Channel Interaction with Local Enhancement for Few-Shot Semantic Segmentation

: The scorpion toxins are the largest potassium channel-blocking peptide family. The understanding of toxin binding interfaces is usually restricted by two classical binding interfaces: one is the toxin α-helix motif, the other is the antiparallel β-sheet motif. In this review, such traditional knowledge was updated by another two different binding interfaces: one is BmKTX toxin using the turn motif between the α-helix and antiparallel β-sheet domains as the binding interface, the other is Ts toxin using turn motif between the β-sheet in the N-terminal and α-helix domains as the binding interface. Their interaction analysis indicated that the scarce negatively charged residues in the scorpion toxins played a critical role in orientating the toxin binding interface. In view of the toxin negatively charged amino acids as “binding interface regulator”, the law of scorpion toxin-potassium channel interaction was proposed, that is, the polymorphism of negatively charged residue distribution determines the diversity of toxin binding interfaces. Such law was used to develop scorpion toxin-potassium channel recognition control technique. According to this technique, three Kv1.3 channel-targeted peptides, using BmKTX as the template, were designed with the distinct binding interfaces from that of BmKTX through modulating the distribution of toxin negatively charged residues. In view of the potassium channel as the common targets of different animal toxins, the proposed law was also shown to helpfully orientate the binding interfaces of other animal toxins. Clearly, the toxin-potassium channel interaction law would strongly accelerate the research and development of different potassium channelblocking animal toxins in the future.

Download Full-text

Development of environment design support mixed reality system capable of environment estimation using deep learning

Impact ◽

10.21820/23987073.2020.2.9 ◽

2020 ◽

Vol 2020 (2) ◽

pp. 9-11

Author(s):

Tomohiro Fukuda

Keyword(s):

Deep Learning ◽

Real Time ◽

Computer Games ◽

Construction Projects ◽

Mixed Reality ◽

Semantic Segmentation ◽

Environment Design ◽

Aviation Training ◽

Architecture And Design ◽

World Environment

Mixed reality (MR) is rapidly becoming a vital tool, not just in gaming, but also in education, medicine, construction and environmental management. The term refers to systems in which computer-generated content is superimposed over objects in a real-world environment across one or more sensory modalities. Although most of us have heard of the use of MR in computer games, it also has applications in military and aviation training, as well as tourism, healthcare and more. In addition, it has the potential for use in architecture and design, where buildings can be superimposed in existing locations to render 3D generations of plans. However, one major challenge that remains in MR development is the issue of real-time occlusion. This refers to hiding 3D virtual objects behind real articles. Dr Tomohiro Fukuda, who is based at the Division of Sustainable Energy and Environmental Engineering, Graduate School of Engineering at Osaka University in Japan, is an expert in this field. Researchers, led by Dr Tomohiro Fukuda, are tackling the issue of occlusion in MR. They are currently developing a MR system that realises real-time occlusion by harnessing deep learning to achieve an outdoor landscape design simulation using a semantic segmentation technique. This methodology can be used to automatically estimate the visual environment prior to and after construction projects.

Download Full-text

DEVELOPMENT OF AN OPEN SOURCE, MACHINE LEARNING BASED TOOLSET FOR THE IDENTIFICATION OF DIKES IN SATELLITE IMAGES THROUGH SEMANTIC SEGMENTATION

10.1130/abs/2020am-357672 ◽

2020 ◽

Author(s):

Ryan Gray ◽

◽

Tushar Mittal

Keyword(s):

Machine Learning ◽

Open Source ◽

Satellite Images ◽

Semantic Segmentation

Download Full-text

Utilizing semantic segmentation method with convolutional neural net to model a partial nephrectomy simulator for 3D printing

European Urology Supplements ◽

10.1016/s1569-9056(19)31264-3 ◽

2019 ◽

Vol 18 (1) ◽

pp. e1747-e1748

Author(s):

Y.S. Kyung ◽

B. Lim ◽

S.Y. Choi ◽

J.H. Han ◽

W. Lee ◽

...

Keyword(s):

3D Printing ◽

Partial Nephrectomy ◽

Semantic Segmentation ◽

Neural Net ◽

Segmentation Method

Download Full-text

Vision-Based Navigation of Autonomous Vehicles in Roadway Environments with Unexpected Hazards

Transportation Research Record Journal of the Transportation Research Board ◽

10.1177/0361198119855606 ◽

2019 ◽

Vol 2673 (12) ◽

pp. 494-507 ◽

Cited By ~ 1

Author(s):

Mhafuzul Islam ◽

Mashrur Chowdhury ◽

Hongda Li ◽

Hongxin Hu

Keyword(s):

Object Detection ◽

Autonomous Vehicles ◽

Autonomous Vehicle ◽

Semantic Segmentation ◽

Steering Wheel ◽

Potential Hazard ◽

Driving System ◽

Hazardous Object ◽

Vision Based Navigation ◽

Navigational System

Vision-based navigation of autonomous vehicles primarily depends on the deep neural network (DNN) based systems in which the controller obtains input from sensors/detectors, such as cameras, and produces a vehicle control output, such as a steering wheel angle to navigate the vehicle safely in a roadway traffic environment. Typically, these DNN-based systems in the autonomous vehicle are trained through supervised learning; however, recent studies show that a trained DNN-based system can be compromised by perturbation or adverse inputs. Similarly, this perturbation can be introduced into the DNN-based systems of autonomous vehicles by unexpected roadway hazards, such as debris or roadblocks. In this study, we first introduce a hazardous roadway environment that can compromise the DNN-based navigational system of an autonomous vehicle, and produce an incorrect steering wheel angle, which could cause crashes resulting in fatality or injury. Then, we develop a DNN-based autonomous vehicle driving system using object detection and semantic segmentation to mitigate the adverse effect of this type of hazard, which helps the autonomous vehicle to navigate safely around such hazards. We find that our developed DNN-based autonomous vehicle driving system, including hazardous object detection and semantic segmentation, improves the navigational ability of an autonomous vehicle to avoid a potential hazard by 21% compared with the traditional DNN-based autonomous vehicle driving system.

Download Full-text