Large-scale Data Acquisition System Research Articles

Towards Landslides Early Warning System With Fog - Edge Computing And Artificial Intelligence**

Landslides are phenomena that cause significant human and economic losses. Researchers have investigated the prediction of high landslides susceptibility with various methodologies based upon statistical and mathematical models, in addition to artificial intelligence tools. These methodologies allow to determine the areas that could present a serious risk of landslides. Monitoring these risky areas is particularly important for developing an Early Warning Systems (EWS). As matter of fact, the variety of landslides’ types make their monitoring a sophisticated task to accomplish. Indeed, each landslide area has its own specificities and potential triggering factors; therefore, there is no single device that can monitor all types of landslides. Consequently, Wireless Sensor Networks (WSN) combined with Internet of Things (IoT) allow to set up large-scale data acquisition systems. In addition, recent advances in Artificial Intelligence (AI) and Federated Learning (FL) allow to develop performant algorithms to analyze this data and predict early landslides events at edge level (on gateways). These algorithms are trained in this case at fog level on specific hardware. The novelty of the work proposed in this paper is the integration of Federated Learning based on Fog-Edge approaches to continuously improve prediction models.

Optimizing the data-collection time of a large-scale data-acquisition system through a simulation framework

The ATLAS detector at CERN records particle collision “events” delivered by the Large Hadron Collider. Its data-acquisition system identifies, selects, and stores interesting events in near real-time, with an aggregate throughput of several 10 GB/s. It is a distributed software system executed on a farm of roughly 2000 commodity worker nodes communicating via TCP/IP on an Ethernet network. Event data fragments are received from the many detector readout channels and are buffered, collected together, analyzed and either stored permanently or discarded. This system, and data-acquisition systems in general, are sensitive to the latency of the data transfer from the readout buffers to the worker nodes. Challenges affecting this transfer include the many-to-one communication pattern and the inherently bursty nature of the traffic. The main performance issues brought about by this workload are addressed in this paper, focusing in particular on the so-called TCP incast pathology. Since performing systematic studies of these issues is often impeded by operational constraints related to the mission-critical nature of these systems, we developed a simulation model of the ATLAS data-acquisition system. The resulting simulation tool is based on the well-established, widely-used OMNeT++ framework. This tool was successfully validated by comparing the obtained simulation results with existing measurements of the system’s behavior. Furthermore, the simulation tool enables the study of the theoretical behavior of the system in numerous what-if scenarios and with modifications that are not immediately applicable to the real system. In this paper, we take advantage of this to analyze the behavior of the system using different traffic shaping and scheduling policies, and with network hardware modifications. This analysis leads to conclusions that could be used to devise future system enhancements.

Development of HTTP Server for Remote Data Monitoring and Recording System

This paper focuses on development of remote data monitoring and recording system in industries. Now a days we are using many Networked embedded systems for monitoring and control the home or industrial devices.These low cost devices are capable of reporting and receiving information in just the same way that computers on a network. The advent of Internet communication standard, TCP/IP, offers significant potential in terms of remote monitoring and management of construction sites using embedded systems. In this paper the design method of low cost system of remote data monitoring, and recording is designed based on ARM. For this a small HTTP SERVER is built in LPC2148 and it is connected with the remote monitoring terminal through Ethernet. The data can be stored in the SD Card via SPI interface. At the same time, for the sake of the versatility, the FAT file system is built in the SD Card. So, an Ethernet-enabled remote data monitoring system with the ability of data recording is built. This design is having advantage of cost-effective, easily realized, stable and reliable transmission. It can be connected to the INTERNET or LAN through TCP/IP protocol. FreeRTOS is used as an operating system running on ARM processor, an industrial grade RTOS for hard time applications. By this design the data is sent without a PC and system favour’s large scale data acquisition system.

Efficient, reliable and fast high-level triggering using a bonsai boosted decision tree

High-level triggering is a vital component of many modern particle physics experiments. This paper describes a modification to the standard boosted decision tree (BDT) classifier,the so-called bonsai BDT, that has the following important properties: it is more efficient than traditional cut-based approaches; it is robust against detector instabilities,and it is very fast. Thus, it is fit-for-purpose for the online running conditions faced by any large-scale data acquisition system.

Generic and Layered Framework Components for the Control of a Large Scale Data Acquisition System

The complexity of today's experiments in High Energy Physics results in a large amount of readout channels which can count up to a million and above. The experiments in general consist of various subsystems which themselves comprise a large amount of detectors requiring sophisticated DAQ and readout electronics. We report here on the structured software layers to control such a data acquisition system for the case of LHCb which is one of the four experiments for LHC. Additional focus is given on the protocols in use as well as the required hardware. An abstraction layer was implemented to allow access on the different and distinct hardware types in a coherent and generic manner. The hierarchical structure which allows propagating commands down to the subsystems is explained. Via finite state machines an expert system with auto-recovery abilities can be modeled.

Artificial neural networks for fault detection in large-scale data acquisition systems

In this paper, a fault detection scheme for application to large-scale data acquisition systems is presented. The detection scheme has to process up to several hundreds of different measurements at a time and check them for consistency. The fault detection scheme works in three steps: First, principal component analysis of training data is used to determine non-sparse areas of the measurement space. Fault detection is accomplished by checking whether a new data record lies in a cluster of training data or not. Therefore, in a second step the distribution function of the available data is estimated using kernel regression techniques. In order to reduce the degrees of freedom and to determine clusters of data efficiently, in a third step the distribution function is approximated by a neural network. In order to use as few basis functions as possible a new training algorithm for ellipsoidal basis function networks is presented: New neurons are placed such that they approximate the distribution function in the vicinity of their centers up to the second order. This is accomplished by adapting the spread parameters using Taylor's theorem. Thus, the amount of necessary parameters and the computational effort for online supervision can be reduced dramatically. An important requirement for the fault detection scheme is that it is able to automatically adapt itself to new data. The present paper also addresses this feature. It is demonstrated how a gradient optimization with algebraic constraints can be applied to adapt a pre-existing network to new data points. Numerical examples with real data show that the proposed method produces excellent results.