Rice, as one of the significant grain products across the world, features a wide range of varieties in terms of usability and efficiency. It may be known with various varieties and regional names depending on the specific locations. To specify a particular rice type, different features are considered, such as shape and color. This study uses an available dataset in Turkey consisting of five different varieties: Ipsala, Arborio, Basmati, Jasmine, and Karacadag. The dataset introduces 75,000 grain images in total; each of the 5 varieties has 15,000 samples with a 256 × 256-pixel dimension. The main contribution of this paper is to create Quantized Neural Network (QNN) models to efficiently classify rice varieties with the purpose of reducing resource usage on edge devices. It is well-known that QNN is a successful method for alleviating high computational costs and power requirements in response to many Deep Learning (DL) algorithms. These advantages of the quantization process have the potential to provide an efficient environment for artificial intelligence applications on microcontroller-driven edge devices. For this purpose, we created eight different QNN networks using the MLP and Lenet-5-based deep learning models with varying quantization levels to be trained by the dataset. With the Lenet-5-based QNN network created at the W3A3 quantization level, a 99.87% classification accuracy level was achieved with only 23.1 Kb memory size used for the parameters. In addition to this tremendous benefit of memory usage, the number of billion transactions per second (GOPs) is 23 times less than similar classification studies.

This paper investigates the laser cutting performance regarding CO ₂ of four fused filament fabrication-printed thermoplastics, namely polylactic acid (PLA), carbon fiber reinforced PLA (PLA-CF), acrylonitrile styrene acrylate (ASA), and polyethylene terephthalate glycol (PETG). We investigate kerf open deviation, kerf angle, bottom heat-affected zone, and material removal rate. A total of 72 trial runs were conducted with various states of material type, plate thickness, laser power, and cutting speed. The resulting experimental data were then fed into several machine learning algorithms to assess and compare their predictive abilities: linear regression, decision tree, random forest, CatBoost, support vector regression, k-nearest neighbors, and multi-layer perceptron. Of all the machine learning algorithms, random forest and multi-layer perceptron performed best with high R ² in conjunction with low error metrics for all response variables. The study also shows that PLA-CF achieves the highest material removal rate, while ASA and PETG yield high dimensional stability with minimum kerf and thermal distortion. Hence, the research study has made it clear that, with machine learning algorithms, the laser cutting performance can be modeled for additively manufactured polymers, and the processing parameters can be optimized for laser cutting; thus, this will enhance the smart manufacturing approaches for the processing of polymers.

Recently, convolutional neural networks (CNNs) have received a massive amount of interest due to their ability to achieve high accuracy in various artificial intelligence tasks. With the development of complex CNN models, a significant drawback is their high computational burden and memory requirements. The performance of a typical CNN model can be enhanced by the improvement of hardware accelerators. Practical implementations on field-programmable gate arrays (FPGA) have the potential to reduce resource utilization while maintaining low power consumption. Nevertheless, when implementing complex CNN models on FPGAs, these may may require further computational and memory capacities, exceeding the available capacity provided by many current FPGAs. An effective solution to this issue is to use quantized neural network (QNN) models to remove the burden of full-precision weights and activations. This article proposes an accelerator design framework for FPGAs, called FPGA-QNN, with a particular value in reducing high computational burden and memory requirements when implementing CNNs. To approach this goal, FPGA-QNN exploits the basics of quantized neural network (QNN) models by converting the high burden of full-precision weights and activations into integer operations. The FPGA-QNN framework comes up with 12 accelerators based on multi-layer perceptron (MLP) and LeNet CNN models, each of which is associated with a specific combination of quantization and folding. The outputs from the performance evaluations on Xilinx PYNQ Z1 development board proved the superiority of FPGA-QNN in terms of resource utilization and energy efficiency in comparison to several recent approaches. The proposed MLP model classified the FashionMNIST dataset at a speed of 953 kFPS with 1019 GOPs while consuming 2.05 W.

Rice cultivation, the foundation of global food security, is vulnerable to leaf diseases, which significantly reduce both yield and quality. Early and accurate detection is crucial for effective and sustainable disease management. This study presents an efficient and deployable real-time system for rice leaf disease detection, optimized for edge-computing environments. A novel Dual-Branch Lightweight Attention MobileNetV2 (DBLA-MobileNetV2) architecture is proposed and compared with a baseline MobileNetV2 model fine-tuned via transfer learning. DBLA-MobileNetV2 employs a dual-branch structure to enhance multi-scale feature extraction, where one branch focuses on fine-grained visual patterns and the other captures high-level semantic information. Integrated Squeeze-and-Excitation (SE) attention mechanisms further improve channel-wise feature representation and increase accuracy, while maintaining computational efficiency. To demonstrate real-world applicability, we developed a portable hardware prototype using an NVIDIA Jetson Nano Core Processing Unit. The device was designed as an arm-mounted unit, enabling direct field deployment without reliance on a cloud infrastructure. The proposed system was tested in six rice fields at various growth stages. The experimental results show that DBLA-MobileNetV2 achieved 97.9% precision and 12.40 FPS under the quantization of FP16 using the TensorRT framework. The combination of lightweight architecture and mobile implementation provides a practical pathway for precision agriculture, allowing rapid in-field disease diagnosis and timely agronomic interventions to enhance productivity.

Wind energy is a critical renewable resource in the global effort toward sustainable development and climate change mitigation. This paper introduces a hybrid forecasting framework that integrates multistep gated recurrent unit (GRU) modeling with Weibull distribution analysis to assess wind energy potential and predict long-term wind speed dynamics. The approach combines deterministic and probabilistic components, improving robustness against seasonal variability and uncertainties. To demonstrate its effectiveness, the framework was applied to hourly wind data collected from multiple stations across diverse geographical regions in Turkey. Weibull parameters, wind power density, capacity factor, and annual energy production were estimated, while five machine learning models were compared for forecasting accuracy. The GRU model outperformed alternative methods, and the hybrid GRU–Weibull approach produced highly consistent forecasts aligned with historical patterns. Results highlight that the proposed framework offers a reliable and transferable methodology for evaluating wind energy resources, with applicability beyond the case study region.

Ultraviolet (UV) radiation has emerged as a powerful, non-chemical disinfection method, gaining significant attention for its ability to inactivate pathogenic microorganisms, particularly viruses, amid global public health challenges such as the COVID-19 pandemic. This study provides a comprehensive analysis of UV-based viral inactivation technologies, with a focus on ultraviolet germicidal irradiation (UVGI) using the UV-C spectrum (200-280 nm). It explores the fundamental physical principles of UV radiation, the photochemical mechanisms disrupting microbial DNA and RNA, and the critical parameters influencing disinfection efficacy, including UV dose, irradiance, wavelength, exposure time, and environmental conditions. Theoretical frameworks are supported by calculations and experimental data to evaluate the impact of material properties, surface characteristics, and atmospheric factors on UV performance. The study critically assesses UVGI applications in diverse settings, such as healthcare facilities, public spaces, ventilation systems, and water treatment, while addressing safety considerations, technological limitations, and potential health risks associated with UV exposure. By synthesizing theoretical insights, experimental findings, and a detailed review of UV sensitivity across various pathogens, including SARS-CoV-2 and other coronaviruses, this work highlights the high susceptibility of viral pathogens to UV-C radiation. It also examines the implications of RNA mutations on UV efficacy and provides estimated inactivation doses for a range of microorganisms. These findings underscore the potential of UV-based technologies as a cornerstone of modern infection control strategies, offering insights into optimizing system design and implementation for effective microbial inactivation while ensuring safety and scalability in real-world applications.