Sensor Database Research Articles

Application of electronic nose and machine learning used to detect soybean gases under water stress and variability throughout the daytime.

The development of non-invasive methods and accessible tools for application to plant phenotyping is considered a breakthrough. This work presents the preliminary results using an electronic nose (E-Nose) and machine learning (ML) as affordable tools. An E-Nose is an electronic system used for smell global analysis, which emulates the human nose structure. The soybean (Glycine Max) was used to conduct this experiment under water stress. Commercial E-Nose was used, and a chamber was designed and built to conduct the measurement of the gas sample from the soybean. This experiment was conducted for 22 days, observing the stages of plant growth during this period. This chamber is embedded with relative humidity [RH (%)], temperature (°C), and CO2 concentration (ppm) sensors, as well as the natural light intensity, which was monitored. These systems allowed intermittent monitoring of each parameter to create a database. The soil used was the red-yellow dystrophic type and was covered to avoid evapotranspiration effects. The measurement with the electronic nose was done daily, during the morning and afternoon, and in two phenological situations of the plant (with the healthful soy irrigated with deionized water and underwater stress) until the growth V5 stage to obtain the plant gases emissions. Data mining techniques were used, through the software "Weka™" and the decision tree strategy. From the evaluation of the sensors database, a dynamic variation of plant respiration pattern was observed, with the two distinct behaviors observed in the morning (~9:30 am) and afternoon (3:30 pm). With the initial results obtained with the E-Nose signals and ML, it was possible to distinguish the two situations, i.e., the irrigated plant standard and underwater stress, the influence of the two periods of daylight, and influence of temporal variability of the weather. As a result of this investigation, a classifier was developed that, through a non-invasive analysis of gas samples, can accurately determine the absence of water in soybean plants with a rate of 94.4% accuracy. Future investigations should be carried out under controlled conditions that enable early detection of the stress level.

Effect of environmental variables on the incidence of Visceral Leishmaniasis in Brazil and Colombia

Visceral Leishmaniasis (VL) is the most severe of the three forms of Leishmaniasis. In the Americas, Brazil and Colombia present more than 90 % of the cases in the region. Our aim in this research was to estimate the association of the incidence rate of Visceral Leishmaniasis with the following environmental variables: the percentage of area suitable for the vector Lutzomyia longipalpis, the episodes of La Niña and El Niño, the Brazilian and Colombian biomes. Epidemiological data were obtained from the Brazilian Notifiable Diseases Information System and the Colombian National Public Health Surveillance System. Environmental data were downloaded from the NASA Giovanni web app, the Modis Sensor database, and the meteorological agencies of Australia, Japan, and the United States of America. Records of the presence of Lu. longipalpis were obtained from public databases and previous studies. As a result, the incidence per 10,000 inhabitants with LEBS for each El Niño-Southern Oscillation (ENSO) episode showed the largest values during El Niño 2015–2016, mainly in Brazil's Northeast and Central regions and the Northeast region of Colombia. Compared with the Neutral 2012–2014 episode, the episodes of El Niño 2015–2016 and La Niña 2010–2011 showed an average increase in the monthly incidence rate of VL, and the average increase was higher during El Niño 2015–2016 (aIRR = 2.304 vs.1.453) We found a positive association between the incidence rate of VL and the El Niño 2015–2016 episode and an impressive% of area suitable for the vector Lu. longipalpis in the Amazon region.An increase of 1 % in the area suitable for the vector Lu. longipalpis leads to an average rise of 0.8 % in the monthly incidence rate of VL. Our study shows a possible association between VL incidence and ENSO, with the most considerable incidence rates observed during El Niño 2015–2016 in Brazil's Northeast and Central regions and the Northeast region of Colombia. The present study is very important to better understand the Visceral Leishmaniasis transmission dynamics.

PENERAPAN SENSOR CJMCU101 UNTUK MENDUKUNG SISTEM SMART LECTURE ROOM

This study presents the design of a Smart Lecture Room system that utilizes light intensity sensors, specifically CJMCU101. These sensors are installed in each classroom to monitor the ambient conditions. The implementation of the designed system was carried out in the classrooms of the Udayana University Electrical Engineering Study Program. To achieve this goal, the classroom utilized by the Electrical Engineering Study Program of Udayana University was divided into two classes (DH101 and DH102) and a sensor was installed in each class as an IoT device. The IoT devices are connected to a Raspberry Pi Access Point, where the data from the sensors is stored and monitored using the Thinger.io platform. The validation of the sensor testing is carried out by comparing the results obtained from the sensors with the results obtained from a thermohygrometer measurement. This research produces a prototype smart lecture system, applied to a classroom mockup, that employs IoT devices, sensor databases, and sensor monitoring. The data from each sensor's detection is stored in the LAMP database, which employs Linux, Apache, MySQL, and PHP. The Thinger.io platform monitors the values of each sensor. A variation in accuracy between the sensor and measuring instrument results in a difference in their values. The CJMCU101 light intensity sensor has an average accuracy of 93.48% compared to the measuring instrument on DH101. The average accuracy of the sensor value compared to the measuring instrument on DH102 is 95.96%.

PREDICTION, MONITORING, AND EARLY WARNING SYSTEM OF WATER LEVELS IN FLOOD PROGRAM AREAS IN BANJARMASIN USING IoT AND LINEAR REGRESSION

Banjarmasin is a city of a thousand rivers, floods often occur due to high tides and accompanied by rain. An early warning system is needed for monitoring and predicting river tides, especially in rivers that are prone to disasters. This study aims to develop an early warning system for river water levels using IoT and predicting linear regression analysis. The research method is through the manufacture of the NodeMCU V3 early warning system device , Microcontroller, and Ultrasonic A02YYUW. Monitoring to collect water level data at high tide is carried out on the banks of the river, then predictions are made using simple linear regression analysis. The results showed that an early warning system for river water levels at high tide can be read in the A02YYUW ultrasonic sensor database which is sent to the Mysql database. Water surface distance data with tools are used to predict early warning, simple regression analysis shows significant results on the t test and simple linear regression equation = 29.472 - 0.061 X + e. This means that the river water level at high tide approaches an early warning tool, namely an ultrasonic sensor. The conclusion of this study is that an IoT-based early warning system combined with simple linear regression can monitor and predict river water level rise.

IOT BASED RAILWAY ACCIDENT PREVENTION AND MONITORING SYSTEM

The railways are the most common and flexible mode of transportation in the majority of the world's urban areas. The railway is a popular, inexpensive, and pleasurable mode of transportation. It is accessible to people from all walks of life. The rail transportation infrastructure is essential for travel in the modern day; nonetheless, numerous accidents occur on railway lines as a result of reckless driving, particularly during morning and evening rush hours, and pedestrians crossing while using mobile phones. To prevent railway accidents, a better technique must be invented, thus we created this project to tell pedestrians when a train is coming within a specific distance, so ensuring their safety and providing the security department with an alarm signal. The project entitled "IOT based Railway Accident Prevention and Monitoring System" is based on the Internet of Things and a live sensor database, which offers a method for preventing railway accidents. Its objective is to keep people safe by employing sirens to inform them of potential accidents at railroad grade crossings, to monitor any potentially hazardous conduct that might cause an accident at a railway grade crossing, and to provide the department and a person with an alert signal.

(Invited) Ceramic Nano-Heterostructures By Materials Design: Platforms for Sensing Applications – Opportunities and Challengess

This talk summarizes R&D efforts in the author’s laboratory on the fabrication of oxide nano-heterostructures, exploiting intrinsic material properties, that are highly scalable and do not require use of lithography. One such process creates crystallographically oriented nanofiber arrays of single crystal TiO2 in H2/N2 environment. H2/N2 heat treatment was also used to grow nanofibers on polycrystalline SnO2, showing directional growth on grains with crystal facets. We have also developed a process to create nanofibers of TiO2 on Ti metal/alloys via oxidation under a limited supply of oxygen. In another process, SnO2 nanowires grown from commercial FTO slides using the vapor-liquid-solid (VLS) method were placed in a microwave-assisted hydrothermal chamber where TiO2 nanorods nucleated radially from the SnO2 nanowire cores. We developed yet another interesting nano-structure (nanoislands and/or nanobars) during thermal annealing of an oxide (GDC) on top of another oxide (YSZ) substrate that self-assembles along the softest elastic direction of the substrate. What is common about these structures is that they are fabricated without the use of lithographic techniques and involves simple processes such as gas-phase reactions and stress-driven processes. These nano-heterostructures can be used as platforms for chemical sensing, catalysis, photocatalysis, photovoltaics and biomedical applications. Sensing application presents opportunities and challenges that are presented including an Open access Database Of Resistive type gas Sensors (ODORS) that has been developed and can be used to select suitable sensing materials.

Secure and Sustainable Framework for Cattle Recognition Using Wireless Multimedia Networks and Machine Learning Techniques

Towards the successful operation of any farm, effective livestock management is necessary. The efficiency, affordability, and scalability of management solutions play a crucial role in modern farming. In this paper, a novel low-cost framework is proposed to recognize for health monitoring of individual cattle based on their sensed behavioral activity data and muzzle (nose) pattern image database using incremental decision tree classification techniques and accelerometer-based activity monitoring method. The proposed system performs image prepossessing on the captured muzzle point images of cattle to mitigate the noise, enhance the contrast, and increase quality. We extract the minutiae features to improve the system’s accuracy for recognizing the cattle for accurate and early classification of behavioral activity for health monitoring. The proposed system uses a support vector machine and incremental decision tree classifiers to classify the extracted feature of cattle’s muzzle images and health database. The server has encrypted databases that consist of captured muzzle images, owner database, health sensor database provided by the owners and systems. We use a similarity score measurement using incremental decision tree classification for matching and classify the muzzle point featutes with the database for cattle identification and health monitoring. We also developed a prototype for evaluating the accuracy of the proposed system with 97.99% accuarcy for unique identification of individual cattle.

Traffic controlling and monitoring using IoT

The population is increasing the number of vehicles and the number of highways day after day; the time spent travelling, waste fuel, air pollution and related transport problems are also increasing. The greatest challenge for traffic administration authorities is therefore to monitor and monitor traffic. The related work has shown the Internet of Things and the integration of artificial intelligence to facilitate techniques for better urban and decision­making. This document creates a system model for IoT-based traffic information collection, processing and storing in real time. The aim is to ensure smooth mobility by providing roadside communications updates and rare incidents in real time. In particular, pre-alerting messages prevent and delay road congestion and peak hours in emergencies. The system also sends traffic updates from the database of administrative sensors. The system proposed evaluates the feature of the model and shows expected accurate results for vehicle detection and the minimum error in the estimates of occupancy.

An Efficient HVAC Network Control for Safety Enhancement of a Typical Uninterrupted Power Supply Battery Storage Room

Lead-acid batteries utilised in electrical substations release hydrogen and oxygen when these are charged. These gases could be dangerous and cause a risk of fire if they are not properly ventilated. Therefore, this research seeks to design and implement a network control panel for heating, ventilation, and air conditioning system (HVACS). This is achieved by using a specific range of controllers, which have more than thirty loops of proportional, integral, and derivative (PID) control to achieve a cost-effective design. It performs the required function of extracting hydrogen and oxygen, maintaining the desired temperature of the battery storage room within recommended limits (i.e., 25 ± 1 °C tolerance) without compromising quality, as set out in the user requirement specification. The system control panel allows the user to access control parameters such as changing temperature set-points, fan-speed, sensor database, etc. It does this automatically and allows no human interface after all necessary settings and installation are completed. The hardware is configured to detect extreme hydrogen and oxygen gas content in the battery room and to ensure that the HVACS extracts the gas content to the outside environment. The system’s results show that the network control panel operates effectively as per the recommended system requirements. Therefore, the effective operation of the HVACS ensures sufficient gas ventilation, thus mitigating the risk of fire in a typical battery storage room. Furthermore, this also enhances battery lifespan because of regulated operating temperature, which is conducive to minimise the effect of sulfation in lead–acid batteries (LAB). The extraction of toxic gases, regulation of temperature, ensuring suitable humidity in UPS battery room is important as it provides longer operational service of equipment, thus reducing frequent maintenance in these rooms. This benefits the electricity supply industry and helps in saving for unplanned maintenance costs.

Data Mining-based Structural Damage Identification of Composite Bridge using Support Vector Machine

A structural health monitoring system contains two components, i.e. a data collection approach comprising a network of sensors for recording the structural responses as well as an extraction methodology in order to achieve beneficial information on the structural health condition. In this regard, data mining which is one of the emerging computer-based technologies, can be employed for extraction of valuable information from obtained sensor databases. On the other hand, data inverse analysis scheme as a problem-based procedure has been developing rapidly. Therefore, the aforesaid scheme and data mining should be combined in order to satisfy increasing demand of data analysis, especially in complex systems such as bridges. Consequently, this study develops a damage detection methodology based on these strategies. To this end, an inverse analysis approach using data mining is applied for a composite bridge. To aid the aim, the support vector machine (SVM) algorithm is utilized to generate the patterns by means of vibration characteristics dataset. To compare the robustness and accuracy of the predicted outputs, four kernel functions, including linear, polynomial, sigmoid, and radial basis function (RBF) are applied to build the patterns. The results point out the feasibility of the proposed method for detecting damage in composite slab-on-girder bridges.

Recording earthquakes for tomographic imaging of the mantle beneath the South Pacific by autonomous MERMAID floats

SUMMARYWe present the first 16 months of data returned from a mobile array of 16 freely floating diving instruments, named mermaid for Mobile Earthquake Recording in Marine Areas by Independent Divers, launched in French Polynesia in late 2018. Our 16 are a subset of the 50 mermaid deployed over a number of cruises in this vast and understudied oceanic province as part of the collaborative South Pacific Plume Imaging and Modeling (SPPIM) project, under the aegis of the international EarthScope-Oceans consortium. Our objective is the hydroacoustic recording, from within the oceanic water column, of the seismic wavefield generated by earthquakes worldwide, and the nearly real-time transmission by satellite of these data, collected above and in the periphery of the South Pacific Superswell. This region, characterized by anomalously elevated oceanic crust and myriad seamounts, is believed to be the surface expression of deeply rooted mantle upwellings. Tomographically imaging Earth’s mantle under the South Pacific with data from these novel instruments requires a careful examination of the earthquake-to-mermaid traveltimes of the high-frequency P-wave detections within the windows selected for reporting by the discrimination algorithms on board. We discuss a workflow suitable for a fast-growing mobile sensor database to pick the relevant arrivals, match them to known earthquakes in global earthquake catalogues, calculate their traveltime residuals with respect to global seismic reference models, characterize their quality and estimate their uncertainty. We detail seismicity rates as recorded by mermaid over 16 months, quantify the completeness of our catalogue and discuss magnitude–distance relations of detectability for our network. The projected lifespan of an individual mermaid is 5 yr, allowing us to estimate the final size of the data set that will be available for future study. To prove their utility for seismic tomography we compare mermaid data quality against ‘traditional’ land seismometers and their low-cost Raspberry Shake counterparts, using waveforms recovered from instrumented island stations in the geographic neighbourhood of our floats. Finally, we provide the first analyses of traveltime anomalies for the new ray paths sampling the mantle under the South Pacific.

A new open-access online database for resistive-type gas sensor properties and performance

A new database has been established which will allow the gas sensor researcher to quickly and effectively compare published data to evaluate the state-of-the-art, identify deficiencies in the field, and discover trends in properties and performance that would otherwise be unidentifiable from the efforts of any one research group. This Open-access Database Of Resistive-type Sensors (ODORS) will remain openly accessible through a web browser at (www.odorsdatabase.com). The interface allows the user to search for, filter, and sort results based on materials composition, gas analyte, response magnitude, morphology, synthesis method, and many other relevant properties. The database has been established with data from over 150 recently published papers, but its further growth will rely on researchers around the world submitting their own published data via an easy-to-use form also available on the website. It is to the benefit of all researchers that they submit their own published data for inclusion in the database to increase discoverability and citations of their papers and exposure to their work.

Oblivious transfer with hidden access control and outsourced decryption from deterministic finite automata‐based functional encryption for an in‐vehicle sensor database system

AbstractVehicle sensors are continuously observing the state of the vehicle, collecting and transmitting data from/to surrounding road users. The sensors data are then processed and stored in an in‐vehicle sensor database in the form of records. These records can be accessed and shared by other vehicles or road side units with the aim to improve road safety. However, these records may contain a very sensitive information, such as vehicles' identifiers and location. This information requires extraordinary protection to ensure privacy and confidentiality of the vehicle users. In this article, we propose a secure oblivious transfer protocol with hidden access control and outsourced decryption from deterministic finite automata (DFA)‐based functional encryption (HACOT‐DFA). To reduce the computational costs for users with limited resources, we securely offload the heavy decryption overhead on the user side to an untrusted cloud server. Then, we experimentally compare our HACOT‐DFA protocol against existing HACOT protocols in three different platform settings: the smartphone, the desktop personal computer, and the embedded device Raspberry Pi. The analyses demonstrate that the proposed HACOT‐DFA protocol is more efficient and computationally stable than previous work. Our security proof holds in the standard model using a dual‐system encryption approach.

A Deep One-Pass Learning based on Pre-Training Weights for Smartphone-Based Recognition of Human Activities and Postural Transitions

We describe a new deep learning model – Deep One-Pass Learning (DOPL) for Smartphone-Based Recognition of Human Activities and Postural Transitions based on the Pre-Trained Weights, DOPL consists of several stacked convolutional layers to learn the features of the input and is able to learn features automatically, followed by the Extreme gradient boosting (XGBoost) as the last layer for predicting the class labels. DOPL is much faster in the training phase, because the input weights are optimal weights from the Pre-Trained weights module and it does not have to re-adjust weights repeatedly. Further, we replaced the final fully connected layer with XGBoost to increase predictive efficiency. In the worst case, our model with demonstrated an accuracy of 99.2% for the smartphone sensors database data, which was significantly better than CNN or XGBoost alone as well as several other models assessed.

Generation of Frequent sensor epochs using efficient Parallel Distributed mining algorithm in large IOT

Numerous data mining algorithms are implemented using huge volume of sensor data to generate the frequent item sets that are useful in many aspects such as to predict the behavioural sensor patterns of future events and to detect the survival of sensors in large IOT . Traditional data mining algorithms transactional databases to produce the frequent patterns. Since the rate of input data arrival in large IOT varies, it becomes difficult to mine the dynamic sensor database. This work proposes an efficient algorithm known as Vertical Partitioning Parallel Distributed Algorithm(VPPDA) that uses MapReduce framework to mine sensor epochs to detect the survival of sensors using association rules formed by generated frequent patterns. The proposed VPPDA eliminates overhead of interprocess communication, by introducing overlapped window concept implemented in MapReduce framework combined with Vertical partitioning approach to get better progress in execution time and accurate results. Additionally pipelining processing has been implemented in MapReduce framework that still increases the performance and generates the frequent sensor epochs patterns. The concept of pipeline processing was introduced to minimize the execution time and also make the situation adaptable to any input rate of incoming sensor epochs.

Data-Driven Identification of Hydrogen Sulfide Scavengers.

Hydrogen sulfide (H2 S) is an important signaling molecule whose up- and down-regulation have specific biological consequences. Although significant advances in H2 S up-regulation, by the development of H2 S donors, have been achieved in recent years, precise H2 S down-regulation is still challenging. The lack of potent/specific inhibitors for H2 S-producing enzymes contributes to this problem. We expect the development of H2 S scavengers is an alternative approach to address this problem. Since chemical sensors and scavengers of H2 S share the same criteria, we constructed a H2 S sensor database, which summarizes key parameters of reported sensors. Data-driven analysis led to the selection of 30 potential compounds. Further evaluation of these compounds identified a group of promising scavengers, based on the sulfonyl azide template. The efficiency of these scavengers in in vitro and in vivo experiments was demonstrated.

Data‐Driven Identification of Hydrogen Sulfide Scavengers

AbstractHydrogen sulfide (H2S) is an important signaling molecule whose up‐ and down‐regulation have specific biological consequences. Although significant advances in H2S up‐regulation, by the development of H2S donors, have been achieved in recent years, precise H2S down‐regulation is still challenging. The lack of potent/specific inhibitors for H2S‐producing enzymes contributes to this problem. We expect the development of H2S scavengers is an alternative approach to address this problem. Since chemical sensors and scavengers of H2S share the same criteria, we constructed a H2S sensor database, which summarizes key parameters of reported sensors. Data‐driven analysis led to the selection of 30 potential compounds. Further evaluation of these compounds identified a group of promising scavengers, based on the sulfonyl azide template. The efficiency of these scavengers in in vitro and in vivo experiments was demonstrated.

A survey on wireless sensor network databases

In recent years, the use of wireless sensors has increased drastically in most fields. Wireless Sensor Networks (WSNs) have attracted the interest of industries and they have been used in several application areas (military, health, transportation, agriculture). WSNs are ad-hoc networks, composed of sensor nodes, which are deployed in an area of interest, in order to monitor and to return information requested by users. Sensor data is transmitted to users over a central station, named base station. Data collection becomes more difficult when the number of sensors increases. Since about a decade, intensive research has started in order to deal with these problems. Many researchers suggested to structure the sensor data in the form of a database and reduce the number of communications and energy consumption in the network. They have often considered the network as a large database and the sensor node as a virtual table. In this article, the existing sensor database approaches in WSNs are studied. Firstly, we will provide the definition of sensor databases, then we will present their architecture and their characteristics. Thereafter, we will present and compare existing sensor database systems. Finally, we will conclude this paper with a discussion of some research issues in the field of sensor databases.

Dynamic Field Monitoring Based on Multitask Learning in Sensor Networks.

Field monitoring serves as an important supervision tool in a variety of engineering domains. An efficient monitoring would trigger an alarm timely once it detects an out-of-control event by learning the state change from the collected sensor data. However, in practice, multiple sensor data may not be gathered appropriately into a database for some unexpected reasons, such as sensor aging, wireless communication failures, and data reading errors, which leads to a large number of missing data as well as inaccurate or delayed detection, and poses a great challenge for field monitoring in sensor networks. This fact motivates us to develop a multitask-learning based field monitoring method in order to achieve an efficient detection when considerable missing data exist during data acquisition. Specifically, we adopt a log likelihood ratio (LR)-based multivariate cumulative sum (MCUSUM) control chart given spatial correlation among neighboring regions within the monitored field. To deal with the missing data problem, we integrate a multitask learning model into the LR-based MCUSUM control chart in the sensor network. Both simulation and real case studies are conducted to validate our proposed approach and the results show that our approach can achieve an accurate and timely detection for an out-of-control state when a large number of missing data exist in the sensor database. Our model provides an effective field monitoring strategy for engineering applications to accurately and timely detect the products with abnormal quality during production and reduce product losses.

The end user sensor tree: An end-user friendly sensor database

Detailed knowledge regarding sensor based technologies for the detection of food contamination often remains concealed within scientific journals or divided between numerous commercial kits which prevents optimal connectivity between companies and end-users. To overcome this barrier The End user Sensor Tree (TEST) has been developed. TEST is a comprehensive, interactive platform including over 900 sensor based methods, retrieved from the scientific literature and commercial market, for aquatic-toxins, mycotoxins, pesticides and microorganism detection. Key analytical parameters are recorded in excel files while a novel classification system is used which provides, tailor-made, experts’ feedback using an online decision tree and database introduced here. Additionally, a critical comparison of reviewed sensors is presented alongside a global perspective on research pioneers and commercially available products. The lack of commercial uptake of the academically popular electrochemical and nanomaterial based sensors, as well as multiplexing platforms became very apparent and reasons for this anomaly are discussed.