Denoising is a vital aspect of image preprocessing, often explored to eliminate noise in an image to restore its proper characteristic formation and clarity. Unfortunately, noise often degrades the quality of valuable images, making them meaningless for practical applications. Several methods have been deployed to address this problem, but the quality of the recovered images still requires enhancement for efficient applications in practice. In this paper, a wavelet-based universal thresholding technique that possesses the capacity to optimally denoise highly degraded noisy images with both uniform and non-uniform variations in illumination and contrast is proposed. The proposed method, herein referred to as the modified wavelet-based universal thresholding (MWUT), compared to three state-of-the-art denoising techniques, was employed to denoise five noisy images. In order to appraise the qualities of the images obtained, seven performance indicators comprising the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Structural Content (SC), Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Method (SSIM), Signal-to-Reconstruction-Error Ratio (SRER), Blind Spatial Quality Evaluator (NIQE), and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) were employed. The first five indicators – RMSE, MAE, SC, PSNR, SSIM, and SRER- are reference indicators, while the remaining two – NIQE and BRISQUE- are referenceless. For the superior performance of the proposed wavelet threshold algorithm, the SC, PSNR, SSIM, and SRER must be higher, while lower values of NIQE, BRISQUE, RMSE, and MAE are preferred. A higher and better value of PSNR, SSIM, and SRER in the final results shows the superior performance of our proposed MWUT denoising technique over the preliminaries. Lower NIQE, BRISQUE, RMSE, and MAE values also indicate higher and better image quality results using the proposed modified wavelet-based universal thresholding technique over the existing schemes. The modified wavelet-based universal thresholding technique would find practical applications in digital image processing and enhancement.

Mushrooms are the most familiar delicious food which is cholesterol free as well as rich in vitamins and minerals. Though nearly 45,000 species of mushrooms have been known throughout the world, most of them are poisonous and few are lethally poisonous. Identifying edible or poisonous mushroom through the naked eye is quite difficult. Even there is no easy rule for edibility identification using machine learning methods that work for all types of data. Our aim is to find a robust method for identifying mushrooms edibility with better performance than existing works. In this paper, three ensemble methods are used to detect the edibility of mushrooms: Bagging, Boosting, and random forest. By using the most significant features, five feature sets are made for making five base models of each ensemble method. The accuracy is measured for ensemble methods using five both fixed feature set-based models and randomly selected feature set based models, for two types of test sets. The result shows that better performance is obtained for methods made of fixed feature sets-based models than randomly selected feature set-based models. The highest accuracy is obtained for the proposed model-based random forest for both test sets.

The presence of illegal activities such as illegitimate mining and sand theft in river dredging areas leads to economic losses. However, manual monitoring is expensive and time-consuming. Therefore, automated surveillance systems are preferred to mitigate such activities, as they are accurate and available at all times. In order to monitor river dredging areas, two essential steps for surveillance are vehicle detection and license plate recognition. Most current frameworks for vehicle detection employ plain feed-forward Convolutional Neural Networks (CNNs) as backbone architectures. However, these are scale-sensitive and cannot handle variations in vehicles' scales in consecutive video frames. To address these issues, Scale Invariant Hybrid Convolutional Neural Network (SIH-CNN) architecture is proposed for real-time vehicle detection in this study. The publicly available benchmark UA-DETRAC is used to validate the performance of the proposed architecture. Results show that the proposed SIH-CNN model achieved a mean average precision (mAP) of 77.76% on the UA-DETRAC benchmark, which is 3.94% higher than the baseline detector with real-time performance of 48.4 frames per seconds.

In the field of medical image analysis, supervised deep learning strategies have achieved significant development, while these methods rely on large labeled datasets. Self-Supervised learning (SSL) provides a new strategy to pre-train a neural network with unlabeled data. This is a new unsupervised learning paradigm that has achieved significant breakthroughs in recent years. So, more and more researchers are trying to utilize SSL methods for medical image analysis, to meet the challenge of assembling large medical datasets. To our knowledge, so far there still a shortage of reviews of self-supervised learning methods in the field of medical image analysis, our work of this article aims to fill this gap and comprehensively review the application of self-supervised learning in the medical field. This article provides the latest and most detailed overview of self-supervised learning in the medical field and promotes the development of unsupervised learning in the field of medical imaging. These methods are divided into three categories: context-based, generation-based, and contrast-based, and then show the pros and cons of each category and evaluates their performance in downstream tasks. Finally, we conclude with the limitations of the current methods and discussed the future direction.

Automatic lane detection to help the driver is an issue considered for the advancement of Advanced Driver Assistance Systems (ADAS) and a high level of application frameworks because of its importance in drivers and passerby safety in vehicular streets. But still, now it is a most challenging problem because of some factors that are faced by lane detection systems like as vagueness of lane patterns, perspective consequence, low visibility of the lane lines, shadows, incomplete occlusions, brightness and light reflection. The proposed system detects the lane boundary lines using computer vision-based technologies. In this paper, we introduced a system that can efficiently identify the lane lines on the smooth road surface. Gradient and HLS thresholding are the central part to detect the lane lines. We have applied the Gradient and HLS thresholding to identify the lane line in binary images. The color lane is estimated by a sliding window search technique that visualizes the lanes. The performance of the proposed system is evaluated on the KITTI road dataset. The experimental results show that our proposed method detects the lane on the road surface accurately in several brightness conditions.

Ultrasound based breast screening is gaining attention recently especially for dense breast. The technological advancement, cancer awareness, and cost-safety-availability benefits lead rapid rise of breast ultrasound market. The irregular shape, intensity variation, and additional blood vessels of malignant cancer are distinguishable in ultrasound images from the benign phase. However, classification of breast cancer using ultrasound images is a difficult process owing to speckle noise and complex textures of breast. In this paper, a breast cancer classification method is presented using VGG16 model based transfer learning approach. We have used median filter to despeckle the images. The layers for convolution process of the pretrained VGG16 model along with the maxpooling layers have been used as feature extractor and a proposed fully connected two layers deep neural network has been designed as classifier. Adam optimizer is used with learning rate of 0.001 and binary cross-entropy is chosen as the loss function for model optimization. Dropout of hidden layers is used to avoid overfitting. Breast Ultrasound images from two databases (total 897 images) have been combined to train, validate and test the performance and generalization strength of the classifier. Experimental results showed the training accuracy as 98.2% and testing accuracy as 91% for blind testing data with a reduced of computational complexity. Gradient class activation mapping (Grad-CAM) technique has been used to visualize and check the targeted regions localization effort at the final convolutional layer and found as noteworthy. The outcomes of this work might be useful for the clinical applications of breast cancer diagnosis.

The article deals with creating an algorithm for processing information in a digital system for quadrotor flight control. The minimization of L2-gain using simple parametric optimization for the synthesis of the control algorithm based on static output feedback is proposed. The kinematical diagram and mathematical description of the linearized quadrotor model are represented. The transformation of the continuous model into a discrete one has been implemented. The new optimization procedure based on digital static output feedback is developed. Expressions for the optimization criterion and penalty function are given. The features of the creating algorithm and processing information are described. The development of the closed-loop control system with an extended model augmented with some essential nonlinearities inherent to the real control plant is implemented. The simulation of the quadrotor guidance in the turbulent atmosphere has been carried out. The simulation results based on the characteristics of the studied quadrotor are represented. These results prove the efficiency of the proposed algorithm for navigation information processing. The obtained results can be useful for signal processing and designing control systems for unmanned aerial vehicles of the wide class.

This paper presents a design and development of an Artificial Intelligence (AI) based mobile application to detect the type of skin disease. Skin diseases are a serious hazard to everyone throughout the world. However, it is difficult to make accurate skin diseases diagnosis. In this work, Deep learning algorithms Convolution Neural Networks (CNN) is proposed to classify skin diseases on the HAM10000 dataset. An extensive review of research articles on object identification methods and a comparison of their relative qualities were given to find a method that would work well for detecting skin diseases. The CNN-based technique was recognized as the best method for identifying skin diseases. A mobile application, on the other hand, is built for quick and accurate action. By looking at an image of the afflicted area at the beginning of a skin illness, it assists patients and dermatologists in determining the kind of disease present. Its resilience in detecting the impacted region considerably faster with nearly 2x fewer computations than the standard MobileNet model results in low computing efforts. This study revealed that MobileNet with transfer learning yielding an accuracy of about 85% is the most suitable model for automatic skin disease identification. According to these findings, the suggested approach can assist general practitioners in quickly and accurately diagnosing skin diseases using the smart phone.

During past few years, brain tumor segmentation in magnetic resonance imaging (MRI) has become an emergent research area in the field of medical imaging system. Brain tumor detection helps in finding the exact size and location of tumor. An efficient algorithm is proposed in this paper for tumor detection based on segmentation and morphological operators. Firstly quality of scanned image is enhanced and then morphological operators are applied to detect the tumor in the scanned image.

A huge number of algorithms are found in recent literature to de-noise a signal or enhancement of signal. In this paper we use: static filters, digital adaptive filters, discrete wavelet transform (DWT), backpropagation, Hopfield neural network (NN) and convolutional neural network (CNN) to de-noise both speech and biomedical signals. The relative performance of ten de-noising methods of the paper is measured using signal to noise ratio (SNR) in dB shown in tabular form. The objective of this paper is to select the best algorithm in de-noising of speech and biomedical signals separately. In this paper we experimentally found that, the backpropagation NN is the best for de-noising of biomedical signal and CNN is found as the best for de-noising of speech signal, where the processing time of CNN is found three times higher than that of backpropagation.

Denoising is a vital aspect of image preprocessing, often explored to eliminate noise in an image to restore its proper characteristic formation and clarity. Unfortunately, noise often degrades the quality of valuable images, making them meaningless for practical applications. Several methods have been deployed to address this problem, but the quality of the recovered images still requires enhancement for efficient applications in practice. In this paper, a wavelet-based universal thresholding technique that possesses the capacity to optimally denoise highly degraded noisy images with both uniform and non-uniform variations in illumination and contrast is proposed. The proposed method, herein referred to as the modified wavelet-based universal thresholding (MWUT), compared to three state-of-the-art denoising techniques, was employed to denoise five noisy images. In order to appraise the qualities of the images obtained, seven performance indicators comprising the Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Structural Content (SC), Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Method (SSIM), Signal-to-Reconstruction-Error Ratio (SRER), Blind Spatial Quality Evaluator (NIQE), and Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) were employed. The first five indicators – RMSE, MAE, SC, PSNR, SSIM, and SRER- are reference indicators, while the remaining two – NIQE and BRISQUE- are referenceless. For the superior performance of the proposed wavelet threshold algorithm, the SC, PSNR, SSIM, and SRER must be higher, while lower values of NIQE, BRISQUE, RMSE, and MAE are preferred. A higher and better value of PSNR, SSIM, and SRER in the final results shows the superior performance of our proposed MWUT denoising technique over the preliminaries. Lower NIQE, BRISQUE, RMSE, and MAE values also indicate higher and better image quality results using the proposed modified wavelet-based universal thresholding technique over the existing schemes. The modified wavelet-based universal thresholding technique would find practical applications in digital image processing and enhancement.

Mushrooms are the most familiar delicious food which is cholesterol free as well as rich in vitamins and minerals. Though nearly 45,000 species of mushrooms have been known throughout the world, most of them are poisonous and few are lethally poisonous. Identifying edible or poisonous mushroom through the naked eye is quite difficult. Even there is no easy rule for edibility identification using machine learning methods that work for all types of data. Our aim is to find a robust method for identifying mushrooms edibility with better performance than existing works. In this paper, three ensemble methods are used to detect the edibility of mushrooms: Bagging, Boosting, and random forest. By using the most significant features, five feature sets are made for making five base models of each ensemble method. The accuracy is measured for ensemble methods using five both fixed feature set-based models and randomly selected feature set based models, for two types of test sets. The result shows that better performance is obtained for methods made of fixed feature sets-based models than randomly selected feature set-based models. The highest accuracy is obtained for the proposed model-based random forest for both test sets.

In the field of medical image analysis, supervised deep learning strategies have achieved significant development, while these methods rely on large labeled datasets. Self-Supervised learning (SSL) provides a new strategy to pre-train a neural network with unlabeled data. This is a new unsupervised learning paradigm that has achieved significant breakthroughs in recent years. So, more and more researchers are trying to utilize SSL methods for medical image analysis, to meet the challenge of assembling large medical datasets. To our knowledge, so far there still a shortage of reviews of self-supervised learning methods in the field of medical image analysis, our work of this article aims to fill this gap and comprehensively review the application of self-supervised learning in the medical field. This article provides the latest and most detailed overview of self-supervised learning in the medical field and promotes the development of unsupervised learning in the field of medical imaging. These methods are divided into three categories: context-based, generation-based, and contrast-based, and then show the pros and cons of each category and evaluates their performance in downstream tasks. Finally, we conclude with the limitations of the current methods and discussed the future direction.

Ultrasound based breast screening is gaining attention recently especially for dense breast. The technological advancement, cancer awareness, and cost-safety-availability benefits lead rapid rise of breast ultrasound market. The irregular shape, intensity variation, and additional blood vessels of malignant cancer are distinguishable in ultrasound images from the benign phase. However, classification of breast cancer using ultrasound images is a difficult process owing to speckle noise and complex textures of breast. In this paper, a breast cancer classification method is presented using VGG16 model based transfer learning approach. We have used median filter to despeckle the images. The layers for convolution process of the pretrained VGG16 model along with the maxpooling layers have been used as feature extractor and a proposed fully connected two layers deep neural network has been designed as classifier. Adam optimizer is used with learning rate of 0.001 and binary cross-entropy is chosen as the loss function for model optimization. Dropout of hidden layers is used to avoid overfitting. Breast Ultrasound images from two databases (total 897 images) have been combined to train, validate and test the performance and generalization strength of the classifier. Experimental results showed the training accuracy as 98.2% and testing accuracy as 91% for blind testing data with a reduced of computational complexity. Gradient class activation mapping (Grad-CAM) technique has been used to visualize and check the targeted regions localization effort at the final convolutional layer and found as noteworthy. The outcomes of this work might be useful for the clinical applications of breast cancer diagnosis.

Nowadays, the primary concern of any society is providing safety to an individual. It is very hard to recognize the human behaviour and identify whether it is suspicious or normal. Deep learning approaches paved the way for the development of various machine learning and artificial intelligence. The proposed system detects real-time human activity using a convolutional neural network. The objective of the study is to develop a real-time application for Activity recognition using with and without transfer learning methods. The proposed system considers criminal, suspicious and normal categories of activities. Differentiate suspicious behaviour videos are collected from different peoples(men/women). This proposed system is used to detect suspicious activities of a person. The novel 2D-CNN, pre-trained VGG-16 and ResNet50 is trained on video frames of human activities such as normal and suspicious behaviour. Similarly, the transfer learning in VGG16 and ResNet50 is trained using human suspicious activity datasets. The results show that the novel 2D-CNN, VGG16, and ResNet50 without transfer learning achieve accuracy of 98.96%, 97.84%, and 99.03%, respectively. In Kaggle/real-time video, the proposed system employing 2D-CNN outperforms the pre-trained model VGG16. The trained model is used to classify the activity in the real-time captured video. The performance obtained on ResNet50 with transfer learning accuracy of 99.18% is higher than VGG16 transfer learning accuracy of 98.36%. 

A huge number of algorithms are found in recent literature to de-noise a signal or enhancement of signal. In this paper we use: static filters, digital adaptive filters, discrete wavelet transform (DWT), backpropagation, Hopfield neural network (NN) and convolutional neural network (CNN) to de-noise both speech and biomedical signals. The relative performance of ten de-noising methods of the paper is measured using signal to noise ratio (SNR) in dB shown in tabular form. The objective of this paper is to select the best algorithm in de-noising of speech and biomedical signals separately. In this paper we experimentally found that, the backpropagation NN is the best for de-noising of biomedical signal and CNN is found as the best for de-noising of speech signal, where the processing time of CNN is found three times higher than that of backpropagation.

Smartphones are one of the communication technology tools currently used by both children and the elderly, so that interest in shopping for smartphones in Indonesia is increasing. The variety of smartphone brands makes buyers confused about which smartphone to buy. This research can help buyers to choose a smartphone to buy and help sellers provide recommendations. This study applies the Simple Multi Attribute Rating Technique (SMART) and Fuzzy Multi Criteria Decision Making (FMCDM) methods for the decision making process for smartphone selection. The purpose of this study is to apply and analyze the comparison of the SMART method and the FMCDM method in the Smartphone Selection Decision Support System. The study compared: the differences and similarities between the two methods, the results of the selection process for the two methods, and calculating the value of the sensitivity analysis of the selection results so that the best method could be determined. The criteria used: price, screen size, battery capacity, operating system, RAM, camera, and smartphone brand. The comparison results show that there are differences between the standard for determining the results, while the similarities in the calculation results, the smartphone recommended to buy is the same, namely the Asus Zenfone 2 Laser ZE500KG (16 GB) smartphone. Measurement of the accuracy of the results of the two methods uses sensitivity analysis values. It can be concluded that the better method is the FMCDM method because it has a smaller average sensitivity value than the SMART method, namely 0.2795 <0.3906.

Diabetic retinopathy is one of the most serious eye diseases and can lead to permanent blindness if not diagnosed early. The main cause of this is diabetes. Not every diabetic will develop diabetic retinopathy, but the risk of developing diabetes is undeniable. This requires the early diagnosis of Diabetic retinopathy. Segmentation is one of the approaches which is useful for detecting the blood vessels in the retinal image. This paper proposed the three models based on a deep learning approach for recognizing blood vessels from retinal images using region-based segmentation techniques. The proposed model consists of four steps preprocessing, Augmentation, Model training, and Performance measure. The augmented retinal images are fed to the three models for training and finally, get the segmented image. The proposed three models are applied on publically available data set of DRIVE, STARE, and HRF. It is observed that more thin blood vessels are segmented on the retinal image in the HRF dataset using model-3. The performance of proposed three models is compare with other state-of-art-methods of blood vessels segmentation of DRIVE, STARE, and HRF datasets.

Deep learning (DL) architectures are becoming increasingly popular in modern traffic systems and self-driven vehicles owing to their high efficiency and accuracy. Emerging technological advancements and the availability of large databases have made a favorable impact on such improvements. In this study, we present a traffic sign recognition system based on novel DL architectures, trained and tested on a locally collected traffic sign database. Our approach includes two stages; traffic sign identification from live video feed, and classification of each sign. The sign identification model was implemented with YOLO architecture and the classification model was implemented with Xception architecture. The input video feed for these models were collected using dashboard camera recordings. The classification model has been trained with the German Traffic Sign Recognition Benchmark dataset as well for comparison. Final accuracy of classification for the local dataset was 96.05% while the standard dataset has given an accuracy of 92.11%. The final model is a combination of the detection and classification algorithms and it is able to successfully detect and classify traffic signs from an input video feed within an average detection time of 4.5fps

The article deals with creating an algorithm for processing information in a digital system for quadrotor flight control. The minimization of L2-gain using simple parametric optimization for the synthesis of the control algorithm based on static output feedback is proposed. The kinematical diagram and mathematical description of the linearized quadrotor model are represented. The transformation of the continuous model into a discrete one has been implemented. The new optimization procedure based on digital static output feedback is developed. Expressions for the optimization criterion and penalty function are given. The features of the creating algorithm and processing information are described. The development of the closed-loop control system with an extended model augmented with some essential nonlinearities inherent to the real control plant is implemented. The simulation of the quadrotor guidance in the turbulent atmosphere has been carried out. The simulation results based on the characteristics of the studied quadrotor are represented. These results prove the efficiency of the proposed algorithm for navigation information processing. The obtained results can be useful for signal processing and designing control systems for unmanned aerial vehicles of the wide class.