An Automatic Instrument Recognition Approach Based on Deep Convolutional Neural Network

Background: This paper presents an automatic instrument recognition method highlighting the deep learning aspect of instrument identification in order to advance the automatic process of video monitoring remotely equipment of substation. Methodology: This work utilizes the Scale Invariant Feature Transform approach (SIFT) and the Gaussian difference model for instrument positioning while proposing a design scheme of instrument identification system. Results: The experimental outcomes obtained proves that the proposed system is capable of automatically recognizing a modest graphical interface and study independently while improving the operation effectiveness of appliance and realizing the purpose of spontaneous self-check. The proposed approach is applicable for musical instrument recognition and it provides 92% of the accuracy rate, 87.5% precision value and recall rate of 91.2%. Conclusion: The comparative analysis with other state of the art methods justifies that the proposed deep learning based music recognition method outperforms the other existing approaches in terms of accuracy, thereby providing a practicable music instrument recognition solution.

Deep-Learning Based Label-Free Classification of Activated and Inactivated Neutrophils for Rapid Immune State Monitoring

The differential count of white blood cells (WBCs) is one widely used approach to assess the status of a patient’s immune system. Currently, the main methods of differential WBC counting are manual counting and automatic instrument analysis with labeling preprocessing. But these two methods are complicated to operate and may interfere with the physiological states of cells. Therefore, we propose a deep learning-based method to perform label-free classification of three types of WBCs based on their morphologies to judge the activated or inactivated neutrophils. Over 90% accuracy was finally achieved by a pre-trained fine-tuning Resnet-50 network. This deep learning-based method for label-free WBC classification can tackle the problem of complex instrumental operation and interference of fluorescent labeling to the physiological states of the cells, which is promising for future point-of-care applications.

Image-Based Automatic Watermeter Reading under Challenging Environments

With the rapid development of artificial intelligence and fifth-generation mobile network technologies, automatic instrument reading has become an increasingly important topic for intelligent sensors in smart cities. We propose a full pipeline to automatically read watermeters based on a single image, using deep learning methods to provide new technical support for an intelligent water meter reading. To handle the various challenging environments where watermeters reside, our pipeline disentangled the task into individual subtasks based on the structures of typical watermeters. These subtasks include component localization, orientation alignment, spatial layout guidance reading, and regression-based pointer reading. The devised algorithms for orientation alignment and spatial layout guidance are tailored to improve the robustness of our neural network. We also collect images of watermeters in real scenes and build a dataset for training and evaluation. Experimental results demonstrate the effectiveness of the proposed method even under challenging environments with varying lighting, occlusions, and different orientations. Thanks to the lightweight algorithms adopted in our pipeline, the system can be easily deployed and fully automated.

Foot 3D Reconstruction and Measurement using Depth Data

Background: The need for shoes with non-standard sizes is increasing, but this is not followed by the competence to measure the foot effectively. The high cost of such an instrument in the market has led to the development of a precise yet affordable measurement system.Objective: This research attempts to solve the measuring problem by employing an automatic instrument utilizing a depth image sensor that is available on the market at an affordable price.Methods: Data from several Realsense sensors that have been preprocessed are combined using transformation techniques and noise cleaning is performed afterward. Finally the 3D model of the foot is ready and hence the length and width can be obtained.Results: The experimental results show that the proposed method produces a measurement error of 0.351 cm in foot length, and 0.355 cm in foot width.Conclusion: The result shows that multiple angles of a static Realsense sensor can produce a good 3D foot model automatically. This proposed system configuration can reduce complexity as well as being an affordable solution.

An Automatic Instrument Integration Scheme for Interoperable Ocean Observatories

Due to the heterogeneity, high cost, and harsh environment, ocean observatories demand a flexible, robust, and capable scheme to integrate science instruments. To deal with the challenges of automatic instrument integration and machine-to-machine interaction in ocean observatories, a systematic scheme is proposed based on Zero Configuration Networking (Zeroconf), Programmable Underwater Connector with Knowledge (PUCK), Constrained Application Protocol (CoAP), and Message Queuing Telemetry Transport (MQTT) protocols, as well as a smart interface module to achieve instrument plug-and-play and standard communication among heterogeneous ocean instruments. The scheme specifically considers the resource-constrained ocean observatories and machine-to-machine interoperability, which is of great significance to interoperable ocean observatories. The laboratory tests have verified the feasibility of the proposed scheme.

Development and research of the mechanism for improvement of soil processing instruments

Annotation Purpose. Improving the quality of tillage with implements with disk working bodies. Methods. Analytical and experimental laboratory-field research using the developed mechanism, installed on the serial disk Harrow. Results. The mechanism of automatic regulation of soil tillage in disc instruments has been elaborated and developed. It was established that the developed mechanism ensures the improvement of soil processing quality by disk instruments by automatic alignment of the instruments in relation to the unit movement direction. Conclusions. As a result of research, the mechanism of automated soil tillage quality control instruments was elaborated and developed. It was established that the experimental mechanism of the provisionis to increase the quality of soil tillage by means of automatic instrument alignment with regard to movement direction of the unit. With the soil cultivation depth of 138–139 mm, the automatic control mechanism improves the processing quality, which indicates a decrease in the average quadratic deviation of the depth from ±36.1 mm to ±23.8 mm and a decrease in the depth variation coefficient from 26.2% to 17.2%. Keywords: soil tillage, disk tools, automatic adjustment mechanism.