Automatic Detection Technique Research Articles

Performance analysis of deep transfer learning approaches in detecting and classifying brain tumor from magnetic resonance images

The Central Nervous System (CNS) is one of the most crucial parts of the human body. Brain tumor is one of the deadliest diseases that affect CNS and they should be detected earlier to avoid serious health implications. As it is one of the most dangerous types of cancer, its diagnosis is a crucial part of the healthcare sector. A brain tumor can be malignant or benign and its grade recognition is a tedious task for the radiologist. In the recent past, researchers have proposed various automatic detection and classification techniques that use different imaging modalities focusing on increased accuracy. In this paper, we have done an in-depth study of 19 different trained deep learning models like Alexnet, VGGnet, DarkNet, DenseNet, ResNet, InceptionNet, ShuffleNet, NasNet and their variants for the detection of brain tumors using deep transfer learning. The performance parameters show that NASNet-Large is outperforming others with an accuracy of 98.03% for detection and 97.87% for classification. The thresholding algorithm is used for segmenting out the tumor region if the detected output is other than normal.

Investigating the effect of distance on the implementation of RCNN automatic detection technique to the human body

The identification of humans constitutes a crucial component of monitoring systems, given the significance of the timely detection of individuals. Despite advancements in people detection systems, detecting humans at long distances remains challenging. In this study, we employed the Region-based Convolutional Neural Network (RCNN) approach to training a system on images captured at varying distances between the camera and individuals. The results demonstrate promising outcomes, with the system achieving a maximum detection recall of 1 for identifying people at distances of up to 40 meters and maximum precision of 1 for identifying people at distances of up to 50 meters.

Automated diagnosis of EEG abnormalities with different classification techniques.

Automatic seizure detection and prediction using clinical Electroencephalograms (EEGs) are challenging tasks due to factors such as low Signal-to-Noise Ratios (SNRs), high variance in epileptic seizures among patients, and limited clinical data constraints. To overcome these challenges, this paper presents two approaches for EEG signal classification. One of these approaches depends on Machine Learning (ML) tools. The used features are different types of entropy, higher-order statistics, and sub-band energies in the Hilbert Marginal Spectrum (HMS) domain. The classification is performed using Support Vector Machine (SVM), Logistic Regression (LR), and K-Nearest Neighbor (KNN) classifiers. Both seizure detection and prediction scenarios are considered. The second approach depends on spectrograms of EEG signal segments and a Convolutional Neural Network (CNN)-based residual learning model. We use 10000 spectrogram images for each class. In this approach, it is possible to perform both seizure detection and prediction in addition to a 3-state classification scenario. Both approaches are evaluated on the Children's Hospital Boston and the Massachusetts Institute of Technology (CHB-MIT) dataset, which contains 24 EEG recordings for 6 males and 18 females. The results obtained for the HMS-based model showed an accuracy of 100%. The CNN-based model achieved accuracies of 97.66%, 95.59%, and 94.51% for Seizure (S) versus Pre-Seizure (PS), Non-Seizure (NS) versus S, and NS versus S versus PS classes, respectively. These results demonstrate that the proposed approaches can be effectively used for seizure detection and prediction. They outperform the state-of-the-art techniques for automatic seizure detection and prediction. Block diagram of proposed epileptic seizure detection method using HMS with different classifiers.

Using file and folder naming and structuring to improve automated detection of child sexual abuse images on the Dark Web

Increasing dissemination of child sexual abuse material (CSAM), especially on the Dark Web, has necessitated greater reliance on automated detection tools. These tools typically match images and videos to known CSAM databases, which is an ineffective method for identifying unknown CSAM. To identify potential complimentary methods, we analysed 162 unique known images, displayed 7289 times on 988 Dark Web websites, to determine if patterns in file/folder naming and structuring tendencies existed on websites. Overall, websites prioritised organisation (ease of access) over obfuscation (security) and hosted almost all images they displayed. File/folder names were commonly alphanumeric, however, there was evidence of sequence file naming patterns. Webpages displaying CSAM were explicitly named, often using underage and/or incest-related keywords. Structuring patterns revealed presence of website copies (mirrors) which can impede effective CSAM removal. Recommendations for supplementing automated detection techniques are discussed.

A Comprehensive Review on Advancement in Deep Learning Techniques for Automatic Detection of Tuberculosis from Chest X-ray Images

A Comprehensive Review on Advancement in Deep Learning Techniques for Automatic Detection of Tuberculosis from Chest X-ray Images

Automatic Detection and Classification of Epileptic Seizures from EEG Data: Finding Optimal Acquisition Settings and Testing Interpretable Machine Learning Approach.

Deep learning (DL) is emerging as a successful technique for automatic detection and differentiation of spontaneous seizures that may otherwise be missed or misclassified. Herein, we propose a system architecture based on top-performing DL models for binary and multigroup classifications with the non-overlapping window technique, which we tested on the TUSZ dataset. The system accurately detects seizure episodes (87.7% Sn, 91.16% Sp) and carefully distinguishes eight seizure types (95-100% Acc). An increase in EEG sampling rate from 50 to 250 Hz boosted model performance: the precision of seizure detection rose by 5%, and seizure differentiation by 7%. A low sampling rate is a reasonable solution for training reliable models with EEG data. Decreasing the number of EEG electrodes from 21 to 8 did not affect seizure detection but worsened seizure differentiation significantly: 98.24 ± 0.17 vs. 85.14 ± 3.14% recall. In detecting epileptic episodes, all electrodes provided equally informative input, but in seizure differentiation, their informative value varied. We improved model explainability with interpretable ML. Activation maximization highlighted the presence of EEG patterns specific to eight seizure types. Cortical projection of epileptic sources depicted differences between generalized and focal seizures. Interpretable ML techniques confirmed that our system recognizes biologically meaningful features as indicators of epileptic activity in EEG.

Skin Lesion Segmentation Using an Ensemble of Different Image Processing Methods.

In recent times, there has been a huge increase in the average number of cases of skin cancer per year, which sometimes become life threatening for humans. Early detection of various skin diseases through automated detection techniques plays a crucial role. However, the presence of numerous artefacts makes this task challenging. Dermoscopic images exhibit various variations, including hair artefacts, markers, and ill-defined boundaries. These artefacts make automatic analysis of skin lesion quite a difficult task. To address these issues, it is essential to have an accurate and efficient automated method which will delineate a skin lesion from the rest of the image. Unfortunately, due to the presence of several types of skin artefacts, there is no such thresholding method that can provide a sufficient segmentation result for every type of skin lesion. To overcome this limitation, an ensemble-based method is proposed that selects the optimal thresholding based on an objective function. A group of state-of-the-art different thresholding methods such as Otsu, Kapur, Harris hawk, and grey level are used. The proposed method obtained superior results (dice score = 0.89 with p-value ≤ 0.05) as compared to other state-of-the-art methods (Otsu = 0.79, Kapur = 0.80, Harris hawk = 0.60, grey level = 0.69, active contour model = 0.72). The experiments conducted in this study utilize the ISIC 2016 dataset, which is publicly available and specifically designed for skin-related research. Accurate segmentation will help in the early detection of many skin diseases.

An innovative deep neural network coordinating with percussion-based technique for automatic detection of concrete cavity defects

Cavity defects are usually invisible in concrete, failure to detect and repair them in time could significantly weaken the load-bearing capacity of engineering structures, potentially threatening the structural safety during the construction and operation periods. Therefore, it is essential to explore efficient approaches to detect concrete cavity defects. In this study, we propose a novel method to detect concrete cavity defects based on percussion and deep learning (DL) techniques. First, the percussion sound dataset was collected from concrete specimens with different types of precast cavity defects. Next, an innovative DL framework named the multi-scale convolutional bidirectional memory network (MCBMNet) was developed for classifying these percussion sound signals associated with specified concrete cavity defects. The MCBMNet utilizes the multi-scale convolutional operation to generate various scale features directly from raw percussion sounds, and then employs the bidirectional memory units to capture intrinsic feature connections and enhance feature separability, thus improving prediction accuracy and robustness. Finally, two experimental cases, including water-free and water-filled conditions, were designed to test the feasibility of the proposed method considering the influences of humidity environment in reality. Experimental results well demonstrate the excellent performances of the proposed MCBMNet for concrete cavity defect detection, with its average accuracy over 98% in both cases. Additionally, the anti-noise capacity and adaptability of MCBMNet were thoroughly investigated, which outperforms conventional learning algorithms.

Optimization with Deep Learning Classifier-Based Foliar Disease Classification in Apple Trees Using IoT Network

The development of any country is influenced by the growth in the agriculture sector. The prevalence of pests and diseases in plants affects the productivity of any agricultural product. Early diagnosis of the disease can substantially decrease the effort and the fund required for disease management. The Internet of Things (IoT) provides a framework for offering solutions for automatic farming. This paper devises an automated detection technique for foliar disease classification in apple trees using an IoT network. Here, classification is performed using a hybrid classifier, which utilizes the Deep Residual Network (DRN) and Deep [Formula: see text] Network (DQN). A new Adaptive Tunicate Swarm Sine–Cosine Algorithm (TSSCA) is used for modifying the learning parameters as well as the weights of the proposed hybrid classifier. The TSSCA is developed by adaptively changing the navigation foraging behavior of the tunicates obtained from the Tunicate Swarm Algorithm (TSA) in accordance with the Sine–Cosine Algorithm (SCA). The outputs obtained from the Adaptive TSSCA-based DRN and Adaptive TSSCA-based DQN are merged using cosine similarity measure for detecting the foliar disease. The Plant Pathology 2020 — FGVC7 dataset is utilized for the experimental process to determine accuracy, sensitivity, specificity and energy and we achieved the values of 98.36%, 98.58%, 96.32% and 0.413 J, respectively.

A Deep Learning-Based Automatic Segmentation and 3D Visualization Technique for Intracranial Hemorrhage Detection Using Computed Tomography Images.

Intracranial hemorrhage (ICH) occurs when blood leaks inside the skull as a result of trauma to the skull or due to medical conditions. ICH usually requires immediate medical and surgical attention because the disease has a high mortality rate, long-term disability potential, and other potentially life-threatening complications. There are a wide range of severity levels, sizes, and morphologies of ICHs, making accurate identification challenging. Hemorrhages that are small are more likely to be missed, particularly in healthcare systems that experience high turnover when it comes to computed tomography (CT) investigations. Although many neuroimaging modalities have been developed, CT remains the standard for diagnosing trauma and hemorrhage (including non-traumatic ones). A CT scan-based diagnosis can provide time-critical, urgent ICH surgery that could save lives because CT scan-based diagnoses can be obtained rapidly. The purpose of this study is to develop a machine-learning algorithm that can detect intracranial hemorrhage based on plain CT images taken from 75 patients. CT images were preprocessed using brain windowing, skull-stripping, and image inversion techniques. Hemorrhage segmentation was performed using multiple pre-trained models on preprocessed CT images. A U-Net model with DenseNet201 pre-trained encoder outperformed other U-Net, U-Net++, and FPN (Feature Pyramid Network) models with the highest Dice similarity coefficient (DSC) and intersection over union (IoU) scores, which were previously used in many other medical applications. We presented a three-dimensional brain model highlighting hemorrhages from ground truth and predicted masks. The volume of hemorrhage was measured volumetrically to determine the size of the hematoma. This study is essential in examining ICH for diagnostic purposes in clinical practice by comparing the predicted 3D model with the ground truth.

Artificial Intelligence Techniques for Automatic Detection of Peri-implant Marginal Bone Remodeling in Intraoral Radiographs

Peri-implantitis can cause marginal bone remodeling around implants. The aim is to develop an automatic image processing approach based on two artificial intelligence (AI) techniques in intraoral (periapical and bitewing) radiographs to assist dentists in determining bone loss. The first is a deep learning (DL) object-detector (YOLOv3) to roughly identify (no exact localization is required) two objects: prosthesis (crown) and implant (screw). The second is an image understanding-based (IU) process to fine-tune lines on screw edges and to identify significant points (intensity bone changes, intersections between screw and crown). Distances between these points are used to compute bone loss. A total of 2920 radiographs were used for training (50%) and testing (50%) the DL process. The mAP@0.5 metric is used for performance evaluation of DL considering periapical/bitewing and screws/crowns in upper and lower jaws, with scores ranging from 0.537 to 0.898 (sufficient because DL only needs an approximation). The IU performance is assessed with 50% of the testing radiographs through the t test statistical method, obtaining p values of 0.0106 (line fitting) and 0.0213 (significant point detection). The IU performance is satisfactory, as these values are in accordance with the statistical average/standard deviation in pixels for line fitting (2.75/1.01) and for significant point detection (2.63/1.28) according to the expert criteria of dentists, who establish the ground-truth lines and significant points. In conclusion, AI methods have good prospects for automatic bone loss detection in intraoral radiographs to assist dental specialists in diagnosing peri-implantitis.

ADTBO: Aquila driving training-based optimization with deep learning for skin cancer detection

ABSTRACT Generally, melanoma skin disease is also a type of cancer, which is complex to determine. In case, various skin cancer diseases are identified at an early stage, then the death rate is to be reduced. Medical imaging technology acts as an important role in perceiving these types of skin lesions perfectly. This research introduced the automatic skin cancer detection technique, namely Aquila Driving Training-Based optimization (ADTBO) with Squeeze Net. The ADTBO is derived by the combination of Aquila Optimizer (AO) and Driving Training-Based optimization (DTBO). The skin cancer segmentation is completed by the Minkowski-based dual network, where the dual network encompasses the PsiNet and Deep Joint segmentation. The data augmentation and feature extraction are completed to enhance the effectiveness of detection. The ADTBO-SqueezeNet achieved the higher performance based on the accuracy of 0.976, specificity of 0.984 and sensitivity of 0.987. The segmentation accuracy achieved by the Minkowski-based Dual Network is 0.948.

An Automatic Wound Detection System Empowered by Deep Learning

The wound can be defined as a breakdown in the protective function of the skin. Perceiving the types of wounds at the initial stages can be more viable in the treatment process. The paramedical staff usually examines the wound with its size and healing status is determined through visual assessment. Telemedicine and rest of the healthcare services delivered through digital means aim to ensure the availability of health facilities at doorstep. Especially, in COVID-19 period these services played significant role where physical examination of patient in hospital may enhance the spread of the disease. The remote assessment of wound demands high quality of medical images or videos and localization of wound area. The manual diagnosis is not very robust and reliable because of variability in the appearance of wound site. Whereas an automatic wound detection, localization and classification may assist a physician with more accuracy and robustness. In this work, an automatic wound detection technique using YOLO v3 model is proposed. The proposed technique detects, localizes and classifies the wound into four main categories containing stitch-wound, cut-wound, open-wound and normal-skin. The experimental results show that the proposed technique is more efficient and robust with 99% accuracy and outperforms other counter parts.

Automated detection of auditory response: non-detection stopping criterion and repeatability studies for multichannel EEG

An Auditory Steady-State Response (ASSR) is a valuable tool for determining auditory thresholds in individuals who are either unable or unwilling to cooperate with conventional behavioral testing methods. This study proposes a sequential test technique for automatic detection of ASSRs, incorporating a non-detection stopping criterion. The electrophysiological thresholds of a normal hearing volunteer were established using data collected from multichannel EEG signals. The detection probabilities and critical values were obtained via Monte Carlo simulations. Remarkably, application of the non-detection stopping criterion resulted in a 60% reduction in exam time in the absence of a response. These findings clearly demonstrate the significant potential of the sequential test in enhancing the performance of automatic audiometry.

Image-Based Crack Detection Using Total Variation Strain DVC Regularization

Introduction: Accurately detecting cracks is crucial for assessing the health of materials. Manual detection methods are time-consuming, leading to the development of automatic detection techniques based on image processing and machine learning. These methods utilize morphological image processing and material deformation analysis through Digital Image or Volume Correlation techniques (DIC/DVC) to identify cracks. The strain field derived from DIC/DVC tends to be noisy. Traditional denoising methods sacrifice spatial resolution, limiting their effectiveness in capturing abrupt structural deformations such as fractures. Method: In this study, a novel DVC regularization method is proposed to obtain a sharper and less noisy strain field. The method minimizes the total variation of spatial strain field components based on the assumption of approximate strain constancy within material phases. Results: The proposed methodology is validated using simulated data and actual 4D μ-CT experimental data. Compared to classical denoising methods, the proposed DVC regularization method provides a more reliable crack detection with fewer false positives. Conclusions: These results highlight the possibility of estimating a low-noise strain field without relying on the spatial smoothness assumption, thereby improving accuracy and reliability in crack detection.

K-mean clustering and local binary pattern techniques for automatic brain tumor detection

Tumors in brains are caused by the unregulated emergence of tissue cells inside the brain. The early diagnosis and determining the precise location of the tumor in magnetic resonance imaging (MRI) and its size are essential for the teams of physicians. Image segmentation is often considered a preliminary step in medical image analyses. K-means clustering has been widely adopted for brain tumor detection. The result of this technique is a list of cluster images. The challenge of this method is the difficulty of selecting the appropriate cluster section that depicts the tumor. In this work, we analyze the influence of different image clusters. Each cluster is then split into the left and right parts. After that, the texture features are depicted in each part. Furthermore, the bilateral symmetry measure is applied to estimate the cluster that contains the tumor. Finally, the connected component labeling is employed to determine the target cluster for brain tumor detection. The developed technique is applied to 30 MRI images. The encouraging accuracy of 87% is obtained.

An Experimental Analysis on Multicepstral Projection Representation Strategies for Dysphonia Detection.

Biometrics-based authentication has become the most well-established form of user recognition in systems that demand a certain level of security. For example, the most commonplace social activities stand out, such as access to the work environment or to one's own bank account. Among all biometrics, voice receives special attention due to factors such as ease of collection, the low cost of reading devices, and the high quantity of literature and software packages available for use. However, these biometrics may have the ability to represent the individual impaired by the phenomenon known as dysphonia, which consists of a change in the sound signal due to some disease that acts on the vocal apparatus. As a consequence, for example, a user with the flu may not be properly authenticated by the recognition system. Therefore, it is important that automatic voice dysphonia detection techniques be developed. In this work, we propose a new framework based on the representation of the voice signal by the multiple projection of cepstral coefficients to promote the detection of dysphonic alterations in the voice through machine learning techniques. Most of the best-known cepstral coefficient extraction techniques in the literature are mapped and analyzed separately and together with measures related to the fundamental frequency of the voice signal, and its representation capacity is evaluated on three classifiers. Finally, the experiments on a subset of the Saarbruecken Voice Database prove the effectiveness of the proposed material in detecting the presence of dysphonia in the voice.

Unsupervised deep learning techniques for automatic detection of plant diseases: reducing the need of manual labelling of plant images

Crop protection from diseases through applications of plant protection products is crucial to secure worldwide food production. Nevertheless, sustainable management of plant diseases is an open challenge with a major role in the economic and environmental impact of agricultural activities. A primary contribution is expected to come from precision crop protection approaches, with treatments tailored to spatial and time-specific needs of the crop, in contrast to the current practice of applying treatments uniformly to fields. In view of this, image-based automatic detection of early disease symptoms is considered a key enabling technology for high throughput scouting of the crop, in order to timely target the treatments on emerging infection spots. Thanks to the unprecedented performance in image-recognition problems, Deep Learning (DL) methods based on Convolutional Neural Networks (CNNs) have recently entered the domain of plant disease detection. This work develops two DL approaches for automatic recognition of powdery mildew disease on cucumber leaves, with a specific focus on exploring unsupervised techniques to overcome the need of large training set of manually labelled images. To this aim, autoencoder networks were implemented for unsupervised detection of disease symptoms through: i) clusterization of features in a compressed space; ii) anomaly detection. The two proposed approaches were applied to multispectral images acquired during in-vivo experiments, and the obtained results were assessed by quantitative indices. The clusterization approach showed only partially capability to provide accurate disease detection, even if it gathered some relevant information. Anomaly detection showed instead to possess a significant potential of discrimination which could be further exploited as a prior step to train more powerful supervised architectures with a very limited number of labelled samples.

Discrimination strategy using machine learning technique for oestrus detection in dairy cows by a dual-channel-based acoustic tag

Timely identification of cows in heat is a fundamental issue in dairy farming. Although current studies have confirmed that several cow vocalisation characteristics can be used for oestrus identification, the reliability and practicability of oestrus detection methods are limited due to background noise, a lack of data support for sound feature selection, and the unsatisfactory effectiveness of vocalisation recognition algorithms.To overcome these predicaments, a dual-channel recording device and a sound event extraction method were developed in this study. The experimental results in respect of 62 Holstein dairy cows showed that the sound sample recording accuracy was 80.4%, and the noise filtering accuracy was 94.3%, indicating the effectiveness of the vocalisation extraction algorithm in a noisy farm environment. Moreover, two unique sound features with remarkable discrimination ability, i.e., the number of consecutive vocalisations and the maximum consecutive times, were used to improve the effectiveness of oestrus detection. The Friedman test, the Spearman rank order correlation coefficient, and the Kruskal-Wallis test were used to obtain the combination of features with the most optimal discrimination. Subsequently, a dual-LSTM (Long Short-Term Memory) joint discriminant strategy based on optimal combinations was proposed to promote oestrus detection performance. The results of the blind test on the vocalisation data of 20 oestrus cows and 11 non-oestrus cows demonstrated that the oestrus detection rate of the discrimination strategy reached 100%, and had a temporal advantage over the activity-index-based method in determining the onset of oestrus.The improvements of the selection and-based oestrus detection method mainly included accurately extracting individual cow vocalisations, supplementing the explicability of feature selection, and enhancing the refinement of oestrus recognition. Meanwhile, it is of positive significance for applying sound acquisition devices in oestrus detection. Furthermore, combining sound identification with other automated detection techniques appears to be a promising method for promoting the oestrus detection rate.

Real-Time Vehicle Accident Recognition from Traffic Video Surveillance using YOLOV8 and OpenCV

The automatic detection of traffic accidents is a significant topic in traffic monitoring systems. It can reduce irresponsible driving behavior, improve emergency response, improve traffic management, and encourage safer driving practices. Computer vision can be a promising technique for automatic accident detection because it provides a reliable, automated, and speedy accident detection system that can improve emergency response times and ultimately save lives. This paper proposed an ensemble model that uses the YOLOv8 approach for efficient and precise event detection. The model framework's robustness is evaluated using YouTube video sequences with various lighting circumstances. The proposed model has been trained using the open-source dataset Crash Car Detection Dataset, and its produced precision, recall, and mAP are 93.8% and 98%, 96.1%, respectively, which is a significant improvement above the prior precision, recall, and mAP figures of 91.3%, 87.6%, and 93.8%. The effectiveness of the proposed approach in real-time traffic surveillance applications is proved by experimental results using actual traffic video data.