KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1

Browse

Search Results

Now showing 1 - 5 of 5

Some of the metrics are blocked by your
consent settings
A deep contrastive learning-based image retrieval system for automatic detection of infectious cattle diseases
(2025-12-01)
Kittichai, Veerayuth
;
Kaewthamasorn, Morakot
;
Arnuphaprasert, Apinya
;
Jomtarak, Rangsan
;
Naing, Kaung Myat
Anaplasmosis, which is caused by Anaplasma spp. and transmitted by tick bites, is one of the most serious livestock animal diseases worldwide, causing significant economic losses as well as public health issues. Anaplasma marginale, a gram-negative intracellular obligate bacterium, can cause disease in cattle and other ruminants. Because of the insufficient quality of the slides, a microscopic diagnostic procedure is time-consuming and challenging to diagnose. Intra- and inter-rater variation is frequently imposed on by technicians who are underqualified and unexperienced. Alternatively, algorithms could support local employees in tracking disease transmission and quick action, especially in Thailand where this cattle disease is common. As a result, the study intends to create an automated tool based on a deep neural network linked with an image-retrieval procedure for recognizing infections in microscopic pictures. The Resnext-50 model, which serves as the embedding space’s backbone and is optimized by Triplet-Margin loss, outperforms, with averaged accuracy and specificity ratings of 91.30 percent and 92.83 percent, respectively. The model’s performance was also improved by a fine-tuned procedure between k-nearest neighbor and its normalized distance of each data point, including precision of 0.833 ± 0.134, specificity of 0.930 ± 0.054, recall of 0.838 ± 0.118, and accuracy of 0.915 ± 0.025, respectively. Five-fold cross-validation confirms that the trained model using the optimal k-nearest neighbor (kNN) for the image-based retrieval system, involving 12 images, prevents overfitting via dataset variations indicating areas under the receiver operating curve rankings ranging from 0.917 to 0.922. The image retrieval technique demonstrated in this research is a prototype for a variety of applications. The findings may aid in the early diagnosis of anaplasmosis infections in remote areas without access to veterinary care or costly molecular diagnostic tools.
Some of the metrics are blocked by your
consent settings
A deep neural network-correlation phase sensitive mask based estimation to improve speech intelligibility
(2023-09-01)
Sivapatham, Shoba
;
Kar, Asutosh
;
Bodile, Roshan
;
Mladenovic, Vladimir
;
Sooraksa, Pitikhate
General masking-based speech enhancement using a deep learning architecture (DNN) approach focuses on the spectral values of the speech in order to show improvement in intelligibility. But, the residual noise present in the phase spectrum and inter-channel correlation dependency between noise and noisy speech can impact the results of intelligibility in speech enhancement. This research work proposes a correlation phase-sensitive novel mask which contains phase, magnitude spectral and inter-channel correlation for a tangible improvement in speech intelligibility. The correlation parameter finds the dependency between the signals and phase spectrum factor eliminates the residual noise. In addition, selecting the prior features from the feature combination also helps in reducing the dimensionality and increases the accuracy of the enhanced speech. This work also aims to decrease the complexity of the DNN by analysing the network with different parameters. The performance of the mask is evaluated with various intelligibility factors. The proposed mask has been compared with different mask estimators. The proposed mask has generated estimated speech with an increase in the intelligibility of 0.02-0.001 over six different noises and four different signal-to-noise (SNR) levels.
Some of the metrics are blocked by your
consent settings
The Cattle Rut Behavior Detection Base on AI Deep Neural Network
(2022-01-01)
Phaechaiyaphum, Phatsarut
;
Konghuayrob, Poom
This paper proposes an application model of camera object detection to observe the cattle rut through its pose. This research is based on deep neural network method along with transfer learning technique. This paper employs four different deep convolutional neural network architectures 1) SSD Mobile-Net V2 2) SSD ResNet 101 V1 FPN 3) YOLOv5s and 4) Mask R-CNN. All the network mentioned above are pre-trained on COCO dataset. To observe the cattle rut behavior, the images of cattle behavior were taken in natural open environment, the data obtained are split into training and testing datasets. In this research cattle behaviors are categorized mainly in two classes, (1) normal behavior and (2) the cattle rut behavior. The result obtained after training the models shows that the YOLOv5s model obtained the highest mean average precision which is 95.5% and least training time. Thus, this paper proposes that YOLOv5s model can be applied to detect the cattle behavior for precise artificial breeding in order to increase the cattle population in farm to serve higher consumption demand in the near future.
Some of the metrics are blocked by your
consent settings
Vertical speed prediction for the efficient landing of aircraft using GRU
(2020-11-04)
Pavitpok, Siwagorn
;
Phasukkit, Pattarapong
;
Pradabpet, Chusit
Air traffic management is currently the process of managing air traffic demand. For support the capacity to handle the amount of air traffic. Whether it is in the airspace sector or the airport area. There are many factors such as the ability of the air traffic providers, physical characteristics of airspace and airport terrain. The main goal of air traffic management is to manage air traffic control. Streamlined and demand-capacity balancing are safe and effective. Whether it is air traffic service providers or passengers. In this research, the experiment was carried out on specific aircraft model A-320. Traveling from Bangkok Suvarnabhumi Airport to Phuket International Airport. In which the landing airport has island terrain. Therefore, requires high security due to physical characteristics in the airspace which has many factors such as wind and wind direction and to provide safety and effective landing. Therefore, take the factors affecting the landing to predict the vertical speed. The epoch =2000, learning rate =0.01, accuracy more than 90% for training set and 90% for test set.
Some of the metrics are blocked by your
consent settings
Hybrid Loss for Improving Classification Performance with Unbalanced Data
(2020-01-01)
Lodkaew, Thanawat
;
Pasupa, Kitsuchart
Unbalanced data is widespread in practice and presents challenges which have been widely studied in classical machine learning. A classification algorithm trained with unbalanced data is likely to be biased towards the majority class and thus show inferior performance on the minority class. To improve the performance of deep neural network (DNN) models on poorly balanced data, we hybridized two well-performing loss functions, specially designed for learning imbalanced data, mean false error and focal loss. Since mean false error can effectively balance between majority and minority classes and focal loss can reduce the contribution of unnecessary samples, which are usually samples from the majority class, which may cause a DNN model to be biased towards the majority class when learning. We show that hybridizing the two losses can improve the classification performance of the model. Our hybrid loss function was tested with unbalanced data sets, extracted from CIFAR-100 and IMDB review datasets, and showed that, overall, it performed better than mean false error or focal loss.

KMITL

Browse

Filters

Settings

Sort By

Results per page

Search Results