20 research outputs found
Data-driven Digital Therapeutics Analytics
No full textDigital therapeutics (DTx), in contrast to traditional treatments such as pills, use software installed in smartphones or wearable devices as a medical device to cure diseases and improve health conditions, which represents a significant departure from existing wellness products such as Fitbits. DTx requires clinical validation of efficacy through systematic clinical trials, as do conventional therapeutics. Mobile DTx apps transform conventional treatment approaches such as counseling, self-help, and self-tracking into app-based micro-interventions that can be delivered via notifications, short videos, and chatbots. This article presents a data-driven DTx analytics framework for analyzing and optimizing DTx delivery processes in everyday life contexts by leveraging passive sensor data analysis and human-in-the-loop interaction support
Zero-bias anomaly and role of electronic correlations in a disordered metal film
No full textLocalization and electron correlation play significant roles in understanding the electronic states of low-dimensional systems. We carried out the tunneling spectroscopy measurements on a crystalline nano-sized island and a disordered two-dimensional metal film. The low temperature zero-bias anomaly was studied using theory and statistical analysis of the spatial distribution of the local density of states in both the systems. The effective capacitance and resistance of the tunnel junction extracted from theory gives the energy and temperature dependency of the measured ZBA. Statistical analysis reveals the electron correlation effect and the electron correlation length. By combining theory and the statistical analysis, we found that the microscopic origin of ZBA formation in the disordered two-dimensional film is strongly related to the electron localization and the correlations. © 2020 The Author(s). Published by IOP Publishing Ltd on behalf of the Institute of Physics and Deutsche Physikalische Gesellschaft.1
GraspClutter6D: A Large-Scale Real-World Dataset for Robust Perception and Grasping in Cluttered Scenes
No full textRobust grasping in cluttered environments remains an open challenge in robotics. While benchmark datasets have significantly advanced deep learning methods, they mainly focus on simplistic scenes with light occlusion and insufficient diversity, limiting their applicability to practical scenarios. We present GraspClutter6D, a large-scale real-world grasping dataset featuring: (1) 1,000 highly cluttered scenes with dense arrangements (14.1 objects/scene, 62.6% occlusion), (2) comprehensive coverage across 200 objects in 75 environment configurations (bins, shelves, and tables) captured using four RGB-D cameras from multiple viewpoints, and (3) rich annotations including 736 K 6D object poses and 9.3B feasible robotic grasps for 52 K RGB-D images. We benchmark state-of-the-art segmentation, object pose estimation, and grasp detection methods to provide key insights into challenges in cluttered environments. Additionally, we validate the dataset's effectiveness as a training resource, demonstrating that grasping networks trained on GraspClutter6D significantly outperform those trained on existing datasets in both simulation and real-world experiments.
IRIS-A New Plagiarized Code Detection System
No full textPlagiarism is defined as an activity to use someone\u27s work without the author\u27s agreement or without a proper citation about the reference[l]. To detect plagiarized programming source codes should be performed by instructors to promote the quality of school education. However, it is virtually impossible to detect those source codes completely within the limited time by only using human\u27s ability. Therefore, it is natural to try to adopt computing power to this operation. Most of the existing plagiarism detection systems use an algorithm to find Longest Common Subsection to measure the similarity between two program sources, but does not provide a way to compare algorithms used for those program source files[2-6]. In this paper, we discuss how to build a new detection system named IRIS that uses Strict Binary Tree structure that was introduced in JK system[7] and execution function call sequences in order to determine the algorithms used in program source files, which will be the major factor to measure the similarity of two compared files by applying Software Metrics additionally
Automatic Detection and Identification of Fasteners with Simple Visual Calibration using Synthetic Data
No full textConvolutional Neural Network with Biologically Inspired Retinal Structure
No full textAbstractIn this paper, we propose a new Convolutional Neural Network (CNN) with biologically inspired retinal structure and ON/OFF Rectified Linear Unit (ON/OFF ReLU). Retinal structure enhances input images by center surround difference of green-red and blue-yellow components, which in turn creates positive as well as negative features like ON/OFF visual pathway of retina to make a total of 12 feature channels. This ON/OFF concept is also adopted to each convolutional layer of CNN. We prefer to call this ON/OFF ReLU. In contrast, conventional ReLU passes only positive features of each convolutional layer and may loose important information from negative features. Moreover, it also happens to loose learning chance if results are saturated to zero. However, in our proposed model, we use both positive and negative information, which provides a possibility to learn through negative results. We also present the experimental results conducted on CIFAR-10 dataset and atrial fibrillation prediction for health monitoring, and show how effectively the negative information and retinal structure improves the performance of conventional CNN
Growth phase diagram of graphene grown through chemical vapor deposition on copper
No full text© 2020 The Author(s).The phase diagram for graphene growth was obtained to understand the physics of the growth mechanism and control the layer number or coverage of graphene deposited on copper via low-pressure chemical vapor deposition (LPCVD). Management of the number of graphene layers and vacancies is essential for producing defect-free monolayer graphene and engineering multilayered functionalized graphene. In this work, the effects of the CH4 and H2 flow rates were investigated to establish the phase diagram for graphene growth. Using this phase diagram, we selectively obtained fully covered and partially grown monolayer graphene, graphene islands through Volmer-Weber growth, and multilayer graphene through Stranski-Krastanov-like growth. The layer numbers and coverage were determined using optical microscopy, scanning electron microscopy, transmission electron microscopy, atomic force microscopy and Raman spectroscopy. The growth modes were determined by the competition between catalytic growth with CH4 and catalytic etching with H2 on the copper surface during CVD growth. Intriguingly, this phase diagram showed that multilayer graphene flakes can be grown via LPCVD even with low CH4 and H2 flows11sciescopuskc
PolyFit: A Peg-in-hole Assembly Framework for Unseen Polygon Shapes via Sim-to-real Adaptation
No full textThe study addresses the foundational and challenging task of peg-in-hole
assembly in robotics, where misalignments caused by sensor inaccuracies and
mechanical errors often result in insertion failures or jamming. This research
introduces PolyFit, representing a paradigm shift by transitioning from a
reinforcement learning approach to a supervised learning methodology. PolyFit
is a Force/Torque (F/T)-based supervised learning framework designed for 5-DoF
peg-in-hole assembly. It utilizes F/T data for accurate extrinsic pose
estimation and adjusts the peg pose to rectify misalignments. Extensive
training in a simulated environment involves a dataset encompassing a diverse
range of peg-hole shapes, extrinsic poses, and their corresponding contact F/T
readings. To enhance extrinsic pose estimation, a multi-point contact strategy
is integrated into the model input, recognizing that identical F/T readings can
indicate different poses. The study proposes a sim-to-real adaptation method
for real-world application, using a sim-real paired dataset to enable effective
generalization to complex and unseen polygon shapes. PolyFit achieves
impressive peg-in-hole success rates of 97.3% and 96.3% for seen and unseen
shapes in simulations, respectively. Real-world evaluations further demonstrate
substantial success rates of 86.7% and 85.0%, highlighting the robustness and
adaptability of the proposed method.Comment: 8 pages, 8 figures, 3 table
Learning to Place Unseen Objects Stably using a Large-scale Simulation
No full textObject placement is a fundamental task for robots, yet it remains challenging
for partially observed objects. Existing methods for object placement have
limitations, such as the requirement for a complete 3D model of the object or
the inability to handle complex shapes and novel objects that restrict the
applicability of robots in the real world. Herein, we focus on addressing the
Unseen Object Placement (UOP}=) problem. We tackled the UOP problem using two
methods: (1) UOP-Sim, a large-scale dataset to accommodate various shapes and
novel objects, and (2) UOP-Net, a point cloud segmentation-based approach that
directly detects the most stable plane from partial point clouds. Our UOP
approach enables robots to place objects stably, even when the object's shape
and properties are not fully known, thus providing a promising solution for
object placement in various environments. We verify our approach through
simulation and real-world robot experiments, demonstrating state-of-the-art
performance for placing single-view and partial objects. Robot demos, codes,
and dataset are available at https://gistailab.github.io/uop/Comment: 8 pages (main
Learning to Place Unseen Objects Stably using a Large-scale Simulation
No full textObject placement is a fundamental task for robots, yet it remains challenging for partially observed objects. Existing methods for object placement have limitations, such as the requirement for a complete 3D model of the object or the inability to handle complex shapes and novel objects that restrict the applicability of robots in the real world. Herein, we focus on addressing the Unseen Object Placement (UOP) problem. We tackled the UOP problem using two methods: (1) UOP-Sim, a large-scale dataset to accommodate various shapes and novel objects, and (2) UOP-Net, a point cloud segmentation-based approach that directly detects the most stable plane from partial point clouds. Our UOP approach enables robots to place objects stably, even when the object's shape and properties are not fully known, thus providing a promising solution for object placement in various environments. We verify our approach through simulation and real-world robot experiments, demonstrating state-of-the-art performance for placing single-view and partial objects. Robot demos, codes, and dataset are available at https://gistailab.github.io/uop/ AuthorsTRUEsciescopu
