We present a new images dataset called PTL-AI Furnas Dataset as a new benchmark for fault detection in power transmission lines. this dataset has 6,295 images, with resolution 1280x720, extracted from the maintenance ...
详细信息
ISBN:
(数字)9781665453851
ISBN:
(纸本)9781665453851
We present a new images dataset called PTL-AI Furnas Dataset as a new benchmark for fault detection in power transmission lines. this dataset has 6,295 images, with resolution 1280x720, extracted from the maintenance process of the energy transmission lines at Furnas company. It contains annotations of 17,808 components classified as baliser, bird nest, insulator, spacer and stockbridge. Furnas is a company that generates or transmits electricity to 51% of households in Brazil and more than 40% of the nation's electricity passes through their grid enabling generating the dataset in different backgrounds and climatic conditions. We performed experiments using data augmentation techniques to train Faster R-CNN, Single-Shot Detects (SSD) and YoloV5 models. the benchmark result was obtained using the metrics of Mean Average Precision (mAP) and the Mean Average Recall (mAR) with values mAP=91.9% and mAR=89.7%. the PTL-AI Furnas Dataset is publicly available at https://***/freds0/PTL-AI_Furnas_Dataset.
Breast cancer is the most common cancer type and is the leading cause of death among females worldwide. Despite these negative statistics, early diagnosis gives patients a high probability of survival. In literature, ...
详细信息
ISBN:
(数字)9781665453851
ISBN:
(纸本)9781665453851
Breast cancer is the most common cancer type and is the leading cause of death among females worldwide. Despite these negative statistics, early diagnosis gives patients a high probability of survival. In literature, diagnostic techniques based on histopathological images were proposed for early diagnosis. However, they are limited because they depend on the pathologist's work and experience. In other words, a patient may receive a different diagnosis from different pathologists, or inexperienced pathologists may misdiagnose. In this work, we implement five Deep Neural Networks (DNNs) and evaluate classification accuracy and interpretability from real tumour images. To evaluate our models, we propose a metric to assess the interpretability of Deep Neural Networks (DNNs). the experiments withthe BreCaHAD annotated dataset have shown that MobileNetV2 presented a higher accuracy in classifying histopathological images and interpreting their features, leading the way to improve the pathologist's work.
Histological image analysis through systems to aid diagnosis plays an important role in medicine with supplementary reading for the specialist's diagnosis. this work proposes a method based on the association of e...
详细信息
ISBN:
(数字)9781665453851
ISBN:
(纸本)9781665453851
Histological image analysis through systems to aid diagnosis plays an important role in medicine with supplementary reading for the specialist's diagnosis. this work proposes a method based on the association of extracted features by fractal techniques, regularization and polynomial classifier. the feature vectors were classified by applying the cross-validation technique with 10 folds. the evaluation of the results occurred through metrics such as accuracy (ACC) and imbalance accuracy metric (IAM). the proposed approach achieved significant results for all metrics with non-Hodgkin lymphoma lesion sets. the proposed approach provided values around 0.97 of IAM and 99% of ACC for investigated groups. these results are considered relevant to studies in the literature and the association of Hermite polynomial and regularization can contribute to the detection of the lesions by supporting specialists in clinical practices.
Unmanned Aerial Vehicles (UAVs) has stood out for assisting, enhancing, and optimizing agricultural production. images captured by UAVs allow a detailed view of the analyzed region since the flight occurs at low and m...
详细信息
ISBN:
(数字)9781665453851
ISBN:
(纸本)9781665453851
Unmanned Aerial Vehicles (UAVs) has stood out for assisting, enhancing, and optimizing agricultural production. images captured by UAVs allow a detailed view of the analyzed region since the flight occurs at low and medium altitudes (50m to 400m). In addition, there is a wide variety of sensors (RGB cameras, heat capture sensors, multi and hyperspectral cameras, among others), each with its own characteristics and capable of producing different information. In multi-spectral images acquisition, we use a distinct sensor to capture each image band and at different time, leading to misalignments. To tackle this problem we propose to train a deep neural network to predict the vector deformation fields to perform the registration between bands of a multi-spectral image. the proposed approach has an accuracy ranging from 89.90% to 93.79% in the task of estimating the displacement field between bands. Withthis field estimated by the network, it is possible to register between the bands without the need for manual marking of points.
Tourette Syndrome (TS) is a genetically induced disorder that is believed to be caused by morphological alterations in brain structure, resulting in involuntary movements known as tics. the current clinical standard f...
详细信息
ISBN:
(数字)9781665453851
ISBN:
(纸本)9781665453851
Tourette Syndrome (TS) is a genetically induced disorder that is believed to be caused by morphological alterations in brain structure, resulting in involuntary movements known as tics. the current clinical standard for diagnosing TS is by clinical assessments performed by physicians. Mild stages of TS, however, commonly go underdiagnosed as tics are infrequent or often suppressed. Brain imaging has been suggested to be a reliable tool to detect brain alterations and possible biomarkers that correspond to neurological disorders. In Magnetic Resonance Imaging (MRI), anatomical brain changes can be identified in the scan by variation in texture patterns of certain regions. the main goal of this work is to identify the statistical significance of texture features in specific brain regions to distinguish TS from control subjects. the proposed approach consists of four main steps: (i) image acquisition, where the data is also organized using demographic information;(ii) brain segmentation, where the structural MRI is parcellated into anatomical regions;(iii) registration, where functional MRI is aligned to structural MRI;(iv) obtaining texture features and statistical analysis, where texture features are extracted from the anatomical brain regions. We adopted 68 subjects aged between 6 to 14 years, divided equally into TS and Normal Control groups. We evaluated the texture features in a statistical manner, where our main findings are: (i) After False Discovery Rate (FDR) correction, only one texture feature was significant (p-value < 0.08) in structural MRI;(ii) Following FDR correction, eight texture features in functional MRI for three anatomical regions were considered significant;(iii) the right amygdala presented significance in distinct texture features, matching its importance in the literature. Texture features aligned withthe literature can serve as a reliable tool to identify imaging changes, which can lead to future work applied to clinical studies.
暂无评论