Search

In the realm of computer vision, the integration of advanced techniques into the processing of RGB-D camera inputs poses a significant challenge, given the inherent complexities arising from diverse environmental conditions and varying object appearances. Therefore, this paper introduces FusionVision, an exhaustive pipeline adapted for the robust 3D segmentation of objects in RGB-D imagery. Traditional computer vision systems face limitations in simultaneously capturing precise object boundaries and achieving high-precision object detection on depth map as they are mainly proposed for RGB cameras. To address this challenge, FusionVision adopts an integrated approach by merging state-of-the-art object detection techniques, with advanced instance segmentation methods. The integration of these components enables a holistic (unified analysis of information obtained from both color \textit{RGB} and depth \textit{D} channels) interpretation of RGB-D data, facilitating the extraction of comprehensive and accurate object information. The proposed FusionVision pipeline employs YOLO for identifying objects within the RGB image domain. Subsequently, FastSAM, an innovative semantic segmentation model, is applied to delineate object boundaries, yielding refined segmentation masks. The synergy between these components and their integration into 3D scene understanding ensures a cohesive fusion of object detection and segmentation, enhancing overall precision in 3D object segmentation. The code and pre-trained models are publicly available at https://github.com/safouaneelg/FusionVision/., Comment: 14 pages, 9 figures, 1 table

The impact of using artificial intelligence (AI) to guide patient care or operational processes is an interplay of the AI model's output, the decision-making protocol based on that output, and the capacity of the stakeholders involved to take the necessary subsequent action. Estimating the effects of this interplay before deployment, and studying it in real time afterwards, are essential to bridge the chasm between AI model development and achievable benefit. To accomplish this, the Data Science team at Stanford Health Care has developed a Testing and Evaluation (T&E) mechanism to identify fair, useful and reliable AI models (FURM) by conducting an ethical review to identify potential value mismatches, simulations to estimate usefulness, financial projections to assess sustainability, as well as analyses to determine IT feasibility, design a deployment strategy, and recommend a prospective monitoring and evaluation plan. We report on FURM assessments done to evaluate six AI guided solutions for potential adoption, spanning clinical and operational settings, each with the potential to impact from several dozen to tens of thousands of patients each year. We describe the assessment process, summarize the six assessments, and share our framework to enable others to conduct similar assessments. Of the six solutions we assessed, two have moved into a planning and implementation phase. Our novel contributions - usefulness estimates by simulation, financial projections to quantify sustainability, and a process to do ethical assessments - as well as their underlying methods and open source tools, are available for other healthcare systems to conduct actionable evaluations of candidate AI solutions.

Recently, there has been a growing interest in utilizing machine learning for accurate classification of power quality events (PQEs). However, most of these studies are performed assuming an ideal situation, while in reality, we can have measurement noise, DC offset, and variations in the voltage signal's amplitude and frequency. Building on the prior PQE classification works using deep learning, this paper proposes a deep-learning framework that leverages attention-enabled Transformers as a tool to accurately classify PQEs under the aforementioned considerations. The proposed framework can operate directly on the voltage signals with no need for a separate feature extraction or calculation phase. Our results show that the proposed framework outperforms recently proposed learning-based techniques. It can accurately classify PQEs under the aforementioned conditions with an accuracy varying between 99.81%$-$91.43% depending on the signal-to-noise ratio, DC offsets, and variations in the signal amplitude and frequency., Comment: Accepted in the IEEE Power and Energy Society General Meeting, 2024

The study investigated the impact of healthcare system efficiency on the delivery of maternal, newborn, and child services in Africa. Data Envelopment Analysis and Tobit regression were employed to assess the efficiency of 46 healthcare systems across the continent, utilizing the Variable Returns to Scale model with Input orientation to evaluate technical efficiency. The Tobit method was utilized to explore factors contributing to inefficiency, with inputs variables including hospital, physician, and paramedical staff, and outputs variables encompassing maternal, newborn, and child admissions, cesarean interventions, functional competency, and hospitalization days. Results revealed that only 26% of countries exhibited efficiency, highlighting a significant proportion of 74% with inefficiencies. Financial determinants such as current health expenditures, comprehensive coverage index, and current health expenditure per capita were found to have a negative impact on the efficiency of maternal-child services. These findings underscore a marginal deficiency in technical efficiency within Africa's healthcare systems, emphasizing the necessity for policymakers to reassess the roles of both human resources and financial dimensions in enhancing healthcare system performance.

Background: The public hospital network in Morocco plays a crucial role in providing healthcare services. However, this network faces challenges in terms of technical efficiency in healthcare management. Objectives: This study aimed to assess the technical efficiency of the public hospital network in Morocco. Methods: This article compares the efficiency of 77 public hospital networks from 2017 to 2020. Data were collected from the Directorate of Planning and Financial Resources (DPFR) of the Health Ministry Marocco. The Data Envelopment Analysis (DEA) method was employed, using three inputs (Hospital, Physician and Paramedical) and four outputs (Functional capacity, Hospitalization days and Admission). Additionally, the Malmquist index (MI) is utilized to analyse the factors of production, and peer modelling is incorporated to address hospital inefficiency. Results: The average technical efficiency of public hospital networks under the CRS hypothesis from 2017 to 2020 is 0.697 (71% of DMUs have a score lower than 1), indicating that these networks need to minimize their inputs by approximately 30.3%. The Malmquist index reveals a decline in productivity gain from 2017/2018 (score of 0.980) followed by improvement in 2018/2019 (score of 1.163). In terms of peer modelling, 72.7% of the DMUs should emulate the most effective DMUs beginning in 2020, whereas the lowest score was observed in 2019. Conclusion: These findings highlight the need for the public hospital network in Morocco to enhance the effective and efficient utilization of inputs, such as the number of hospitals and medical and paramedical staff, to produce the same outputs, including the number of surgical procedures, hospitalization days, admissions, and functional capacity.

We study the problem of selecting $k$ experiments from a larger candidate pool, where the goal is to maximize mutual information (MI) between the selected subset and the underlying parameters. Finding the exact solution is to this combinatorial optimization problem is computationally costly, not only due to the complexity of the combinatorial search but also the difficulty of evaluating MI in nonlinear/non-Gaussian settings. We propose greedy approaches based on new computationally inexpensive lower bounds for MI, constructed via log-Sobolev inequalities. We demonstrate that our method outperforms random selection strategies, Gaussian approximations, and nested Monte Carlo (NMC) estimators of MI in various settings, including optimal design for nonlinear models with non-additive noise.

The possibility of adversarial (a.k.a., {\em Byzantine}) clients makes federated learning (FL) prone to arbitrary manipulation. The natural approach to robustify FL against adversarial clients is to replace the simple averaging operation at the server in the standard $\mathsf{FedAvg}$ algorithm by a \emph{robust averaging rule}. While a significant amount of work has been devoted to studying the convergence of federated {\em robust averaging} (which we denote by $\mathsf{FedRo}$), prior work has largely ignored the impact of {\em client subsampling} and {\em local steps}, two fundamental FL characteristics. While client subsampling increases the effective fraction of Byzantine clients, local steps increase the drift between the local updates computed by honest (i.e., non-Byzantine) clients. Consequently, a careless deployment of $\mathsf{FedRo}$ could yield poor performance. We validate this observation by presenting an in-depth analysis of $\mathsf{FedRo}$ tightly analyzing the impact of client subsampling and local steps. Specifically, we present a sufficient condition on client subsampling for nearly-optimal convergence of $\mathsf{FedRo}$ (for smooth non-convex loss). Also, we show that the rate of improvement in learning accuracy {\em diminishes} with respect to the number of clients subsampled, as soon as the sample size exceeds a threshold value. Interestingly, we also observe that under a careful choice of step-sizes, the learning error due to Byzantine clients decreases with the number of local steps. We validate our theory by experiments on the FEMNIST and CIFAR-$10$ image classification tasks.

This study presents AraSpider, the first Arabic version of the Spider dataset, aimed at improving natural language processing (NLP) in the Arabic-speaking community. Four multilingual translation models were tested for their effectiveness in translating English to Arabic. Additionally, two models were assessed for their ability to generate SQL queries from Arabic text. The results showed that using back translation significantly improved the performance of both ChatGPT 3.5 and SQLCoder models, which are considered top performers on the Spider dataset. Notably, ChatGPT 3.5 demonstrated high-quality translation, while SQLCoder excelled in text-to-SQL tasks. The study underscores the importance of incorporating contextual schema and employing back translation strategies to enhance model performance in Arabic NLP tasks. Moreover, the provision of detailed methodologies for reproducibility and translation of the dataset into other languages highlights the research's commitment to promoting transparency and collaborative knowledge sharing in the field. Overall, these contributions advance NLP research, empower Arabic-speaking researchers, and enrich the global discourse on language comprehension and database interrogation., Comment: 11 pages, 4 figures

In this paper, we propose a new visual navigation method based on a single RGB perspective camera. Using the Visual Teach & Repeat (VT&R) methodology, the robot acquires a visual trajectory consisting of multiple subgoal images in the teaching step. In the repeat step, we propose two network architectures, namely ViewNet and VelocityNet. The combination of the two networks allows the robot to follow the visual trajectory. ViewNet is trained to generate a future image based on the current view and the velocity command. The generated future image is combined with the subgoal image for training VelocityNet. We develop an offline Model Predictive Control (MPC) policy within VelocityNet with the dual goals of (1) reducing the difference between current and subgoal images and (2) ensuring smooth trajectories by mitigating velocity discontinuities. Offline training conserves computational resources, making it a more suitable option for scenarios with limited computational capabilities, such as embedded systems. We validate our experiments in a simulation environment, demonstrating that our model can effectively minimize the metric error between real and played trajectories., Comment: Accepted at ROBOVIS 2024 : 4th International Conference on Robotics, Computer Vision and Intelligent Systems

We implement coherent delocalization as a tool for improving the two primary metrics of atomic clock performance: systematic uncertainty and instability. By decreasing atomic density with coherent delocalization, we suppress cold-collision shifts and two-body losses. Atom loss attributed to Landau-Zener tunneling in the ground lattice band would compromise coherent delocalization at low trap depths for our $^{171}$Yb atoms; hence, we implement for the first time delocalization in excited lattice bands. Doing so increases the spatial distribution of atoms trapped in the vertically-oriented optical lattice by $\sim7$ times. At the same time we observe a reduction of the cold-collision shift by 6.5(8) times, while also making inelastic two-body loss negligible. With these advantages, we measure the trap-light-induced quenching rate and natural lifetime of the ${}^3$P${}_0$ excited-state as $5.7(7)\times10^{-4}$ $E_r^{-1}s^{-1}$ and 19(2) s, respectively.

Discovering the creative potentials of a random signal to various artistic expressions in aesthetic and conceptual richness is a ground for the recent success of generative machine learning as a way of art creation. To understand the new artistic medium better, we conduct a comprehensive analysis to position AI-generated art within the context of human art heritage. Our comparative analysis is based on an extensive dataset, dubbed ``ArtConstellation,'' consisting of annotations about art principles, likability, and emotions for 6,000 WikiArt and 3,200 AI-generated artworks. After training various state-of-the-art generative models, art samples are produced and compared with WikiArt data on the last hidden layer of a deep-CNN trained for style classification. We actively examined the various art principles to interpret the neural representations and used them to drive the comparative knowledge about human and AI-generated art. A key finding in the semantic analysis is that AI-generated artworks are visually related to the principle concepts for modern period art made in 1800-2000. In addition, through Out-Of-Distribution (OOD) and In-Distribution (ID) detection in CLIP space, we find that AI-generated artworks are ID to human art when they depict landscapes and geometric abstract figures, while detected as OOD when the machine art consists of deformed and twisted figures. We observe that machine-generated art is uniquely characterized by incomplete and reduced figuration. Lastly, we conducted a human survey about emotional experience. Color composition and familiar subjects are the key factors of likability and emotions in art appreciation. We propose our whole methodologies and collected dataset as our analytical framework to contrast human and AI-generated art, which we refer to as ``ArtNeuralConstellation''. Code is available at: https://github.com/faixan-khan/ArtNeuralConstellation

Prescriptive AI represents a transformative shift in decision-making, offering causal insights and actionable recommendations. Despite its huge potential, enterprise adoption often faces several challenges. The first challenge is caused by the limitations of observational data for accurate causal inference which is typically a prerequisite for good decision-making. The second pertains to the interpretability of recommendations, which is crucial for enterprise decision-making settings. The third challenge is the silos between data scientists and business users, hindering effective collaboration. This paper outlines an initiative from IBM Research, aiming to address some of these challenges by offering a suite of prescriptive AI solutions. Leveraging insights from various research papers, the solution suite includes scalable causal inference methods, interpretable decision-making approaches, and the integration of large language models (LLMs) to bridge communication gaps via a conversation agent. A proof-of-concept, PresAIse, demonstrates the solutions' potential by enabling non-ML experts to interact with prescriptive AI models via a natural language interface, democratizing advanced analytics for strategic decision-making., Comment: 14 pages

Factual knowledge encoded in Pre-trained Language Models (PLMs) enriches their representations and justifies their use as knowledge bases. Previous work has focused on probing PLMs for factual knowledge by measuring how often they can correctly predict an object entity given a subject and a relation, and improving fact retrieval by optimizing the prompts used for querying PLMs. In this work, we consider a complementary aspect, namely the coherency of factual knowledge in PLMs, i.e., how often can PLMs predict the subject entity given its initial prediction of the object entity. This goes beyond evaluating how much PLMs know, and focuses on the internal state of knowledge inside them. Our results indicate that PLMs have low coherency using manually written, optimized and paraphrased prompts, but including an evidence paragraph leads to substantial improvement. This shows that PLMs fail to model inverse relations and need further enhancements to be able to handle retrieving facts from their parameters in a coherent manner, and to be considered as knowledge bases., Comment: Accepted to EACL Findings 2024

This paper presents a framework to address the challenges involved in building point cloud cleaning, plane detection, and semantic segmentation, with the ultimate goal of enhancing building modeling. We focus in the cleaning stage on removing outliers from the acquired point cloud data by employing an adaptive threshold technique based on z-score measure. Following the cleaning process, we perform plane detection using the robust RANSAC paradigm. The goal is to carry out multiple plane segmentations, and to classify segments into distinct categories, such as floors, ceilings, and walls. The resulting segments can generate accurate and detailed point clouds representing the building's architectural elements. Moreover, we address the problem of semantic segmentation, which plays a vital role in the identification and classification of different components within the building, such as walls, windows, doors, roofs, and objects. Inspired by the PointNet architecture, we propose a deep learning architecture for efficient semantic segmentation in buildings. The results demonstrate the effectiveness of the proposed framework in handling building modeling tasks, paving the way for improved accuracy and efficiency in the field of building modelization.

Data generation remains a bottleneck in training surrogate models to predict molecular properties. We demonstrate that multitask Gaussian process regression overcomes this limitation by leveraging both expensive and cheap data sources. In particular, we consider training sets constructed from coupled-cluster (CC) and density functional theory (DFT) data. We report that multitask surrogates can predict at CC-level accuracy with a reduction to data generation cost by over an order of magnitude. Of note, our approach allows the training set to include DFT data generated by a heterogeneous mix of exchange-correlation functionals without imposing any artificial hierarchy on functional accuracy. More generally, the multitask framework can accommodate a wider range of training set structures -- including full disparity between the different levels of fidelity -- than existing kernel approaches based on $\Delta$-learning, though we show that the accuracy of the two approaches can be similar. Consequently, multitask regression can be a tool for reducing data generation costs even further by opportunistically exploiting existing data sources., Comment: 21 pages, 9 figures

We study the strong Nakano property in Banach lattices with a special focus on free Banach lattices. We show that for every finite dimensional Banach space $E$, the free Banach lattice $FBL[E]$ has the strong Nakano property with a constant independent of the dimension. It is also shown that if $FBL[E]$ has the strong Nakano property, then $E$ cannot contain subspaces isomorphic to neither $c_0$ nor $L_1$., Comment: 21 pages