THE FUNCTIONAL CONTROLABILITY OF MILK EJECTION OF THE ADAPTIVE MILKING SYSTEM

The concept of functional controllability of the milk ejection is considered, which makes it possible to predict the intensity of milk ejection in the online mode of the milking machine. The architecture of the functional controllability by intensity of milk ejection is developed. Input and output parameters of the structural-functional scheme of adaptive control of milk ejection intensity are described. An analytical model of milk ejection intensity based on Pearson's distribution is developed. The milk ejection intensity for different productivity and duration of cows milking is modelled. The microprocessor unit is designed using a single-chip microcontroller. It ensures the algorithm set by the central computer and implements a step of changing the pulsation frequency of 0.1 Hz, the ratio between the cycles of 0.25%, the phase shift step of 0.1 s.

PSX-A-1 Late-Breaking: A fully automated system for 3D image acquisition, classification and processing for real-time monitoring growth of finishing cattle in feedlots

Computer vision has been proposed as an alternative to monitor livestock growth, for example using 3D cameras to estimate body weight and condition. However, implementing this technology outdoors and with unrestrained animals poses a great challenge, because of harsh conditions for the equipment, as well as varying lighting and animal movement. Here we propose an automated system to acquire 3D images of individual animals, integrate the animal ID in the image file, and process images. This comprises a fundamental step for implementing a real-time assessment tool of growth of animals grouped in pens, to aid optimal feed management and marketing decision. The study comprised 50 beef cattle of Nellore breed during a finishing phase at DSM Innovation and Applied Center, in Brazil. Animals were tagged with RFID eartags, and 5 Intel RealSense D435 cameras were installed on the top of the water sources in each pen. For each animal approaching the water tank, an RFID antenna read the animal ID and triggered the camera to acquire a top-down view image. Images were then sent to a central computer using Wi-Fi, and later to the cloud. A decision tree algorithm was trained to sort images as usable or unusable, where the retained images had one single animal on the frame, with full body and relatively straight position. Selected frames were then processed using a threshold Otsu’s method to segment the animal body and obtain the necessary biological features, including body length, multiple width and height values, body area and volume. A total of 16,000+ images were collected, from which 3,100 were deemed usable. The algorithm successfully extracted the animal body from each image and obtained the biological features (cross-correlation values above 0.90). The proposed system was demonstrated to be extremely promising and the next stage of the study will be devoted to individual body weight prediction.

A Fully Wireless Wearable Motion Tracking System with 3D Human Model for Gait Analysis

This paper presents a wearable motion tracking system with recording and playback features. This system has been designed for gait analysis and interlimb coordination studies. It can be implemented to help reduce fall risk and to retrain gait in a rehabilitation setting. Our system consists of ten custom wearable straps, a receiver, and a central computer. Comparing with similar existing solutions, the proposed system is affordable and convenient, which can be used in both indoor and outdoor settings. In the experiment, the system calculates five gait parameters and has the potential to identify deviant gait patterns. The system can track upper body parameters such as arm swing, which has potential in the study of pathological gaits and the coordination of the limbs.

TCN Units, Solution in Recognition of Human Activities

Activities and human faces recognition infrastructure are used everywhere behavior analysis is required. Since a video approach is built over an already existing infrastructure comprised of CCTV-Closed Circuit Television and a central computer, it can be used in any space where actions’ monitoring is necessary. Main objective of this paper consists of building a reliable and lightweight human faces and actions’ recognition classifier, able to classify a large number of actions, lightweight enough that it can work in real time. It processes at least 30 frames per second, using of-the-shelf computer hardware, connected to a normal CCTV infrastructure. The temporal convolutional network - TCN represents a viable solution for a proposed problem. It classifies a large number of actions - 60, using only RGB (red-green-blue) images of fairly low resolution, in real time. Deciding which class of action belongs to should not be connected to environment, background, person, view angle, or other specific identifiers. This selection should be associated only with the person executing it and the spatial-temporal context of the person. As technology and processing power improve, the problem slightly shifts. When more processing power to a system is added, in this model is possible either to increase the number of frames per second or the number of cameras in the infrastructure, or to increase the quality of the images, resulting most likely higher accuracy of the predictions. This model can be extended to a larger number of classes, with a minimal impact on performance. The proposed model has a tested accuracy of 82% which can be attributed to the recurrent property of the network. The model performs close to the most performing existing solutions. The present TCN + 3D Convolution Model is built with the smaller TCN units. Its architecture uses an alternation of a Simple Unit and a Complex Unit, in order to maximize the diversity of features the model learns. This paper illustrates a deep learning classifier based on TCNs for human actions recognition. Is relatively lightweight compared to other methods, and performs very well, competing with the best architectures. Ideally, it is able to classify an action irrespective of the person executing it or the environment where it was executed. This is achieved as much as possible through a diverse dataset on which the model is trained and tested, namely NTU RGB+D. After a simple and a complex unit, an Average Pool 3D layer reduces at least one dimension to half.

Monitoring Print Engine Output Using Arduino and Raspberry Pi

In the printing industry process, monitoring is necessary for quality control of the product. The making of the tool on this project serves to monitor the output of the production machine. This monitoring is done by detecting the product output from the production machine using Sensor E18 D80NK. When the sensor detects the output, the sensor sends a signal to the Arduino UNO R3 which will calculate the amount of output from the product. Arduino will send information of the number of outputs via a USB connection to a central computer that is a Raspberry Pi 3 model B. The Python program on Raspberry Pi will read input from each Arduino address and display the data in realtime. At the same time, the data will be stored as a text file. This text file contains the number of product output and the time of the output. The prototype of this tool has been successfully created and there is still much development to do.

A Study of Hexagon Star Network with Vertex-Edge-Based Topological Descriptors

There are many network topology designs that have emerged to fulfill the growing need for networks to provide a robust platform for a wide range of applications like running businesses and managing emergencies. Amongst the most famous network topology designs are star network, mesh network, hexagonal network, honeycomb network, etc. In a star network, a central computer is linked with various terminals and other computers over point-to-point lines. The other computers and terminals are directly connected to the central computer but not to one another. As such, any failure in the central computer will result in a failure of the entire network and computers in star network will not be able to communicate. The star topology design can be represented by a graph where vertices represent the computer nodes and edges represent the links between the computer nodes. In this paper, we study the vertex-edge-based topological descriptor for a newly designed hexagon star network.

Development control system robotic platform for horticulture

The article presents a control system for a robotic platform for horticulture. The electronic control system consists of a running engine control unit, a stepper motor steering unit, an electronic differential control unit, a power plant automatic on / off control unit, and battery charging balancing. The developed control system of the robotic vehicle contains a central computer that collects information from sensors and sensors, processes it and transmits control signals to the drives of the machine movement. The movement of the robotic platform is carried out both by a radio signal with a remote control, and in offline mode on a pre-set map of the area according to data from the GLONASS/GPS differential receiver of the satellite navigation system. It is also possible to independently control the movement of a robotic platform using a vision system. The autonomy of the robotic platform provides 10 hours of continuous operation in low-light conditions in various weather conditions.

THE CONCEPT OF THE THEMATIC QUEST-ROOM FOR FORMATION OF CHILDREN'S READYNESS TO ACTION IN FIRE

Introduction. The data obtained by questionnaires indicate that not enough attention system of education gives to the formation of children’s psychological readiness for action in case of fire. Training evacuations in educational institutions are quite rare. At home, parents do not conduct such training at all. As of the beginning of 2020, the average Ukrainian child aged 4-10 visits game entertainment centres about 1.8 times a year. This information suggests that we should not be reduced to the banal annual repetition of the same rules to prepare children.Aim. The article aims to develop the concept of a thematic quest, in reality, the use of which would increase the readiness of players to act in a fire and also would help to accumulate experimental data for further study of the behaviour of children of different ages in a fire.The paper presents the results of test training with school students, based on the results of which have proposed the optimal spatial planning solutions of the thematic educational quest room, as well as the quantity and composition of technical equipment necessary for its effective functioning. It has given the schematic configuration of the quest room management system. Such a management system allows centralized control of all game processes and devices from the central computer. There are also considered examples of game tasks and possible scenarios.Conclusion. Execution of game tasks promotes the formation of psychological readiness of participants to actions in the conditions of fire and also allows to fix theoretical knowledge of rules of fire safety and to develop some practical skills. Observation of players opens up the prospect of obtaining experimental data for a wide range of research (especially on the behaviour of children of different ages).

Security of medical devices (Preprint)

UNSTRUCTURED Cybersecurity of medical devices is a decisive factor in people's lives. In fact, if criminals could get an access to these devices, they can do anything with the patient or their property. In this article, we will discuss some types of criminal activities related to hacking medical devices or getting an access to the central computer of the hospital. Moreover, I mentioned that why should some countries care about these devices' security and which countries now have laws in this field. Also, we will talk about governments' responsibilities and what people should know about the importance of cybersecurity of medical devices and what should they do.