scholarly journals The Extended Multidimensional Neo-Fuzzy System and Its Fast Learning in Pattern Recognition Tasks

Data ◽  
2018 ◽  
Vol 3 (4) ◽  
pp. 63 ◽  
Author(s):  
Yevgeniy Bodyanskiy ◽  
Nonna Kulishova ◽  
Olha Chala
Keyword(s):  
Real Time ◽  
Information Technologies ◽  
Learning Algorithm ◽  
Video Stream ◽  
System Structure ◽  
System Architectures ◽  
Fast Learning ◽  
Video Recognition ◽  
Entropy Criterion ◽  
Time Image

Methods of machine learning and data mining are becoming the cornerstone in information technologies with real-time image and video recognition methods getting more and more attention. While computational system architectures are getting larger and more complex, their learning methods call for changes, as training datasets often reach tens and hundreds of thousands of samples, therefore increasing the learning time of such systems. It is possible to reduce computational costs by tuning the system structure to allow fast, high accuracy learning algorithms to be applied. This paper proposes a system based on extended multidimensional neo-fuzzy units and its learning algorithm designed for data streams processing tasks. The proposed learning algorithm, based on the information entropy criterion, has significantly improved the system approximating capabilities. Experiments have confirmed the efficiency of the proposed system in solving real-time video stream recognition tasks.

Design of Real-Time Image Data Acquisition and Processing System Based on SOPC

2013 ◽  
Vol 373-375 ◽  
pp. 650-653
Author(s):  
Wei Song ◽  
Shu Yuan Qin ◽  
Yan Xiao Chen ◽  
Long Ji Zhang
Keyword(s):  
Data Acquisition ◽  
Real Time ◽  
Design Theory ◽  
Processing System ◽  
Image Data ◽  
System Structure ◽  
Design Flexibility ◽  
Real Time Image ◽  
Data Acquisition And Processing ◽  
Time Image

A real-time image data acquisition and processing system based on SOPC in intelligent cart with automatic tracking function was designed. In this paper, the basic design theory and the system structure was analyzed. The Quartus II and Nios II software was used to make the system with real-time image acquisition function. And the data in SDRAM of two CMOS cameras based on SOPC was read. The design was tested with the system, and results showed that this module had the characters of design flexibility, fast image processing and expansibility.

Robot Visual Design with the Panorama Synthesis Function with Manufacturing Technology

2013 ◽  
Vol 312 ◽  
pp. 705-709
Author(s):  
Wen Ming Wang ◽  
Ya Peng Yu
Keyword(s):  
Target Tracking ◽  
Real Time ◽  
Target Selection ◽  
Video Stream ◽  
Selection Function ◽  
Present System ◽  
Video File ◽  
Detection And Tracking ◽  
Time Image ◽  
Visual Range

Panorama synthesis is basis of the target tracking. Through the synthesis of panorama, can enlarge the visual range to capture for the cameras, in the big background, the suspicious target which needs to be tracked are more easily detected, then selects the target, and Tracks it. In the existing target tracking of robot integrated machine, adds panorama synthesis function and the suspicious target selection function, the target tracking runs only on selected target, make the tracking more targeted. In the Panorama synthesis module of the present system, there are two ways to obtain video stream that is real-time image stream from Cameras and the local AVI video file. Through the algorithm to judge the position relationship between two adjacent frames, finishes the image stitching, and displays panorama of the in the user interface in real time. By a particular target selection from users, complete moving object detection and tracking in motion camera environment. After the test, the system can meet the general needs of application oriented robot visual.

NEURAL NETWORK FEATURE DETECTOR FOR REAL-TIME VIDEO SIGNAL PROCESSING

1993 ◽  
Vol 04 (04) ◽  
pp. 337-349
Author(s):  
DAVID NAYLOR ◽  
SIMON JONES ◽  
DAVID MYERS ◽  
JOHN VINCENT
Keyword(s):  
Image Processing ◽  
Real Time ◽  
High Performance ◽  
Feature Recognition ◽  
Learning Algorithm ◽  
Neural System ◽  
Neural Learning ◽  
Network Feature ◽  
On Chip ◽  
Time Image

The application of artificial neural networks to real-time image processing tasks requires the use of dedicated, high performance hardware. A linear array processor called HANNIBAL has been developed which implements the backpropagation neural learning algorithm on-chip. This paper considers the design of a complete neural system which integrates HANNIBAL into an existing image processing environment. The goals for the design of the system have been set partly by the primary application, namely feature recognition, but mainly by the desire for a flexible, high performance hardware tool for the study and evaluation of range of neural image processing applications.

397 Intra-tumor immunotherapy injections utilizing image guidance in interventional radiology: clinical trial experience at a tertiary care cancer center

2020 ◽  
Vol 8 (Suppl 3) ◽  
pp. A422-A422
Author(s):  
Ravi Murthy ◽  
Rahul Sheth ◽  
Alda Tam ◽  
Sanjay Gupta ◽  
Vivek Subbiah ◽  
...  
Keyword(s):  
Clinical Trials ◽  
Interventional Radiology ◽  
Real Time ◽  
Image Guidance ◽  
Tertiary Care ◽  
Cancer Center ◽  
Imaging Guidance ◽  
Image Guided ◽  
Real Time Image ◽  
Time Image

BackgroundImage guided intra-tumor administration of investigational immunotherapeutic agents represents an expanding field of interest. We present a retrospective review of the safety, feasibility & technical nuances of real-time image guidance for injection & biopsy across a spectrum of extracranial solid malignancies utilizing the discipline of Interventional Radiology.MethodsPatients who were enrolled in image guided intratumoral immunotherapy injection (ITITI) clinical trials over a 6 year period (2013–19) at a single tertiary care cancer center were included in this analysis. Malignancy, location, imaging guidance utilized for ITITI & biopsy for injected (adscopal) & non-injected (abscopal) lesions were determined and categorized. Peri-procedural adverse events were noted.Results262 pts (146 female, 61 yrs median) participating in 29 immunotherapeutic clinical trials (TLR & STING agonists, gene therapy, anti CD-40, viral/bacterial/metabolic oncolytics) met study criteria. Malignancies included melanoma 88, sarcoma 32, colorectal 29, breast 23, lung 17, head & neck 15, ovarian 8, neuroendocrine 7, pancreatic adenocarcinoma 6, 3 each (cholangioCA, endometrial, bladder, GI tract), 2 each (RCC, thymicCA, lymphoma, merkel cell, prostate) & others 1 each (CUP, GIST, dermatofibrosarcoma, DSRT, neuroblastoma, thyroid). All 169 & 93 patients received the intended 1371 ITITI in parietal (abdominal/chest wall, extremity, neck, pelvis) or visceral (liver, lung, peritoneum, adrenal) locations respectively; 83 patients received lymph node injections within either location. Imaging guidance was US in 68% of the cohort (US 161, CT+US 19); CT was used in 30% (81) & MRI in 1 patient. Median diameter of the ITITI lesion was 32 mm (8–230 mm). Median volume of the ITITI therapeutic material/session was 2 ml (1–6.9 ml). Lesions were accessed using a coaxial technique. ITITI delivery needles used at operator preference & tailored to lesion characteristics were either a 21G/22G Chiba, 21G Profusion (Cook Medical), 22G Morrison (AprioMed), 25G hypodermic (BD) & 18G Quadrafuse (Rex Medical). 2840 core biopsies (>18G Tru-cut core, Mission, Bard Medical) were performed in 237 patients during 690 procedures; biopsy sessions were often concurrent & of the ITITI site. 137 patients also underwent biopsy of a non-ITITI site (89 parietal location). Dimensions of the non-ITITI lesion were median 10 mm (7–113 mm); US image guidance was used in 97 patients (72%) to obtain a total of 1257, >18G Tru-core samples. 1.3% of injections resulted in SAE (NCI CTC AE >3) and 0.5% of 4097 biopsies developed major complications (SIR Criteria); both categories were manageable.ConclusionsUtilizing real time image guidance, ITITI to the administration of a myriad of investigational immunotherapeutic agents with concomitant biopsy procedures to date are associated with a high technical success rate & favorable safety profile.AcknowledgementsJoshua Hein, Mara Castaneda, Jyotsna Pera, Yunfang Jiang,Shuang Liu, Holly Liu and Anna LuiTrial RegistrationN/AEthics ApprovalThe study was approved by Institution’s Ethics Board, approval number 2020-0536: A retrospective study to determine the safety, feasibility and technical challenges of real-time image guidance for intra-tumor injection and biopsy across multiple solid tumors.Consent2020-0536 Waiver of Informed ConsentReferenceSheth RA, Murthy R, Hong DS, et al. Assessment of image-guided intratumoral delivery of immunotherapeutics in patients with cancer. JAMA Netw Open 2020;3(7):e207911. doi:10.1001/jamanetworkopen.2020.7911

Sign in / Sign up

Export Citation Format

Share Document