Auto-Feed. IoT-Enabled Chicken Feeder Using Raspberry Pi

Dave Allan A. Tagacay

Iloilo State University of Fisheries Science and Technology – San Enrique Campus

Abstract

This research endeavor aimed to develop an Internet of Things (IoT)-enabled Chicken Feeder designed specifically for the needs of poultry farm operators and assess its usability. The study was conducted at Iloilo State University of Fisheries Science and Technology between December 2022 and March 2023, employing the descriptive developmental research method. The system's development utilized tools such as Arduino IDE, PyCharm, and Google Sites for software development, with hardware components including a Raspberry Pi 4b, Arduino UNO, Timer, Servomotor with a food level sensor, Water pump with a water level sensor, a pull-up button, and an LCD display. The development process followed the System Development Life Cycle-Rapid Application Development (SDLC-RAD) methodology, comprising the stages of Define, Design, Construct, and Implement. To assess the system's usability, an evaluation panel consisting of three small-scale poultry farm owners and thirty 4th-year students majoring in Animal Science and Agriculture was purposefully selected using quota sampling. Data collected from the respondents was tabulated and analyzed using the System Usability Scale (SUS). The developed IoT-based poultry feeding system achieved an impressive SUS score of 90.30, placing it in the "A+" grade within the 96-100 percentile range. This high score reflects a favorable evaluation of the system’s usability, highlighting its potential to significantly improve poultry farm management and operational efficiency. In conclusion, the study demonstrates that the IoT-enabled chicken feeder is a practical and effective tool for optimizing poultry farm operations, with high usability as assessed by the respondents.

Keywords: agriculture, internet-of-things, smart farming

Read more: https://vjsti.org/wp-content/uploads/2024/12/VJSTI-011.pdf


Value Chain Analysis of the Philippine Native Chicken Industry in Western Visayas Region, Philippines

Reynold D. Tan¹ and Lovella Mae M. Magluyan
¹College of Management, University of the Philippines Visayas

Abstract

The Philippine native chicken industry contributes significantly to the country's food security and economic growth, with Western Visayas as the country's top-producing region. The pandemic in 2020 paralyzed the transportation system, thus affecting the distribution of food and agricultural products. This descriptive study characterizes the native chicken value chain in Western Visayas. In particular, it aims to provide an overview of the current state of the native chicken value chain using the backward tracing approach -- tracing backward all the key players from consumers to the input suppliers. This study maps out the supply or value chain, showing the a) activities and processes involved; b) key players and their roles; c) key customers and their product requirements; d) flow of product, payment, and information; and e) vertical and horizontal linkages. Results showed that in Western Visayas, native chickens are usually raised in the backyards of rural households, generating an estimated monthly income of PHP 2,122.82 per household. Consolidators bring together native chickens from far-flung areas-- to come up with the desired quantities needed by their eventual end-markets. Native chickens are sold live or dressed with cash as the most common form of payment. There is a ready market for native chicken in the region; however, the industry remains fragmented. There are no standards for weight, size, age, and quality of meat. Marketing and pricing remain arbitrary in the absence of product standards. It is challenged by increasing input costs due to the pandemic.

Keywords: native chicken, poultry, value chain analysis, Western Visayas, Philippines

Read more: https://vjsti.org/wp-content/uploads/2024/12/VJSTI-004.pdf

 

 


Wireless monitoring devices for regulation of vehicular events with Internet-of-Things (IoT)

Russel M. Dela Torre

Carlos Hilado Memorial State University

Abstract

The desire of men to conveniently commute and travel is evident in the staggering increase in the production and sales of automobiles. However, this pronounced rise in the usage of vehicles also brought a proportional increase in road accidents as indicated by local and international safety agencies reports showing a surprising number of vehicle accidents which rank it among the top causes of global deaths. The study aims to create a means of providing immediate response to car drivers during vehicular accidents. The study followed the framework of development and technology research in developing a technical model for monitoring and tracking mobile vehicles in outdoor environments using the Global Positioning System (GSM), Global System for Mobile Communication (GSM), and Internet-of-Things (IoT). A drive-permission feature was also implemented to provide an anti-theft function. The system was subjected to technical functionality testing to check if the system performs its intended functions and the standard Post-Study System Usability Questionnaire (PSSUQ ver 3) to evaluate user usability. The system achieved a functionality test result of 92.5% and a PSSUQ mean of 1.78. Based on the development and results of the testing and evaluation, it was concluded that (1) the system can monitor various vehicular events such as head-on collisions of the vehicle (bump and crash), the vehicle speed, location, heading, and time, and vehicle theft attempt,  (2) a high degree of system functionality in terms of the mentioned vehicular events and the integrated web application, and (3) a PSSUQ score indicating a high level of system usability.

Keywords: global positioning system, internet-of-things, microcontroller, usability testing, vehicle monitoring, vehicle tracking

Read more: https://vjsti.org/wp-content/uploads/2024/12/VJSTI-005.pdf

 


Impact of neuron count and learning rate on the accuracy of a NumPy-based artificial neural network in predictive modeling of nonlinear dynamical systems

David Mark M. Mueller
School of Engineering, Computer Studies, and Architecture (SECSA), Southland College, Kabankalan City, Negros Occidental

Abstract

The impact of neuron count and learning rate on the accuracy of an artificial neural network (ANN) in predictive modeling of nonlinear dynamical systems is explored. This study is focused on the Lorenz, Rössler, and Chen systems, which are renowned for their sensitivity to initial conditions, intricate dynamics, and strangely attractive plot of their trajectories. The model’s performance was assessed using symmetric mean absolute percentage error (SMAPE) and coefficient of determination (R²).  The results shows that the model with 24 neurons and 0.1 learning rate consistently outperformed other parameters across all three systems.

Keywords: chaotic system, forecasting, machine learning, complex dynamics

Read more: https://vjsti.org/wp-content/uploads/2024/12/VJSTI-003.pdf