المؤلفون: Jia, Xiaogang, Wang, Qian, Donat, Atalay, Xing, Bowen, Li, Ge, Zhou, Hongyi, Celik, Onur, Blessing, Denis, Lioutikov, Rudolf, Neumann, Gerhard

مصطلحات موضوعية: Computer Science - Machine Learning, Computer Science - Robotics

الوصف: This work introduces Mamba Imitation Learning (MaIL), a novel imitation learning (IL) architecture that offers a computationally efficient alternative to state-of-the-art (SoTA) Transformer policies. Transformer-based policies have achieved remarkable results due to their ability in handling human-recorded data with inherently non-Markovian behavior. However, their high performance comes with the drawback of large models that complicate effective training. While state space models (SSMs) have been known for their efficiency, they were not able to match the performance of Transformers. Mamba significantly improves the performance of SSMs and rivals against Transformers, positioning it as an appealing alternative for IL policies. MaIL leverages Mamba as a backbone and introduces a formalism that allows using Mamba in the encoder-decoder structure. This formalism makes it a versatile architecture that can be used as a standalone policy or as part of a more advanced architecture, such as a diffuser in the diffusion process. Extensive evaluations on the LIBERO IL benchmark and three real robot experiments show that MaIL: i) outperforms Transformers in all LIBERO tasks, ii) achieves good performance even with small datasets, iii) is able to effectively process multi-modal sensory inputs, iv) is more robust to input noise compared to Transformers.

الوصول الحر: http://arxiv.org/abs/2406.08234Test

المؤلفون: Zhong, Zhusi, Zhang, Helen, Fayad, Fayez H., Lancaster, Andrew C., Sollee, John, Kulkarni, Shreyas, Lin, Cheng Ting, Li, Jie, Gao, Xinbo, Collins, Scott, Greineder, Colin, Ahn, Sun H., Bai, Harrison X., Jiao, Zhicheng, Atalay, Michael K.

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition

الوصف: Purpose: Pulmonary embolism (PE) is a significant cause of mortality in the United States. The objective of this study is to implement deep learning (DL) models using Computed Tomography Pulmonary Angiography (CTPA), clinical data, and PE Severity Index (PESI) scores to predict PE mortality. Materials and Methods: 918 patients (median age 64 years, range 13-99 years, 52% female) with 3,978 CTPAs were identified via retrospective review across three institutions. To predict survival, an AI model was used to extract disease-related imaging features from CTPAs. Imaging features and/or clinical variables were then incorporated into DL models to predict survival outcomes. Four models were developed as follows: (1) using CTPA imaging features only; (2) using clinical variables only; (3) multimodal, integrating both CTPA and clinical variables; and (4) multimodal fused with calculated PESI score. Performance and contribution from each modality were evaluated using concordance index (c-index) and Net Reclassification Improvement, respectively. Performance was compared to PESI predictions using the Wilcoxon signed-rank test. Kaplan-Meier analysis was performed to stratify patients into high- and low-risk groups. Additional factor-risk analysis was conducted to account for right ventricular (RV) dysfunction. Results: For both data sets, the PESI-fused and multimodal models achieved higher c-indices than PESI alone. Following stratification of patients into high- and low-risk groups by multimodal and PESI-fused models, mortality outcomes differed significantly (both p<0.001). A strong correlation was found between high-risk grouping and RV dysfunction. Conclusions: Multiomic DL models incorporating CTPA features, clinical data, and PESI achieved higher c-indices than PESI alone for PE survival prediction.

الوصول الحر: http://arxiv.org/abs/2406.01302Test

المؤلفون: Zhong, Zhusi, Li, Jie, Sollee, John, Collins, Scott, Bai, Harrison, Zhang, Paul, Healey, Terrence, Atalay, Michael, Gao, Xinbo, Jiao, Zhicheng

مصطلحات موضوعية: Electrical Engineering and Systems Science - Image and Video Processing, Computer Science - Computer Vision and Pattern Recognition

الوصف: In response to the worldwide COVID-19 pandemic, advanced automated technologies have emerged as valuable tools to aid healthcare professionals in managing an increased workload by improving radiology report generation and prognostic analysis. This study proposes Multi-modality Regional Alignment Network (MRANet), an explainable model for radiology report generation and survival prediction that focuses on high-risk regions. By learning spatial correlation in the detector, MRANet visually grounds region-specific descriptions, providing robust anatomical regions with a completion strategy. The visual features of each region are embedded using a novel survival attention mechanism, offering spatially and risk-aware features for sentence encoding while maintaining global coherence across tasks. A cross LLMs alignment is employed to enhance the image-to-text transfer process, resulting in sentences rich with clinical detail and improved explainability for radiologist. Multi-center experiments validate both MRANet's overall performance and each module's composition within the model, encouraging further advancements in radiology report generation research emphasizing clinical interpretation and trustworthiness in AI models applied to medical studies. The code is available at https://github.com/zzs95/MRANetTest.

الوصول الحر: http://arxiv.org/abs/2405.14113Test

المؤلفون: Zhong, Zhusi, Li, Jie, Ma, Zhuoqi, Collins, Scott, Bai, Harrison, Zhang, Paul, Healey, Terrance, Gao, Xinbo, Atalay, Michael K., Jiao, Zhicheng

مصطلحات موضوعية: Computer Science - Computer Vision and Pattern Recognition, Computer Science - Artificial Intelligence

الوصف: The COVID-19 pandemic has strained global public health, necessitating accurate diagnosis and intervention to control disease spread and reduce mortality rates. This paper introduces an interpretable deep survival prediction model designed specifically for improved understanding and trust in COVID-19 prognosis using chest X-ray (CXR) images. By integrating a large-scale pretrained image encoder, Risk-specific Grad-CAM, and anatomical region detection techniques, our approach produces regional interpretable outcomes that effectively capture essential disease features while focusing on rare but critical abnormal regions. Our model's predictive results provide enhanced clarity and transparency through risk area localization, enabling clinicians to make informed decisions regarding COVID-19 diagnosis with better understanding of prognostic insights. We evaluate the proposed method on a multi-center survival dataset and demonstrate its effectiveness via quantitative and qualitative assessments, achieving superior C-indexes (0.764 and 0.727) and time-dependent AUCs (0.799 and 0.691). These results suggest that our explainable deep survival prediction model surpasses traditional survival analysis methods in risk prediction, improving interpretability for clinical decision making and enhancing AI system trustworthiness.

الوصول الحر: http://arxiv.org/abs/2405.02815Test

المؤلفون: Sharma, Pragya, Atalay, Tolga, Gibbs, Hans-Andrew, Stojadinovic, Dragoslav, Stavrou, Angelos, Wang, Haining

مصطلحات موضوعية: Computer Science - Networking and Internet Architecture

الوصف: 5G mobile networks leverage Network Function Virtualization (NFV) to offer services in the form of network slices. Each network slice is a logically isolated fragment constructed by service chaining a set of Virtual Network Functions (VNFs). The Network Repository Function (NRF) acts as a central OpenAuthorization (OAuth) 2.0 server to secure inter-VNF communications resulting in a single point of failure. Thus, we propose 5G-WAVE, a decentralized authorization framework for the 5G core by leveraging the WAVE framework and integrating it into the OpenAirInterface (OAI) 5G core. Our design relies on Side-Car Proxies (SCPs) deployed alongside individual VNFs, allowing point-to-point authorization. Each SCP acts as a WAVE engine to create entities and attestations and verify incoming service requests. We measure the authorization latency overhead for VNF registration, 5G Authentication and Key Agreement (AKA), and data session setup and observe that WAVE verification introduces 155ms overhead to HTTP transactions for decentralizing authorization. Additionally, we evaluate the scalability of 5G-WAVE by instantiating more network slices to observe 1.4x increase in latency with 10x growth in network size. We also discuss how 5G-WAVE can significantly reduce the 5G attack surface without using OAuth 2.0 while addressing several key issues of 5G standardization.

الوصول الحر: http://arxiv.org/abs/2404.13242Test

المؤلفون: Jia, Xiaogang, Blessing, Denis, Jiang, Xinkai, Reuss, Moritz, Donat, Atalay, Lioutikov, Rudolf, Neumann, Gerhard

مصطلحات موضوعية: Computer Science - Robotics

الوصف: Imitation learning with human data has demonstrated remarkable success in teaching robots in a wide range of skills. However, the inherent diversity in human behavior leads to the emergence of multi-modal data distributions, thereby presenting a formidable challenge for existing imitation learning algorithms. Quantifying a model's capacity to capture and replicate this diversity effectively is still an open problem. In this work, we introduce simulation benchmark environments and the corresponding Datasets with Diverse human Demonstrations for Imitation Learning (D3IL), designed explicitly to evaluate a model's ability to learn multi-modal behavior. Our environments are designed to involve multiple sub-tasks that need to be solved, consider manipulation of multiple objects which increases the diversity of the behavior and can only be solved by policies that rely on closed loop sensory feedback. Other available datasets are missing at least one of these challenging properties. To address the challenge of diversity quantification, we introduce tractable metrics that provide valuable insights into a model's ability to acquire and reproduce diverse behaviors. These metrics offer a practical means to assess the robustness and versatility of imitation learning algorithms. Furthermore, we conduct a thorough evaluation of state-of-the-art methods on the proposed task suite. This evaluation serves as a benchmark for assessing their capability to learn diverse behaviors. Our findings shed light on the effectiveness of these methods in tackling the intricate problem of capturing and generalizing multi-modal human behaviors, offering a valuable reference for the design of future imitation learning algorithms.

الوصول الحر: http://arxiv.org/abs/2402.14606Test

المؤلفون: Atalay Biresaw (ORCID 0000-0003-1210-4416), Berhanu Bogale

المصدر: Education and Information Technologies. 2024 29(4):4745-4761.

تمت مراجعته من قبل الزملاء: Y

Page Count: 17

الواصفات: Web Based Instruction, Feedback (Response), Reading Skills, Skill Development, Pretests Posttests, Reading Comprehension, Reading Tests, Electronic Learning, Technology Uses in Education, Educational Technology, Evaluation

مستخلص: When students are provided with detailed and immediate feedback on their performance in an online test, they may get some pedagogical benefits from the exercise. This study examined the effects of elaborative feedback on students' reading comprehension skills: inference, reading for gist, and detail reading. The study followed a pre-test post-test quasi-experimental design in which a total of 43 students were involved. The students took a paper-based reading comprehension test before the training was given to measure their current performance. The Moodle Cloud learning management system was used to train the participants of the study. The training was given twice a week for two months. Data were analyzed using mean, paired samples t-test, Cohen's d and NVIVO software. It was found that there was a statistically significant difference for inference questions before and after the intervention of web based feedback (t = -10.85, sig. = 0.000 and Cohen's d = 1.63). Similarly, the mean difference for detail reading questions was statistically significant before and after the use of online elaborative feedback (t = -7.340, sig. = 0.000 and Cohen's d = 1.11). The mean difference of the main idea questions was also statistically significant (t = -6.443, sig. = 0.000, and Cohen's d = 0.98). The findings clearly show that students' reading comprehension sub-skills improved after the treatment of the online elaborative feedback provided to the students. The effect size test conducted using Cohen's d also indicated that the improvements students made in all the sub-skills tested were quite substantial. Thus, as online elaborative feedback has a considerable contribution to improving students' reading comprehension skills, instructors are encouraged to facilitate situations for online elaborative feedback for their students.

Abstractor: As Provided

المؤلفون: Yenin, Kemal Erdem, Sayin, Reha Oguz, Arar, Kuzey, Atalay, Kadir Kaan, Stroppa, Fabio

مصطلحات موضوعية: Computer Science - Neural and Evolutionary Computing, Computer Science - Artificial Intelligence

الوصف: Multi-modal optimization is often encountered in engineering problems, especially when different and alternative solutions are sought. Evolutionary algorithms can efficiently tackle multi-modal optimization thanks to their features such as the concept of population, exploration/exploitation, and being suitable for parallel computation. This paper introduces a multi-modal optimization version of the Big Bang-Big Crunch algorithm based on clustering, namely, k-BBBC. This algorithm guarantees a complete convergence of the entire population, retrieving on average the 99\% of local optima for a specific problem. Additionally, we introduce two post-processing methods to (i) identify the local optima in a set of retrieved solutions (i.e., a population), and (ii) quantify the number of correctly retrieved optima against the expected ones (i.e., success rate). Our results show that k-BBBC performs well even with problems having a large number of optima (tested on 379 optima) and high dimensionality (tested on 32 decision variables). When compared to other multi-modal optimization methods, it outperforms them in terms of accuracy (in both search and objective space) and success rate (number of correctly retrieved optima) -- especially when elitism is applied. Lastly, we validated our proposed post-processing methods by comparing their success rate to the actual one. Results suggest that these methods can be used to evaluate the performance of a multi-modal optimization algorithm by correctly identifying optima and providing an indication of success -- without the need to know where the optima are located in the search space.
Comment: 17 pages, 7 figures

الوصول الحر: http://arxiv.org/abs/2401.06153Test

المؤلفون: Atalay, Tolga O., Stojadinovic, Dragoslav, Famili, Alireza, Stavrou, Angelos, Wang, Haining

مصطلحات موضوعية: Computer Science - Networking and Internet Architecture

الوصف: The Fifth Generation (5G) mobile core network is designed as a set of Virtual Network Functions (VNFs) hosted on Commercial-Off-the-Shelf (COTS) hardware. This creates a growing demand for general-purpose compute resources as 5G deployments continue to expand. Given their elastic infrastructure, cloud services such as Amazon Web Services (AWS) are attractive platforms to address this need. Therefore, it is crucial to understand the control and user plane Quality of Service (QoS) performance associated with deploying the 5G core on top of a public cloud. To account for both software and communication costs, we build a 5G testbed using open-source components spanning multiple locations within AWS. We present an operational breakdown of the performance overhead for various 5G use cases using different core deployment strategies. Our results indicate that moving specific VNFs into edge regions reduces the latency overhead for key 5G operations. Furthermore, we instantiated multiple user plane connections between availability zones and edge regions with different traffic loads. We observed that the deterioration of connection quality varies depending on traffic loads and is use case specific. Ultimately, our findings provide new insights for Mobile Virtual Network Operators (MVNOs) for optimal placements of their 5G core functions.

الوصول الحر: http://arxiv.org/abs/2312.04833Test

المؤلفون: Atalay, Sina, Schnaubelt, Erik, Wozniak, Mariusz, Dular, Julien, Zachou, Georgia, Schöps, Sebastian, Verweij, Arjan

المصدر: Superconductor Science and Technology, Volume 37, Number 6, June 2024

مصطلحات موضوعية: Condensed Matter - Superconductivity

الوصف: A new module, Pancake3D, of the open-source Finite Element Quench Simulator (FiQuS) has been developed in order to perform transient simulations of no-insulation (NI) high-temperature superconducting (HTS) pancake coils in 3-dimensions. FiQuS/Pancake3D can perform magnetodynamic or coupled magneto-thermal simulations. Thanks to the use of thin shell approximations, an $\vec{H}-\phi$ formulation, and anisotropic homogenization techniques, each turn can be resolved on the mesh level in an efficient and robust manner. FiQuS/Pancake3D relies on pre-formulated finite-element (FE) formulations and numerical approaches that are programmatically adjusted based on a text input file. In this paper, the functionalities and capabilities of FiQuS/Pancake3D are presented. The challenges of FE simulation of NI coils and how FiQuS/Pancake3D addresses them are explained. To highlight the functionalities, the results of a magneto-thermal analysis of a double pancake coil with 40 turns per pancake with local degradation of the critical current density are conducted and discussed. Furthermore, a parameter sweep of the size of this local degradation is presented. All the FiQuS input files for reproducing the simulations are provided.
Comment: This work has been submitted to the Superconductor Science and Technology for possible publication

الوصول الحر: http://arxiv.org/abs/2311.09177Test