A Novel Horror Scene Detection Scheme on Revised Multiple Instance Learning Model

2011 ◽  
pp. 359-370 ◽  
Author(s):  
Bin Wu ◽  
Xinghao Jiang ◽  
Tanfeng Sun ◽  
Shanfeng Zhang ◽  
Xiqing Chu ◽  
...  
Keyword(s):  
Learning Model ◽  
Multiple Instance Learning ◽  
Detection Scheme ◽  
Scene Detection

Nighttime Motion Vehicle Detection Based on Multiple Instance Learning

2014 ◽  
Vol 529 ◽  
pp. 370-374
Author(s):  
Shao Ping Zhu
Keyword(s):  
Vehicle Detection ◽  
Learning Model ◽  
Multiple Instance Learning ◽  
Urban Traffic ◽  
Detection Accuracy ◽  
Road Detection ◽  
Traffic Condition ◽  
Sift Feature ◽  
Moving Vehicles ◽  
Label Information

In this paper, we propose an effective approach for detecting moving vehicles in nighttime traffic scenes. We use Multiple Instance Learning method to automatically detect vehicle from video sequences by constructing the Multiple Instance Learning model at nighttime. At first, we extract SIFT feature using SIFT feature extraction algorithm, which is used to characterize moving vehicles at nighttime. Then Multiple Instance Learning model is used for the on-road detection of vehicles at nighttime, in order to improve the detection accuracy, the class label information was used for the learning of the Multiple Instance Learning model. Final experiments were performed and evaluate the proposed method at nighttime under urban traffic condition, the experiment results show that the average detection accuracy is over 96.2%, which validates that the proposed vehicle detection approach is feasible and effective for the on-road detection of vehicles at nighttime and identification in various nighttime environments.

scholarly journals A transferrable and interpretable multiple instance learning model for microsatellite instability prediction based on histopathology images

2020 ◽  
Author(s):  
Rui Cao ◽  
Fan Yang ◽  
Si-Cong Ma ◽  
Li Liu ◽  
Yan Li ◽  
...  
Keyword(s):  
Deep Learning ◽  
Microsatellite Instability ◽  
Transfer Learning ◽  
Area Under The Curve ◽  
Learning Model ◽  
Multiple Instance Learning ◽  
The Cancer Genome Atlas ◽  
Data Set ◽  
Histopathology Images ◽  
Deep Learning Model

ABSTRACTBackgroundMicrosatellite instability (MSI) is a negative prognostic factor for colorectal cancer (CRC) and can be used as a predictor of success for immunotherapy in pan-cancer. However, current MSI identification methods are not available for all patients. We propose an ensemble multiple instance learning (MIL)-based deep learning model to predict MSI status directly from histopathology images.DesignTwo cohorts of patients were collected, including 429 from The Cancer Genome Atlas (TCGA-COAD) and 785 from a self-collected Asian data set (Asian-CRC). The initial model was developed and validated in TCGA-COAD, and then generalized in Asian-CRC through transfer learning. The pathological signatures extracted from the model are associated with genotypes for model interpretation.ResultsA model called Ensembled Patch Likelihood Aggregation (EPLA) was developed in the TCGA-COAD training set based on two consecutive stages: patch-level prediction and WSI-level prediction. The EPLA model achieved an area-under-the -curve (AUC) of 0.8848 in the TCGA-COAD test set, which outperformed the state-of-the-art approach, and an AUC of 0.8504 in the Asian-CRC after transfer learning. Furthermore, the five pathological imaging signatures identified using the model are associated with genomic and transcriptomic profiles, which makes the MIL model interpretable. Results show that our model recognizes pathological signatures related to mutation burden, DNA repair pathways, and immunity.ConclusionOur MIL-based deep learning model can effectively predict MSI from histopathology images and are transferable to a new patient cohort. The interpretability of our model by association with genomic and transcriptomic biomarkers lays the foundation for prospective clinical research.

scholarly journals ON GENERALIZED MULTIPLE-INSTANCE LEARNING

2005 ◽  
Vol 05 (01) ◽  
pp. 21-35 ◽  
Author(s):  
STEPHEN SCOTT ◽  
JUN ZHANG ◽  
JOSHUA BROWN
Keyword(s):  
Image Retrieval ◽  
Protein Sequence ◽  
Robot Vision ◽  
Learning Model ◽  
Multiple Instance Learning ◽  
Content Based Image Retrieval ◽  
Target Point ◽  
Empirical Results ◽  
Sequence Identification ◽  
Single Target

We describe a generalisation of the multiple-instance learning model in which a bag's label is not based on a single instance's proximity to a single target point. Rather, a bag is positive if and only if it contains a collection of instances, each near one of a set of target points. We then adapt a learning-theoretic algorithm for learning in this model and present empirical results on data from robot vision, content-based image retrieval, and protein sequence identification.

scholarly journals Multiple instance learning tracking based on Fisher linear discriminant with incorporated priors

2018 ◽  
Vol 15 (1) ◽  
pp. 172988141775072 ◽  
Author(s):  
Zhiyu Zhou ◽  
Xu Gao ◽  
Jingsong Xia ◽  
Zefei Zhu ◽  
Donghe Yang ◽  
...  
Keyword(s):  
Motion Tracking ◽  
Learning Model ◽  
Descent Method ◽  
Multiple Instance Learning ◽  
Detection Methods ◽  
Gradient Descent Method ◽  
Tracking Accuracy ◽  
Fisher Linear Discriminant ◽  
Linear Discriminant ◽  
Tracking Object

Traditional tracking-by-detection methods use online classifier to track object, and the classifier can be degenerated easily using self-learning process. The article presents a multiple instance learning (MIL) tracking method based on a semi-supervised learning model with Fisher linear discriminant (MILFLD). First, the overlap rate of sampled instances and tracking object served as the prior information. Using both labeled and unlabeled data, the tracking drift problem in the learning model could be alleviated. Second, the lost function of MILFLD is built using Fisher linear discriminant model incorporated with priors. Hence the optimal classifier can be selected out directly in instance level. Last but not least, the classifiers are chosen by gradient descent method, assuring the maximum descent of lost function. Therefore, the classifiers selected at previous frames are still discriminative to future frames, which can help to constrain the error propagation. Comparison experiments show that the center location errors of online AdaBoosting , online MIL tracking, weighted MIL tracking (WMIL), compressive tracking (CT), struck tracking, and MILFLD are 78, 66, 62,74, 59, and 25 pixels, respectively, which demonstrates the tracking accuracy of our method. The experiments of robot motion tracking in realistic scenario have been complemented for comparison as well. Despite the variations in illumination, deformation, or occlusions of the objects, the proposed method can track the target accurately and has high real-time performance.

Prediction of Ionizing Radiation Resistance in Bacteria Using a Multiple Instance Learning Model

2016 ◽  
Vol 23 (1) ◽  
pp. 10-20 ◽  
Author(s):  
Sabeur Aridhi ◽  
Haïtham Sghaier ◽  
Manel Zoghlami ◽  
Mondher Maddouri ◽  
Engelbert Mephu Nguifo
Keyword(s):  
Ionizing Radiation ◽  
Radiation Resistance ◽  
Learning Model ◽  
Multiple Instance Learning ◽  
Ionizing Radiation Resistance

Early Detection Of Life-Threatening Cardiac Arrhythmias Using Deep Learning Techniques

2019 ◽  
Vol 14 ◽  
Author(s):  
Sumathi S ◽  
Agalya V
Keyword(s):  
Deep Learning ◽  
Cardiac Arrhythmias ◽  
Clinical Training ◽  
Normal Sinus Rhythm ◽  
False Negative ◽  
Learning Model ◽  
Detection Scheme ◽  
Ecg Signals ◽  
Deep Learning Model

: A progressive and flourishing technological advancement occurs across the communities working on a domain that needs clinical training and Technology Transfer. There is an essentiality for the evolution of advanced concepts in the Classification of healthcare, particularly in relation to arrhythmia detection towards clinical operations. Being the forerunner among the emerging areas in science and technology, this field demands an extensive practical and verification research. These innovative technological progress has significantly contributed to high-quality, on-time, acceptable and affordable healthcare. This paper approaches a novel method of Detecting and classifying the cardiac arrhythmias using deep learning model for classification of electrocardiogram (ECG) signals. This method is based on using Cubic Wavelet Transform for analyzing the ECG signals and extracting the parameters related to dangerous cardiac arrhythmias. In these parameters ar used as input to these classifier, five most important types of ECG signals they are Normal Sinus Rhythm (NSR), Atrial Fibrillation (AF), Pre-Ventricular Contraction (PVC), Ventricular Fibrillation (VF), and Ventricular Flutter (VFLU). By using the deep learning algorithm to recognition and classification capabilities across a broad area of biomedical engineering. The performance of the deep learning model was evaluated in terms of training performance and classification accuracies. The classification accuracy of 99.24% is achieved. . Good accuracy of ECG patterns is achievable only over a large number of files.These difficulties have necessitated us to develop a new detection scheme, which gives a high level of accuracy, low false-positive and low false-negative statistics.

Sign in / Sign up

Export Citation Format

Share Document