This paper is devoted to the study of the effectiveness of methods for deploying cloud infrastructures to create a distributedcomputing automation platform for big data processing based on cloud infrastructures. Depl...
详细信息
Wireless IoT sensor Networks have a wide range of applications in many areas of modern life, including environmental monitoring where data is sent to a sink. In such networks, it is likely for node failures to occur d...
详细信息
ISBN:
(纸本)9781665495516
Wireless IoT sensor Networks have a wide range of applications in many areas of modern life, including environmental monitoring where data is sent to a sink. In such networks, it is likely for node failures to occur during the course of normal operation, e.g., when nodes run out of battery power or they have crashed due to defective hardware. Increasingly sophisticated applications, such as fire sprinkler systems, however deploy multiple sources and multiple sinks, in what is called many-many IoT networks. For these critical applications, it is necessary to develop a fault-tolerant routing protocol that is able to route messages around failed nodes, without a significant overhead. Focusing on many-many IoT networks, we present a novel distributed fault-tolerant routing protocol for wireless IoT sensor networks based on ant colony optimisation, that is able to route from multiple sources to multiple sinks. Our results show that our protocol is able to achieve more than 80% delivery ratio with 5% node failures. Our approach is scalable, compared to several approaches that require periodic topology maintenance to work.
Recent studies showed that Photoplethysmography (PPG) sensors embedded in wearable devices can estimate heart rate (HR) with high accuracy. However, despite of prior research efforts, applying PPG sensor based HR esti...
详细信息
Recent studies showed that Photoplethysmography (PPG) sensors embedded in wearable devices can estimate heart rate (HR) with high accuracy. However, despite of prior research efforts, applying PPG sensor based HR estimation to embedded devices still faces challenges due to the energy-intensive high-frequency PPG sampling and the resource-intensive machine-learning models. In this work, we aim to explore HR estimation techniques that are more suitable for lower-power and resource-constrained embedded devices. More specifically, we seek to design techniques that could provide high-accuracy HR estimation with low-frequency PPG sampling, small model size, and fast inference time. First, we show that by combining signal processing and ML, it is possible to reduce the PPG sampling frequency from 125 Hz to only 25 Hz while providing higher HR estimation accuracy. This combination also helps to reduce the ML model feature size, leading to smaller models. Additionally, we present a comprehensive analysis on different ML models and feature sizes to compare their accuracy, model size, and inference time. The models explored include Decision Tree (DT), Random Forest (RF), K-nearest neighbor (KNN), Support vector machines (SVM), and Multi-layer perceptron (MLP). Experiments were conducted using both a widely-utilized dataset and our self-collected dataset. The experimental results show that our method by combining signal processing and ML had only 5 % error for HR estimation using low-frequency PPG data. Moreover, our analysis showed that DT models with 10 to 20 input features usually have good accuracy, while are several magnitude smaller in model sizes and faster in inference time.
In this paper, sequential and distributed fusion state estimation algorithms based on local filter are proposed for nonlinear multi-sensorsystems with asynchronously correlated noises. At first, in order to avoid the...
详细信息
ISBN:
(纸本)9781665478373
In this paper, sequential and distributed fusion state estimation algorithms based on local filter are proposed for nonlinear multi-sensorsystems with asynchronously correlated noises. At first, in order to avoid the computational burden of measurement augmentation in centralized fusion filter, a sequential fusion filter is deduced by correcting measurement noises recursively. Subsequently, considering the problem that the parameters in covariance intersection (CI) fusion algorithm are difficult to estimate and the estimation accuracy of the sequential fast CI (SFCI) fusion algorithm is poor, a novel distributed fusion filter is proposed, where local filters are sent to the fusion center as the measurements and fusion predictor in the fusion center is sent to local filters by feedback. Then, to be suitable for practical applications, the numerical implementation based on third-degree spherical-radial rule is given. Finally, the superiority of the proposed algorithms is shown by using a nonlinear model.
The proceedings contain 135 papers. The topics discussed include: real-time operating systems for cyber-physical systems: current status and future research;a semi-supervised dynamic ensemble algorithm for IoT anomaly...
ISBN:
(纸本)9781728176475
The proceedings contain 135 papers. The topics discussed include: real-time operating systems for cyber-physical systems: current status and future research;a semi-supervised dynamic ensemble algorithm for IoT anomaly detection;an efficient hybrid approach for brain tumor detection in MR images using Hadoop-MapReduce;drug-drug interaction extraction using pre-training model of enhanced entity information;breast cancer image classification based on CNN classifier;an assessment of the usability of machine learning based tools for the security operations center;machine learning recognition of gait identity via shoe embedded accelerometer;leveraging walking inertial pattern for terrain classification;multicast traffic throughput maximization through dynamic modulation and coding scheme assignment in wireless sensor networks;and X-DOG: an intelligent x-ray-based dangerous goods detection and automatic alarm system.
Statistical structure learning (SSL)-based approaches have been employed in the recent years to detect different types of anomalies in a variety of cyber-physical systems (CPS). Although these approaches outperform co...
详细信息
ISBN:
(纸本)9781728161273
Statistical structure learning (SSL)-based approaches have been employed in the recent years to detect different types of anomalies in a variety of cyber-physical systems (CPS). Although these approaches outperform conventional methods in the literature, their computational complexity, need for large number of measurements and centralized computations have limited their applicability to large-scale networks. In this work, we propose a distributed, multi-agent maximum likelihood (ML) approach to detect anomalies in smart grid applications aiming at reducing computational complexity, as well as preserving data privacy among different players in the network. The proposed multi-agent detector breaks the original ML problem into several local (smaller) ML optimization problems coupled by the alternating direction method of multipliers (ADMM). Then, these local ML problems are solved by their corresponding agents, eventually resulting in the construction of the global solution (network's information matrix). The numerical results obtained from two ieee test (power transmission) systems confirm the accuracy and efficiency of the proposed approach for anomaly detection.
A few years ago, hitting the silo container from the outside was the only way of knowing whether it had to be refilled with feed or water. However, current advances make it possible to develop more evolved mechanisms ...
详细信息
ISBN:
(纸本)9783030005245;9783030005238
A few years ago, hitting the silo container from the outside was the only way of knowing whether it had to be refilled with feed or water. However, current advances make it possible to develop more evolved mechanisms that not only allow the farmer to know if it is necessary to fill the silo with feed but give a precise estimate of the quantity of feed or water remaining in the silo and information on other parameters that help control the quality of the feed. To this end, it is necessary to design a device that will be placed on the inside of the silo and will detect if there is feed and how much of it by means of a sensor with ultrasonic technology. The prototype includes several motion engines which perform a complete sweep for the calculation of volume;this is important as each type of feed has a different density. In addition, the development of such a system will make it possible to optimize the delivery of feed to livestock holdings through route planning for the truck, for example, in cases where two nearby farms are short of supply. For this purpose, we have developed a system that incorporates an IoT device with a laser for calculating the volume of feed inside a silo. In addition, this system includes a series of sensors that can monitor temperature and humidity. Thus, the owners obtain more information from which they can draw conclusions about the conservation of the feed and about its general exploitation. Furthermore, it is possible to understand to what extent the cold and humidity affect animals and their consumption of the feed. This research work describes the evaluation of the developed prototype in several independent silos on the Hermi Group's farm (Salamanca) and outlines the obtained results.
Mobile clients that consume and produce data are abundant in fog environments and low latency access to this data can only be achieved by storing it in their close physical proximity. To adapt data replication in fog ...
ISBN:
(纸本)9781450391634
Mobile clients that consume and produce data are abundant in fog environments and low latency access to this data can only be achieved by storing it in their close physical proximity. To adapt data replication in fog data stores in an efficient manner and make client data available at the fog node that is closest to the client, the systems need to predict both client movement and pauses in data *** this paper, we present variations of Markov model algorithms that can run on clients to increase the data availability while minimizing excess data. In a simulation, we find the availability of data at the closest node can be improved by 35% without incurring the storage and communication overheads of global replication.
We present a trajectory-based routing (TBR) protocol, which efficiently routes data to a mobile sink on the shortest path in Wireless sensor Networks (WSNs). Using the idea of vector images (sensors representing pixel...
详细信息
ISBN:
(纸本)9781728105703
We present a trajectory-based routing (TBR) protocol, which efficiently routes data to a mobile sink on the shortest path in Wireless sensor Networks (WSNs). Using the idea of vector images (sensors representing pixels), we use two kinds of geometric shapes, hyperbola and arc as the smallest elements within the shortest routing path. Our protocol let sink nodes transmit the compressed routing request to source nodes through a routing path. Each individual node uses the DV-Hop (Distance Vector Hop) of the virtual anchor nodes as the dictionary which helps in efficiently decipher a compressed routing request. Finally, the routing path is distributed to each individual node within the path. The mobile sink can integrate updated routing path to the existing active path by sending new requests. Our protocol relaxes the constraints such as use of nodes' GPS information, the reliability of nodes, and also, places no restrictions on the sink's moving speed and direction. Using a WSN test-bed, and simulations on TOSSIM, we show that our trajectory-based routing protocol using DV-Hop is faster, reliable against node failures, provide location anonymity of nodes, and transmits less routing packets than two other known approaches.
This paper presents the design of an efficient soft computing technique for increasing the accuracy of the Infrared sensor, by using the Support Vector Machines (SVM) and Neural Networks (NN). The analysis for SVM was...
详细信息
暂无评论