Search

Fire is one of the most commonly occurring disasters and is the main cause of catastrophic personal injury and devastating property damage. An early detection system is necessary to prevent fires from spreading out of control. In this paper, we propose a multistage fire detection method using convolutional neural networks (CNNs) and long short-term memory (LSTM) networks. In the first stage, fire candidates are detected by using their salient features, such as their color, flickering frequency, and brightness. In the second stage, a pretrained CNN model is used to extract the 2D features of flames that are the input for the LSTM network. In the last stage, a softmax classifier is utilized to determine whether the flames represent a true fire or a nonfire moving object. The experimental results show that our proposed method can achieve competitive performance compared with other state-of-the-art methods and is suitable for real-world applications.

Sinkholes can cause severe property damage and threaten public safety. Therefore, the early prediction and detection of sinkholes are important measures for protecting both citizenry and infrastructure. Although many studies have made significant progress on sinkhole detection, challenges remain, including long-term data collection and the discovery of lightweight machine learning models that can be deployed to analyze sinkhole images. In this paper, we propose a method that takes advantage of the recent success of deep learning models to detect and track sinkholes via video streaming. Our system consists of two main stages: sinkhole detection with a cascaded convolutional neural network and sinkhole tracking with a data association algorithm. The experimental results show that a sinkhole can be tracked in real time using the dataset [1]. Furthermore, we implement the system on a Jetson TX2 embedded board (weighing 85 grams), which can operate at 13.2 FPS (frames per second). With an average IoU (intersection over union) score of 88% for sinkhole tracking and an accuracy of 97,6% for sinkhole detection on a 45-minute dataset, this study demonstrates the feasibility of sinkhole detection and tracking using IR images and their suitability for practical applications.

This paper considers a system consisting of a nonorthogonal multiple access (NOMA)-based device-to-device (D2D) communication system within a cellular network, in which the time and frequency resources are shared by everyone. In particular, D2D groups that constitute different pairs are assigned to the subchannels that the cellular users occupy. A max&ndash, min fairness optimization problem with power budget constraints is formulated and solved in this paper to reduce the mutual interference between the cellular users and D2D devices that substantially impacts that with the worst channel condition. For a low computational complexity solution, we propose the use of the bisection method together with the solution of a system of linear equalities. The proposed algorithm can provide uniformly good service to all of the cellular users and D2D devices in the coverage area by utilizing the minimal total transmit power. The simulation results indicate the effectiveness of the proposed algorithm in the improvement of the spectral efficiency of the worst user under the different widely used subchannel assignments and pairing techniques.

Accurate tracking of the sinkholes that are appearing frequently now is an important method of protecting human and property damage. Although many sinkhole detection systems have been proposed, it is still far from completely solved especially in-depth area. Furthermore, detection of sinkhole algorithms experienced the problem of unstable result that makes the system difficult to fire a warning in real-time. In this paper, we proposed a method of sinkhole tracking that takes advantage of the recent development of CNN transfer learning. Our system consists of three main parts which are binary segmentation, sinkhole classification, and sinkhole tracking. The experiment results show that the sinkhole can be tracked in real-time on the dataset. These achievements have proven that the proposed system is able to apply to the practical application.

The Locator/Identifier Separation Protocol (LISP) is a new routing architecture that implements a new semantic for IP addressing. It enables the separation of IP addresses into two new numbering spaces: Endpoint Identifiers (EIDs) and Routing Locators (RLOCs). This approach will solve the issue of rapid growth of the Internet’s DFZ (default-free zone). In this paper, we propose an algorithm called the Propagated-Mode Mapping System to improve the map request process of LISP-DDT.

In recent years, intelligent transport system (ITS) applications with unmanned ground vehicles (UGV) have increased dramatically to improve the safety, efficiency, and unique services in low- to medium-range communication deployment. Orthogonal frequency division multiplexing (OFDM) is adopted as a modulation scheme for this communication system to combat fading. Unfortunately, because of possible high UGV speed, the orthogonality between subcarriers in OFDM signals is prone to intercarrier interference (ICI) caused by the Doppler spread. This paper discusses ICI suppression analysis using Universal Software Radio Peripheral (USRP) N210 under several Harbor transmission scenarios. Such communication links may contain line of sight (LoS) components in transmission. The channel is thus modeled as the well-known fast time varying path loss model. Furthermore, this paper derives the signal to interference ratio (SIR) and evaluates this parameter for several types of fading and Doppler spread shapes in UGV channels. Additionally, the paper presents a practical method for calculating the spectral efficiency of OFDM systems, with an example for actual implementation in UGV systems. Eventually, the testbed results indicate that the SIR will decrease if the maximum Doppler spread expands. In the Rician channel, it can be seen that the SIR depends on the maximum Doppler speed, the angle of arrival (AoA), and even the Rician element of the LoS component. Published version

In this paper, we present experimental results evaluating the performance of the Multipath TCP over shared bottleneck path in series of benchmark tests. In summary, we find that the Multipath TCP’s fairness as well as its competitive responds to the change of network conditions such as latency, loss rate... MPTCP is extremely unfair and powerful with regular TCP in ideal network conditions but its throughput decreases clearly even less than regular TCP in worse network conditions with very high latency, higher packet loss rate.

In this paper, the perceived loudness metering algorithm based on ITU-R BS.1387-1 was investigated and implemented, and its performance was evaluated by applying to 23 pure tones and 9 digital audio samples. Error of the tone test results compared with ISO226:2003 was below 5%, and sample test results, in comparison with Moore`s algorithm, showed deviation of less than 4.7% and correlation of 0.96. On the other hand, it was investigated how the implemented algorithm`s performance was subject to auditory pitch scale. Its result showed that the algorithm with 37 auditory filters, through correcting a bias effect, has a good performance of less than 2% in comparison with the one with 109 auditory filters.

The Long Term Evolution (LTE) system is already able to provide a background of variety services for mobile users with multimedia services such as audio, video, and data. In fact, the High Speed Packet Access plus (HSPA+) solution can greatly enhance bit rates on down-link. However, the supporting for multimedia applications with different QoS (Quality of Service) requirements is not devised yet. Hence, in this paper we propose an effective packet scheduling algorithm based on Proportional Fairness (PF) scheduling algorithms for the LTE. In this proposed packet scheduling scheme, we optimized instantaneous user data rates and the traffic class weight which prioritize user`s packets. Finally, we evaluated and showed the performance of the proposed scheduling algorithm through simulations of multimedia traffics being transmitted to users over LTE links in a multi-cell environment.

In maritime communication, QoS problem caused by routing is very important. In this paper, we propose a method based on AOMDV protocol providing a route recovery mechanism when a link breaks in an active route to reduce lost packets. The results show that the proposed method can reduce packet loss ratio and delay time compared with the AOMDV.

XVC (eXtensible Viewer Composition) is an in-vehicle user interface framework for telematics applications. It provides a document-oriented application model, which enables drivers to simultaneously make use of multiple information services, while maintaining satisfactory control of their vehicles. XVC is a new client model that makes use of the beneficial functions of in-vehicle navigation devices. This paper presents the results from usability tests performed on the XVC framework in order to evaluate how the XVC client affects drivers' navigation while using its functions. The evaluations are performed using the Advanced Automotive Simulator System located at KATECH (Korea Automobile Technology Institute). The advantages of the XVC framework are evaluated and compared to a non-XVC framework. The test results show that the XVC framework navigation device significantly reduces the scanning time needed while a driver obtains information from the navigation device.

A large ship has an expensive electronic chart display and information system (ECDIS) installed on its bridge for the safety of navigation and uses a variety of mobile equipment for auxiliary purposes. In contrast, small- and mid-sized vessels, passenger ships and fishing boats employ mobile equipment instead of such ECDISs, as their primary devices for navigation. Small-sized vessels only require some information and features of the ECDIS owing to the performance and resource restrictions of mobile devices and the characteristics of inshore or offshore navigation. This study proposed information lightening and indexing methods for electronic navigational charts to fit mobile equipment and implemented a tailored display configuration feature for navigators.

Maritime communication is internationally protected because closely related to the maritime safety, and it has evolved slower than terrestrial communication technologies. However, with the recent rapid advances in communication technology, maritime communications have become faster and increasingly modernized. A maritime broadband wireless data communication (MariComm) system was developed to make two-way high-speed internet/multimedia services available at a rate of 1 Mbps or more on the sea by extending the communication coverage of terrestrial wireless communications networks to sea areas. The MariComm system uses high-gain directional antennas to extend the transmission range and has multiple directional antennas to cover 360 degrees in azimuth. In this paper, we introduce a directional antenna tracking technique and apparatus using received RF signal and ship location information in the MariComm system.

This paper is a postprint of a paper submitted to and accepted for publication in the Proceedings of the IEE Eurowearable 2003 Conference, and is subject to Institution of Engineering and Technology Copyright. The copy of record is available at the IET Digital Library. A revised version of this paper was also published in Electronics Systems and Software, also subject to Institution of Engineering and Technology Copyright. The copy of record is also available at the IET Digital Library.

Recent paradime for convergrnce technology between traditional maritime industry and ICT has spotlighted, especially applied for the prevention of accidents and for remedies. With the introduction of samrt ship and recent addvance in the communication technology, the accidents in coastal areas has not been reduced. The reason is that those accidents were caused by small vessels which have not fully eqipped with navigational and communication system. In this paper, we introduce a electronics chart system for mobile devices based on international standard, S-57, in small vessels. For this system, we propose a data transformation scheme applicable to mobile device. Finally, we illustrate some experiments and results of the system which is implemented with Android platform.

Mobile IPv6 provides a mode of operation that allows the mobile node(MN) and its correspondent to communicate directly. This mode of operation is called route optimization. When route optimization is used, the MN notifies the correspondent node (CN) of its care-of address. Before using route optimization, the MN must perform the return routability test, and then sends the binding update message to the CN. The Fast Handover for Mobile IPv6 (FMIPv6) also has to perform the return routability test to allow the MN to communicate with CN directly. However, the Return Routability test has long latency. In this paper we propose Fast Return Routability Test method and applied to Fast Handover for Mobile IPv6 that could reduce the handoff latency.

In maritime communication, QoS problem caused by routing is very important. In this paper, we propose a method based on AOMDV protocol providing a route recovery mechanism when a link breaks in an active route to reduce lost packets. The results show that the proposed method can reduce packet loss ratio and delay time compared with the AOMDV.

The Proxy Mobile IPv6 (PMIPv6) is a network localized mobility management protocol that is independent of global mobility management protocols. In a single mobility domain (LMD), the mobile node (MN) is not involved in any IP mobility-related signaling and uses only its PMIPv6 home address for all its communication. Subsequently, when the MN moves into another LMD, the MN must change its PMIPv6 home address. In such a circumstance, host-based mobility signaling is activated. Thus, the nature of the network-based mobility of the PMIPv6 cannot be retained. Additionally, if the MN does not support global mobility, it cannot maintain communication with its correspondent node (CN). In this paper, we propose a solution for global mobility support in PMIPv6 networks, called G-PMIPv6 that allows current communication sessions of a MN without mobility protocol stacks to be maintained, even when the MN moves into another LMD. Thus, G-PMIPv6 retains the advantages of the PMIPv6 for global mobility support. We then evaluate and compare network performance between our proposed solution and PMIPv6.

XVC (extensible viewer composition) is an in- vehicle user interface framework for telematics applications. It provides a document-oriented applications model enables drivers to make use of multiple information services simultaneously, while maintaining satisfactory control of their vehicles. XVC is a new client model which makes use of beneficial functions of in-vehicle navigation devices. However, there was no usability evaluation on XVC framework before this work. In this paper, we present the usability test on XVC framework that was performed to evaluate how the XVC client may affect the driving work of drivers while trying to make use of its functions. The evaluation was performed using the advanced automotive simulator system at KATECH (Korea Automobile Technology Institute). Furthermore, we also analyzed the advantages of XVC Framework and compared over non-XVC Framework through test results.

The Fast Handovers for Mobile IPv6 (FMIPv6) protocol [2] is one of the most representative extensions of the Mobile IPv6 that provides a seamless handover in mobile IP networks. However, it is also the same as in the standard Mobile IPv6 [I], the mobile node must still perform the correspondent registration including return routability procedure on every handover as soon as it gets connected to the new access router. Thus, the handover latency is considerably prolonged. This paper proposes an enhancement for FMIPv6, a temporary correspondent registration which is performed on the previous link before getting connected to the new link. Accordingly, it could significantly reduce the handover latency in the FMIPv6 protocol with the same level of security assurances as in the standard protocol. Additionally, it could remarkably reduce the buffering and forwarding packets and thereby the extra network resource consuming could considerably be reduced.

In this paper, a novel radio resource allocation scheme is proposed and analyzed for OFDM-TDD systems in the multi-cell and multi-user environment and frequency selective time-varying channels. The optimal frame size and mode switching level of each user is determined by maximizing the spectrum efficiency. The performance of the proposed scheme are evaluated by considering the co-channel interference of other cells and the measured SINR is changed in one frame size because the interference is changed. The frame size is determined to consider both the optimal frame size and cochannel user's frame size of other cells. We evaluated the performance of proposed resource allocation scheme, which satisfy the target BER, by providing the related simulation results. The proposed scheme attains the better spectral efficiencies compared with those of conventional schemes. The results in this paper can be utilized in the areas of the performance estimation and application of radio resource allocation strategy of OFDM-TDD based cellular mobile communication systems.