Detection of Anomalous Behavior in Modern Smartphones Using Software Sensor-Based Data

This paper describes the steps involved in obtaining a set of relevant data sources and the accompanying method using software-based sensors to detect anomalous behavior in modern smartphones based on machine-learning classifiers. Three classes of models are investigated for classification: logistic regressions, shallow neural nets, and support vector machines. The paper details the design, implementation, and comparative evaluation of all three classes. If necessary, the approach could be extended to other computing devices, if appropriate changes were made to the software infrastructure, based upon mandatory capabilities of the underlying hardware.

Software Sensor for Airflow Modulation and Noise Detection by Cyclostationary Tools

The paper presents tools to model low speed airflow coming from a turbulent machine. This low speed flow have instabilities who generate noise disturbances in the environment. The aim of the study proposed in this paper, is the using of cyclostationary tools with audio signals to model this airflow and detect the noisy frequencies to eliminate this noise. This paper also deals with the extraction in real time of the frequency corresponding to the noise nuisance. This extraction makes it possible to build a software sensor. This software sensor can be used to estimate the air flow rate and also to control a future actuator which will reduce the intensity of the noise nuisance. This paper focuses on the characteristic of the sound signal (property of cyclostationarity) and on the development of a software sensor. The results are established using an experimental setup representative of the physical phenomenon to be characterised.

PENGGUNAAN DHT11 DAN ARDUINO UNO SEBAGAI PENDETEKSI SUHU PADA LAPTOP

Laptop merupakan salah satu perangkat elektronik atau komputer yang membantu pekerjaan manusia yang sangat sering digunakan. Penggunaan laptop yang terlalu berlebihan dapat menyebabkan laptop menjadi panas/overheat. Jika dibiarkan akan menimbulkan masalah pada laptop. Overheating merupakan salah satu penyebab utama kerusakan hard drive. Kerusakan ini dapat dicegah dengan menggunakan software sensor suhu, salah satunya adalah DHT11 dan Aduino Uno. DHT11 adalah salah satu sensor yang digunakan untuk mengukur suhu dan kelembaman (humidity). Sedangkan Aduino Uno adalah kit atau papan rangkaian elektronik yang di dalamnya terdapat komponen utama yaitu sebuah chip mikrokontroler. Mikrokontroler pada arduino dapat di program menggunakan komputer sesuai kebutuhan. Tujuan dari penelitian ini adalah untuk membuat alat pendeteksi suhu pada laptop dengan menggunakan sensor DHT11 sebagai sensor suhu pada laptop yang diteliti, mikrokontroler ATMega328P sebagai pemrosesan data dan memanfaatkan teknologi kode pemrogram sebagai sarana informasi secara cepat dan akurat. Penggunaan Arduino uno sebagai sistem pengendali pada alat pendeteksi dengan menggunakan kode pemrogram dan sebagai hasil output yang dikeluarkan pada laptop. Metode penelitian yang digunakan dalam penelitian ini adalah metode Research and Development dengan model prototype. Berdasarkan penelitian yang telah dilakukan pada berbagai merek laptop, hasil menunjukkan bahwa suhu ketiga merek laptop masih dalam keadaan baik dan ideal. Secara umum hasil penelitian dapat disimpulkan bahwa: 1) Alat pendeteksi suhu yang dirancang dapat mengukur suhu pada laptop secara terus menerus, 2) Sistem dapat memberikan informasi suhu pada laptop kepada pengguna secara tepat dan akurat. 3) Alat pendeteksi dapat mendeteksi suhu dan melihat suhu ideal, suhu normal dan suhu yang tidak stabil.

Software Sensors for Biomass Concentration Estimation in Filamentous Microorganism Cultivation Process

In this study, the potential of two software sensors for on-line estimation of biomass concentration during cultivation of filamentous microorganisms is examined. The first sensor is based on common bioreactor off-gas analyses, and uses the assumption of the biomass concentration linear dependence on the square root of cumulative O2 consumption. Parameters of the semi-empirical data-driven software sensor based on off-gas analysis were calculated from experimental cultivation data using linear regression. The second sensor is based on biocalorimetry, i.e., the on-line calculation of metabolic heat flux from general enthalpy balance of the bioreactor. The software sensor based on biocalorimetry thus essentially represents a model-driven approach, making use of a fundamental process model based on the enthalpy balance around the bioreactor. This approach has been combined with the experimental identification of the specific biomass heat production, which represents the main process-specific parameter of the software sensor based on biocalorimetry. For this sensor, the accuracy requirements on the process variable on-line measurements were also analysed. The experimental data from the pilot-scale antibiotics Nystatin production by a bacterium Streptomyces noursei were used to calculate the specific bioprocess heat production value using linear regression. The achieved results enabled us to propose a new on-line indicator calculated as the ratio of the outputs of both sensors, which can serve as a timely warning of the risk of undesired nutritional conditions of a culture characterized as underfeeding.

Software Sensor for Activity-Time Monitoring and Fault Detection in Production Lines

Industry 4.0-based human-in-the-loop cyber-physical production systems are transforming the industrial workforce to accommodate the ever-increasing variability of production. Real-time operator support and performance monitoring require accurate information on the activities of operators. The problem with tracing hundreds of activity times is critical due to the enormous variability and complexity of products. To handle this problem a software-sensor-based activity-time and performance measurement system is proposed. To ensure a real-time connection between operator performance and varying product complexity, fixture sensors and an indoor positioning system (IPS) were designed and this multi sensor data merged with product-relevant information. The proposed model-based performance monitoring system tracks the recursively estimated parameters of the activity-time estimation model. As the estimation problem can be ill-conditioned and poor raw sensor data can result in unrealistic parameter estimates, constraints were introduced into the parameter-estimation algorithm to increase the robustness of the software sensor. The applicability of the proposed methodology is demonstrated on a well-documented benchmark problem of a wire harness manufacturing process. The fully reproducible and realistic simulation study confirms that the indoor positioning system-based integration of primary sensor signals and product-relevant information can be efficiently utilized in terms of the constrained recursive estimation of the operator activity.