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

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

Data Mining - Concepts and Techniques.

We will review some of the major results in random graphs and some of the more challenging open problems. We will cover algorithmic and structural questions. We will touch on newer models, including those related to the WWW.

Random graphs

Data gathering is a common but critical operation in many applications of wireless sensor networks. Innovative techniques that improve energy efficiency to prolong the network lifetime are highly required. Clustering is an effective topology control approach in wireless sensor networks, which can increase network scalability and lifetime. In this paper, we propose a novel clustering schema EECS for wireless sensor networks, which better suits the periodical data gathering applications. Our approach elects cluster heads with more residual energy through local radio communication while achieving well cluster head distribution; further more it introduces a novel method to balance the load among the cluster heads. Simulation results show that EECS outperforms LEACH significantly with prolonging the network lifetime over 35%.

/pdf/eecs-an-energy-efficient-clustering-scheme-in-wireless-8yhh1ly93k.pdf

EECS: an energy efficient clustering scheme in wireless sensor networks

Clustering provides an effective way for prolonging the lifetime of a wireless sensor network. Current clustering algorithms usually utilize two techniques, selecting cluster heads with more residual energy and rotating cluster heads periodically, to distribute the energy consumption among nodes in each cluster and extend the network lifetime. However, they rarely consider the hot spots problem in multihop wireless sensor networks. When cluster heads cooperate with each other to forward their data to the base station, the cluster heads closer to the base station are burdened with heavy relay traffic and tend to die early, leaving areas of the network uncovered and causing network partition. To address the problem, we propose an energy-efficient unequal clustering (EEUC) mechanism for periodical data gathering in wireless sensor networks. It partitions the nodes into clusters of unequal size, and clusters closer to the base station have smaller sizes than those farther away from the base station. Thus cluster heads closer to the base station can preserve some energy for the inter-cluster data forwarding. We also propose an energy-aware multihop routing protocol for the inter-cluster communication. Simulation results show that our unequal clustering mechanism balances the energy consumption well among all sensor nodes and achieves an obvious improvement on the network lifetime

/pdf/an-energy-efficient-unequal-clustering-mechanism-for-13gxubphmm.pdf

An energy-efficient unequal clustering mechanism for wireless sensor networks

In this paper, we investigate the theoretical aspects of the nonuniform node distribution strategy used to mitigate the energy hole problem in wireless sensor networks (WSNs). We conclude that in a circular multihop sensor network (modeled as concentric coronas) with nonuniform node distribution and constant data reporting, the unbalanced energy depletion among all the nodes in the network is unavoidable. Even if the nodes in the inner coronas of the network have used up their energy simultaneously, the ones in the outermost corona may still have unused energy. This is due to the intrinsic many-to-one traffic pattern of WSNs. Nevertheless, nearly balanced energy depletion in the network is possible if the number of nodes increases in geometric progression from the outer coronas to the inner ones except the outermost one. Based on the analysis, we propose a novel nonuniform node distribution strategy to achieve nearly balanced energy depletion in the network. We regulate the number of nodes in each corona and derive the ratio between the node densities in the adjacent (i + 1)th and ith coronas by the strategy. Finally, we propose (q-switch routing, a distributed shortest path routing algorithm tailored for the proposed nonuniform node distribution strategy. Extensive simulations have been performed to validate the analysis.

Avoiding Energy Holes in Wireless Sensor Networks with Nonuniform Node Distribution

Clustering provides an effective method for prolonging the lifetime of a wireless sensor network. Current clustering algorithms usually utilize two techniques; selecting cluster heads with more residual energy, and rotating cluster heads periodically to distribute the energy consumption among nodes in each cluster and extend the network lifetime. However, they rarely consider the hot spot problem in multihop sensor networks. When cluster heads cooperate with each other to forward their data to the base station, the cluster heads closer to the base station are burdened with heavier relay traffic and tend to die much faster, leaving areas of the network uncovered and causing network partitions. To mitigate the hot spot problem, we propose an Unequal Cluster-based Routing (UCR) protocol. It groups the nodes into clusters of unequal sizes. Cluster heads closer to the base station have smaller cluster sizes than those farther from the base station, thus they can preserve some energy for the inter-cluster data forwarding. A greedy geographic and energy-aware routing protocol is designed for the inter-cluster communication, which considers the tradeoff between the energy cost of relay paths and the residual energy of relay nodes. Simulation results show that UCR mitigates the hot spot problem and achieves an obvious improvement on the network lifetime.

/pdf/an-unequal-cluster-based-routing-protocol-in-wireless-sensor-3te92fur7z.pdf

An unequal cluster-based routing protocol in wireless sensor networks

Industrial Internet of Things (IIoT) plays an indispensable role for Industry 4.0, where people are committed to implement a general, scalable, and secure IIoT system to be adopted across various industries. However, existing IIoT systems are vulnerable to single point of failure and malicious attacks, which cannot provide stable services. Due to the resilience and security promise of blockchain, the idea of combining blockchain and Internet of Things (IoT) gains considerable interest. However, blockchains are power-intensive and low-throughput, which are not suitable for power-constrained IoT devices. To tackle these challenges, we present a blockchain system with credit-based consensus mechanism for IIoT. We propose a credit-based proof-of-work (PoW) mechanism for IoT devices, which can guarantee system security and transaction efficiency simultaneously. In order to protect sensitive data confidentiality, we design a data authority management method to regulate the access to sensor data. In addition, our system is built based on directed acyclic graph -structured blockchains, which is more efficient than the Satoshi-style blockchain in performance. We implement the system on Raspberry Pi, and conduct a case study for the smart factory. Extensive evaluation and analysis results demonstrate that credit-based PoW mechanism and data access control are secure and efficient in IIoT.

Guihai Chen

Papers

EECS: an energy efficient clustering scheme in wireless sensor networks

An energy-efficient unequal clustering mechanism for wireless sensor networks

Avoiding Energy Holes in Wireless Sensor Networks with Nonuniform Node Distribution

An unequal cluster-based routing protocol in wireless sensor networks

Towards Secure Industrial IoT: Blockchain System With Credit-Based Consensus Mechanism