检索结果-内蒙古大学图书馆

Embedding with Large Language Models for Classification of HIPAA Safeguard Compliance Rules

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Rahman, Md Abdur Barek, Md Abdul Riad, A.B.M. Kamrul Islam Rahman, Md Mostafizur Rashid, Md Bajlur Ambedkar, Smita Miaa, Md Raihan Wu, Fan Cuzzocrea, Alfredo Ahamed, Sheikh Iqbal Dept. of Intelligent Systems and Robotics University of West Florida FL United States University of West Florida FL United States Department of Computer Science Tuskegee University TuskegeeAL United States IDEA Lab University of Calabria Rende Italy Department of Computer Science Marquette University WI United States

Although software developers of mHealth apps are responsible for protecting patient data and adhering to strict privacy and security requirements, many of them lack awareness of HIPAA regulations and struggle to distinguish between HIPAA rules categories. Therefore, providing guidance of HIPAA rules patterns classification is essential for developing secured applications for Google Play Store. In this work, we identified the limitations of traditional Word2Vec embeddings in processing code patterns. To address this, we adopt multilingual BERT (Bidirectional Encoder Representations from Transformers) which offers contextualized embeddings to the attributes of dataset to overcome the issues. Therefore, we applied this BERT to our dataset for embedding code patterns and then uses these embedded code to varioud machine learning approaches. Our results demonstrate that the models significantly enhances classification performance, with Logistic Regression achieving a remarkable accuracy of 99.95%. Additionally, we obtained high accuracy from Support Vector Machine (99.79%), Random Forest (99.73%), and Naive Bayes (95.93%), outperforming existing approaches. This work underscores the effectiveness and showcases its potential for secure application development. © 2024, CC BY.

关键词： Embeddings

Exploring Behaviors of Hybrid Systems via the Voronoi Bias over Output Signals

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ernst, Gidon Fejlek, Jiří Software and Computational Systems Lab Department of Computer Science Ludwig-Maximilians-Universität München Oettingenstraße 67 Munich80538 Germany The Czech Academy of Sciences Institute of Computer Science Pod Vodárenskou věží 271/2 Prague182 07 Czech Republic

In this paper, we consider an analysis of temporal properties of hybrid systems based on simulations, so-called falsification of requirements. We present a novel exploration-based algorithm for falsification of black-box models of hybrid systems based on the Voronoi bias in the output space. This approach is inspired by techniques used originally in motion planning: rapidly exploring random trees. Instead of commonly employed exploration that is based on coverage of inputs, the proposed algorithm aims to cover all possible outputs directly. Compared to other state-of-the-art falsification tools, it also does not require robustness or other guidance metrics tied to a specific behavior that is being falsified. This allows our algorithm to falsify specifications for which robustness is not conclusive enough to guide the falsification procedure. Copyright © 2024, The Authors. All rights reserved.

关键词： Decision trees

Early Stage Design of a mHealth Intervention for Managing Gestational Diabetes Mellitus in Bangladeshi Women 25th

学校读者我要写书评

暂无评论

Early Stage Design of a mHealth Intervention for Managing...

25th International Conference on Human-computer Interaction, HCII 2023

作者： Islam, Ashraful Ahmed, Eshtiak Islam, Md Rakibul EMPATHY Lab Center for Computational and Data Sciences Independent University Bangladesh Dhaka Bangladesh Department of Computer Science and Engineering Independent University Bangladesh Dhaka Bangladesh Faculty of Information Technology and Communication Sciences Tampere University Tampere Finland Computer Science Department University of Wisconsin - Eau Claire Eau ClaireWI United States

ISBN: (纸本)9783031492112

Gestational Diabetes Mellitus (GDM) is a rising concern worldwide, particularly in low-resource countries such as Bangladesh, where access to healthcare facilities is limited and awareness of GDM management is inadequate. This work proposes an early-stage design of user interfaces (UIs) for a mobile health (mHealth) intervention using the Bengali language that allows users to input daily measures of blood glucose, weight, and other GDM-related health data. The intervention is designed to provide users with personalized feedback based on their input and the necessary coaching for managing GDM. It also reminds users to take medication if prescribed by their doctors. The app has six key features: blood glucose tracking, food logging, medication reminders, activity tracking, educational resources, and personalized recommendations. Overall, this work provides a valuable contribution to the field of mHealth-based maternal and child health in Bangladesh. However, further research is necessary to evaluate the effectiveness and feasibility of the intervention in real-world scenarios. Such evaluations will provide valuable insights into its potential impact and help refine the design to better serve the needs of GDM patients in Bangladesh. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： mHealth

Socially CompliAnt Navigation Dataset (SCAND): A Large-Scale Dataset Of Demonstrations For Social Navigation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Karnan, Haresh Nair, Anirudh Xiao, Xuesu Warnell, Garrett Pirk, Sören Toshev, Alexander Hart, Justin Biswas, Joydeep Stone, Peter The University of Texas at Austin Department of Computer Science United States Robotics Google Sony AI Computational and Information Sciences Directorate Army Research Laboratory United States

Social navigation is the capability of an autonomous agent, such as a robot, to navigate in a "socially compliant" manner in the presence of other intelligent agents such as humans. With the emergence of autonomously navigating mobile robots in human-populated environments (e.g., domestic service robots in homes and restaurants and food delivery robots on public sidewalks), incorporating socially compliant navigation behaviors on these robots becomes critical to ensuring safe and comfortable human-robot coexistence. To address this challenge, imitation learning is a promising framework, since it is easier for humans to demonstrate the task of social navigation rather than to formulate reward functions that accurately capture the complex multi-objective setting of social navigation. The use of imitation learning and inverse reinforcement learning to social navigation for mobile robots, however, is currently hindered by a lack of large-scale datasets that capture socially compliant robot navigation demonstrations in the wild. To fill this gap, we introduce Socially CompliAnt Navigation Dataset (SCAND)-a large-scale, first-person-view dataset of socially compliant navigation demonstrations. Our dataset contains 8.7 hours, 138 trajectories, 25 miles of socially compliant, human tele-operated driving demonstrations that comprises multi-modal data streams including 3D lidar, joystick commands, odometry, visual and inertial information, collected on two morphologically different mobile robots-a Boston Dynamics Spot and a Clearpath Jackal-by four different human demonstrators in both indoor and outdoor environments. We additionally perform preliminary analysis and validation through real-world robot experiments and show that navigation policies learned by imitation learning on SCAND generate socially compliant behaviors. © 2022, CC BY.

关键词： Navigation

An Efficient Scene Coordinate Encoding and Relocalization Method

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Xu, Kuan Jiang, Zeyu Cao, Haozhi Yuan, Shenghai Wang, Chen Xie, Lihua School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue 639798 Singapore Spatial AI & Robotics Lab Department of Computer Science and Engineering University at Buffalo BuffaloNY14260 United States

Scene Coordinate Regression (SCR) is a visual localization technique that utilizes deep neural networks (DNN) to directly regress 2D-3D correspondences for camera pose estimation. However, current SCR methods often face challenges in handling repetitive textures and meaningless areas due to their reliance on implicit triangulation. In this paper, we propose an efficient scene coordinate encoding and relocalization method. Compared with the existing SCR methods, we design a unified architecture for both scene encoding and salient keypoint detection, enabling our system to focus on encoding informative regions, thereby significantly enhancing efficiency. Additionally, we introduce a mechanism that leverages sequential information during both map encoding and relocalization, which strengthens implicit triangulation, particularly in repetitive texture environments. Comprehensive experiments conducted across indoor and outdoor datasets demonstrate that the proposed system outperforms other state-of-the-art (SOTA) SCR methods. Our single-frame relocalization mode improves the recall rate of our baseline by 6.4% and increases the running speed from 56Hz to 90Hz. Furthermore, our sequence-based mode increases the recall rate by 11% while maintaining the original efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Triangulation

Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Huang, Wen Gu, Yanmei Wang, Zhiming Zhu, Huijia Qian, Yanmin Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China SJTU Paris Elite lnstitute of Technology China Ant Group Shanghai China

Advances in speech synthesis technologies, like text-to-speech (TTS) and voice conversion (VC), have made detecting deepfake speech increasingly challenging. Spoofing countermeasures often struggle to generalize effectively, particularly when faced with unseen attacks. To address this, we propose a novel strategy that integrates Latent Space Refinement (LSR) and Latent Space Augmentation (LSA) to improve the generalization of deepfake detection systems. LSR introduces multiple learnable prototypes for the spoof class, refining the latent space to better capture the intricate variations within spoofed data. LSA further diversifies spoofed data representations by applying augmentation techniques directly in the latent space, enabling the model to learn a broader range of spoofing patterns. We evaluated our approach on four representative datasets, i.e. ASVspoof 2019 LA, ASVspoof 2021 LA and DF, and In-The-Wild. The results show that LSR and LSA perform well individually, and their integration achieves competitive results, matching or surpassing current state-of-the-art methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Speech recognition

Emerging Trends and Applications of Neuromorphic Dynamic Vision Sensors: A Survey

学校读者我要写书评

暂无评论

IEEE Sensors Reviews

IEEE Sensors Reviews 2024年 1卷 14-63页

作者： Hadi AliAkbarpour Ahmad Moori Javad Khorramdel Erik Blasch Omar Tahri Department of Computer Science Saint Louis University St Louis MO USA Artificial Intelligence and Robotics Lab (AIRLab) Saint Louis University St Louis MO USA Javad Khorramdel resides in Tehran Iran MOVEJ Analytics Fairborn OH USA Universite de Bourgogne CNRS UMR 6303 ICB Dijon France Visiting Professor in the Department of Computer Science Saint Louis University St Louis MO USA

Traditional frame-based cameras, foundational in computer vision, face challenges, such as motion blur, restricted dynamic range, and limited temporal resolution, which limit their use in various scenarios. Neuromorphic dynamic vision sensors (DVSs), inspired by biological vision systems, offer a significant shift with exceptional temporal resolution and pixel-level detection of light intensity changes, generating a continuous stream of events that encode time, location, and polarity. DVSs surpass traditional cameras with a dynamic range of 140 dB (compared to 60 dB), resilience to uneven lighting, minimal latency, ultra-high temporal resolution equivalent to over 100 000 frames per second, and low power consumption of just 1 mW. These capabilities mark DVSs as a transformative advancement in sensing technology. However, DVSs demand novel processing techniques due to their unique data output. This survey revisits both overlooked and newly available research, categorizing established and emerging techniques. It explores a range of applications, from autonomous systems, vehicle navigation, object detection, and depth estimation to gesture recognition. In addition, the survey introduces newer applications, such as super-resolution, rolling shutter correction, robotic manipulation, data compression, and space situational awareness. This article also tackles key challenges, such as DVS calibration, frame reconstruction, and simulation. To support future advancements, it provides a comprehensive overview of simulation platforms and the latest datasets, aiming to inspire further research and promote wider adoption of DVS technology in rapidly evolving fields.

关键词： Surveys Voltage control Sensors Reviews Robot sensing systems Superresolution Lighting Hardware Cameras Calibration

FDCT: Fast Depth Completion for Transparent Objects

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Tianan Chen, Zhehan Liu, Huan Wang, Chen The School of Mechanical Engineering University of Science and Technology Beijing Beijing100083 China The Department of Electrical and Computer Engineering McMaster University Canada The Spatial AI & Robotics Lab The Department of Computer Science and Engineering State University of New York BuffaloNY14260 United States

Depth completion is crucial for many robotic tasks such as autonomous driving, 3-D reconstruction, and manipulation. Despite the significant progress, existing methods remain computationally intensive and often fail to meet the real-time requirements of low-power robotic platforms. Additionally, most methods are designed for opaque objects and struggle with transparent objects due to the special properties of reflection and refraction. To address these challenges, we propose a Fast Depth Completion framework for Transparent objects (FDCT), which also benefits downstream tasks like object pose estimation. To leverage local information and avoid overfitting issues when integrating it with global information, we design a new fusion branch and shortcuts to exploit low-level features and a loss function to suppress overfitting. This results in an accurate and user-friendly depth rectification framework which can recover dense depth estimation from RGB-D images alone. Extensive experiments demonstrate that FDCT can run about 70 FPS with a higher accuracy than the state-of-the-art methods. We also demonstrate that FDCT can improve pose estimation in object grasping tasks. The source code is available at https://***/Nonmy/FDCT. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

A Distributed Deep Learning Approach for A Team of Unmanned Aerial Vehicles for Wildfire Tracking and Coverage

学校读者我要写书评

暂无评论

A Distributed Deep Learning Approach for A Team of Unmanned ...

IEEE International Conference on Robotic Computing (IRC)

作者： Kripash Shrestha Hung Manh La Hyung-Jin Yoon Amazon Robotics Research Department of Computer Science and Engineering Advanced Robotics and Automation (ARA) Lab University of Nevada Reno USA Department of Mechanical Engineering University of Nevada Reno USA

ISBN: (纸本)9781665472616

Recent large wildfires in the United States and the subsequent damage that they have caused have increased the importance of wildfire monitoring and tracking. However, human monitoring on the ground or in the air may be too dangerous and therefore, there need to be alternatives to monitoring wildfires. Unmanned Aerial Vehicles (UAVs) have been previously used in this problem domain to track and monitor wildfires with approaches such as artificial potential fields and reinforcement learning. Our work aims to look at a team of UAVs, in a distributed approach, over an area to maximize the sensor coverage in dynamic wildfire environments. We proposed and implemented the Deep Q-Network (DQN) with a state estimator (auto-encoder), then compared it to existing methods including a Q-learning, a Q-learning with experience replay, and a DQN. The proposed DQN with a state estimator outperformed existing deep learning methods in terms of reward maximization and convergence.

关键词： Deep learning Q-learning computational modeling Fires Autonomous aerial vehicles Vehicle dynamics Task analysis