Improved community structure detection using a modified fine-tuning strategy

At present, the detection of urban community structures is mainly based on existing administrative divisions, and is performed using qualitative methods. The lack of quantitative methods makes it difficult to judge the rationality of urban community divisions. In this study, we used complex network association mining methods to detect a city community structure by using the Origin-Destinations (OD) at traffic analysis zone (TAZ) level, and successively assigned all the TAZs into different communities. Based on the community results, we calculated the community core degree of each TAZ within every community, and then calculated the Traffic Core Degree and Location Core Degree indicators of the community based on OD passenger flow and spatial location relationship between communities. Finally, we analyzed the correlation among three indicators to ensure the rationality of the community structure. We used the city of Zhengzhou in 2016 as an example case study. For Zhengzhou, we detected a total of six communities. We found a relatively low correlation between Traffic Core Degree and Location Core Degree. Within each group, the correlation between community core degree and Traffic Core Degree was higher than that between community core degree and Location Core Degree, indicating that the urban community structure is more reasonably based on traffic characteristics. The development of a quantitative approach for determining reasonable city community structures has important implications for transportation planning and industrial layout.

Download Full-text

Two-Stage Mask-RCNN Approach for Detecting and Segmenting the Optic Nerve Head, Optic Disc, and Optic Cup in Fundus Images

Applied Sciences ◽

10.3390/app10113833 ◽

2020 ◽

Vol 10 (11) ◽

pp. 3833 ◽

Cited By ~ 3

Author(s):

Haidar Almubarak ◽

Yakoub Bazi ◽

Naif Alajlan

Keyword(s):

Optic Nerve ◽

Optic Disc ◽

Optic Nerve Head ◽

Fine Tuning ◽

Fundus Images ◽

Two Stage ◽

Second Stage ◽

Retinal Fundus Images ◽

Tuning Strategy ◽

Retinal Fundus

In this paper, we propose a method for localizing the optic nerve head and segmenting the optic disc/cup in retinal fundus images. The approach is based on a simple two-stage Mask-RCNN compared to sophisticated methods that represent the state-of-the-art in the literature. In the first stage, we detect and crop around the optic nerve head then feed the cropped image as input for the second stage. The second stage network is trained using a weighted loss to produce the final segmentation. To further improve the detection in the first stage, we propose a new fine-tuning strategy by combining the cropping output of the first stage with the original training image to train a new detection network using different scales for the region proposal network anchors. We evaluate the method on Retinal Fundus Images for Glaucoma Analysis (REFUGE), Magrabi, and MESSIDOR datasets. We used the REFUGE training subset to train the models in the proposed method. Our method achieved 0.0430 mean absolute error in the vertical cup-to-disc ratio (MAE vCDR) on the REFUGE test set compared to 0.0414 obtained using complex and multiple ensemble networks methods. The models trained with the proposed method transfer well to datasets outside REFUGE, achieving a MAE vCDR of 0.0785 and 0.077 on MESSIDOR and Magrabi datasets, respectively, without being retrained. In terms of detection accuracy, the proposed new fine-tuning strategy improved the detection rate from 96.7% to 98.04% on MESSIDOR and from 93.6% to 100% on Magrabi datasets compared to the reported detection rates in the literature.

Download Full-text

Community structure detection in social networks based on dictionary learning

Science China Information Sciences ◽

10.1007/s11432-011-4319-3 ◽

2011 ◽

Vol 56 (7) ◽

pp. 1-12 ◽

Cited By ~ 5

Author(s):

ZhongYuan Zhang

Keyword(s):

Social Networks ◽

Community Structure ◽

Dictionary Learning ◽

Structure Detection

Download Full-text

On-device Prior Knowledge Incorporated Learning for Personalized Atrial Fibrillation Detection

ACM Transactions on Embedded Computing Systems ◽

10.1145/3476987 ◽

2021 ◽

Vol 20 (5s) ◽

pp. 1-25

Author(s):

Zhenge Jia ◽

Yiyu Shi ◽

Samir Saba ◽

Jingtong Hu

Keyword(s):

Atrial Fibrillation ◽

Prior Knowledge ◽

Domain Knowledge ◽

Fine Tuning ◽

Cardiac Monitoring ◽

Patient Specific ◽

Detection Accuracy ◽

Specific Patient ◽

Deep Model ◽

Tuning Strategy

Atrial Fibrillation (AF), one of the most prevalent arrhythmias, is an irregular heart-rate rhythm causing serious health problems such as stroke and heart failure. Deep learning based methods have been exploited to provide an end-to-end AF detection by automatically extracting features from Electrocardiogram (ECG) signal and achieve state-of-the-art results. However, the pre-trained models cannot adapt to each patient’s rhythm due to the high variability of rhythm characteristics among different patients. Furthermore, the deep models are prone to overfitting when fine-tuned on the limited ECG of the specific patient for personalization. In this work, we propose a prior knowledge incorporated learning method to effectively personalize the model for patient-specific AF detection and alleviate the overfitting problems. To be more specific, a prior-incorporated portion importance mechanism is proposed to enforce the network to learn to focus on the targeted portion of the ECG, following the cardiologists’ domain knowledge in recognizing AF. A prior-incorporated regularization mechanism is further devised to alleviate model overfitting during personalization by regularizing the fine-tuning process with feature priors on typical AF rhythms of the general population. The proposed personalization method embeds the well-defined prior knowledge in diagnosing AF rhythm into the personalization procedure, which improves the personalized deep model and eliminates the workload of manually adjusting parameters in conventional AF detection method. The prior knowledge incorporated personalization is feasibly and semi-automatically conducted on the edge, device of the cardiac monitoring system. We report an average AF detection accuracy of 95.3% of three deep models over patients, surpassing the pre-trained model by a large margin of 11.5% and the fine-tuning strategy by 8.6%.

Download Full-text

Community Structure Detection Using Firefly Algorithm

International Journal of Applied Metaheuristic Computing ◽

10.4018/ijamc.2018100103 ◽

2018 ◽

Vol 9 (4) ◽

pp. 52-70 ◽

Cited By ~ 5

Author(s):

Ameera Saleh Jaradat ◽

Safa'a Bani Hamad

Keyword(s):

Community Structure ◽

Community Detection ◽

Graph Partitioning ◽

Firefly Algorithm ◽

Real Life ◽

People Detection ◽

Continuous Growth ◽

Structure Detection ◽

Partitioning Problem ◽

And Function

This article describes how parallel to the continuous growth of the Internet, which allows people to share and collaborate more, social networks have become more attractive as a research topic in many different disciplines. Community structures are established upon interactions between people. Detection of these communities has become a popular topic in computer science. How to detect the communities is of great importance for understanding the organization and function of networks. Community detection is considered a variant of the graph partitioning problem which is NP-hard. In this article, the Firefly algorithm is used as an optimization algorithm to solve the community detection problem by maximizing the modularity measure. Firefly algorithm is a new Nature-inspired heuristic algorithm that proved its good performance in a variety of applications. Experimental results obtained from tests on real-life networks demonstrate that the authors' algorithm successfully detects the community structure.

Download Full-text

Scanning electron microscope fine tuning using four-bar piezoelectric actuated mechanism

Journal of Electrical Engineering ◽

10.1515/jee-2018-0003 ◽

2018 ◽

Vol 69 (1) ◽

pp. 24-31

Author(s):

Khaled S. Hatamleh ◽

Qais A. Khasawneh ◽

Adnan Al-Ghasem ◽

Mohammad A. Jaradat ◽

Laith Sawaqed ◽

...

Keyword(s):

Electron Microscope ◽

Scanning Electron Microscope ◽

Inverse Kinematic ◽

Fine Tuning ◽

Electron Microscopes ◽

Tuning Strategy ◽

Scanning Electron Microscopes ◽

Fine Tune ◽

Kinematic Solution ◽

Scanning Electron

Abstract Scanning Electron Microscopes are extensively used for accurate micro/nano images exploring. Several strategies have been proposed to fine tune those microscopes in the past few years. This work presents a new fine tuning strategy of a scanning electron microscope sample table using four bar piezoelectric actuated mechanisms. The introduced paper presents an algorithm to find all possible inverse kinematics solutions of the proposed mechanism. In addition, another algorithm is presented to search for the optimal inverse kinematic solution. Both algorithms are used simultaneously by means of a simulation study to fine tune a scanning electron microscope sample table through a pre-specified circular or linear path of motion. Results of the study shows that, proposed algorithms were able to minimize the power required to drive the piezoelectric actuated mechanism by a ratio of 97.5% for all simulated paths of motion when compared to general non-optimized solution.

Download Full-text

Beyond Network Pruning: a Joint Search-and-Training Approach

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2020/358 ◽

2020 ◽

Author(s):

Xiaotong Lu ◽

Han Huang ◽

Weisheng Dong ◽

Xin Li ◽

Guangming Shi

Keyword(s):

Random Perturbation ◽

Search Space ◽

Fine Tuning ◽

Superior Performance ◽

Network Pruning ◽

Training Approach ◽

Target Network ◽

Tuning Strategy ◽

Coarse To Fine ◽

And Training

Network pruning has been proposed as a remedy for alleviating the over-parameterization problem of deep neural networks. However, its value has been recently challenged especially from the perspective of neural architecture search (NAS). We challenge the conventional wisdom of pruning-after-training by proposing a joint search-and-training approach that directly learns a compact network from the scratch. By treating pruning as a search strategy, we present two new insights in this paper: 1) it is possible to expand the search space of networking pruning by associating each filter with a learnable weight; 2) joint search-and-training can be conducted iteratively to maximize the learning efficiency. More specifically, we propose a coarse-to-fine tuning strategy to iteratively sample and update compact sub-network to approximate the target network. The weights associated with network filters will be accordingly updated by joint search-and-training to reflect learned knowledge in NAS space. Moreover, we introduce strategies of random perturbation (inspired by Monte Carlo) and flexible thresholding (inspired by Reinforcement Learning) to adjust the weight and size of each layer. Extensive experiments on ResNet and VGGNet demonstrate the superior performance of our proposed method on popular datasets including CIFAR10, CIFAR100 and ImageNet.

Download Full-text