Search

In most pig barns, intensive breeding is being carried out, and social problems such as manure disposal and large-scale infectious diseases have emerged due to this livestock farming method. In particular, organic matter from the manure is decomposed and odorous gases such as ammonia and hydrogen sulfide are emitted. The emitted harmful gases cause problems such as causing stress in pig barns, reducing immunity, and causing various diseases. To solve these problems, cleaning robots for handling manure in pig barns have been developed, and algorithms for planning optimal routes for autonomous driving or methods for cost reduction due to efficient cleaning are being studied. Most cleaning robots currently in use, employ a method of treating accumulated manure by spraying high-pressure water from a stored water tank. If water can be sprayed only on areas that need cleaning, water consumption can be reduced, so we propose a technology that can determine this through a camera. If it is possible to determine whether cleaning is necessary by segmenting only manure from the image into objects, it is expected to significantly reduce unnecessary water consumption. The purpose of this study is to determine whether cleaning is necessary by dividing excrement into objects from images taken during autonomous driving with a camera mounted on the front of a cleaning robot. The final goal is to obtain a segmented image capable of recognizing only the manure part requiring cleaning from the captured image. The first step acquires image information using an RGB camera. At the beginning of the study, when the number of images is insufficient, the segmentation performance is checked through semantic segmentation using the difference between manure and other objects or backgrounds using image information. Depending on the segmentation performance and the number of acquired images, we plan to use a deep learning-based algorithm in the future. The ultimate goal of this study is to develop a technology for obtaining segmented images capable of recognizing excreta by utilizing image information from captured images. In addition, if only the manure part can be accurately recognized through this study, we plan to apply the technology of spraying water only to the necessary part by using it as information to determine whether cleaning is necessary from the segmented image. Through this, the company plans to apply the technology to self-driving cleaning robots to develop high-efficiency intelligent cleaning robots capable of efficiently handling manure. This achievement was made by the support of the Ministry of Agriculture, Food and Rural Affairs, R&D project(421044043HD030)

In this paper, a memristive artificial neural circuit imitating the excitatory chemical synaptic transmission of biological synapse is designed. The proposed memristor-based neural circuit exhibits synaptic plasticity, one of the important neurochemical foundations for learning and memory, which is demonstrated via the efficient imitation of short-term facilitation and long-term potentiation. Moreover, the memristive artificial circuit also mimics the distinct biological attributes of strong stimulation and deficient synthesis of neurotransmitters. The proposed artificial neural model is designed in SPICE, and the biological functionalities are demonstrated via various simulations. The simulation results obtained with the proposed artificial synapse are similar to the biological features of chemical synaptic transmission and synaptic plasticity.

Livestock farming generates a significant amount of manure, which must be effectively managed to prevent environmental pollution and ensure the health and well-being of animals. The cleaning machine is a commonly used tool for removing manure from pig barns: however, it often leaves behind residual waste that is difficult to remove. To address this issue, a new equipment design that combines a high-pressure jet and a translational scraper has been proposed. This design aims to improve the efficiency of manure treatment by weakening the adhesion and removing stubborn waste particles, making it easier for the cleaning machine to collect the manure. The high-pressure jet provides a powerful stream of water that can dislodge even the most stubborn waste particles. For high-pressure washing, a DC 10V/10A standard water pump and a 70L water tank are included. The translational scraper, on the other hand, can move left and right across the surface of the slatted floor, effectively scraping away any remaining waste. For this work, an actuator was installed to move the blade part and the hook type work part. These two components work together to improve the efficiency of manure treatment and reduce the amount of waste left behind. By improving the efficiency of manure treatment, this new equipment design can help to reduce environmental pollution and improve the overall health and well-being of pigs. In addition, it can also reduce labor costs and improve the profitability of pig farming operations. In conclusion, the design of equipment that combines a high-pressure jet and a translational scraper has the potential to significantly improve the manure treatment efficiency of a pig barn cleaning machine. This new design can help to address the challenges associated with manure management in pig farming and promote a more sustainable and efficient approach to livestock farming. This achievement was made by the support of the Ministry of Agriculture, Food and Rural Affairs, R&D project(421044043HD030)

Nonlinear memristor-based neural network and a circuit-based learning system is addressed in this work. The weights of the neural network are based on the memristor bridge synapse and the learning architecture is designed in analog–digital mixed circuits by adopting a simple learning algorithm called random weight change algorithm. Though the memristor bridge can be efficiently used as a synapse, it still suffers from nonlinearity in weight programming at its extremes due to the boundary effect of memristors, which is a common phenomenon in most of the nano-devices. In this study, a novel architecture of a modified memristor bridge synapse is proposed that avoids the boundary effect issue by shifting the programming origin to the middle of the linear region. To demonstrate the effectiveness of the proposed method, multilayer neural network along with the end-to-end learning architecture is designed in circuit with nonlinear memristors and tested for several classical learning problems. Simulation results showing successful learning and correct behavior of replicated neural network are presented. [ABSTRACT FROM AUTHOR]

In this paper, a generic model of memristive systems, which can emulate the behavior of real memristive devices is proposed. Non-ideal pinched hysteresis loops are sometimes observed in real memristive devices. For example, the hysteresis loops may deviate from the origin over a broad range of amplitude A and frequency f of the input signal. This deviation from the ideal case is often caused by parasitic circuit elements exhibited by real memristive devices. In this paper, we propose a generic memristive circuit model by adding four parasitic circuit elements, namely, a small capacitance, a small inductance, a small DC current source, and a small DC voltage source, to the memristive device. The adequacy of this model is verified experimentally and numerically with two thermistors (NTC and PTC) memristors. [ABSTRACT FROM AUTHOR]

Memristor-based circuit architecture for multilayer neural networks is proposed. It is a first of its kind demonstrating successful circuit-based learning for multilayer neural network built with memristors. Though back-propagation algorithm is a powerful learning scheme for multilayer neural networks, its hardware implementation is very difficult due to complexities of the neural synapses and the operations involved in the learning algorithm. In this paper, the circuit of a multilayer neural network is designed with memristor bridge synapses and the learning is realized with a simple learning algorithm called Random Weight Change (RWC). Though RWC algorithm requires more iterations than back-propagation algorithm, we show that a circuit-based learning using RWC is two orders faster than its software counterpart. The method to build a multilayer neural network using memristor bridge synapses and a circuit-based learning architecture of RWC algorithm is proposed. Comparison between software-based and memristor circuit-based learning are presented via simulations. [ABSTRACT FROM AUTHOR]

A memristor emulator which imitates the behavior of a \ TiO2 memristor is presented. Our emulator is built from off-the-shelf solid state components. To develop real world memristor circuit applications, the emulator can be used for breadboard experiments in real time. Two or more memristor emulators can be connected in serial, in parallel, or in hybrid (serial and parallel combined) with identical or opposite polarities. With a simple change of connection, each memristor emulator can be switched between a decremental configuration or an incremental configuration. The hardware and spice simulation of the proposed emulator showed promising results that provides an alternative solution of hp∼\ TiO2 memristor model in real circuit. [ABSTRACT FROM AUTHOR]

Analog hardware architecture of a memristor bridge synapse-based multilayer neural network and its learning scheme is proposed. The use of memristor bridge synapse in the proposed architecture solves one of the major problems, regarding nonvolatile weight storage in analog neural network implementations. To compensate for the spatial nonuniformity and nonideal response of the memristor bridge synapse, a modified chip-in-the-loop learning scheme suitable for the proposed neural network architecture is also proposed. In the proposed method, the initial learning is conducted in software, and the behavior of the software-trained network is learned by the hardware network by learning each of the single-layered neurons of the network independently. The forward calculation of the single-layered neuron learning is implemented on circuit hardware, and followed by a weight updating phase assisted by a host computer. Unlike conventional chip-in-the-loop learning, the need for the readout of synaptic weights for calculating weight updates in each epoch is eliminated by virtue of the memristor bridge synapse and the proposed learning scheme. The hardware architecture along with the successful implementation of proposed learning on a three-bit parity network, and on a car detection network is also presented.