Automatic Meter Reading using Deep Learning

2021 ◽  
Author(s):  
S.H. Wong ◽  
◽  
S.L. Yang ◽  
C.M. Tsui
Keyword(s):  
Deep Learning ◽  
Data Acquisition ◽  
Human Errors ◽  
Improve Efficiency ◽  
Automatic Meter Reading ◽  
Learning Techniques ◽  
Automatic Meter Reading System ◽  
Reading System

Laboratory instruments are commonly equipped with communication interfaces (e.g., GPIB, USB or LAN port) for data acquisition or control through a computer. However, such interface might not be available on handheld equipment, e.g., multi-meters, where readings have to be taken manually by operators during calibration. To improve efficiency and reduce possible human errors, SCL has developed an automatic meter reading system for seven segment displays using deep learning techniques.

scholarly journals A Citizen Science Unmanned Aerial System Data Acquisition Protocol and Deep Learning Techniques for the Automatic Detection and Mapping of Marine Litter Concentrations in the Coastal Zone

Drones ◽  
2021 ◽  
Vol 5 (1) ◽  
pp. 6
Author(s):  
Apostolos Papakonstantinou ◽  
Marios Batsaris ◽  
Spyros Spondylidis ◽  
Konstantinos Topouzelis
Keyword(s):  
Deep Learning ◽  
Data Acquisition ◽  
Citizen Science ◽  
Coastal Zone ◽  
Automatic Detection ◽  
Monitoring Methods ◽  
Monitoring Method ◽  
Marine Litter ◽  
Density Maps ◽  
Learning Techniques

Marine litter (ML) accumulation in the coastal zone has been recognized as a major problem in our time, as it can dramatically affect the environment, marine ecosystems, and coastal communities. Existing monitoring methods fail to respond to the spatiotemporal changes and dynamics of ML concentrations. Recent works showed that unmanned aerial systems (UAS), along with computer vision methods, provide a feasible alternative for ML monitoring. In this context, we proposed a citizen science UAS data acquisition and annotation protocol combined with deep learning techniques for the automatic detection and mapping of ML concentrations in the coastal zone. Five convolutional neural networks (CNNs) were trained to classify UAS image tiles into two classes: (a) litter and (b) no litter. Testing the CCNs’ generalization ability to an unseen dataset, we found that the VVG19 CNN returned an overall accuracy of 77.6% and an f-score of 77.42%. ML density maps were created using the automated classification results. They were compared with those produced by a manual screening classification proving our approach’s geographical transferability to new and unknown beaches. Although ML recognition is still a challenging task, this study provides evidence about the feasibility of using a citizen science UAS-based monitoring method in combination with deep learning techniques for the quantification of the ML load in the coastal zone using density maps.

scholarly journals Android APP Development of Remote Wireless Automatic Meter Reading System based on 3G

2017 ◽  
Vol 13 (02) ◽  
pp. 18
Author(s):  
Lei Feng ◽  
Chuang Yang ◽  
Wenbin Zheng ◽  
Ping Fu
Keyword(s):  
Water Supply ◽  
Research Work ◽  
Pipe Network ◽  
Monitoring Methods ◽  
Water Safety ◽  
Efficient Operation ◽  
Automatic Meter Reading ◽  
Data Feedback ◽  
Automatic Meter Reading System ◽  
Reading System

Urban water supply pipe network is critical infrastructure for the survival of people. Efficient operation of equipment, water supply and water safety are always received great attention from the government and operators. The existing way of manual meter reading and manual inspection has the drawbacks of waste time and labor. To solve this problem, we developed databases, software platforms and mobile terminal APP (Application) based on Android operating system to integrate a remote wireless automatic meter reading system based on the existing remote wireless automatic reading meter devices which are our previous research work. The system realizes the remote monitoring of the pipe network, and it also realizes the remote control of the monitoring nodes, such as the camera shooting, selection of monitoring node's working mode and so on, which data feedback is accurate and timely, monitoring methods is simple, fast and efficient. In addition, compared to traditional methods, the system greatly reduced the manpower and resources, reduce monitoring costs. And the tests and experiments show this remote wireless automatic meter reading and control system is useful and effective.

scholarly journals Designing Automatic Meter Reading System Using Open Source Hardware and Software

2017 ◽  
Vol 7 (6) ◽  
pp. 3282 ◽  
Author(s):  
Dragan Mlakić ◽  
Srete Nikolovski ◽  
Emir Alibašić
Keyword(s):  
Open Source ◽  
Low Voltage ◽  
Electronic Components ◽  
Unlimited Number ◽  
Automatic Meter Reading ◽  
Automatic Meter Reading System ◽  
Reading System ◽  
Open Source Hardware ◽  
Physical Quantities

The importance of quality of the measured values is very dependent on the device that measures these values: the size of the sample, the time of measurement, periods of measurement, the mobility and the robustness of the device, etc. Contemporary devices intended for the measurement of physical quantities that are on the market vary in price, as well as and the quality of the measured values. The rule "the more expensive the better" is not necessarily always a rule that is valid because it all depends on the characteristics and capabilities of the device, and the customer’s needs. In this paper, a device based on "Open Source" components of hardware and software will be presented. Device was used to measure voltages and currents on low voltage networks, on which a virtually unlimited number of sensors can be added, and the device is assembled of components available on electronic components Internet.

Sign in / Sign up

Export Citation Format

Share Document