Search Results (8)

The escalating global water usage and the increasing strain on major cities due to water shortages highlights the critical need for efficient water management practices. In water-stressed regions worldwide, significant water wastage is primarily attributed to leakages, inefficient use, and aging infrastructure. Undetected water leakages in buildings’ pipelines contribute to the water waste problem. To address this issue, an effective water leak detection method is required. In this paper, we explore the application of edge computing in smart buildings to enhance water management. By integrating sensors and embedded Machine Learning models, known as TinyML, smart water management systems can collect real-time data, analyze it, and make accurate decisions for efficient water utilization. The transition to TinyML enables faster and more cost-effective local decision-making, reducing the dependence on centralized entities. In this work, we propose a solution that can be adapted for effective leakage detection in real-world scenarios with minimum human intervention using TinyML. We follow an approach that is similar to a typical machine learning lifecycle in production, spanning stages including data collection, training, hyperparameter tuning, offline evaluation and model optimization for on-device resource efficiency before deployment. In this work, we considered an existing water leakage acoustic dataset for polyvinyl chloride pipelines. To prepare the acoustic data for analysis, we performed preprocessing to transform it into scalograms. We devised a water leak detection method by applying transfer learning to five distinct Convolutional Neural Network (CNN) variants, which are namely EfficientNet, ResNet, AlexNet, MobileNet V1, and MobileNet V2. The CNN models were found to be able to detect leakages where a maximum testing accuracy, recall, precision, and F1 score of 97.45%, 98.57%, 96.70%, and 97.63%, respectively, were observed using the EfficientNet model. To enable seamless deployment on the Arduino Nano 33 BLE edge device, the EfficientNet model is compressed using quantization resulting in a low inference time of 1932 ms, a peak RAM usage of 255.3 kilobytes, and a flash usage requirement of merely 48.7 kilobytes. Full article

Cell density is an important factor in all microbiome research, where interactions are of interest. It is also the most important parameter for the operation and control of most biotechnological processes. In the past, cell density determination was often performed offline and manually, resulting in a delay between sampling and immediate data processing, preventing quick action. While there are now some online methods for rapid and automated cell density determination, they are unable to distinguish between the different cell types in bacterial communities. To address this gap, an online automated flow cytometry procedure is proposed for real-time high-resolution analysis of bacterial communities. On the one hand, it allows for the online automated calculation of cell concentrations and, on the other, for the differentiation between different cell subsets of a bacterial community. To achieve this, the OC-300 automation device (onCyt Microbiology, Zürich, Switzerland) was coupled with the flow cytometer CytoFLEX (Beckman Coulter, Brea, USA). The OC-300 performs the automatic sampling, dilution, fixation and 4′,6-diamidino-2-phenylindole (DAPI) staining of a bacterial sample before sending it to the CytoFLEX for measurement. It is demonstrated that this method can reproducibly measure both cell density and fingerprint-like patterns of bacterial communities, generating suitable data for powerful automated data analysis and interpretation pipelines. In particular, the automated, high-resolution partitioning of clustered data into cell subsets opens up the possibility of correlation analysis to identify the operational or abiotic/biotic causes of community disturbances or state changes, which can influence the interaction potential of organisms in microbiomes or even affect the performance of individual organisms. Full article

The paper proposes a new methodology for revamping design and optimization of a process piping system. Starting from ASME B31.3 Process Piping prescriptions for stress analysis, a nonlinear model is built to express the relationship between stress distribution generated by expansion and sustained loads (pressure, weight) and the geometry and routing of the pipeline, focusing on geometric parameters of expansion loops. The number of design variables affecting stress distribution over the pipe, together with the constraints to be respected, would make it hard to formulate an optimization procedure based on deterministic methods. This problem is overcome by applying a Feed Forward Neural Network, backpropagation trained, which makes it possible to interpolate a non-linear and multidimensional relation over a domain enclosed within the boundaries of a training set. Prediction of code stresses is obtained through the fitting of an artificial neural network for each examined loadcases. Network parameters are tuned offline, starting from a set of data obtained by finite element numerical simulation. As a result, an optimal geometry for expansion loops is found, allowing to revamp pipe routing by halving loops number and keeping code stress within the allowable limits. Full article

With the increase in transmission pressure and pipe diameter of long-distance oil and gas pipelines, automatic welding of the pipeline has become the mainstream welding method. The multi-layer and multi-pass welding path planning of large-diameter pipelines with typical narrow gap grooves are studied, and a welding strategy for pipeline external welding robot is proposed. By analyzing the shape of the weld bead section of the narrow gap groove and comparing the advantages and disadvantages of the equal-height method and the equal-area method, the mathematical model of the filling layer is established. Through the test and analysis in the workshop, the predicted lifting value meets the actual welding requirements. The microstructure of the weld was analyzed by SEM. The main structure of the weld was fine acicular ferrite, which could improve the mechanical properties of the welded joint. After multi-layer filling, the filling layer is flush with the edge of the groove. The establishment of this model lays a foundation for the formulation of welding process parameters for large-diameter pipes and the off-line programming of welding procedures. Full article

Dynamic data security in embedded systems is raising more and more concerns in numerous safety-critical applications. In particular, the data exchanges in embedded Systems-on-Chip (SoCs) using main memory are exposing many security vulnerabilities to external attacks, which will cause confidential information leakages and program execution failures for SoCs at key points. Therefore, this paper presents a security SoC architecture with integrating a four-parallel Advanced Encryption Standard-Galois/Counter Mode (AES-GCM) cryptographic accelerator for achieving high-efficiency data processing to guarantee data exchange security between the SoC and main memory against bus monitoring, off-line analysis, and data tampering attacks. The architecture design has been implemented and verified on a Xilinx Virtex-5 Field Programmable Gate Array (FPGA) platform. Based on evaluation of the cryptographic accelerator in terms of performance overhead, security capability, processing efficiency, and resource consumption, experimental results show that the parallel cryptographic accelerator does not incur significant performance overhead on providing confidentiality and integrity protections for exchanged data; its average performance overhead reduces to as low as 2.65% on typical 8-KB I/D-Caches, and its data processing efficiency is around 3 times that of the pipelined AES-GCM construction. The reinforced SoC under the data tampering attacks and benchmark tests confirms the effectiveness against external physical attacks and satisfies a good trade-off between high-efficiency and hardware overhead. Full article

This paper introduces a technique using a k-nearest neighbor (k-NN) classifier and hybrid features extracted from acoustic emission (AE) signals for detecting leakages in a gas pipeline. The whole algorithm is embedded in a microcontroller unit (MCU) to detect leaks in real-time. The embedded system receives signals continuously from a sensor mounted on the surface of a gas pipeline to diagnose any leak. To construct the system, AE signals are first recorded from a gas pipeline testbed under various conditions and used to synthesize the leak detection algorithm via offline signal analysis. The current work explores different features of normal/leaking states from corresponding datasets and eliminates redundant and outlier features to improve the performance and guarantee the real-time characteristic of the leak detection program. To obtain the robustness of leak detection, the paper normalizes features and adapts the trained k-NN classifier to the specific environment where the system is installed. Aside from using a classifier for categorizing normal/leaking states of a pipeline, the system monitors accumulative leaking event occurrence rate (ALEOR) in conjunction with a defined threshold to conclude the state of the pipeline. The entire proposed system is implemented on the 32F746G-DISCOVERY board, and to verify this system, numerous real AE signals stored in a hard drive are transferred to the board. The experimental results show that the proposed system executes the leak detection algorithm in a period shorter than the total input data time, thus guaranteeing the real-time characteristic. Furthermore, the system always yields high average classification accuracy (ACA) despite adding a white noise to input signal, and false alarms do not occur with a reasonable ALEOR threshold. Full article

Field laboratories interested in using the MinION often need the internet to perform sample analysis. Thus, the lack of internet connectivity in resource-limited or remote locations renders downstream analysis problematic, resulting in a lack of sample identification in the field. Due to this dependency, field samples are generally transported back to the lab for analysis where internet availability for downstream analysis is available. These logistics problems and the time lost in sample characterization and identification, pose a significant problem for field scientists. To address this limitation, we have developed a stand-alone data analysis packet using open source tools developed by the Nanopore community that does not depend on internet availability. Like Oxford Nanopore Technologies’ (ONT) cloud-based What’s In My Pot (WIMP) software, we developed the offline MinION Detection Software (MINDS) based on the Centrifuge classification engine for rapid species identification. Several online bioinformatics applications have been developed surrounding ONT’s framework for analysis of long reads. We have developed and evaluated an offline real time classification application pipeline using open source tools developed by the Nanopore community that does not depend on internet availability. Our application has been tested on ATCC’s 20 strain even mix whole cell (ATCC MSA-2002) sample. Using the Rapid Sequencing Kit (SQK-RAD004), we were able to identify all 20 organisms at species level. The analysis was performed in 15 min using a Dell Precision 7720 laptop. Our offline downstream bioinformatics application provides a cost-effective option as well as quick turn-around time when analyzing samples in the field, thus enabling researchers to fully utilize ONT’s MinION portability, ease-of-use, and identification capability in remote locations. Full article

The use of a personal computer together with a Data Acquisition System (DAQ) as the processing tool in optical tomography systems has been the norm ever since the beginning of process tomography. However, advancements in silicon fabrication technology allow nowadays the fabrication of powerful Digital Signal Processors (DSP) at a reasonable cost. This allows this technology to be used in an optical tomography system since data acquisition and processing can be performed within the DSP. Thus, the dependency on a personal computer and a DAQ to sample and process the external signals can be reduced or even eliminated. The DSP system was customized to control the data acquisition process of 16x16 optical sensor array, arranged in parallel beam projection. The data collected was used to reconstruct the cross sectional image of the pipeline conveyor. For image display purposes, the reconstructed image was sent to a personal computer via serial communication. This allows the use of a laptop to display the tomogram image besides performing any other offline analysis. Full article