Search

In this paper, we present a virtualized resource allocation algorithm (vRAS), which is capable of dynamically predicting VM resource demands based on the real-time snapshot of server resource states. Furthermore, VMs experiencing the heavy resource utilization in the previous time period can be incentivized by obtaining more resources in the next time period, while trying to not aggravate other VMs’ application bandwidth running on the same host. We compared our method to other schemes to verify its effectiveness.

It is becoming increasingly necessary to improve people's daily living environments for their quality of life. Indoor air quality is also important, as most people spend a lot of time indoors. It is known that a significant proportion of indoor pollution is caused by outdoor pollution. However, the size of the outdoor influence may depend on the characteristics of indoor space. In this paper, we collected air and environmental data for 21 spaces and analyzed how much they relate to external environmental pollution. The result shows that the influence on the external environment varies greatly depending on the spaces.

Recently, virtualization is becoming the critical issue in the cloud computing due to its advantages of resource utilization and consolidation. In order to efficiently use virtualization services, several issues should be taken into account, including data reliability, security, and performance. In particular, a high write bandwidth on the virtual machine must be guaranteed to provide fast responsiveness to users. In this study, we implemented a way of visualizing comparison results between the block write pattern of KVM-based virtual machine and that of the real machine. Our final objective is to propose an optimized virtualization environment that enables to accelerate the disk write bandwidth.

Performance enhancement of thermal desalination processes requires the excellent water separation capabilities in demisters. However, in high-speed gas flow, the re-entrainment of captured water from the surfaces to the gas flow can considerably decrease the water collection capabilities and the corresponding separation efficiency. Herein, we report fabrication of micro-structured polymer surfaces with excellent water capturing properties in low- and high-speed gas flow conditions by using a facile molding process. Inspired by the surfaces of bio-species, the fabricated surfaces possess vertically-aligned micro-scale cone arrays and sets of microchannels to significantly enhance the capillary pressure. As a result, those hybrid-structured surfaces exhibit up to 2.4 and 4.7 times higher excellent water collection capabilities than control planar at low- and high-speed flow conditions, respectively. In addition, the mist eliminator with the hybrid surfaces performs 1.8 times higher water collection behavior than the control mist eliminator with bare surfaces. The results show the promise of developing the surfaces with engineered structures for significantly enhancing water collection without changing the shapes of flow passages in target objects.

The interaction between wireless sensors such as Internet of Things (IoT) and Cloud is a new paradigm of communication virtualization to overcome resource and efficiency restriction. Cloud computing provides unlimited platform, resources, services and also covers almost every area of computing. On the other hand, Wireless Sensor Networks (WSN) has gained attention for their potential supports and attractive solutions such as IoT, environment monitoring, healthcare, military, critical infrastructure monitoring, home and industrial automation, transportation, business, etc. Besides, our virtual groups and social networks are in main role of information sharing. However, this sensor network lacks resource, storage capacity and computational power along with extensibility, fault-tolerance, reliability and openness. These data are not available to community groups or cloud environment for general purpose research or utilization yet. If we reduce the gap between real and virtual world by adding this WSN driven data to cloud environment and virtual communities, then it can gain a remarkable attention from all over, along with giving us the benefit in various sectors. We have proposed a Pub/Sub-based sensor virtualization framework Cloud environment. This integration provides resource, service, and storage with sensor driven data to the community. We have virtualized physical sensors as virtual sensors on cloud computing, while this middleware and virtual sensors are provisioned automatically to end users whenever they required. Our architecture provides service to end users without being concerned about its implementation details. Furthermore, we have proposed an efficient content-based event matching algorithm to analyze subscriptions and to publish proper contents in a cost-effective manner. We have evaluated our algorithm which shows better performance while comparing to that of previously proposed algorithms.

In Signage network systems, cooperative communication system is effective when a direct link between two nodes doesn't exist or a condition of the link is poor by allocating another node between the two nodes to relay signals. As a relay node, a half-duplex relay is widely used for ease of implementation. The half-duplex cooperative communication system using one half-duplex relay node has problems for loss of spectral efficiency and capacity. To solve these problems, a two-path relay cooperative communication system using two half-duplex relays has been actively studied. Although the two-path relay cooperative communication system solves the loss problems by transmitting signals to relay nodes alternately, the simultaneous transmission of the source node and one of the relay nodes causes inter-relay interference (IRI) at the other relay nodes. This paper proposes new two-path relay cooperative transmission method which cancels the IRI at the relay nodes and obtains the spatial diversity gain by using two antennas at the relay nodes. Unlike the conventional scheme which cancels the IRI at the destination node, the interferences aren't accumulated and aren't propagated to the destination node when the distance between the relay nodes decreases in the proposed method. Therefore, the proposed method can improve the reliability of multi-hop based signage network by canceling interference at the relay nodes.

Together with the rapid development of IT technology, cloud computing has been considered as the next generation's computing infrastructure. One of the essential components of cloud computing is the virtual machine technology that enables to reduce the data center cost with better resource utilization. Especially, VDI (Virtual Desktop Infrastructure) is receiving explosive attentions from IT markets due to its advantages of easier software management, greater data protection, and lower expenses. However, sharing the hosting server’s resources between VMs is a tradeoff in VDI because it can cause significant I/O degradation. In this paper, we present a VM-level cache, called virtCache, that is combined with a light-weight, real-time monitoring module to check the resource utilization of VM and hosting server in a transparent way. Our performance measurement shows that virtCache not only generates better I/O bandwidth by using the efficient data access prediction but it also provides easier resource management by offering the real-time resource states.

Flash memory storage such as SSDs (Solid State disks) have been gaining popularity due to its low energy consumption and durability in embedded systems and laptops. With the fast technical improvement, Solid State Disks (SSDs) are becoming an important part of the computer storage hierarchy to significantly improve performance and energy efficiency. However, due to its relatively high price and low capacity, a major system research issue to address is on how to make SSDs play their most effective roles as a high-performance storage system in cost- and performance-effective ways. In this paper, we describe a NAS prototype that eliminates most software overheads and makes Solid State Disks a high-performance storage system in cost- and performance-effective ways. NAS integrates a network adapter into SSDs, so the SSDs remove the random access time, Reduce administrative overhead while delivering scalable, reliable data storage. NAS can also give support block based I/O rather than traditional NAS system which supports only file I/O protocol such as NFS and CIFS. Our scale-out NAS solutions can boost capacity and performance while enabling flexible provisioning, no disruptive operations, easy scalability, and virtualization. As the storage and processing requirements of the file server continued to increase data security and integrity became difficult to

Healthcare is the diagnosis, treatment, and prevention of disease, illness, injury, and other physical and mental impairments in human beings. Healthcare is delivered by practitioners in allied health, dentistry, midwifery-obstetrics, medicine, nursing, optometry, pharmacy, psychology and other care providers. In healthcare service to provide better performance to identify some diseases like blood pressure, skin cancer, diabetes etc. with the sensor devices those are connected with home server by using wireless sensor or wired network policies. The size of data sets being collected and analyzed in the industry for healthcare business intelligence is growing rapidly. In healthcare service case we have to concern about massive data services. To store and process huge amount of unstructured data by using traditional database system is so difficult. To alleviate this drawback we can use Hadoop architecture that has functionality to store and process huge amount of unstructured data. Hadoop Distributed file system (HDFS) can store and the Hadoop MapReduce framework process huge amount of unstructured data that enables easy development of scalable parallel applications. This paper's main motivation is to ensure better data transmission, data reliability and massive data processing with High Availability (HA) based network storage solution. So, in this paper we proposed MapReduce Agent (MRA) to process Big-Data and also proposed iSCSI Protocol adapted Network Attached Storage (NAS) system for healthcare service.

A cyclic loading test was performed to investigate the seismic performance of exterior beam-column joints of concrete-encased-and-filled steel tubular (CEFT) columns. Two specimens with steel beams and two specimens with precast concrete (PC) beams were tested under cyclic loading. The dimensions of the column cross section were 670×670 mm, which was a two-thirds-scale model of the prototype column. The test parameters for the steel beam and the PC beam were the beam depth (488 and 588 mm) and the flexural rebar ratio (1.1% and 1.5%), respectively. In the steel beam-CEFT column joints, continuity plates were used, while in the PC beam-CEFT column joints, couplers were used for the rebar connection. The steel beam-column connections failed due to early fracture of the continuity plate, and the PC beam-column connections failed due to rebar buckling and concrete spalling after beam yielding. The strength of the steel beam-column connections was evaluated using an existing design method, and the sei...

As the virtual machine technology is becoming the essential component in the cloud environment, VDI is receiving explosive attentions from IT market due to its advantages of easier software management, greater data protection, and lower expenses. However, I/O overhead is the critical obstacle to achieve high system performance in VDI. Reducing I/O overhead in the virtualization environment is not an easy task, because it requires scrutinizing multiple software layers of guest-to-hypervisor and also hypervisor-to-host. In this paper, we propose multilayered cache implementation, called MultiCache, which combines the guest-level I/O optimization with the hypervisor-level I/O optimization. The main objective of the guest-level optimization is to mitigate the I/O latency between the back end, shared storage, and the guest VM by utilizing history logs of I/O activities in VM. On the other hand, the hypervisor-level I/O optimization was implemented to minimize the latency caused by the “passing I/O path to the host” and the “contenting physical I/O device among VMs” on the same host server. We executed the performance measurement of MultiCache using the postmark benchmark to verify its effectiveness.

An experimental study was performed to investigate the axial-flexural load-carrying capacity of concrete-filled steel tube columns encased with thin precast concrete (PC). Six eccentrically loaded columns and one concentrically loaded column were tested. To prevent the premature failure of the concrete encasement, various reinforcement details such as studs, steel fiber, welded wire mesh, and cross ties were used. The maximum axial loads of the specimens agreed with the strengths predicted by current design codes, although in some specimens, the load-carrying capacity decreased immediately after the peak strength owing to early spalling of the concrete encasement. On the basis of the test results, the use of fiber-reinforced concrete is recommended to increase the ductility of columns by restraining the spalling of the concrete encasement.

In large area scanning with a micro-electron-column, the operating condition for the best resolution was investigated in factors of working distance and field of view. The resolution of a test sample was dependent on electron beam energy and scanning field size. The best resolution with single deflector was obtained at 300 V and 30 mm in the electron emitting tip voltage and a working distance, respectively. The scanning area at that condition was , linearly increased with the working distance. Double deflector was employed for larger scanning size without increasing working distance, but showed only 1.7 times larger than that of single deflector, and the resolution was inverse proportional to the scanning size.

The exponential growth of data first presented challenges to cutting-edge businesses such as Goggle, Yahoo, Amazon, Microsoft, Facebook, and Twitter. Data volumes to be processed by cloud applications are growing much faster than computing power. This growth demands new strategies for processing and analyzing information. Hadoop MapReduce has become a powerful computation model that addresses those problems. MapReduce is a programming model that enables easy development of scalable parallel applications to process vast amounts of data on large clusters. Through a simple interface with two functions, map and reduce, this model facilitates parallel implementation of many real world tasks such as data processing for search engines and machine learning. Earlier versions of Hadoop MapReduce had several performance problems like connection between map to reduce task, data overload and slow processing. In this paper, we propose a modified MapReduce architecture – MapReduce Agent (MRA) – that resolves those performance problems. MRA can reduce completion time, improve system utilization, and give better performance. MRA employs multi-connection which resolves error recovery with a Q-chained load balancing system. In this paper, we also discuss various applications and implementations of the MapReduce programming model in cloud environments.

In large internet enterprise and data management system, Hadoop MapReduce is a popular framework. For data intensive batch jobs, MapReduce provided its impact. To build consistent, hi-availability (HA) and scalable data management system to serve peta bytes of data for the massive users, are the main focused objects. MapReduce is a programming model that enables easy development of scalable parallel applications to process vast amount of data on large cluster. Through a simple interface with two functions map and reduce, this model facilities parallel implementation of real world tasks such as data processing for search engine and machine learning. Earlier version of Hadoop MapReduce has several performance problems like connection between Map to Reduce task, data overload and time consumption. In this paper, we proposed a modified MapReduce architecture MRA (MapReduce Agent) which is a fusion of iSCSI protocol and the downloaded reference code of Hadoop*. Our developed MRA can reduce completion time, improve system utilization and give better performance.

Cloud computing and virtual communities have been changing the face of communication. Cloud computing covers almost every services and provides most of data services. On the other hand, wireless sensor networks (WSN) gained attention for their potential supports such as environment monitoring, bio-median acknowledgment, healthcare monitoring, industrial automation etc. But this sensor network is not available to community groups or cloud environment for general purpose research or utilization yet. If we can reduce the gap between real and virtual world by adding this WSN produced data to cloud environment and virtual communities to alert the general researchers about environmental situations, it can gain a remarkable attention all over and we can be benefited in all our ability. To do this we need to make collaboration between sensor networks and the cloud environment. Here we have proposed a pub/sub based middleware service for WSN and Cloud platform collaboration which will provide resource, service, and storage with sensor driven data to the community. We proposed a content based event matching algorithm to analyze subscriptions and match proper content easily to convey WSN driven data to subscribers. The validation shows this content matching algorithm works efficiently compared with previously proposed algorithms to integrate WSN to cloud environment to lower the gap between real and virtual world.

This paper focuses on I/O optimizations of N-hybrid (New-Form of hybrid), which provides a hybrid file system space constructed on SSD and HDD. Although the promising potentials of SSD, such as the absence of mechanical moving overhead and high random I/O throughput, have drawn a lot of attentions from IT enterprises, its high ratio of cost/capacity makes it less desirable to build a large-scale data storage subsystem composed of only SSDs. In this paper, we present N-hybrid that attempts to integrate the strengths of SSD and HDD, to offer a single, large hybrid file system space. Several experiments were conducted to verify the performance of N-hybrid.

In this paper, we proposed an error recovery module for iSCSI protocol based NAS (Network Attached Storage) system in wireless network environment, which ensures reliability and efficiency data transmission.

The continued growth of both mobile appliances and wireless Internet technologies is bringing a new telecommunication revolution and it has extended the demand of various services with mobile appliances. However, in wireless environment the availability of mass storage is limited due to their limited size and weight. Although the problem can be alleviated by iSCSI (Internet Small Computer Interface) based Network Storage System, it has drawbacks in high availability and performance. To address this issue, this paper presents an architecture to adapt iSCSI protocol with traditional NAS (Network Attached Storage) cluster system with an error recovery method. To realize the access to a NAS storage system, our experiments suggest the optimal values for various parameters. The test cases show that the best values of the parameters are not always the default values specified in the iSCSI standard.

In this paper we have proposed a parameter-evaluated iSCSI protocol that automates the multi-agent coordination on the resource-constrained devices for the healthcare service. The coordination between the resource control devices and automated agents are maintained by a two-way handshaking mode iSCSI with some evaluated parameters.

In this paper, we focus on iSCSI protocol adaptation on NAS technology with mobile appliances, which are ensuring the best performance and high availability in wireless network environment.

In Mobile appliance, users have a limited amount of storage availability to them due to their limited size and weight. To relieve problem we developed iSCSI remote storage system, which is an excellent solution for smart home automation too. User can store or access their valuable data to the home server from anywhere, anytime and also get facility to use mass storage space. The iSCSI protocol has emerged as a transport for carrying SCSI block-level access protocol over the ubiquitous TCP protocol. It enables a client's block-level access to the data on remote storage over an existing IP infrastructure. However, the performance of the iSCSI based remote storage system for mobile appliances were sharply dropped in wireless networks; especially when we adapt default parameters value suggested in standard for our remote storage system in wireless networks. This paper focuses our experiments, which are performed to investigate the best performance values of iSCSI parameters for iSCSI-based remote storage system, are taken out in CDMA networks in order to realize the access to a remote storage system anytime and anywhere. And after the experiment, we suggest the optimal value of parameters. The experiment results from several test cases show us the best values are not the default values specified in the iSCSI standard.

Basic components of micro-electron column were assembled with optical alignment and laser bonding. Source and Einzel lenses were aligned with the diffraction method of laser beam and bonded simultaneously by laser welding.

Hemobilia, in patients with the diagnosis of polyarteritis nodosa, is rare at clinical presentation and has a grave prognosis. We describe a case of massive hemobilia, due to aneurysmal rupture, in a patient with polyarteritis nodosa. A 39-year-old man was admitted to the hospital with upper abdominal pain. The patient had a history of partial small bowel resection, for intestinal infarction, about 5 years prior to this presentation. Abdominal computed tomography demonstrated multiple high attenuation areas in the bile duct and gallbladder. Hemobilia with blood seepage was visualized on endoscopic retrograde cholangiopancreatography; this bleeding stopped spontaneously. The following day, the patient developed a massive gastrointestinal bleed with resultant hypovolemic shock. Emergent hepatic angiogram revealed multiple microaneurysms; a communication was identified between a branch of the left hepatic artery and the bile duct. Hepatic arterial embolization was successfully performed. The underlying disease, polyarteritis nodosa, was managed with prednisolone and cyclophosphamide.

The continued growth of both mobile appliance and wireless Internet technologies is bringing a new telecommunication revolution and has extended the demand of various services with mobile appliance. However, during working with wireless access devices, users have a limited amount of storage available to them due to their limited size and weight. To relieve this problem iSCSI (Internet Small Computer Interface) remote storage system would be one solution but the question is high availability and performance. In this paper, we propose a new approach of Multi-Connection in one session based remote storage system for mobile appliance with error recovery method that avoids drastic reduction of transmission rate from TCP congestion control in wireless environment as compared to traditional iSCSI.

Data replication is an important issue in computational grid environments where many data-intensive scientific applications require high-performance data accesses to remote storages. However, providing the consistent data replication service for computational grid environments is not an easy task because it requires a sophisticated technique to minimize I/O and communication latencies incurred during data copy steps to the remote clients. We have developed a replication architecture that is combined with data compression to reduce I/O and network overheads, with the help of data base. In this paper we describe the design and implementation of our replication architecture and present performance results on Linux clusters.

Driven by the market growth of mobile phones with camera, production of image sensor devices has increased dramatically in recent years. From 2004 an increasing number of these mobile phones contain megapixel cameras. The packaging of an image sensor in a camera module presents several unique engineering challenges. Megapixel camera module assembly poses further challenges due to more stringent particle control criteria. For particle control, special attention has to be given on facilities control, equipment and material selection, process flow, discipline among line personnel and continuous particle reduction effort. Other material, process and equipment selection criteria for megapixel module are also discussed. Test for megapixel camera module also has its own challenges. This paper discusses these challenges and methods to meet them.

Many large-scale scientific experiments and simulations generate very large amounts of data (on the order of terabytes to petabytes), spanning thousands of files and data sets. We have developed a software system, called Grid Environment-based Data Management System (GEDAS), that provides a high-level, user-friendly interface, while maintaining the consistent data replicas among the grid communities. We describe the design and implementation of GEDAS and present performance results on Linux cluster.

Production of image sensor devices has increased dramatically in recent years due to wide scale adoption of camera modules in mobile phones. It is expected that over 150M camera modules will be shipped in mobile phones in 2004. The packaging of an image sensor in a camera module presents several unique engineering challenges. Materials selection, assembly process, optical test, and facilities control are all areas where technology is rapidly developing. This paper focuses on current challenges, and highlights several areas where advances in research and development are needed.

Concurrent accesses to a file frequently occur in a distributed computing environment where a few number of network-attached servers are designated as a data storage pool and the clients are physically connected to the servers via network, like GigaEthernet or Fibre Channel. In such a distributed computing environment, one of the major issues affecting in achieving substantial I/O performance and scalability is to build an efficient locking protocol. We present a distributed locking protocol that enables multiple client nodes to simultaneously write their data to distinct data portions of a file, while providing the consistent view of client cached data, and conclude with an evaluation of the performance of our locking protocol on a Linux cluster.

In this study, the beam-to column connections of concrete-encased-and-filled steel tube columns were tested under cyclic loading. Two specimens using steel beams and two specimens using precast concrete beams were tested. The dimension of the column cross section was 670mm×670mm. The beam depths were 488mm and 588mm for the steel beams and 700mm for the precast concrete beams. The longitudinal bar ratios of the pr ecast concrete beams were 1.1% and 1.5%. For the connections to the steel beams, continuity plates were used in the tube co lumns. For the connections to the PC beams, couplers were used fo r beam re-bar connections. The test results showed that except for a specimen, deformation capacities of the specimens were greater than 4% rotation angle, which is the requirement for the Special Moment Frame. Particularly, specimens using precast concrete beam showed excellent performances in the strength, deformation, and energy dissipation. Keywords - Beam-column connection, Concrete-encased-and-filled steel tubular column, Precast concrete beam, Steel beam, Cyclic load testNote.-Discussion open until August 31, 2014. This manuscript for this paper was submitted for review and possible publication on August 18, 2013; revised January 13, 2014; approved on February 4, 2014.Copyright ⓒ 2014 by Korean Society of Steel Construction

In this paper, concrete-filled steel tubular columns encased with precast reinforced concrete were studied. Four eccentrically loaded columns and a concentrically loaded column were tested to investigate the axial load-carrying capacity. The test parameters were the use of fiber reinforcement for cover concrete, eccentricity, column length, and lateral reinforcement. The maximum axial loads of the specimens agreed with the nominal strengths predicted by KBC 2009. However, in some specimens, the load carrying capacity quickly decreased after the peak strength due to spalling of the cover concrete.

Background and Objectives:The local delivery of drugs to the arterial wall represents a strategy for the treatment of fibroproliferative vascular disease. Paclitaxel has been shown to inhibit vascular smooth muscle cell proliferation and migration, which contribute to neointimal formation. This study tested whether the perivascular delivery of paclitaxel can prevent neointimal formation in a rat carotid artery injury model. Materials and Methods:The ability of locallyadministered paclitaxel to prevent the neointimal hyperplastic response was tested by incorporating 10 μg paclitaxel into 40% F-127 pluronic gel, which was then applied to the adventitial surface of the rat carotid artery immediately following balloon injury. Fourteen days after angioplasty, the neointimal growth was compared between paclitaxel(n=12) and pluronic gel only treated (control group, n=11) rats. Results:The paclitaxel-treated group showed significant neointimal formation reductions compared to the control group (0.10±0.05 versus 0.21±0.05 mm , p