An operation theatre (OT) is a special room inside the hospital where medical surgery is carried out by a surgeon with the help of medical personnel. Technical standards or requirements which have been set for heating, ventilation and air conditioning (HVAC) inside an operation theatre is important not only for the comfort of surgeon, patient, and medical personnel, but also to reduce the risk of surgical site infection during surgery. This research focus on Minor Operation Theatre (MOT) which is dental surgery room at Universiti Malaysia Perlis Health Centre with room dimensions of 2.89 m(H)×3.12 m(W)×3.4 m(L) is used for numerical analysis. The air flow supplied to the MOT is from single unit air-conditioning system. Computational Fluid Dynamics (CFD) analysis is a part of an investigation to determine the air flow and temperature distribution inside the MOT. A simulation conducted by using ANSYS Fluent only consider dry air inside MOT. Therefore, the main aim of this research is to compare and analyze the simulation of dry air conducted with previously obtained experimental data of humid air distribution inside the MOT. The comparison of humid and dry air temperature throughout the MOT shows that the difference is 25.3%. The average temperature of humid air inside the MOT is 21.8 °C while for dry air is 16.3 °C. Moreover, the cooling capacity of humid air and dry air are 2.23 kW and 1.64 kW respectively. Thus, the difference between humid air and dry air-cooling capacity is 26.5%. However, the dry air simulation and humid air simulation is the same if only the process is considered as simple cooling.

Numerous research have demonstrated that Convolutional Neural Network (CNN) models are capable of classifying visual field (VF) defects with great accuracy. In this study, we evaluated the performance of different pre-trained models (VGG-Net, MobileNet, ResNet, and DenseNet) in classifying VF defects and produced a comprehensive comparative analysis to compare the performance of different CNN models before and after hyperparameter tuning and fine-tuning. Using 32 batch sizes, 50 epochs, and ADAM as the optimizer to optimize weight, bias, and learning rate, VGG-16 obtained the highest accuracy of 97.63 percent, according to experimental findings. Subsequently, Bayesian optimization was utilized to execute automated hyperparameter tuning and automated fine-tuning layers of the pre-trained models to determine the optimal hyperparameter and fine-tuning layer for classifying many VF defect with the highest accuracy. We found that the combination of different hyperparameters and fine-tuning of the pre-trained models significantly impact the performance of deep learning models for this classification task. In addition, we also discovered that the automated selection of optimal hyperparameters and fine-tuning by Bayesian has significantly enhanced the performance of the pre-trained models. The results observed the best performance for the DenseNet-121 model with a validation accuracy of 98.46% and a test accuracy of 99.57% for the tested datasets.

Living mammalian especially European cats will face some problems when traveling from cold ambient in Europe to hot ambient country. Some of the problems are, these cats will become panting when exposed to the high temperature of ambient for a short term. Also, for a long term exposed to high temperature, the cats will experience heat stress and hair loss. The objectives of this study are on cat thermal comfort, cooling load for cat compartment, and analysis of air flow to achieve the desired temperature for the cat compartment using CFD simulation. In this study, three parts of analysis will be considered in CFD simulations which are the thermal distribution for four Peltier plates with aluminium heat sink using ANSYS Transient Thermal, air flow in the ducting to a cold heat sink, and air flow distribution in cat compartment using ANSYS Fluent. The temperature for the Persian cat’s thermal comfort is around 20-25°C. Cooling load gain from designed portable cat compartment with the desired space is 177 W. By ANSYS Transient Thermal, time taken for heat sink change from 22°C to 12°C is around 200-250 seconds. Then, by using ANSYS Fluent, the temperature of initial air temperature in the ducting when flow through a cold heat sink was changed from 27.15°C to 20.93°C by simple cooling. Next, the average air temperature in the cat’s compartment is 23.83°C that achieved average thermal comfort for mammal or Persian cat which is 20-25°C of dry bulb temperature. However, the study only focuses on steady-state dry air simple cooling analysis only with the laminar flow as a preliminary result by CFD simulation before build the actual portable cat compartment. The dry air simulation can be assumed similar as humid air for simple cooling process only proved by the comparison of the same cooling capacities values towards the different value of absolute humidity.

In this work, a custom deep learning method is proposed to develop a detection of visual fields defects which are the markers for serious optic pathway disease. Convolutional Neural Networks (CNN) is a deep learning method that is mostly used in images processing. Therefore, a custom 10 layers of CNN algorithm is built to detect the visual field defect. In this work, 1200 visual field defect images acquired from the Humphrey Field Analyzer 24–2 collected from Google Image have been used to classify 6 types of visual field defect. The defect patterns are including defects at central scotoma, right/left/upper/lower quadratopia, right/left hemianopia, vision tunnel, superior/inferior field defect and normal as baseline. The custom designed CNN is trained to discriminate between defect patterns in visual field images. In the proposed method, a mechanism of pre-processing is included to improve the classification of visual field defects. Then, the 6 visual field defect patterns are detected using a convolutional neural network. The dataset is evaluated using 5-fold cross-validation. The results of this work have shown that the proposed algorithm achieved a high classification rate with 96%. As comparison, traditional machine learning Support Vector Machine (SVM) and Classical Neural Network (NN) is chose and obtained classification rate at 74.54% and 90.72%.

Bayesian optimization (BO) is commonly used to optimize the hyperparameters of transfer learning models to improve the model’s performance significantly. In BO, the acquisition functions direct the hyperparameter space exploration during the optimization. However, the computational cost of evaluating the acquisition function and updating the surrogate model can become prohibitively expensive due to increasing dimensionality, making it more challenging to achieve the global optimum, particularly in image classification tasks. Therefore, this study investigates and analyses the effect of incorporating metaheuristic methods into BO to improve the performance of acquisition functions in transfer learning. By incorporating four different metaheuristic methods, namely Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC) Optimization, Harris Hawks Optimization, and Sailfish Optimization (SFO), the performance of acquisition function, Expected Improvement (EI), was observed in the VGGNet models for visual field defect multi-class classification. Other than EI, comparative observations were also conducted using different acquisition functions, such as Probability Improvement (PI), Upper Confidence Bound (UCB), and Lower Confidence Bound (LCB). The analysis demonstrates that SFO significantly enhanced BO optimization by increasing mean accuracy by 9.6% for VGG-16 and 27.54% for VGG-19. As a result, the best validation accuracy obtained for VGG-16 and VGG-19 is 98.6% and 98.34%, respectively.