Review of Visual Saliency Prediction: Development Process from Neurobiological Basis to Deep Models

The human attention mechanism can be understood and simulated by closely associating the saliency prediction task to neuroscience and psychology. Furthermore, saliency prediction is widely used in computer vision and interdisciplinary subjects. In recent years, with the rapid development of deep learning, deep models have made amazing achievements in saliency prediction. Deep learning models can automatically learn features, thus solving many drawbacks of the classic models, such as handcrafted features and task settings, among others. Nevertheless, the deep models still have some limitations, for example in tasks involving multi-modality and semantic understanding. This study focuses on summarizing the relevant achievements in the field of saliency prediction, including the early neurological and psychological mechanisms and the guiding role of classic models, followed by the development process and data comparison of classic and deep saliency prediction models. This study also discusses the relationship between the model and human vision, as well as the factors that cause the semantic gaps, the influences of attention in cognitive research, the limitations of the saliency model, and the emerging applications, to provide new saliency predictions for follow-up work and the necessary help and advice.

Download Full-text

Research on MATLAB and its Application in Mathematical Modeling

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.687-691.1202 ◽

2014 ◽

Vol 687-691 ◽

pp. 1202-1205

Author(s):

Ying Xu

Keyword(s):

Mathematical Modeling ◽

Computer Technology ◽

Development Process ◽

Rapid Development ◽

Matlab Software ◽

General Process ◽

Modeling Studies ◽

Key Technologies

With the rapid development of society and computer technology, the combination of mathematics with computer technology is playing an increasingly important role in each field of society. In this paper, we mainly discusses the important role of MATLAB software in mathematical modeling, so as to raise the understanding of MATLAB and the efficiency of mathematical modeling with MATLAB software, and then improve the ability to solve practical problems. This paper explains the general process of mathematical modeling, studies the function and characteristic of MATLAB and its application in mathematical modeling. There are analysis of the key technologies and solutions required in the development process. Practice has proved that the MATLAB mathematical modeling can be used to improve the efficiency and quality of mathematical modeling, enriching the ways and means of mathematical modeling, and has great effect on the teaching of mathematical modeling course.

Download Full-text

Controlled Quantized Study of Electroacupuncture in Treating Patients with Alzheimer’s Disease Based on Deep Learning Models

Journal of Medical Imaging and Health Informatics ◽

10.1166/jmihi.2020.2890 ◽

2020 ◽

Vol 10 (5) ◽

pp. 1076-1083

Author(s):

Dejuan Xie ◽

Xiaohong Li ◽

Dawei Chen

Keyword(s):

Alzheimer’S Disease ◽

Alzheimer's Disease ◽

Deep Learning ◽

Rapid Development ◽

Biological Indicators ◽

Medical Community ◽

Stimulation Parameters ◽

Diagnosis Of Dementia ◽

The Brain

The incidence of Alzheimer’s Disease (AD) in the world’s elderly over 65 is about 4% to 6%. Recent statistics show that there are nearly 40 million AD patients worldwide. According to the knowledge of neuroscience, there are two main biological indicators for the diagnosis of dementia in the medical community: one is the size of the hippocampus (equivalent to the brain memory chip), and the other is the size of the ventricle. Because the volume of the ventricles increases as the brain tissue degenerates. Because the cause of AD is unknown, it is generally found that it is late, even if the treatment will not have much effect. Therefore, early diagnosis of AD is a better way to inhibit the rapid development of the disease or even avoid the disease. At present, the pathogenesis and etiology of AD have not been fully elucidated, and there is a lack of a specific anti-AD drug. Electroacupuncture treatment of AD has been proven to have a certain effect, and has the advantages of diversified stimulation parameters, easy operation and no toxic side effects. In this paper, we study the role of electroacupuncture based on deep learning in patients with Alzheimer’s disease. The experimental results can prove the effectiveness of the proposed methodology.

Download Full-text

Feature Channel Expansion and Background Suppression as the Enhancement for Infrared Pedestrian Detection

Sensors ◽

10.3390/s20185128 ◽

2020 ◽

Vol 20 (18) ◽

pp. 5128

Author(s):

Shengzhe Wang ◽

Bo Wang ◽

Shifeng Wang ◽

Yifeng Tang

Keyword(s):

Deep Learning ◽

Intelligent Systems ◽

Feature Fusion ◽

Pedestrian Detection ◽

Visual Saliency ◽

Human Vision ◽

Background Suppression ◽

Training Process ◽

Fusion Algorithm ◽

Channel Expansion

Pedestrian detection is an important task in many intelligent systems, particularly driver assistance systems. Recent studies on pedestrian detection in infrared (IR) imagery have employed data-driven approaches. However, two problems in deep learning-based detection are the implicit performance and time-consuming training. In this paper, a novel channel expansion technique based on feature fusion is proposed to enhance the IR imagery and accelerate the training process. Besides, a novel background suppression method is proposed to stimulate the attention principle of human vision and shrink the region of detection. A precise fusion algorithm is designed to combine the information from different visual saliency maps in order to reduce the effect of truncation and miss detection. Four different experiments are performed from various perspectives in order to gauge the efficiency of our approach. The experimental results show that the Mean Average Precisions (mAPs) of four different datasets have been increased by 5.22% on average. The results prove that background suppression and suitable feature expansion will accelerate the training process and enhance the performance of IR image-based deep learning models.

Download Full-text

Visual Saliency Prediction Using Deep Learning

2021 7th International Conference on Advanced Computing and Communication Systems (ICACCS) ◽

10.1109/icaccs51430.2021.9441903 ◽

2021 ◽

Author(s):

P Anju ◽

Ashly Roy ◽

S Sheethal M ◽

M. Rajeswari

Keyword(s):

Deep Learning ◽

Visual Saliency ◽

Saliency Prediction

Download Full-text

A novel fully convolutional network for visual saliency prediction

PeerJ Computer Science ◽

10.7717/peerj-cs.280 ◽

2020 ◽

Vol 6 ◽

pp. e280

Author(s):

Bashir Muftah Ghariba ◽

Mohamed S. Shehata ◽

Peter McGuire

Keyword(s):

Deep Learning ◽

Visual Saliency ◽

Superior Performance ◽

Convolutional Network ◽

Fully Convolutional Network ◽

Proposed Model ◽

Saliency Prediction ◽

Benchmark Datasets ◽

The Many ◽

Deep Learning Model

A human Visual System (HVS) has the ability to pay visual attention, which is one of the many functions of the HVS. Despite the many advancements being made in visual saliency prediction, there continues to be room for improvement. Deep learning has recently been used to deal with this task. This study proposes a novel deep learning model based on a Fully Convolutional Network (FCN) architecture. The proposed model is trained in an end-to-end style and designed to predict visual saliency. The entire proposed model is fully training style from scratch to extract distinguishing features. The proposed model is evaluated using several benchmark datasets, such as MIT300, MIT1003, TORONTO, and DUT-OMRON. The quantitative and qualitative experiment analyses demonstrate that the proposed model achieves superior performance for predicting visual saliency.

Download Full-text

Deep Learning-Based Prediction Model for Breast Cancer Recurrence Using Adjuvant Breast Cancer Cohort in Tertiary Cancer Center Registry

Frontiers in Oncology ◽

10.3389/fonc.2021.596364 ◽

2021 ◽

Vol 11 ◽

Author(s):

Ji-Yeon Kim ◽

Yong Seok Lee ◽

Jonghan Yu ◽

Youngmin Park ◽

Se Kyung Lee ◽

...

Keyword(s):

Breast Cancer ◽

Machine Learning ◽

Deep Learning ◽

Prediction Model ◽

Real Time ◽

Prediction Models ◽

Unmet Need ◽

Absolute Error ◽

Data Set

Several prognosis prediction models have been developed for breast cancer (BC) patients with curative surgery, but there is still an unmet need to precisely determine BC prognosis for individual BC patients in real time. This is a retrospectively collected data analysis from adjuvant BC registry at Samsung Medical Center between January 2000 and December 2016. The initial data set contained 325 clinical data elements: baseline characteristics with demographics, clinical and pathologic information, and follow-up clinical information including laboratory and imaging data during surveillance. Weibull Time To Event Recurrent Neural Network (WTTE-RNN) by Martinsson was implemented for machine learning. We searched for the optimal window size as time-stamped inputs. To develop the prediction model, data from 13,117 patients were split into training (60%), validation (20%), and test (20%) sets. The median follow-up duration was 4.7 years and the median number of visits was 8.4. We identified 32 features related to BC recurrence and considered them in further analyses. Performance at a point of statistics was calculated using Harrell's C-index and area under the curve (AUC) at each 2-, 5-, and 7-year points. After 200 training epochs with a batch size of 100, the C-index reached 0.92 for the training data set and 0.89 for the validation and test data sets. The AUC values were 0.90 at 2-year point, 0.91 at 5-year point, and 0.91 at 7-year point. The deep learning-based final model outperformed three other machine learning-based models. In terms of pathologic characteristics, the median absolute error (MAE) and weighted mean absolute error (wMAE) showed great results of as little as 3.5%. This BC prognosis model to determine the probability of BC recurrence in real time was developed using information from the time of BC diagnosis and the follow-up period in RNN machine learning model.

Download Full-text

Psychological Resilience Provides No Independent Protection From Suicidal Risk

Crisis ◽

10.1027/0227-5910/a000364 ◽

2016 ◽

Vol 37 (2) ◽

pp. 130-139 ◽

Cited By ~ 9

Author(s):

Danica W. Y. Liu ◽

A. Kate Fairweather-Schmidt ◽

Richard Burns ◽

Rachel M. Roberts ◽

Kaarin J. Anstey

Keyword(s):

Risk Factors ◽

Well Being ◽

Current Status ◽

Psychological Resilience ◽

Cross Sectional ◽

Life Project ◽

Resilience Factors ◽

First Time

Abstract. Background: Little is known about the role of resilience in the likelihood of suicidal ideation (SI) over time. Aims: We examined the association between resilience and SI in a young-adult cohort over 4 years. Our objectives were to determine whether resilience was associated with SI at follow-up or, conversely, whether SI was associated with lowered resilience at follow-up. Method: Participants were selected from the Personality and Total Health (PATH) Through Life Project from Canberra and Queanbeyan, Australia, aged 28–32 years at the first time point and 32–36 at the second. Multinomial, linear, and binary regression analyses explored the association between resilience and SI over two time points. Models were adjusted for suicidality risk factors. Results: While unadjusted analyses identified associations between resilience and SI, these effects were fully explained by the inclusion of other suicidality risk factors. Conclusion: Despite strong cross-sectional associations, resilience and SI appear to be unrelated in a longitudinal context, once risk/resilience factors are controlled for. As independent indicators of psychological well-being, suicidality and resilience are essential if current status is to be captured. However, the addition of other factors (e.g., support, mastery) makes this association tenuous. Consequently, resilience per se may not be protective of SI.

Download Full-text