Application-level Requirements Research Articles

SafeFac: Video-based smart safety monitoring for preventing industrial work accidents

This work presents SafeFac, an intelligent camera-based system for managing the safety of factory environments. In SafeFac a set of cameras installed on the assembly line are used to capture images of workers that approach the machinery under hazardous situations to alert system managers and halt the line if needed. Given a challenging set of practical application-level requirements such as multi-camera support and low response latency, SafeFac exploits a YOLOv3-based light-weight human object detection. To address the latency–accuracy tradeoff, SafeFac incorporates a set of algorithms as pre- and post-processing modules and a novel adaptive camera scheduling scheme.Our evaluation with a video dataset containing more that 113,000 frames from real assembly line activity shows that SafeFac achieves high precision (99.93%) and recall (96.44%), and SafeFac successfully satisfies such challenging requirements as a ready-for-deployment system for safe factory management.

Effect and Evaluation of an Ultrasonic Atomizer With Large Vibration Amplitude

An ultrasonic atomizer can produce large vibration amplitude is designed. Different from the structure of the usually seen ultrasonic spray nozzle, the atomizer is fundamentally constructed with a hollow tube encircled with several pieces of sectional type piezoelectric actuators, which can radially oscillate the tube to generate desired vibration profile. Atomization is formed on the surface around the liquid outlet of the tube where maximum vibration amplitude occurs. In search of resonance frequency and vibration amplitude, modal and harmonic analyses of the ultrasonic atomizer are carried out by ANSYS. In comparison the simulated results with the experimental results, both are in good agreement. A measurement system is set up for detecting the atomization droplets and calculating the droplet size and distribution. An attempt is to design an ultrasonic atomizer can produce high distribution and small diameter droplets for some application-level requirements, droplet diameter around 20–60 μm is assumed to be the specification for performance verification of the proposed atomizer. In experiment, it is found nearly 90% of atomized droplets fit for the requirement. Besides the most important factor of operating frequency, a relation of amplitude is found to include in the well-known Lang and Rayleigh’s equation.

TireNet: A high recall rate method for practical application of tire defect type classification

Tire enterprises often use X-ray photographs to inspect tire defects, which is still in the stage of manual inspection. Existing methods have achieved a lot of success in tire defect detection, but have not yet reached the application level requirements. It is hard for unsupervised methods to handle the complex specs and patterns of tires, while the supervised methods suffered from a lack of enough data. In this paper, an end-to-end method (TireNet) is proposed for the practical application of automatic tire defect detection with X-ray images. Object detection models are introduced as the baselines, it is found that the recall rate (missed detection rate) cannot meet the application-level needs of enterprises, since tire defects are quite different from general objects. Inspired by the features of tire X-ray images, which are periodic, the Siamese network is used in the new model as part of the downstream classifier to capture the defective features. Additionally, 120,000 labeled tire images (including qualified tires) were set up and collected as datasets. The experimental results of this method reach a higher recall rate compared to Faster R-CNN, SSD, and YOLO in the labeled datasets. At present, the model has been successfully deployed to the quality inspection department of enterprises and partly replaced artificial jobs. The application results show that the missing rate of TireNet is 0.17%, which is lower than that of the artificial 2.4%. With the help of a deployed assistant detection system, the tire defect detection rate increased by more than 100%, and the tire refund rate decreased by approximately 20%.

Earl

As system complexity grows, embedded operating systems increasingly face the challenge to adhere to various non-functional constraints, such as response times and power limits. These requirements sometimes contradict and, often, no solution satisfies all constraints under all conditions. Changes in environmental conditions, application-level requirements, and user response time expectation hence demand for system-wide adaptions to resource management. We find that process synchronization constitutes a simple yet effective leverage point to balance between timing-related and energy-related constraints. This paper presents Earl, an implementation of reconfigurable locks in Linux that enables seamless transitions between high-performance and low-power operating modes.

5G Applications From Vision to Reality: Multi-Operator Orchestration

Envisioned 5G applications and services, such as Tactile Internet, Industry 4.0 use-cases, remote control of drone swarms, pose serious challenges to the underlying networks and cloud platforms. On the one hand, evolved cloud infrastructures provide the IT basis for future applications. On the other hand, networking is in the middle of a momentous revolution and important changes are mainly driven by Network Function Virtualization (NFV) and Software Defined Networking (SDN). A diverse set of cloud and network resources, controlled by different technologies and owned by cooperating or competing providers, should be coordinated and orchestrated in a novel way in order to enable future applications and fulfill application level requirements. In this paper, we propose a novel cross domain orchestration system which provides wholesale XaaS (Anything as a Service) services over multiple administrative and technology domains. Our goal is threefold. First, we design a novel orchestration system exploiting a powerful information model and propose a versatile embedding algorithm with advanced capabilities as a key enabler. The main features of the architecture include $i$ ) efficient and multi-purpose service embedding algorithms which can be implemented based on graph models, $ii$ ) inherent multi-domain support, $iii$ ) programmable aggregation of different resources, $iv$ ) information hiding together with flexible delegation of certain requirements enabling multi-operator use-cases, and $v$ ) support for legacy technologies. Second, we present our proof-of-concept prototype implementing the proposed system. Third, we establish a dedicated test environment spanning across multiple European sites encompassing sandbox environments from both operators and the academia in order to evaluate the operation of the system. Dedicated experiments confirm the feasibility and good scalability of the whole framework.

Joint Online Coflow Routing and Scheduling in Data Center Networks

A coflow is a collection of related parallel flows that occur typically between two stages of a multi-stage computing task in a network, such as shuffle flows in MapReduce. The coflow abstraction allows applications to convey their semantics to the network so that application-level requirements can be better satisfied. In this paper, we study the routing and scheduling of multiple coflows to minimize the total weighted coflow completion time (CCT). We first propose a rounding-based randomized approximation algorithm, called OneCoflow , for single coflow routing and scheduling. The multiple coflow problem is more challenging as coexisting coflows will compete for the same network resources, such as link bandwidth. To minimize the total weighted CCT, we derive an online multiple coflow routing and scheduling algorithm, called OMCoflow . We then derive a competitive ratio bound of our problem and prove that the competitive ratio of OMCoflow is nearly tight. To the best of our knowledge, this is the first online algorithm with theoretical performance guarantees which considers routing and scheduling simultaneously for multi-coflows. Compared with existing methods, OMCoflow runs more efficiently and avoids frequently rerouting the flows. Extensive simulations on a Facebook data trace show that OMCoflow outperforms the state-of-the-art heuristic schemes significantly (e.g., reducing the total weighted CCT by up to 41.8% and the execution time by up to 99.2% against RAPIER).

An adaptive load balancing scheme for software-defined network controllers

Software-defined networking (SDN) is considered as one of the promising paradigms for the future Internet. It allows users to configure the network depending on the application-level requirements. One of the major challenges in SDN is the uneven distribution of traffic load in the controllers that degrades system performance. In this paper, we propose a self-adaptive load balancing (SALB) scheme that balances load among multiple controllers dynamically with multiple switch migration from source controllers to target controllers. The key feature of our scheme is an effective distribution of load under high load condition while considering the distance between switches and target controllers simultaneously. The efficacy of our proposed scheme is demonstrated through experimentation, where we compare our scheme with existing approaches. The results show that SALB experiences a small number of packet drops, which is less than 1.23% of the total number of message exchanges among the controllers.

MLMAC-HEAP: A Multi-Layer MAC Protocol for Wireless Sensor Networks Powered by Ambient Energy Harvesting

Limited availability of energy is the most crucial constraint of wireless sensor networks (WSN). Most power consuming part of WSN node is transreceiver and operation of transreciever to access medium is controlled by the medium access control (MAC) sublayer of the open systems interconnection (OSI) model. In WSN, till now, most of the present MAC protocols have addressed issues related to power saving. Because of energy constraints, performance is often not a focused design parameter in these MAC protocols. However, recent advances in energy harvesting technology have made it possible to obtain energy from the environment to solve energy limitations. So in this paper, a new multi layer based MAC protocol, MLMAC-HEAP is designed for solar energy harvesting criterion considering performance as the mainly focused parameter. Performance is illustrated in terms of throughput. This paper evaluates the performance of MLMAC-HEAP as a function of energy harvesting rate and number of nodes in network and results are compared and shown to outperform well known MAC protocols. Then, the paper analyses the protocol for various traffic models. Based on application-level requirements, optimization is also done for number of layers.

Solar-powered, wireless smart camera network: An IoT solution for outdoor video monitoring

In this paper, we present SlugCam, a solar-powered, wireless smart camera network that can be used in a variety of outdoor applications including video surveillance of public spaces, habitat and environmental monitoring, wildfire prevention and detection, to name a few. SlugCam was designed such that it can be deployed and left unattended for extended periods without requiring regular maintenance, e.g., frequent battery replacement. The system is built with off-the-shelf components which not only keeps it modular and low cost, but also facilitates its prototyping, rapid duplication, and evolution. SlugCam’s on-board processing capability allows computer vision software to run locally and autonomously. Energy efficiency in SlugCam is accomplished both in: (1) hardware by micro-managing low-power components; as well as in (2) software by having the system’s operation duty cycles automatically adapt to the current state of the battery in order to balance the trade-off between application-level requirements and power awareness. For example, SlugCam’s smart camera node changes its monitoring behavior based on how much battery charge remains. Additionally, using its computer vision software, the system only records and transmits information upon event detection which contributes both to the system’s energy efficiency as well as its low network bandwidth requirements. SlugCam’s networking functionality enables camera nodes to transfer video files, as well as collaborate on tasks such as visual processing, event detection, and object tracking. It allows node-to-node, as well as scoped- or full broadcast communication. For point-to-point communication, SlugCam uses on-demand power-aware multi-path routing to transfer video files efficiently. Another important contribution of SlugCam is to provide an open-source wireless camera network that can adapt to address the requirements of future outdoor video monitoring applications. SlugCam also includes a Web-based server where video data is stored as well as a Web-based user interface that allows end users to interact with the system, tag, query and retrieve video files, and manage SlugCam nodes remotely. In addition to a detailed description of SlugCam, this paper presents an extensive power characterization of the system’s operation and showcases its deployment in a lab testbed and a real world scenario.

Enhanced channel allocation scheme for cross layer management in wireless network based on interference management

The entire spectrum of communication in networks relies on transmitting data from node to node in a scalable manner. Though elastic nature of networks is made possible through protocols and communication, it still remains an open question of how different applications can work together. Hence though a proper channel allocation, it can provide services to users thereby taking care of the application level requirements. This paper proposes an enhanced channel allocation using the strengths of cross layer functionalities. The proposed formulae enhance the cross layer handling considering the interference issues in the wireless network. The proposed algorithm, simulated for the wireless network for different range of nodes and performance, is presented based on routing overhead, packet loss, packet delivery ratio, average delay, energy consumption, and throughput. It is concluded from the results that the performance of the wireless network is improved by using the proposed cross layer technique.

시공간 영상분할을 이용한 이동 및 이동 중 정지물체 검출

본 논문에서는 이동 카메라 환경에서 이동 및 이동 중 정지물체를 검출하기 위한 방법을 제안한다. 이동 중에 일시적으로 정지한 물체는 검출 결과의 응용관점에서 볼 때 이동물체의 검출만큼이나 중요한데, 기존의 이동물체 검출 방법들은 이들을 배경과 구분하지 못하는 한계를 갖는다. 이러한 문제를 해결하기 위해 제안하는 방법에서는 이동 가능성 큐, 위치 가능성 큐, 그리고 색 분포 유사성 큐를 정의하여 이동물체 검출 및 지속적인 추적에 이용한다. 그래프 컷 알고리즘은 세 개의 큐를 결합하여 시공간 영상분할을 수행함으로써 이동 및 이동 중 정지물체를 검출한다. 제안하는 방법은 이동물체 뿐 아니라 이동 중 정지물체에 대해서도 검출이 가능함을 실험을 통해 증명하였다. This paper proposes a method for detection of objects temporally stop moving in video sequences taken by a moving camera. Even though the consequence of missed detection of those objects could be catastrophic in terms of application level requirements, not much attention has been paid in conventional approaches. In the proposed method, we introduce cues for consistent detection and tracking of objects: motion potential, position potential, and color distribution similarity. Integration of the three cues in the graph-cut algorithm makes possible to detect objects that temporally stop moving and are newly appearing. Experiment results prove that the proposed method can not only detect moving objects but also track objects stop moving.

Efficient coflow scheduling with Varys

Communication in data-parallel applications often involves a collection of parallel flows. Traditional techniques to optimize flow-level metrics do not perform well in optimizing such collections, because the network is largely agnostic to application-level requirements. The recently proposed coflow abstraction bridges this gap and creates new opportunities for network scheduling. In this paper, we address inter-coflow scheduling for two different objectives: decreasing communication time of data-intensive jobs and guaranteeing predictable communication time. We introduce the concurrent open shop scheduling with coupled resources problem, analyze its complexity, and propose effective heuristics to optimize either objective. We present Varys, a system that enables data-intensive frameworks to use coflows and the proposed algorithms while maintaining high network utilization and guaranteeing starvation freedom. EC2 deployments and trace-driven simulations show that communication stages complete up to 3.16X faster on average and up to 2X more coflows meet their deadlines using Varys in comparison to per-flow mechanisms. Moreover, Varys outperforms non-preemptive coflow schedulers by more than 5X.

Investigating the Privacy versus Forwarding Accuracy Tradeoff in OpportunisticInterest-Casting

Many mobile social networking applications are based on a “friend proximity detection” step, according to which two mobile users try to jointly estimate whether they have friends in common, or share similar interests, etc. Performing “friend proximity detection” in a privacy-preserving way is fundamental to achieve widespread acceptance of mobile social networking applications. However, the need of privacy preservation is often at odds with application-level performance of the mobile social networking application, since only obfuscated information about the other user's profile is available for optimizing performance. In this paper, we study for the first time the fundamental tradeoff between privacy preservation and application-level performance in mobile social networks. More specifically, we consider a mobile social networking application for opportunistic networks called interest-casting. In the interest-casting model, a user wants to deliver a piece of information to other users sharing similar interests (“friends”), possibly through multi-hop forwarding. In this paper, we propose a privacy-preserving friend proximity detection scheme based on a protocol for solving the Yao's “Millionaire's Problem”, and we introduce three interest-casting protocols achieving different tradeoffs between privacy and accuracy of the information forwarding process. The privacy versus accuracy tradeoff is analyzed both theoretically, and through simulations based on a real-world mobility trace. The results of our study demonstrate for the first time that privacy preservation is at odds with forwarding accuracy, and that the best tradeoff between these two conflicting goals should be identified based on the application-level requirements.

Average end-to-end delay computation in IEEE 802.11 ad hoc networks

In this study, we present a new analytic model for evaluating average end-to-end delay in IEEE 802.11 multihop wireless networks. Our model gives closed expressions for the end-to-end delay in function of arrivals and service time patterns. Each node is modelled as a G/G/1/K queue from which we can derive expressions for service time via queueing theory. By combining this delay evaluation with different admission controls, we design a protocol called DEAN (Delay Estimation in Ad hoc Networks). DEAN is able to provide delay guarantees for quality of service applications in function of the application level requirements. Through extensive simulations, we compare the performance evaluation of DEAN with other approaches.

Adaptive Deployment Scheme for Mobile Relays in Substitution Networks

We present how the mobility of routers impacts the performance of a wireless substitution network. To that end, we simulate a scenario where a wireless router moves between three static nodes, a source and two destinations of UDP traffic. Specifically, our goal is to deploy or redeploy the mobile relays so that application-level requirements, such as data delivery or latency, are met. Our proposal for a mobile relay achieves these goals by using an adaptive approach to self-adjust their position based on local information. We obtain results on the performance of end-to-end delay, jitter, loss percentage, and throughput under such mobility pattern for the mobile relay. We show how the proposed solution is able to adapt to topology changes and to the evolution of the network characteristics through the usage of limited neighborhood knowledge.

Bus switched networks: An ad hoc mobile platform enabling urban-wide communications

In this paper we propose to leverage the public transportation system of any given city to obtain a scalable and efficient urban backbone by deploying an opportunistic network on buses. The paper proves that Bus Switched Networks (BSNs) are feasible for deployment in real cities and that they can meet the application level requirements for a large class of applications by ensuring high delivery ratio and acceptable delays under different conditions of packet load. We envision a multi-platform metropolitan network backhaul where BSNs play a relevant role and focus on a novel and lightweight probabilistic routing protocol. We prove that the protocol is highly effective in satisfying the loose QoS required by urban-wide delay-tolerant information services and perfectly scales to urban level. The protocol performance evaluation derives from an benchmark analysis of the protocol on three cities which have been selected to explore geo and structural diversity. Finally, the paper presents URBeS, an analysis platform that, given a specific city served by public transportation, produces bus mobility traces and traffic analysis for any given routing protocol.

Implementation and Evaluation of Multichannel Multi-Interface Routing Mechanism with QoS-Consideration for Ad-Hoc Networks

To accommodate real-time multimedia application while satisfying application-level QoS requirements in a wireless ad-hoc network, we need QoS control mechanisms. We proposed a new routing mechanism for a wireless ad-hoc network composed of nodes equipped with multiple network interfaces. By embedding information about channel usage in control messages of OLSRv2, each node obtains a view of topology and bandwidth information of the whole network. Based on the obtained information, a source node determines a logical path with the maximum available bandwidth to satisfy application-level QoS requirements. In this paper, we evaluated feasibility of the proposal through simulation and practical experiments and confirmed that our proposal effectively transferred multimedia packets over a logical path avoiding congested links. The load on a network is well distributed and the network can accommodate more sessions than OLSRv2 and QOLSR.

Scalable Delay-constrained Multicast Group Key Management

In the last few years, multicasting is increasingly used as an efficient communication mechanism for group-oriented applications in the Internet. Some multicast applications require confidentiality for transmitted data. So, a traffic encryption key is used to assure this confidentiality and has to be changed and distributed to all valid members whenever a membership change (join or leave) occurs in the group. The bandwidth used for re-keying operations could be high when the group size is large. To cope with this limitation, many solutions propose to organize group members into subgroups that use independent traffic encryption keys in order to mitigate the scope of key management and thereby to scale better to large groups. Unfortunately, these solutions require the decryption and re-encryption of multicast messages whenever they pass from one subgroup to another. Moreover, the decryption/re-encryption operations induce delays in packet delivery throughout the delivery path. In order to avoid delays in packet delivery and perturbations caused by re-keying, we propose in this paper an adaptive solution for key management which organizes group members into dynamic and homogeneous clusters according to the application level requirements. First, we show that partitioning the group into clusters of subgroups that use independent traffic encryption keys can be formulated as tree partitioning problem. Then, we propose a protocol to solve the problem with respect to the application requirements and membership behavior. We conducted several simulations of the proposed protocol and the obtained results show that our solution is efficient and achieves better performance trade-offs compared to other schemes.

Visual Grid Workflow in Triana

In this paper, we describe the graphical abstractions for Grids and services that have been implemented within the Triana problem solving environment. We provide an overview of the ways in which Triana interacts with services (e.g., Web and P2P services) and then how we interact with core Grid components, such as resource managers and data management systems through the extensive use of the GridLab GAT interface. We describe in detail the GAT philosophy and implementation and then show how the various GAT primitives can be represented in an intuitive fashion within a Triana workflow. This approach, which we refer to as the Visual GAT, differs substantially from other approaches because we do not tie our implementation to any specific underlying Grid middleware technologies; rather, we base our implementation on application level requirements and model such primitives from a user’s perspective by hiding as much complexity as possible without undermining the core capabilities required. We provide a use case to demonstrate the Visual GAT implementation and show how legacy applications can seamlessly be distributed and integrated in a dynamic fashion within complex data-driven workflow scenarios.

A taxonomy of multicast data origin authentication: Issues and solutions

Multicasting is an efficient communication mechanism for group-oriented applications such as videoconferencing, broadcasting stock quotes, interactive group games, and video on demand. The lack of security obstructs a large deployment of this efficient communication model. This limitation motivated a host of research works that have addressed the many issues relating to securing the multicast, such as confidentiality, authentication, non-repudiation, integrity, and access control. Many applications, such as broadcasting stock quotes and video-conferencing, require data origin authentication of the received traffic. Hence, data origin authentication is an important component in the multicast security architecture. Multicast data origin authentication must take into consideration the scalability and the efficiency of the underlying cryptographic schemes and mechanisms, because multicast groups can be very large and the exchanged data is likely to be heavy in volume (streaming). Besides, multicast data origin authentication must be robust enough against packet loss because most multicast multimedia applications do not use reliable packet delivery. Therefore, multicast data origin authentication is subject to many concurrent and competitive challenges, when considering these miscellaneous application-level requirements and features. In this article we review and classify recent works dealing with the data origin authentication problem in group communication, and we discuss and compare them with respect to some relevant performance criteria.