Thermal imaging and computer vision technologies for the enhancement of pig husbandry: a review

Md Nasim Reza,Md Razob Ali,Samsuzzaman,Md Shaha Nur Kabir,Md Rejaul Karim,Shahriar Ahmed,Hyunjin Kyoung,김국환,Sun-Ok Chung 한국축산학회 2024 한국축산학회지 Vol.66 No.1

Pig farming, a vital industry, necessitates proactive measures for early disease detection and crush symptom monitoring to ensure optimum pig health and safety. This review explores advanced thermal sensing technologies and computer vision-based thermal imaging techniques employed for pig disease and piglet crush symptom monitoring on pig farms. Infrared thermography (IRT) is a non-invasive and efficient technology for measuring pig body temperature, providing advantages such as non-destructive, long-distance, and high-sensitivity measurements. Unlike traditional methods, IRT offers a quick and labor-saving approach to acquiring physiological data impacted by environmental temperature, crucial for understanding pig body physiology and metabolism. IRT aids in early disease detection, respiratory health monitoring, and evaluating vaccination effectiveness. Challenges include body surface emissivity variations affecting measurement accuracy. Thermal imaging and deep learning algorithms are used for pig behavior recognition, with the dorsal plane effective for stress detection. Remote health monitoring through thermal imaging, deep learning, and wearable devices facilitates non-invasive assessment of pig health, minimizing medication use. Integration of advanced sensors, thermal imaging, and deep learning shows potential for disease detection and improvement in pig farming, but challenges and ethical considerations must be addressed for successful implementation. This review summarizes the state-of-the-art technologies used in the pig farming industry, including computer vision algorithms such as object detection, image segmentation, and deep learning techniques. It also discusses the benefits and limitations of IRT technology, providing an overview of the current research field. This study provides valuable insights for researchers and farmers regarding IRT application in pig production, highlighting notable approaches and the latest research findings in this field.

Anti-Fibrotic Effects of DL-Glyceraldehyde in Hepatic Stellate Cells via Activation of ERK-JNK-Caspase-3 Signaling Axis

Samsuzzaman Md.,Kim Sun Yeou 한국응용약물학회 2023 Biomolecules & Therapeutics(구 응용약물학회지) Vol.31 No.4

During liver injury, hepatic stellate cells can differentiate into myofibroblast-like structures, which are more susceptible to proliferation, migration, and extracellular matrix generation, leading to liver fibrosis. Anaerobic glycolysis is associated with activated stellate cells and glyceraldehyde (GA) is an inhibitor of glucose metabolism. Therefore, this study aimed to investigate the anti-fibrotic effects of GA in human stellate LX-2 cells. In this study, we used cell viability, morphological analysis, fluorescence-activated cell sorting (FACS), western blotting, and qRT-PCR techniques to elucidate the molecular mechanism underlying the anti-fibrotic effects of GA in LX-2 cells. The results showed that GA significantly reduced cell density and inhibited cell proliferation and lactate levels in LX-2 cells but not in Hep-G2 cells. We found that GA prominently increased the activation of caspase-3/9 for apoptosis induction, and a pan-caspase inhibitor, Z-VAD-fmk, attenuated the cell death and apoptosis effects of GA, suggesting caspasedependent cell death. Moreover, GA strongly elevated reactive oxygen species (ROS) production and notably increased the phosphorylation of ERK and JNK. Interestingly, it dramatically reduced α-SMA and collagen type I protein and mRNA expression levels in LX-2 cells. Thus, inhibition of ERK and JNK activation significantly rescued GA-induced cell growth suppression and apoptosis in LX-2 cells. Collectively, the current study provides important information demonstrating the anti-fibrotic effects of GA, a glycolytic metabolite, and demonstrates the therapeutic potency of metabolic factors in liver fibrosis.

Theoretical Working Speed Analysis of a 1.54 kW One-row Biodegradable Potted Seedling Transplanting Mechanism

( Md Razob Ali ),( Samsuzzaman ),( Eliezel Habineza ),( Md Shaha Nur Kabir ),( Mohammod Ali ),( Beom-seon Kang ),( Sun-ok Chung ) 한국농업기계학회 2023 한국농업기계학회 학술발표논문집 Vol.28 No.2

Plastic seedling pots have been widely used due to their light weight and durable nature, but they hinder root establishment efficiency. However, recent studies have demonstrated that biodegradable potted seedlings could improve seedling resilience, while also being eco-friendly through natural decomposition. In this research, a transplanting mechanism for biodegradable potted vegetable seedlings was designed using commercial software, incorporating working speed analysis to enhance smooth collection and plantation of leafy vegetable seedlings. Theoretical analysis of the vegetable transplanting mechanism for biodegradable seedling pots was conducted, including calculations of position, velocity, acceleration, and input driving torque. Additionally, the selection of appropriate link combinations within the mechanism was explored to ensure smooth transplantation of potted seedlings in optimum depths and spacings. The kinematic model of the transplanting mechanism was simulated using commercial mechanical design and simulation software. The transplanter was comprised of a 4-bar mechanism: a driving link, a driven link, a connecting link, and a supporting bar. In order to enable better hopper motion, a spring was affixed between the driven link and the ground. The movement of the mechanism was primarily controlled through a crank-rocker mechanism, where the arm lengths play a crucial role in determining the planting trajectory. The mathematical model analysis and simulation revealed that a forward speed of the transplanter of 300 mm/s and a rotating speed of the dibbling mechanism of 40 rpm were favored of 48 seedlings/min in order to obtain a high degree of seedling uprightness. The simulated velocities and accelerations of the end hopper in ‘X’ and ‘Y’ directions for suitable link combination were found to be 430mm/s,530mm/s,and 975 mm/s2,2091mm/s2,respectively.The required driving torque was observed to be 603N-mm,and the vertical linear displacement of the hopper was 281mm.

AI-Enabled Real-Time Pig Disease Detection and Management

( Md Nasim Reza ),( Sumaiya Islam ),( Md Razob Ali ),( Samsuzzaman ),( Md Shaha Nur Kabir ),( Minho Song ),( Gookhwan Kim ),( Sun-ok Chung ) 한국농업기계학회 2023 한국농업기계학회 학술발표논문집 Vol.28 No.2

Surveillance cameras are becoming crucial tools for early livestock disease detection, offering the potential to reduce the negative impact on animal health and the economy in livestock production. This study focused on detecting pig disease symptoms, serving as an initial exploration for practical implementation on pig farms. The aim was to develop an AI-based approach using various video and acoustic sensors in real farm environments. The setup includes two RGB cameras for top and side views, a thermal sensor, and a sound sensor, all controlled by a microcontroller. The collected audio, video, and temperature data are processed in real-time. Using RGB and infrared camera feeds, along with audio analysis, we developed a system to recognize pigs and identify illness states in the video stream. We employed a single-shot multibox (SSD) architecture with MobileNet V2 for video stream processing, achieving an accuracy of 93.6% for pig recognition. The system demonstrated an 89.6% mean average accuracy (mAP) with a frame rate of 21 for disease detection. When tested on sound data, it achieved an average F1-score of 83.7%, with recognition accuracies of 67.5% for snoozing, 74.8% for coughs, 72.9% for crushing sounds, and 82.3% for screaming. Detection accuracy was affected by blurry video and background noises. This research advances precision livestock farming for pig health and disease prevention.

Deep learning based identification of Pepper (Capsicum annuum L.) diseases: A review

Chan Ho Kim,Samsuzzaman,Md Nasim Reza,Ka Young Lee,Md Razob Ali,Sun-Ok Chung,Md. Shaha Nur Kabir 사단법인 한국정밀농업학회 2023 정밀농업과학기술지 Vol.5 No.2

Recent advancements in plant disease identification have leveraged image processing and deep learning techniques for automated detection. Visual deep learning systems are employed to identify diseases accurately in the agricultural sector. This study focuses on reviewing the use of image processing and deep learning approaches in the accurate identification of pepper (Capsicum annuum L.) plant diseases. In most cases, it is quite difficult to classify the infected bacterial spots on pepper plants that affect productivity and quality, leading to substantial economic losses in the agricultural industry. To manage the issues, image processing and deep learning techniques have been applied to diagnose bacterial spots in pepper plants from the symptoms found on the leaves. Various methodologies for data augmentation and deep learning methods of embedding, multitask learning, transfer learning, and meta-learning are also discussed. It summarized how models are optimized for performance with reference to existing studies and potential challenges for AI applications in plant disease recognition. Finally, the review concludes with key findings and future directions and highlights the immense potential of deep learning as a valuable tool for accurate and automated identification and practical applications in pepper disease management.

Machine vision and artificial intelligence for plant growth stress detection and monitoring: A review

ISLAM SUMAIYA,REZA MD NASIM,Samsuzzaman,Ahmed Shahriar,Cho Yeon Jin,노동희,정선옥,홍순중 사단법인 한국정밀농업학회 2024 정밀농업과학기술지 Vol.6 No.1

The agricultural sector faces increasing challenges in ensuring food security and optimizing crop yield, necessitating innovative solutions for early detection and mitigation of plant growth stress. The integration of advanced imaging technologies with artificial intelligence (AI) has emerged as a powerful tool for non-invasive, real-time monitoring of plant health. The objective of this paper was to review the application of machine vision and AI in identifying and classifying plant growth stress, with a focus on stressors, datasets, and the use of intelligent algorithms. The significance of plant growth stress induced by environmental variables, including temperature, light, nutrient deficiencies, and water supply were addressed and the conventional stress detection methodologies, underscores their inherent limitations, and establishes the groundwork for the exploration of state-of-the-art technologies in stress assessment. Various sensor technologies were explored, encompassing traditional RGB cameras, multispectral and hyperspectral sensors, and thermal imaging, each capable of capturing distinct stress signatures. Machine vision, leveraging high-resolution imaging and spectroscopy, offers detailed insights into plant physiological responses. Coupled with AI approaches such as deep learning, neural networks, and pattern recognition, machine vision enables the automated analysis of vast datasets, enhancing the accuracy and speed of stress detection. The recent advancements in image processing techniques tailored for plant stress identification were focused and discussed the role of feature extraction, classification, and predictive modelling in achieving robust results. The potentials of AI in plant stress physiology and its role in overcoming the limitations of traditional methods, and the use of unsupervised identification of visual symptoms to quantify stress severity, allowing for the identification of different types of plant stress were studied. Moreover, the potentials of machine vision technology and AI for real-time monitoring and decision support systems in precision agriculture were discussed. The findings of this review would contribute to the growing field of agricultural technology, offering insights into the development of automated tools that could aid farmers and researchers in mitigating the impact of abiotic stressors on crop/plant health and productivity.

Survey and analysis of national standardization trends for smart farm ICT equipment

Chi-Ju Woo,Ho-Sung An,Ka Young Lee,Samsuzzaman,Md. Shaha Nur Kabir,Sun-Ok Chung,Soon Jung Hong,Jong Kyu Ha 사단법인 한국정밀농업학회 2023 정밀농업과학기술지 Vol.5 No.3

The rapid advancement of information and communication technology (ICT) has significantly transformed the agricultural sector, giving rise to the concept of smart farming. Smart farming involves the integration of various ICT equipment and technologies to enhance agricultural practices, improve productivity, and ensure sustainable resource utilization. As smart farming gains momentum, the need for standardized practices and equipment becomes crucial to ensure interoperability, reliability, and widespread adoption. This paper presents a comprehensive survey and analysis of national standardization trends for smart farm ICT equipment in smart farming. It introduces the standardization trends, smart farm ICT equipment national standard diffusion support project, and evaluation of testing ICT equipments. Additionally, it highlights the necessity and consequences of ensuring interoperability for ICT equipment in smart farming. Furthermore, the paper explores the challenges and opportunities associated with smart farm ICT equipment standardization. Challenges include reconciling diverse technical requirements, addressing security and privacy concerns, and maintaining adaptability to evolving technological landscapes. On the other hand, standardization offers the opportunity to accelerate innovation, enable market growth, and establish a foundation for sustainable agricultural practices.

IoT-based solar-powered smart irrigation system with solar tracker for rice fields

Dey Pabel Kanti,Banu Selina,Milufarzana Milufarzana,Robin Sakib,Mazumdar Nayon Chandra,Samsuzzaman Samsuzzaman,Kabir Md Shaha Nur 사단법인 한국정밀농업학회 2024 정밀농업과학기술지 Vol.6 No.1

Water management in irrigated agricultural fields is a critical issue in Bangladesh due to a lack of improved irrigation facilities for efficient use of irrigation water, and the cost of crop production is high with low agricultural productivity in agriculture. Therefore, this research aimed to design and implement an internet of things (IoT)-based solar-powered smart irrigation system by sensing the soil moisture levels and periodically controlling the pump operations when the soil moisture is below the required level. A sun-tracking solar system was developed to generate more electricity by tracking the orientation of the sun. A comparison was made between the energy of a fixed-panel solar system with a 24.95° tilt angle and a solar tracking system with no tilt angle. The solar tracker device utilizes a Light Dependent Resistor (LDR) sensor to track the sun, aligning the 150 W solar panel perpendicular to maximize energy capture. This energy is converted into electrical energy and stored in a 12V battery for powering the operation of the submersible pump (DC 12V, 150 W). A wireless sensor network was employed to monitor pumping status and energy comparison in a rice field. A sub-station transferred water level data wirelessly to a main station, where a microcontroller processed the data. The relay module automatically triggered pumping, and the data was stored in the cloud. The solar tracking system outperformed the fixed-panel system with a fixed tilt angle of 24.95° in terms of output power by a remarkable 26.72%. There is a huge potential for solar irrigation systems in Bangladesh, and they can provide sustainable solutions with low irrigation costs. Therefore, this IoT-based solar-powered smart irrigation system could play a vital role in improving irrigation management systems with increased water use efficiency.

Investigation of structural phase transition, Curie temperature and energy storage density of Ba0.97Ca0.03Ti1−xSnxO3 electroceramics

Kadhane Pravin S.,Baraskar Bharat G.,Darvade Tulshidas C.,Ramdasi Onkar A.,Samsuzzaman Md.,Kambale Rahul C. 한국세라믹학회 2022 한국세라믹학회지 Vol.59 No.5

Three different measurement methods to determine the structural phase transitions and Curie temperature of Ba 0.97 Ca 0.03 Ti 1−x Sn x O 3 (BCTS, x = 0.025, and 0.035 mol). electroceramics are discussed. At room temperature, both com- positions reveal the tetragonal perovskite lattice symmetry as evidenced by X-ray diffraction, temperature-dependent dielectric constant and Raman active modes. The temperature-dependent dielectric study reveals T R-O at − 60 °C, T O-T at 14 °C, T T-C at 126 °C for composition x = 0.025 and T R-O at − 50 °C, T O-T at 20 °C, T T-C at 118 °C for composition x = 0.035. To evident the structural changes happening at phase transitions as well as Curie temperature the variation of polarization concerning temperature is investigated which supports the temperature-dependent dielectric and Raman spectroscopy studies. The room temperature recoverable energy storage density and efficiency of BCTS are calculated by the integral area 3 of the polarization–electric fi eld (P-E) hysteresis loop. The observed recoverable energy storage density is 21.80 mJ/cm and 32.40 mJ/cm 3 with the efficiency of 43.58% and 52.25% for composition x = 0.025 and 0.035 mol., respectively. These results are having practical importance, due to the higher recoverable energy storage density and efficiency with moderate Curie temperature compared to the pure BaTiO 3 . Thus, it can be used as a promising novel and environmentally friendly, lead-free material, for different applications in low carbon vehicles, renewable energy technologies, integrated circuits, and for the high-temperature aerospace sector.