scholarly journals Self-Protected Virtual Sensor Network for Microcontroller Fault Detection

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 454
Author(s):  
German Sternharz ◽  
Jonas Skackauskas ◽  
Ayman Elhalwagy ◽  
Anthony J. Grichnik ◽  
Tatiana Kalganova ◽  
...  
Keyword(s):  
Sensor Network ◽  
Short Term Memory ◽  
Model Output ◽  
Validation Data ◽  
Virtual Sensor ◽  
Physical Sensor ◽  
Signal Sample ◽  
Electronic Hardware ◽  
Self Protection

This paper introduces a procedure to compare the functional behaviour of individual units of electronic hardware of the same type. The primary use case for this method is to estimate the functional integrity of an unknown device unit based on the behaviour of a known and proven reference unit. This method is based on the so-called virtual sensor network (VSN) approach, where the output quantity of a physical sensor measurement is replicated by a virtual model output. In the present study, this approach is extended to model the functional behaviour of electronic hardware by a neural network (NN) with Long-Short-Term-Memory (LSTM) layers to encapsulate potential time-dependence of the signals. The proposed method is illustrated and validated on measurements from a remote-controlled drone, which is operated with two variants of controller hardware: a reference controller unit and a malfunctioning counterpart. It is demonstrated that the presented approach successfully identifies and describes the unexpected behaviour of the test device. In the presented case study, the model outputs a signal sample prediction in 0.14 ms and achieves a reconstruction accuracy of the validation data with a root mean square error (RMSE) below 0.04 relative to the data range. In addition, three self-protection features (multidimensional boundary-check, Mahalanobis distance, auxiliary autoencoder NN) are introduced to gauge the certainty of the VSN model output.

scholarly journals Survivability-Enhanced Virtual Network Embedding Strategy in Virtualized Wireless Sensor Networks

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 218
Author(s):  
Dapeng Wu ◽  
Zhenli Liu ◽  
Zhigang Yang ◽  
Puning Zhang ◽  
Ruyan Wang ◽  
...  
Keyword(s):  
Wireless Sensor Networks ◽  
Sensor Networks ◽  
Sensor Network ◽  
Sensor Nodes ◽  
Virtual Network ◽  
Wireless Sensor ◽  
Virtual Network Embedding ◽  
Network Embedding ◽  
Virtual Sensor ◽  
Physical Sensor

With the widespread application of wireless sensor networks (WSNs), WSN virtualization technology has received extensive attention. A key challenge in WSN virtualization is the survivable virtual network embedding (SVNE) problem which efficiently maps a virtual network on a WSN accounting for possible substrate failures. Aiming at the lack of survivability research towards physical sensor node failure in the virtualized sensor network, the SVNE problem is mathematically modeled as a mixed integer programming problem considering resource constraints. A heuristic algorithm—node reliability-aware backup survivable embedding algorithm (NCS)—is further put forward to solve this problem. Firstly, a node reliability-aware embedding method is presented for initial embedding. The resource reliability of underlying physical sensor nodes is evaluated and the nodes with higher reliability are selected as mapping nodes. Secondly, a fault recovery mechanism based on resource reservation is proposed. The critical virtual sensor nodes are recognized and their embedded physical sensor nodes are further backed up. When the virtual sensor network (VSN) fails caused by the failure physical node, the operation of the VSN is restored by backup switching. Finally, the experimental results show that the strategy put forward in this paper can effectively guarantee the survivability of the VSN, reduce the failure penalty caused by the physical sensor nodes failure, and improve the long-term operating income of infrastructure provider.

Deep Reinforcement Learning for Multiparameter Optimization in de novo Drug Design

2019 ◽  
Author(s):  
Niclas Ståhl ◽  
Göran Falkman ◽  
Alexander Karlsson ◽  
Gunnar Mathiason ◽  
Jonas Boström
Keyword(s):  
Reinforcement Learning ◽  
Short Term Memory ◽  
De Novo ◽  
De Novo Drug Design ◽  
Generative Process ◽  
New Methods ◽  
Multiparameter Optimization ◽  
Long Short Term Memory ◽  
New Compounds

<p>In medicinal chemistry programs it is key to design and make compounds that are efficacious and safe. This is a long, complex and difficult multi-parameter optimization process, often including several properties with orthogonal trends. New methods for the automated design of compounds against profiles of multiple properties are thus of great value. Here we present a fragment-based reinforcement learning approach based on an actor-critic model, for the generation of novel molecules with optimal properties. The actor and the critic are both modelled with bidirectional long short-term memory (LSTM) networks. The AI method learns how to generate new compounds with desired properties by starting from an initial set of lead molecules and then improve these by replacing some of their fragments. A balanced binary tree based on the similarity of fragments is used in the generative process to bias the output towards structurally similar molecules. The method is demonstrated by a case study showing that 93% of the generated molecules are chemically valid, and a third satisfy the targeted objectives, while there were none in the initial set.</p>

Improving Casthouse Throughput Using Discrete-Event Modelling

2011 ◽  
Vol 693 ◽  
pp. 3-9 ◽  
Author(s):  
Bruce Gunn ◽  
Yakov Frayman
Keyword(s):  
Sensitivity Analysis ◽  
Discrete Event ◽  
Casting Machine ◽  
Production Data ◽  
Model Output ◽  
Arrival Times ◽  
Event Simulation ◽  
Modelling System ◽  
Key Parameter

The scheduling of metal to different casters in a casthouse is a complicated problem, attempting to find the balance between pot-line, crucible carrier, furnace and casting machine capacity. In this paper, a description will be given of a casthouse modelling system designed to test different scenarios for casthouse design and operation. Using discrete-event simulation, the casthouse model incorporates variable arrival times of metal carriers, crucible movements, caster operation and furnace conditions. Each part of the system is individually modelled and synchronised using a series of signals or semaphores. In addition, an easy to operate user interface allows for the modification of key parameters, and analysis of model output. Results from the model will be presented for a case study, which highlights the effect different parameters have on overall casthouse performance. The case study uses past production data from a casthouse to validate the model outputs, with the aim to perform a sensitivity analysis on the overall system. Along with metal preparation times and caster strip-down/setup, the temperature evolution within the furnaces is one key parameter in determining casthouse performance.

scholarly journals Arabic dialect sentiment analysis with ZERO effort. \\ Case study: Algerian dialect

2020 ◽  
Vol 23 (65) ◽  
pp. 124-135
Author(s):  
Imane Guellil ◽  
Marcelo Mendoza ◽  
Faical Azouaou
Keyword(s):  
Sentiment Analysis ◽  
Short Term Memory ◽  
State Of The Art ◽  
Short Term ◽  
Term Memory ◽  
Ongoing Work ◽  
Long Short Term Memory ◽  
Large Corpus ◽  
Unique Condition

This paper presents an analytic study showing that it is entirely possible to analyze the sentiment of an Arabic dialect without constructing any resources. The idea of this work is to use the resources dedicated to a given dialect \textit{X} for analyzing the sentiment of another dialect \textit{Y}. The unique condition is to have \textit{X} and \textit{Y} in the same category of dialects. We apply this idea on Algerian dialect, which is a Maghrebi Arabic dialect that suffers from limited available tools and other handling resources required for automatic sentiment analysis. To do this analysis, we rely on Maghrebi dialect resources and two manually annotated sentiment corpus for respectively Tunisian and Moroccan dialect. We also use a large corpus for Maghrebi dialect. We use a state-of-the-art system and propose a new deep learning architecture for automatically classify the sentiment of Arabic dialect (Algerian dialect). Experimental results show that F1-score is up to 83% and it is achieved by Multilayer Perceptron (MLP) with Tunisian corpus and with Long short-term memory (LSTM) with the combination of Tunisian and Moroccan. An improvement of 15% compared to its closest competitor was observed through this study. Ongoing work is aimed at manually constructing an annotated sentiment corpus for Algerian dialect and comparing the results

scholarly journals Prediksi Kunjungan Wisatawan Taman Nasional Gunung Merbabu dengan Time Series Forecasting dan LSTM

2020 ◽  
Vol 11 (2) ◽  
pp. 131
Author(s):  
Josua Manullang ◽  
Albertus Joko Santoso ◽  
Andi Wahju Rahardjo Emanuel
Keyword(s):  
Time Series ◽  
National Park ◽  
Short Term Memory ◽  
Lag Time ◽  
Time Series Forecasting ◽  
Mean Square ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

Abstract. Prediction of tourist visits of Mount Merbabu National Park (TNGMb) needs to be done to control the number of visitors and to preserve the national park. The combination of time series forecasting (TSF) and deep learning methods has become a new alternative for prediction. This case study was conducted to implement several methods combination of TSF and Long-Short Term Memory (LSTM) to predict the visits. In this case study, there are 18 modelling scenarios as research objects to determine the best model by utilizing tourist visits data from 2013 to 2018. The results show that the model applying the lag time method can improve the model's ability to capture patterns on time series data. The error value is measured using the root mean square error (RMSE), with the smallest value of 3.7 in the LSTM architecture, using seven lags as a feature and one lag as a label.Keywords: Tourist Visit, Taman Nasional Gunung Merbabu, Prediction, Recurrent Neural Network, Long-Short Term MemoryAbstrak. Prediksi kunjungan wisatawan Taman Nasional Gunung Merbabu (TNGMb) perlu dilakukan untul pengendalian jumlah pengunjung dan menjaga kelestarian taman nasional. Gabungan metode antara time series forecasting (TSF) dan deep learning telah menjadi alternatif baru untuk melakukan prediksi. Studi kasus ini dilakukan untuk mengimplementasi gabungan dari beberapa macam metode antara TSF dan Long-Short Term Memory (LSTM) untuk memprediksi kunjungan pada TNGMb. Pada studi kasus ini, terdapat 18 skenario pemodelan sebagai objek penelitian untuk menentukan model terbaik, dengan memanfaatkan data jumlah kunjungan wisatawan di TNGMb mulai dari tahun 2013 sampai dengan tahun 2018. Hasil prediksi menunjukkan pemodelan dengan menerapkan metode lag time dapat meningkatakan kemampuan model untuk menangkap pola pada data deret waktu. Besar nilai kesalahan diukur menggunakan root mean square error (RMSE), dengan nilai terkecil sebesar 3,7 pada arsitektur LSTM, menggunakan tujuh lag sebagai feature dan satu lag sebagai label. Kata Kunci: Kunjungan Wisatawan, Taman Nasional Gunung Merbabu, Prediksi, Recurrent Neural Network, Long-Short Term Memory

Peak Load Forecasting Using Long-Short Term Memory : Case Study of Jawa-Madura-Bali System

2021 ◽  
Author(s):  
Anindita Satria Surya ◽  
Musa Partahi Marbun ◽  
K.G.H. Mangunkusumo ◽  
Muhammad Ridwan
Keyword(s):  
Short Term Memory ◽  
Peak Load ◽  
Load Forecasting ◽  
Short Term ◽  
Term Memory ◽  
Long Short Term Memory

scholarly journals Bayesian network-based methodology for selecting a cost-effective sewer asset management model

2020 ◽  
Author(s):  
Julián Guzmán-Fierro ◽  
Sharel Charry ◽  
Ivan González ◽  
Felipe Peña-Heredia ◽  
Nathalie Hernández ◽  
...  
Keyword(s):  
Asset Management ◽  
Kappa Coefficient ◽  
Wilcoxon Test ◽  
Cohen’S Kappa ◽  
Validation Data ◽  
Statistical Measures ◽  
Proactive Management ◽  
Cohen's Kappa ◽  
Cohen’S Kappa Coefficient

Abstract This paper presents a methodology based on Bayesian Networks (BN) to prioritise and select the minimal number of variables that allows predicting the structural condition of sewer assets to support the strategies in proactive management. The integration of BN models, statistical measures of agreement (Cohen's Kappa coefficient) and a statistical test (Wilcoxon test) were useful for a robust and straightforward selection of a minimum number of variables (qualitative and quantitative) that ensure a suitable prediction level of the structural conditions of sewer pipes. According to the application of the methodology to a specific case study (Bogotás sewer network, Colombia), it found that with only two variables (age and diameter) the model could achieve the same capacity of prediction (Cohen's Kappa coefficient = 0.43) as a model considering several variables. Furthermore, the methodology allows finding the calibration and validation percentage subsets that best fit (80% for calibration and 20% for validation data in the case study) in the model to increase the capacity of prediction with low variations. Furthermore, it found that a model, considering only pipes in critical and excellent conditions, increases the capacity of successful predictions (Cohen's Kappa coefficient from 0.2 to 0.43) for the proposed case study.

Sign in / Sign up

Export Citation Format

Share Document