The productivity and profitability of poultry farming are crucial to support its affordability issues in food security. Criteria in productivity measurement, including Feed Conversion Ratio (FCR) calculation, whereas economic management is essential for profitability. Hence, best management practices need to be implemented throughout the growth period for optimizing the poultry performance. This review provides a comprehensive overview of computer vision technology for poultry industry research. This review relies on the use of several online databases to identify key works in the area of computer vision in a poultry farm. We recommend our search by focusing on four keywords, ‘computer vision’ and ‘poultry’ or ‘chicken’ or ‘broiler’ that had been published between 2010 and early 2020 with open access provided by University Teknologi Malaysia only. All the selected papers were manually examined and sorted to determine their relevance to computer vision in a poultry farm. We focus on the latest developments by focusing on the hardware and software parts used to analyze the poultry data with some examples of various representative studies on poultry farming. Notably, hardware parts can be classified into camera types, lighting units and camera position, whereas software parts can be categorized into data acquisition and analysis software types as well as data processing and analysis methods that can be implemented into the software types. This paper concludes by highlighting the future works and key challenges that needed to be addressed to assure the quality of this technology prior to the successful implementation of the poultry industry.

The massive deployment of small-sized cells for the Fifth Generation (5G) mobile network will increase the Handover Probability (HOP), potentially causing higher Handover Ping-Pong Probability (HPPP) and/or Radio Link Failure (RLF). Inappropriate usage of Handover Control Parameter (HCP) settings may further exasperate this issue. Therefore, Mobility Robustness Optimisation (MRO) has been introduced and further developed as a significant Self-Optimisation Network (SON) function in the 5G network and beyond. The main aim of MRO is to address Mobility Management (MM) issues during user mobility between cells to ensure a smooth connection. Although various algorithms were suggested in the literature, they mostly cater to 4G networks which may not be effective for the 5G network due to different network characterisations. This paper analyses the performance of various MRO algorithms with various system settings and scenarios for the 5G network. The investigated algorithms from the literature include the Distance (Dis), Cost Function (CF), Fuzzy Logic Controller (FLC) and Handover Performance Indicator (HPI). Validation has been accomplished for different mobility conditions in the 5G network. A simulation based on the MATLAB software has been conducted using various system tools. The evaluation analysis is in terms of Signal to-Interference-plus-Noise-Ratio (SINR), HPPP and RLF effects since these are major indicators in assessing system performance and selecting the handover decision during user mobility. The simulation outcomes show that the HPI algorithm performance is more reactive to mobile speed scenarios over time, significantly reducing the HPPP compared to the other algorithms which do not provide large reactions in the same conditions. Simultaneously, the HPI algorithm exhibits the highest RLF and SINR from among the other algorithms. The distance algorithm is the best in terms of RLF and SINR, achieving an acceptable level in terms of HPPP. These results point to that the MRO algorithm that operate based on distance is the most robust compared to the other investigated algorithms, confirming the potential of the Dis approach for the 5G network.

A supervised machine learning (ML) algorithm is proposed for measuring refractive index (RI) values both below and above the RI of the fiber material using a multimode interference (MMI) fiber sensor. The sensor is constructed by splicing a coreless multimode fiber (CMF) segment between two single-mode fiber (SMF) leads. Measurement of low and high RI regimes is accomplished through the Decision Tree (DT) regression algorithm. The trained model algorithm demonstrates a wide dynamic range in RI measurement, covering the ranges of 1.30 to 1.39 (low RI regime) and 1.46 to 1.55 (high RI regime) without any RI ambiguity, achieving model accuracy of 99.77%. The guided and leaky modes mechanisms within the all-silica-based structure of the CMF are fundamentally insensitive to temperature, making it highly practical for deployment in conditions with varying temperatures without the need for any compensating scheme.

This study aims to create a sorting system with high accuracy that can classify various beverage containers based on types and separate them accordingly. This reverse vending machine (RVM) provides an image classification method and allows for recycling three types of beverage containers: drink carton boxes, polyethylene terephthalate (PET) bottles, and aluminium cans. The image classification method used in this project is transfer learning with convolutional neural networks (CNN). AlexNet, GoogLeNet, DenseNet201, InceptionResNetV2, InceptionV3, MobileNetV2, XceptionNet, ShuffleNet, ResNet 18, ResNet 50, and ResNet 101 are the neural networks that used in this project. This project will compare the F1-score and computational time among the eleven networks. The F1-score and computational time of image classification differs for each neural network. In this project, the AlexNet network gave the best F1-score, 97.50% with the shortest computational time, 2229.235 s among the eleven neural networks.