In recent years, an evolutionary change occurred in the digital world when various social networking sites became popular. This led to a big increase of users who share their activities in digital form. A huge amount of digital information has become available, providing researchers with a unique insight into the behavior and activities of entire population. The use of Geo-tagged social media data became an emerging trend to represent user actions and behaviour at specific geographical locations. However, the inaccuracies of Geo-tagged data from social media often limits the utility of this data source in micro scale analysis (at the street or place of interest level (POI)). Our study supports how social media data could be matched accurately with specific physical locations. More specifically, our investigation includes Geo-tweet data and image data from flickr to map accurately physical location using machine leaning and deep learning techniques. In this paper, a preliminary discussion of this work is provided, using Geo-tagged data from Twitter and Open StreetMap in cities such as San Francisco and London as well as for image mapping using Flickr data in cities such as San Francisco and Kyoto.

Extending input/output (I/O) bus networks over wireless Ethernet is expected to provide an effective way of achieving communication between multiple hosts and I/O devices. However, because connections on wireless Ethernet are lossy and unreliable, retransmission of I/O packets increases transmission latency that exceeds the limits of the I/O bus protocol. In this paper, we propose an Ethernet transport mechanism that adopts rateless codes to provide reliable transmission without having to retransmit packets. We further devised a queuing model to set the operating parameters of rateless codes to bound the probability of end-to-end latency that exceeds the defined limit value. Our results obtained through simulations and an FPGA implementation show that the proposed method decreased the transmission latency of I/O packets and enabled it to meet the requirements of the I/O bus protocol.

Input/output (I/O) devices such as a graphics processing unit and a solid-state drive are inserted into I/O slots of a host in data center platforms. With this sort of configuration the I/O devices are used exclusively by the host with resultant inefficient resource usage. In addition, the maximum number of I/O devices that can be assigned to each host is limited by the number of its I/O slots. This paper proposes a method to solve the resource usage inefficiency and assignment limitation by disaggregating I/O devices from hosts. An I/O device accommodated in a device pool is interconnected with multiple hosts by a standard Ethernet and can be flexibly assigned to one of them. Introducing assignment flexibility of I/O devices among hosts improves the resource usage efficiency and enables as many I/O devices as desired being assigned to each host. The authors further propose a method that enables an I/O device to be simultaneously shared among multiple hosts and multiple I/O packets to be aggregated into an Ethernet frame to suppress the performance overhead of the device disaggregation. Evaluation results showed that I/O devices that are compliant to PCI Express are shared with the overhead up to 27 percent.

Presents a conference poster that covers the following topics: bridge chip; PCIe switch; Ethernet; seamless disaggregated computer; and data center.

With the spread of smartphones and machine-to-machine devices that communicate via cellular networks, mobility and communication characteristics in cellular networks have become diverse. However, because existing cellular networks are designed for human-to-human communication, mobility management in cellular networks is not necessarily effective. In this paper, we propose an adaptive method of designing registration and paging areas to reduce costs in the mobility management of cellular networks. The proposed method uses the interacting multiple model algorithm to support multiple motion models that switch over time.

We study a network structure for efficient information dissemination that leverages location-based real-time applications operating in a distributed system. Gossip-based information dissemination is a promising method for a large-scale system to keep nodes in the network quickly updated with new information. The information dissemination efficiency depends strongly on the underlying network structure, so it is important to analyze how the network structure is optimized to achieve agile information dissemination, especially for time-sensitive applications, e.g., for dynamic pursuit of a moving target that requires frequent information updating. To this end, we construct a continuous-space network model extended from Kleinberg's small-world model so that it is applicable to location-based services. Analytical and simulation-based study shows that excellent information dissemination efficiency is achieved when the shortcuts overlaying a uniform cluster network are created nearly uniformly to nodes at all distance scales. We apply our model to the dynamic pursuit problem where a pursuer searches for a moving target. Monte-Carlo simulation shows that the network with well-structured shortcuts surpasses other types of networks in finding a moving target because the pursuer can steadily approach the target regardless of its location, and the network structure greatly influences the dynamic search ability in distributed systems.

We propose an ontology-based technique for recovering trace ability links between a natural language sentence specifying features of a software product and the source code of the product. Some software products have been released without detailed documentation. To automatically detect code fragments associated with sentences describing a feature, the relations between source code structures and problem domains are important. We model the knowledge of the problem domains as domain ontologies having concepts of the domains and their relations. Using semantic relations on the ontologies in addition to method invocation relations and the similarity between an identifier on the code and words in the sentences, we locate the code fragments corresponding to the given sentences. Additionally, our prioritization mechanism which orders the located results of code fragments based on the ontologies enables users to select and analyze the results effectively. To show effectiveness of our approach in terms of accuracy, a case study was carried out with our proof-of-concept tool and summarized.

We present a mapping algorithm for our dynamically reconfigurable architecture suitable for stream applications such as H.264. Because our target architecture consists heterogeneously of four different configuration format units, it's difficult to apply the conventional algorithms. We propose a heuristic mapping algorithm enabling the mapping of generic dataflow graph onto this complex hardware automatically. We mapped five main functions of H.264 decoder onto our architecture and compared the results with those of manual mapping performed by an experienced engineer. The results show optimization of three of the five functions is equal to that in the case of the manual mapping.

This paper proposes an ontology-based technique for recovering traceability links between a natural language sentence specifying features of a software product and the source code of the product. Some software products have been released without detailed documentation. To automatically detect code fragments associated with the functional descriptions written in the form of simple sentences, the relationships between source code structures and problem domains are important. In our approach, we model the knowledge of the problem domains as domain ontologies. By using semantic relationships of the ontologies in addition to method invocation relationships and the similarity between an identifier on the code and words in the sentences, we can detect code fragments corresponding to the sentences. A case study within a domain of painting software shows that we obtained results of higher quality than without ontologies.

In this paper, we propose a simplified multi-path aggregation scheme, Ethernet with flow label for multi-path, called EFL-MP. There are several aggregation schemes, such as link aggregation and multi-path TCP, for multi-path load balancing. However, link aggregation does not distribute a single flow into multiple paths due to its MAC address based flow dispatch. In addition, the multipath TCP scheme is not suitable for implementing into hardware because of the implementation complexity caused by the management of the two stages of sequence number (SEQ) (i.e., the SEQ assigned to a path and the SEQ assigned to the flow); thus it fails to provide high throughput and short latency. To maximize data transfer throughput and minimize latency, we employed a single-stage sequence number scheme with a reorder-buffer-usage-based retransmission activating algorithm. Simulation results show that EFL-MP provides high throughput and short latency despite its simple scheme, and its throughput and its latency suit to use for interconnection transport. In addition, we demonstrate that our proposed retransmission activating algorithm activates retransmission due to packet losses earlier than the conventional timer-based retransmission activating algorithm.

Requirements changes frequently occur at any time of a software development process and their management is a crucial issue to develop software of high quality. Meanwhile, recently goal-oriented analysis techniques are being put into practice to elicit requirements. In this situation, the change management of goal graphs and its support is necessary. This paper presents two topics related to change management of goal graphs; 1) version control of goal graphs and 2) impact analysis on a goal graph when its modifications occur. In our version control system, we extract the differences between successive versions of a goal graph by means of monitoring modification operations performed through a goal graph editor, and store them in a repository. Our impact analysis detects conflicts that arise when a new goal is added, and investigates the achievability of the other goals when the existing goal is deleted.

We propose a method for multilayer in-service reconfiguration for network computing systems that minimizes the total service downtime. Although both software and hardware virtualization technologies has been proposed for dynamic reconfiguration, each one is currently designed to be executed independently and thus their cooperative operations that dynamically reconfigure both of them have not been well-considered. We have developed a method for multilayer in-service reconfiguration that comprises Ethernet-based distributed device reconfiguration (hardware layer), fine-granular I/O service continuity management (software layer), and their orchestration. Application to the management of a session initiation protocol server system built on distributed resources demonstrated that this method achieves dynamic load balancing in response to call rate increases without any failed calls.

This paper reports the application of optical interconnections to a parallel an distributed computing system in the form of a calibration-free 64-Gbps/board parallel optical interconnection sub-system mounted directly on the four-CPU processor board of a newly developed parallel-processing machine, "RWC-1". The sub-system is composed of eight parallel optical module/single-chip link large-scale integrated circuit pairs. The subsystem successfully transmitted parallel data for a variety of link lengths (between 1 m and 1 km), and with deskewing and synchronizing functions, phase-matching calibration for link lengths is automatic. Further, a method is described for the simplified merging of optical interconnections into electronic systems.