다중혈관 관상동맥 환자에서 y-문합을 이용하여 양쪽 내흉동맥만을 사용한 우회술의 조기 성적

[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

In the real world, a realistic setting for computer vision or multimedia recognition problems is that we have some classes containing lots of training data and many classes contain a small amount of training data. Therefore, how to use frequent classes to help learning rare classes for which it is harder to collect the training data is an open question. Learning with Shared Information is an emerging topic in machine learning, computer vision and multimedia analysis. There are different level of components that can be shared during concept modeling and machine learning stages, such as sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, etc. Regarding the specific methods, multi-task learning, transfer learning and deep learning can be seen as using different strategies to share information. These learning with shared information methods are very effective in solving real-world large-scale problems. This special issue aims at gathering the recent advances in learning with shared information methods and their applications in computer vision and multimedia analysis. Both state-of-the-art works, as well as literature reviews, are welcome for submission. Papers addressing interesting real-world computer vision and multimedia applications are especially encouraged. Topics of interest include, but are not limited to:  • Multi-task learning or transfer learning for large-scale computer vision and multimedia analysis • Deep learning for large-scale computer vision and multimedia analysis • Multi-modal approach for large-scale computer vision and multimedia analysis • Different sharing strategies, e.g., sharing generic object parts, sharing attributes, sharing transformations, sharing regularization parameters and sharing training examples, • Real-world computer vision and multimedia applications based on learning with shared information, e.g., event detection, object recognition, object detection, action recognition, human head pose estimation, object tracking, location-based services, semantic indexing. • New datasets and metrics to evaluate the benefit of the proposed sharing ability for the specific computer vision or multimedia problem. • Survey papers regarding the topic of learning with shared information.  Authors who are unsure whether their planned submission is in scope may contact the guest editors prior to the submission deadline with an abstract, in order to receive feedback.

IEEE transactions on pattern analysis and machine intelligence

A review on neural networks with random weights

Healthcare is undergoing a rapid transformation from traditional hospital and specialist focused approach to a distributed patient-centric approach. Advances in several technologies fuel this rapid transformation of healthcare vertical. Among various technologies, communication technologies have enabled to deliver personalized and remote healthcare services. At present, healthcare widely uses the existing 4G network and other communication technologies for smart healthcare applications and are continually evolving to accommodate the needs of future intelligent healthcare applications. As the smart healthcare market expands the number of applications connecting to the network will generate data that will vary in size and formats. This will place complex demands on the network in terms of bandwidth, data rate, and latency, among other factors. As this smart healthcare market matures, the connectivity needs for a large number of devices and machines with sensor-based applications in hospitals will necessitate the need to implement Massive-Machine Type Communication. Further use cases such as remote surgeries and Tactile Internet will spur the need for Ultra Reliability and Low Latency Communications or Critical Machine Type Communication. The existing communication technologies are unable to fulfill the complex and dynamic need that is put on the communication networks by the diverse smart healthcare applications. Therefore, the emerging 5G network is expected to support smart healthcare applications, which can fulfill most of the requirements such as ultra-low latency, high bandwidth, ultra-high reliability, high density, and high energy efficiency. The future smart healthcare networks are expected to be a combination of the 5G and IoT devices which are expected to increase cellular coverage, network performance and address security-related concerns. This paper provides a state-of-the-art review of the 5G and IoT enabled smart healthcare, Taxonomy, research trends, challenges, and future research directions.

/pdf/5g-based-smart-healthcare-network-architecture-taxonomy-2vk57xx6dg.pdf

5G-Based Smart Healthcare Network: Architecture, Taxonomy, Challenges and Future Research Directions

Modelling and forecasting of COVID-19 spread using wavelet-coupled random vector functional link networks

While designing medical diagnosis software, disease prediction is said to be one of the captious tasks The techniques of machine learning have been successfully employed in assorted applications including medical diagnosis By developing classifier system, machine learning algorithm may immensely help to solve the health-related issues which can assist the physicians to predict and diagnose diseases at an early stage We can ameliorate the speed, performance, reliability, and accuracy of diagnosing on the current system for a specific disease by using the machine learning classification algorithms This paper mainly targets the review of diabetes disease detection using the techniques of machine learning Further, PIMA Indian Diabetic dataset is employed in machine learning techniques like artificial neural networks, decision tree, random forest, naive Bayes, k-nearest neighbors, support vector machines, and logistic regression and discussed the results with their pros and cons

A Survey on Medical Diagnosis of Diabetes Using Machine Learning Techniques

In real-world binary class datasets, the total number of samples may not be the same in both the classes, i.e. size of the majority class is much larger than minority class which is called as imbalance problem. In various classification problems, the main interest is to correctly classify the samples belonging to the minority class. Since support vector machine (SVM) and twin support vector machine (TWSVM) obtain the resultant classifier by giving same importance to all the training samples, it results in a biased classifier towards the majority class in imbalanced datasets. In this paper, by considering the fuzzy membership value for each sample, we have proposed an efficient approach, entropy-based fuzzy twin support vector machine for class imbalanced datasets (EFTWSVM-CIL) where fuzzy membership values are assigned based on the entropy values of samples. Here, we give more importance to the minority class by assigning relatively larger fuzzy memberships to the minority class samples. Further, it solves a pair of smaller-size quadratic programming problems (QPPs) rather than a large one as in the case of SVM. Experiments are performed on various real-world imbalanced datasets, and results of our proposed EFTWSVM-CIL are compared with twin support vector machine (TWSVM), fuzzy twin support vector machine (FTWSVM) and entropy-based fuzzy SVM (EFSVM) for imbalanced datasets.

A fuzzy twin support vector machine based on information entropy for class imbalance learning

In real-world binary classification problems, the entirety of samples belonging to each class varies. These types of problems where the majority class is notably bigger than the minority class can be called as class imbalance learning (CIL) problem. Due to the CIL problem, model performance may degrade. This paper presents a new support vector machine (SVM) model based on density weight for binary CIL (DSVM-CIL) problem. Additionally, an improved 2-norm-based density-weighted least squares SVM for binary CIL (IDLSSVM-CIL) is also proposed to increase the training speed of DSVM-CIL. In IDLSSVM-CIL, the least squares solution is obtained by considering 2-norm of slack variables and solving the primal problem of DSVM-CIL with equality constraints instead of inequality constraints. The basic ideas behind the algorithms are that the training datapoints are given weights during the training phase based on their class distributions. The weights are generated by using a density-weighted technique (Cha et al. in Expert Syst Appl 41(7):3343–3350, 2014) to reduce the effects of CIL. Experimental analyses are performed on some interesting imbalanced artificial and real-world datasets, and their performances are measured using the area under the curve and geometric mean (G-mean). The results are compared with SVM, least squares SVM, fuzzy SVM, improved fuzzy least squares SVM, affinity and class probability-based fuzzy SVM and entropy-based fuzzy least squares SVM. Similar or better generalization results indicate the efficacy and applicability of the proposed algorithms.

Deepak Gupta

Papers

Modelling and forecasting of COVID-19 spread using wavelet-coupled random vector functional link networks

A Survey on Medical Diagnosis of Diabetes Using Machine Learning Techniques

A fuzzy twin support vector machine based on information entropy for class imbalance learning

Density-weighted support vector machines for binary class imbalance learning

1-Norm extreme learning machine for regression and multiclass classification using Newton method