine learning in the 3D medical image analysis and diagnosis. In particular, deep convolutional neural networks (D-CNNs) have been key players and were adopted by the medical imaging community to assist clinicians and medical experts in disease diagnosis and treatment. However, training and inferencing deep neural networks such as D-CNN on high-resolution 3D volumes of Computed Tomography (CT) scans for diagnostic tasks pose formidable computational challenges. This challenge raises the need of developing deep learning-based approaches that are robust in learning representations in 2D images, instead 3D scans. In this work, we propose for the first time a new strategy to train \emph{slice-level} classifiers on CT scans based on the descriptors of the adjacent slices along the axis. In particular, each of which is extracted through a convolutional neural network (CNN). This method is applicable to CT datasets with per-slice labels such as the RSNA Intracranial Hemorrhage (ICH) dataset, which aims to predict the presence of ICH and classify it into 5 different sub-types. We obtain a single model in the top 4% best-performing solutions of the RSNA ICH challenge, where model ensembles are allowed. Experiments also show that the proposed method significantly outperforms the baseline model on CQ500. The proposed method is general and can be applied to other 3D medical diagnosis tasks such as MRI imaging. To encourage new advances in the field, we will make our codes and pre-trained model available upon acceptance of the paper., Comment: Accepted for presentation at the 22nd IEEE Statistical Signal Processing (SSP) workshop

This study investigates the integration of an intelligent reflecting surface (IRS) into an unmanned aerial vehicle (UAV) platform to utilize the advantages of these leading technologies for sixth-generation communications, e.g., improved spectral and energy efficiency, extended network coverage, and flexible deployment. In particular, we investigate a downlink IRS-UAV system, wherein single-antenna ground users (UEs) are served by a multi-antenna base station (BS). To assist the communication between UEs and the BS, an IRS mounted on a UAV is deployed, in which the direct links are obstructed owing to the complex urban channel characteristics. The beamforming at the BS, phase shift at the IRS, and the 3D placement of the UAV are jointly optimized to maximize the sum rate. Because the optimization variables, particularly the beamforming and IRS phase shift, are highly coupled with each other, the optimization problem is naturally non-convex. To effectively solve the formulated problem, we propose an iterative algorithm that employs block coordinate descent and inner approximation methods. Numerical results demonstrate the effectiveness of our proposed approach for a UAV-mounted IRS system on the sum rate performance over the state-of-the-art technology using the terrestrial counterpart.

We present a novel sub-8-bit quantization-aware training (S8BQAT) scheme for 8-bit neural network accelerators. Our method is inspired from Lloyd-Max compression theory with practical adaptations for a feasible computational overhead during training. With the quantization centroids derived from a 32-bit baseline, we augment training loss with a Multi-Regional Absolute Cosine (MRACos) regularizer that aggregates weights towards their nearest centroid, effectively acting as a pseudo compressor. Additionally, a periodically invoked hard compressor is introduced to improve the convergence rate by emulating runtime model weight quantization. We apply S8BQAT on speech recognition tasks using Recurrent Neural NetworkTransducer (RNN-T) architecture. With S8BQAT, we are able to increase the model parameter size to reduce the word error rate by 4-16% relatively, while still improving latency by 5%., Comment: Accepted for publication in INTERSPEECH 2022