Automated Detection

The necessity for advanced diagnostic techniques in ophthalmology has become increasingly evident, particularly for conditions such as glaucoma and diabetic retinopathy, which necessitate precise retinal image analysis. Current methodologies, while effective to a degree, fall short in terms of accuracy, efficiency, and adaptability, especially in semantic segmentation and disease classification tasks. These limitations underscore the need for more sophisticated and reliable approaches to retinal image analysis. In response, this work introduces a comprehensive framework leveraging Fully Convolutional Neural Networks (FCNNs) for optic disc segmentation and Cup-to-Disc Ratio (CDR) estimation. The selection of FCNNs is predicated on their demonstrated proficiency in semantic segmentation, ability to discern spatial dependencies, and capacity to learn intricate structures within fundus images without relying on manually engineered features. This approach aims to surpass existing segmentation accuracy benchmarks, targeting over 95% Intersection over Union (IoU) while reducing the mean absolute error in CDR estimation to below 10%. To address the challenges of data variability and quality, the framework incorporates Contrast Limited Adaptive Histogram Equalization (CLAHE) for synthetic data generation, enhancing local contrast while preserving image integrity levels. This method is expected to improve contrast in augmented images by 30%, simultaneously enhancing image quality metrics. Furthermore, the introduction of an overlapping sliding window technique with adaptive patch sizes ensures meticulous coverage and analysis of fundus images, significantly elevating lesion detection sensitivity and reducing false positives. Lastly, the framework employs an innovative multi-disease classification strategy utilizing ensemble learning and stacking of CNN architectures. This synergistic approach amalgamates multiple base models to diminish overfitting risks and enhance generalization capabilities, aiming for a classification accuracy surpassing 95% in binary assessments and 85% for specific retinal diseases. The proposed model not only addresses the current gaps in retinal image analysis but also sets a new standard for precision, reliability, and efficiency in diagnosing and managing ocular diseases, marking a significant step forward in the application of artificial intelligence in ophthalmology.

Heart Rate Variability (HRV) may be used as a psychological marker to assess drivers' states from physiological signals such as an electrocardiogram (ECG), electroencephalogram (EEG), and photoplethysmography (PPG). This paper reviews HRV acquisition methods from drivers and machine learning approaches for driver cardiac health based on HRV classification. The study examines four publicly available ECG datasets and analyzes their HRV features, including time domain, frequency domain, short-term measures, and a combination of time and frequency domains. Eight machine learning classifiers, namely K-Nearest Neighbor, Decision Tree, Naive Bayes, Linear Discriminant Analysis, Support Vector Machine, Random Forest, Gradient Boost, and Adaboost, were used to determine whether the driver's state is normal or abnormal. The results show that K-Nearest Neighbor and Decision Tree classifiers had the highest accuracy at 92.86%. The study concludes by assessing the performance of machine learning algorithms in classifying HRV for the driver's physiological condition using the Man-Whitney U test in terms of accuracy and F1 score. We have statistical evidence to support that the prediction quality is different when HRV analysis applies these three sets: (i) time domain measures or frequency domain measures; (ii) frequency domain measures or short-term measures; and (iii) combining time and frequency domains or only frequency domains.

Automated detection of welding defects in radiographic images becomes non-trivial when uneven illumination, contrast and noise are present. In this paper, a new surface thresholding method is introduced to detect defects in radiographic images of welding joints. In the first stage, several image processing techniques namely fuzzy c means clustering, region filling, mean filtering, edge detection, Otsu's thresholding and morphological operations method are utilised to locate the area in which defects might exist. This is followed by the implementation of inverse surface thresholding with partial differential equation to locate isolated areas that represent the defects in the second stage. The proposed method obtained a promising result with high precision.

This study presents an innovative approach that combines Deep Reinforcement Learning with machine learning techniques to classify cardiovascular disease conditions using ECG and PCG signals from the EPNOGRAM dataset. The core aim is to boost classification accuracy by leveraging Deep Reinforcement Learning(DRL) for enhanced feature extraction, which is then fed into conventional models like CNN, RNN, LSTM, BiLSTM, and hybrid architectures such as CNN-RNN and LSTM &BiLSTM. Experimental results reveal notable performance gains when Deep Reinforcement Learning(DRL) is integrated. Specifically, the CNN-RNN hybrid achieved 90% accuracy, 89% precision, 88% recall, 88% F1-score, and a 92% AUC-ROC. The LSTM-BiLSTM hybrid outperformed with 92% accuracy, 91% precision, 90% recall, and 90% F1-score, and a 94% AUC. These findings highlight the effectiveness of merging Deep Reinforcement Learning(DRL) with supervised models, particularly in addressing the complexity of cardiopulmonary signal classification, and demonstrate the superior performance of hybrid models over standard classifiers in both accuracy and interpretability.

A low level of vigilance is one of the main reasons for traffic and industrial accidents. We conducted experiments to evoke the low level of vigilance and record physiological data through single-channel electroencephalogram (EEG) and electrocardiogram (ECG) measurements. In this study, a deep Q-network (DQN) algorithm was designed, using conventional feature engineering and deep convolutional neural network (CNN) methods, to extract the optimal features. The DQN yielded the optimal features: two CNN features from ECG and two conventional features from EEG. The ECG features were more significant for tracking the transitions within the alertness continuum with the DQN. The classification was performed with a small number of features, and the results were similar to those from using all of the features. This suggests that the DQN could be applied to investigating biomarkers for physiological responses and optimizing the classification system to reduce the input resources.

This paper describes the detection and tracking of static and dynamic underwater object(s). It addresses the case study application of a multi-layer artificial neural network prototype model on the bases of an analytical approach. It supports an Autonomous Underwater Vehicle (AUV) robot's controller system with automated detection of processed-obstacle-signals. The significance of this work is to investigate the neural network learning perception process of signal detection within operational environments. In this case, the acoustic-sound density is the source of detection and classification processes. The outcomes of this work are presented as simulated results that illustrate the error-detection control system. It activates due to a range of training forces originating from encountered acoustic-sensors' signals. In addition, the benefit of further simulation of the proposed technique can provide sufficient knowledge on the set-up of the controller's cyclic triggering towards actuators. The other benefits are included with control overshoot and rotational alignment of thrusters for precise navigational trajectory in real-time.

Drosophila melanogaster is an important organism used in many fields of biological research such as genetics and developmental biology. Drosophila wings have been widely used to study the genetics of development, morphometrics and evolution. Therefore there is much interest in quantifying wing structures of Drosophila. Advancement in technology has increased the ease in which images of Drosophila can be acquired. However such studies have been limited by the slow and tedious process of acquiring phenotypic data. We have developed a system that automatically detects and measures key points and vein segments on a Drosophila wing. Key points are detected by performing image transformations and template matching on Drosophila wing images while vein segments are detected using an Active Contour algorithm. The accuracy of our key point detection was compared against key point annotations of users. We also performed key point detection using different training data sets of Drosophila wing ...

Nowadays, archaeologists have vast amounts of Light Detection and Ranging (LiDAR) and other remote sensing data at their disposal, to search for previously undiscovered archaeological objects, often at a national scale. This leads to a Big Data problem in archaeology: some degree of automation is needed, as humans alone cannot cope with these ever-growing data sources. In this research, we have developed a novel workflow based on the Artificial Intelligence (AI) technology of Convolutional Neural Networks (CNNs), to automate the detection of unknown, complex archaeological objects. Our hypothesis is that a high-quality remote sensing data source such as LiDAR and a curated list of known objects, is sufficient to find a large number-or ideally all-additional undiscovered objects within a landscape. In a case study presented here, we use Prehistoric hillforts in England as an example for this workflow and present a three-step approach to demonstrate its efficiency.

The blurred gray/white matter junction is an important feature of focal cortical dysplasia (FCD) lesions. FCD is the main cause of epilepsy and can be detected through magnetic resonance (MR) imaging. Several earlier studies have focused on computing the gradient magnitude of the MR image and used the resulting map to model the blurred gray/white matter junction. However, gradient magnitude cannot quantify the blurred gray/white matter junction. Therefore, we proposed a novel algorithm called local directional probability optimization (LDPO) for detecting and quantifying the width of the gray/white matter boundary (GWB) within the lesional areas. The proposed LDPO method mainly consists of the following three stages: (1) introduction of a hidden Markov random field-expectation-maximization algorithm to compute the probability images of brain tissues in order to obtain the GWB region; (2) generation of local directions from gray matter (GM) to white matter (WM) passing through the GWB, considering the GWB to be an electric potential field; (3) determination of the optimal local directions for any given voxel of GWB, based on iterative searching of the neighborhood. This was then used to measure the width of the GWB. The proposed LDPO method was tested on real MR images of patients with FCD lesions. The results indicated that the LDPO method could quantify the GWB width. On the GWB width map, the width of the blurred GWB in the lesional region was observed to be greater than that in the non-lesional regions. The proposed GWB width map produced higher F-scores in terms of detecting the blurred GWB within the FCD lesional region as compared to that of FCD feature maps, indicating better trade-off between precision and recall.

 Users may download and print one copy of any publication from the public portal for the purpose of private study or research.  You may not further distribute the material or use it for any profit-making activity or commercial gain  You may freely distribute the URL identifying the publication in the public portal If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

This paper reports a study which utilizes deep learning for automated detection of the symptoms of diseases on vine leaves. Vine fruits or grapes are very important and have existed in Syria and surrounding areas (e.g., Turkey) for many years. Quality of vine fruits is also very important in grape production as it is consumed in these areas every day. The aim of this study is to improve diseasedetection accuracy in vine leaves and to develop a system to help Syrian and Turkish farmers and agricultural engineers to maintain the quality of grape production. In this study, over 1000 images of vine leaves have been collected from vine yards in Syria and the internet. These images are processed using MATLAB 2018B, Deep Learning Toolbox including convolutional neural networks (CNNs) with AlexNet, GoogleNet and ResNet-18. A standard transfer learning (TL) algorithm is also used with CNNs, whereas a multiclass support vector machine (SVM) is used with AlexNet, whilst GPU and CUDA are used for accelerating the process of the disease detection for vine leaves. A software system has been created that enables the automatic and efficient detection of nine types of leaf diseases and the identification of healthy leaves. Experimental studies showed that the total detection accuracy of this system reaches 92.5%, 87.4% and 85.0%, 85.1% when AlexNet+TL, ResNet-18+TL, GoogleNet+TL and AlexNet+SVM are used respectively. This smart agricultural application can provide early identification of the symptoms of grape diseases on leaves and thus help maintain the quality of vine fruits.

A collection of culture extracts obtained from several marine-derived fungal strains collected on the French Atlantic coast was investigated by high performance liquid chromatography-high resolution mass spectrometry (HPLC-HRMS) in order to prospect for halogenated compounds and to identify potentially new ones. To achieve a fast, automated, and efficient data analysis, a bioinformatics tool named MeHaloCoA (Marine Halogenated Compound Analysis) was developed and included into R. After extraction of all the peaks from the metabolic fingerprints and their associated mass spectra, a mathematical filter based on mass isotopic profiles allowed the selective detection of halogenated (Cl and Br) molecules. Integrating MeHaloCoA into a dereplication approach allowed the identification of known and new halogenated compounds in a competitive amount of time. Subsequent targeted purification led to the isolation of several chlorinated metabolites, including two new natural products with bioact...

Histogram Analysis for CFAE Detection. Introduction: Complex fractionated atrial electrograms (CFAEs) might identify the critical substrate maintaining AF. We developed a method based upon histogram analysis of interpeak intervals (IPIs) to automatically quantify fractionation and differentiate between subtypes of CFAEs. Methods: Two experts classified 1,681 fibrillatory electrograms recorded in 13 patients with persistent AF into 3 categories (gold standard): normal electrograms, discontinuous CFAEs, or continuous CFAEs. Histogram analysis of IPI was performed to calculate the P5, P50, P95, and the mean of IPIs, in addition to the total number of IPI (N Total), and the number of IPI within predetermined ranges: 10-60 (N Short), 60-120 (N Intermediate), and >120 ms (N Long). Results: P50 and N Long were higher in the normal electrograms compared to the other 2 categories (P < 0.001). N Intermediate was higher in the discontinuous CFAE category compared to the other 2 categories. P95, mean IPI, N Total , and N Short were all significantly different among the 3 categories (P < 0.001) and correlated with the degree of fractionation (r = −0.52, −0.55, 0.68, and 0.67, respectively). Receiver operating characteristic (ROC) curves showed good diagnostic accuracy (area under curve, AUC > 0.8) of P50 and N Long to detect normal electrograms. An algorithm using N Intermediate showed good diagnostic accuracy (AUC > 0.7) to detect discontinuous CFAEs, whereas P95, mean, N Total , and N Short all revealed high diagnostic accuracy (AUC > 0.85) to detect continuous CFAEs. This was confirmed in a prospective data set. Conclusions: Histogram analysis of IPI can differentiate between normal electrograms, discontinuous and continuous fractionated electrograms. This method might be used to standardize and optimize ablation strategies in AF.

 Users may download and print one copy of any publication from the public portal for the purpose of private study or research.  You may not further distribute the material or use it for any profit-making activity or commercial gain  You may freely distribute the URL identifying the publication in the public portal If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

Glaucoma is an incurable eye disease that leads to slow progressive degeneration of the retina. It cannot be fully cured, however, its progression can be controlled in case of early diagnosis. Unfortunately, due to the absence of clear symptoms during the early stages, early diagnosis are rare. Glaucoma must be detected at early stages since late diagnosis can lead to permanent vision loss. Glaucoma affects the retina by damaging the Optic Nerve Head (ONH). Its diagnosis is dependent on the measurements of Optic Cup (OC) and Optic Disc (OD) in the retina. Computer vision techniques have been shown to diagnose glaucoma effectively and correctly with little overhead. These techniques measure OC and OC dimensions using machine learning based classification and segmentation algorithms. This article aims to provide a comprehensive overview of various existing techniques that use machine learning to detect and diagnose glaucoma based on fundus images. Readers would be able to understand the challenges glaucoma presents from an image processing and machine learning standpoint and will be able to identify gaps in current research. INDEX TERMS Glaucoma, convolutional neural networks (CNN), diabetic retinopathy, cup-to-disc ratio (CDR), optic nerve head (ONH), optic cup (OC), optic disc (OD), intra ocular pressure (IOP).

Acoustic recordings of two closely related species, spinner dolphin (Stenella longirostris) and pantropical spotted dolphin (Stenella attenuata), were investigated from four different geographic locations: two in the Central Tropical Pacific, one in the Eastern Tropical Pacific and one in the Indian Ocean. The two delphinid species occur in tropical and warm temperate waters, with overlapping ranges. They produce very similar vocalizations, but at the same time their calls exhibit a certain degree of intraspecific variation among different geographic locations as has been observed in other delphinid species. Oscillatory whistles (whistles with at least two oscillations in their frequency contours) were identified and manually extracted from the recordings. Whistles with four or more maxima (oscillations) occurred only in spinner dolphins and they were present in all geographic regions investigated. In addition, the oscillatory whistles with two and three maxima were significantly more frequent in spinner than in spotted dolphins. The differences in oscillatory whistles for these two species seem to be consistent across study areas and therefore, could be used in addition to other whistle features to help distinguish between them.

Automated systems for road crack detection are extremely important in road maintenance for vehicle safety and traveler's comfort. Emerging cracks in roads need to be detected and accordingly repaired as early as possible to avoid further damage thus reducing rehabilitation cost. In this paper, a robust method for Gabor filter parameters optimization for automatic road crack detection is discussed. Gabor filter has been used in previous literature for similar applications. However, there is a need for automatic selection of optimized Gabor filter parameters due to variation in texture of roads and cracks. The problem of change of background, which in fact is road texture, is addressed through a learning process by using synthetic road crack generation for Gabor filter parameter tuning. Tuned parameters are then tested on real cracks and a thorough quantitative analysis is performed for performance evaluation.

Automated detection of welding defects in radiographic images becomes non-trivial when uneven illumination, contrast and noise are present. In this paper, a new surface thresholding method is introduced to detect defects in radiographic images of welding joints. In the first stage, several image processing techniques namely fuzzy c means clustering, region filling, mean filtering, edge detection, Otsu's thresholding and morphological operations method are utilised to locate the area in which defects might exist. This is followed by the implementation of inverse surface thresholding with partial differential equation to locate isolated areas that represent the defects in the second stage. The proposed method obtained a promising result with high precision.

The word agriculture takes up the whole loads of positivity in regards to energy all over the world. Agriculture field faces much more difficulties in current situation. One among them is animal intrusion to farm field causing severe financial loss to production. The proposal involves animal movement detection in fencing fields using frame differentiation with OpenCV and motion detection algorithm. The safety measures are initiated once the keyword is spoken to awake the voice assistant and thus help is reached by sending messages that is already given as input to the trustable people to make possible measures. There are two modules here. one is the movement detection using OpenCV and the second module is the voice assistant. Frame differentiation is used, to fetch the difference between stable content and differing content. Hence two frames are referred in this proposal. OpenCV refers to the computer vision process that aids in image processing and other motion
prediction system. OpenCV is a library that is represented as cross-platform

Seagrass is an important component of the marine ecosystem and plays a vital role in preserving the water quality. The traditional approaches for sea grass identification are either manual or semi-automated, resulting in costlier, time consuming and tedious solutions. There has been an increasing interest in the automatic identification of seagrasses and this article provides a survey of automatic classification techniques that are based on machine learning, fuzzy synthetic evaluation model and maximum likelihood classifier along with their performance. The article classifies the existing approaches on the basis of image types (i.e. aerial, satellite, and underwater digital), outlines the current challenges and provides future research directions.

An accurate approach for localization and segmentation of an optic disk (OD) in the retinal images is one of the most imperative tasks in an automated screening system. The retinal fundus images analysis is extensively used in the diagnosis and treatment of several eye diseases such as glaucoma and diabetic retinopathy. This research brings out a new algorithm that has not been used before to detect and segment the optic disk in all categories of retinal images, specifically healthy retinal images plus anomalous, or in other words fundus images affected due to diseases. The technique adopted for the separation of the optic disk is centered on histogram specification, mathematical morphological operations includes erosion as well as dilation along with proper thresholding and detection of circles using the Hough Transform technique. The proposed procedure has been tested on standard databases provided for ophthalmic image processing researches on internet, Diaretdb0, Diaretdb1 and lo...

In this study, the aim is to determine the proficiency of special education teachers in terms&lt;br&gt; of using instructional technologies in the TRNC. A total of 80 special education teachers from&lt;br&gt; rehabilitation institutes in Famagusta, Kyrenia, and Nicosia participated in this study in the 2016 –&lt;br&gt; 2017 education year, of whom 45 were women and 45 were men. The quantitative research method&lt;br&gt; was used and, in terms of collection tools, a demographic information form along with an opinion&lt;br&gt; survey aimed at defining their usage and skill levels of special education teachers in the TRNC&lt;br&gt; related to the use of instructional technologies were used. The data were analysed with the SPSS&lt;br&gt; 20.00 program. Based on the results of the analysis, it was found that the level of using educational&lt;br&gt; technologies was low. According to the data which was obtained from teachers&#39; opinions, the&lt;br&gt; special education teachers were in ...

The technology and innovations that it has provided have begun to show their effect on education too as in all other fields of life. Benefiting from the technological innovations in the field of education in developing world will increase students' compliance to the changing life conditions. Besides that, individuals who have learnt to use technology accurately and productively during their education period will have a set of differences from other individuals in their future life thanks to technology, information and the skills that they will bring in. In this context, this research has been conducted to understand the opinions of administrators, teachers, and parents for the use of technology and to see how much the use of technology is integrated into the system in schools.