Search

• Compared the performance of three algorithms in classifying the age of documents. • FTIR combine with chemometrics can classify the documents of different years. • CNN are proved to be an effective technique. A non-destructive method based on Fourier Transformed Infrared Spectroscopy (FT-IR) was proposed to estimate the date of paper from different years in this article. For the paper samples, dated from 1940 to 1980, naturally aged and conserved in library. Partial least squares-discriminate analysis (PLS-DA), Logistic regression and convolutional neural network (CNN), were employed to evaluate the date of paper, with the accuracy 60.74%, 95.31% and 98.77%, respectively. Based on the characteristics of CNN model and with the help of network localization, active variables could be recognized in the whole spectrum. Although the localization of active variables showed a discriminative pattern, the selected spectral regions were similar. Most important variables focused on the 1700–1400 cm−1, were corresponding to cellulose crystallinity, which was consisted with the ageing processing. The present work gave the potential of FT-IR combined with chemometric techniques could estimate the dating of unknown paper. Meanwhile, the analysis of active variables obtained further indicated the worthy of CNN model for document dating. [ABSTRACT FROM AUTHOR]

An Election is a method of selection of individuals to hold the public office in democracy. Ballot is basically a piece of paper that is used to cast vote during election. In ballot paper voting system each voter uses a ballot paper which is not shared and basically it is a paper printed with the name and symbols of the candidates. The Electronic Voting Machine is basically a memory recorder which records the vote casted by the voters. In this paper, main advantages of E-voting systems for country is highlighted. For constructing E-voting systems, every countries need to do great attention to Verification and Validation requirements. In this research, E-voting scheme with face recognition using deep learning technique is proposed. The process of casting vote is accomplished by blockchain technology and blind signature mechanism. The main objective of the proposed scheme is to explore the positive effects of security and safety in online voting system. • The Election is a method of selection of individuals to hold the public office in democracy. • The Electronic Voting Machine is basically a memory recorder which records the vote casted by the voters. • The aim of the research is to E-voting scheme with face recognition using deep learning technique is proposed. • The main objective of the proposed scheme is to explore the positive effects of security and safety in online voting system. [ABSTRACT FROM AUTHOR]

In order to accurately estimate the period of X-ray pulsars to improve navigation performance, this paper proposes a pulsar period estimation method based on photon energy using reverse Hilbert coding and double Convolutional Neural Networks (CNNs) discrimination. This method uses photon energy information to perform epoch folding. It converts one-dimensional contour information into two-dimensional image signals through reverse Hilbert curve and recognizes contour image features through CNN models to determine the optimal period. According to the simulation results, the period estimation accuracy of this method is 0.5350 ns, which is 65.71% higher than the χ 2 epoch folding method. The contour phase accuracy is 0.0004767, which is 41.93% higher than the χ 2 epoch folding method. At the same time, the observation time and noise interference that may affect the accuracy of period estimation are also quantitatively analyzed. In addition, in order to simulate real navigation scenarios, this paper also conducts dynamic period estimation experiments on PSR B0531+21 pulsar in a specific period of time. The method proposed in this paper has the advantages of high precision, fast calculation speed, strong anti-interference ability and accurate dynamic period estimation, which can significantly improve the navigation performance of X-ray pulsars. • The proposed period estimation method uses photon energy information for contour weighted folding. • The proposed method uses reverse Hilbert curve to convert one-dimensional contour information into two-dimensional image information. • Convolutional Neural Network models are used to optimize pulsar period estimation. [Display omitted] [ABSTRACT FROM AUTHOR]

The paper presented introduces an innovative accident prevention system that employs deep learning models and sensors to identify and alert drivers who lose concentration while driving for a variety of reasons. The system targets drowsiness, cell phone use, and alcohol consumption, which are among the leading causes of automobile accidents. The proposed solution employs neural networks to identify specific patterns associated with driver inattention and generates an audible alert to refocus the driver's attention on the road. In addition, the system utilizes alcohol-detection sensors, as alcohol consumption is another significant cause of accidents. This system seeks to reduce the number of casualties by enhancing road safety considering the high number of daily collisions, which are primarily caused by speeding. The paper describes the design, architecture, and implementation of the system on a modest scale to provide a lifesaving, cost-effective solution. [ABSTRACT FROM AUTHOR]

Skin cancer is one of the most prevalent forms of cancer around the world. Initial diagnosis relies on visual assessment of the affected area, followed by detailed dermoscopic analysis. The development of an automated system for classifying skin lesions poses a considerable challenge due to inherent noise and subtle variability in lesion images. Deep convolutional neural networks have demonstrated exceptional proficiency in image classification tasks spanning diverse domains. This paper demonstrates an end-to-end classification architecture built on top of transfer learning with data augmentation. The proposed model capitalizes on pre-trained architectures such as DenseNet, VGG-16, and Inception for feature extraction, and employs fully connected dense layers for categorizing seven distinct types of lesions. Several data augmentation techniques are also used to handle the class imbalance problem. Extensive experimentation encompassing various hyperparameters, imbalanced data scenarios, and balanced datasets was conducted to refine the automated skin lesion system. The proposed approach achieved a notable accuracy of 98% on the HAM10000 dataset and 94% on the ISIC-2019 dataset. Importantly, the experimental findings surpassed the performance of current state-of-the-art models for lesion classification. Furthermore, this paper examines the impact of class imbalance and data augmentation on the model's accuracy. [ABSTRACT FROM AUTHOR]

Cancer is a condition in which abnormal cells uncontrollably split and damage the body tissues. Hence, detecting cancer at an early stage is highly essential. Currently, medical images play an indispensable role in detecting various cancers; however, manual interpretation of these images by radiologists is observer-dependent, time-consuming, and tedious. An automatic decision-making process is thus an essential need for cancer detection and diagnosis. This paper presents a comprehensive survey on automated cancer detection in various human body organs, namely, the breast, lung, liver, prostate, brain, skin, and colon, using convolutional neural networks (CNN) and medical imaging techniques. It also includes a brief discussion about deep learning based on state-of-the-art cancer detection methods, their outcomes, and the possible medical imaging data used. Eventually, the description of the dataset used for cancer detection, the limitations of the existing solutions, future trends, and challenges in this domain are discussed. The utmost goal of this paper is to provide a piece of comprehensive and insightful information to researchers who have a keen interest in developing CNN-based models for cancer detection. [ABSTRACT FROM AUTHOR]

Deep neural networks have achieved outstanding performance in computer vision tasks. Convolutional Neural Networks (CNNs) typically operate in the spatial domain with raw images, but in practice, images are usually stored and transmitted in their compressed representation where JPEG is one of the most widely used encoder. Also, these networks are computationally intensive and slow. This paper proposes performing the learning and inference processes in the compressed domain in order to reduce the computational complexity and improve the speed of popular CNNs. For this purpose, a novel graph-based frequency channel selection method is proposed to identify and select the most important frequency channels. The computational complexity is reduced by retaining the important frequency components and discarding the insignificant ones as well as eliminating the unnecessary layers of the network. Experimental results show that the modified ResNet-50 operating in the compressed domain is up to 70% faster than the spatial-based traditional ResNet-50 while resulting in similar classification accuracy. Moreover, this paper proposes a preprocessing step with partial encoding to improve the resilience to distortions caused by low-quality encoded images. Finally, we show that training a network with highly compressed data can achieve a good classification accuracy with up to 93% reduction in the storage requirements of the training data. [ABSTRACT FROM AUTHOR]

Word spotting in handwritten documents is challenging due to the high intra-class and inter-class variability of handwritten forms. This paper addresses the word spotting problem in the segmentation and the training scenarios. Overall, this paper makes the following three contributions: (1) a new word text representation, called the Pyramid of Bidirectional Character Sequences (PBCS), which can solve both the word spotting problem and the word recognition problem. The use of the PBCS representation allows trained models to identify the character subsequences shared by words. Thus, words that are not seen during training can be represented and spotted. In addition, the PBCS representation encodes word texts redundantly, allowing for word discrimination. (2) A binary classification modeling of the word spotting problem in the difference space between representations, where spotting of non-vocabulary words is more efficient. Finally, (3) a new deep neural network architecture that combines the strengths of convolutional layers and transformers. We evaluated our solution on IAM and RIEMS datasets and showed that it outperforms recent state-of-the-art methods in the query-by-example scenario. • The Pyramid of Bidirectional Character Sequences (PBCS) word text representation. • Word spotting task as a binary classification problem. • Combing the strengths of convolutional layers and transformers. [ABSTRACT FROM AUTHOR]

In Computer-Controlled Optical Surfacing technology, the precision of the removal function directly affects the accuracy of computer-aided processing software predictions, which in turn influences subsequent polishing machine processing. A key parameter for constructing the removal function is the material removal rate, which is often challenging to obtain accurately. Currently, the Preston equation is widely used to describe the principles of material removal. However, as a linear equation that omits many factors, it struggles to accurately model the removal function in complex machining scenarios. Therefore, this paper proposes a hybrid neural network model combining Convolutional Neural Networks and Bidirectional Long Short-Term Memory to predict the material removal rate. The model's parameters are optimized using an improved Grey Wolf Optimization algorithm, ultimately establishing a removal function closely consistent with an actual removal function. We first tested our method on the PHM2016 Data Challenge dataset, achieving a mean squared error of 6.19 and an R2 of 0.9949, outperforming other mainstream neural network prediction models developed in recent years. Additionally, we further validated the performance of the neural network using a small grinding head polishing dataset, achieving MSE and R2 values of 1.9035 and 0.99902, respectively. Finally, we applied this method to construct the removal function on an actual small grinding head production line. Compared to the traditional Preston equation-based removal function, the predicted residual surface's PV and RMS errors were reduced from 28.24 % to 35.58 %–4.563 % and 4.86 %, respectively. These validation results demonstrate that the proposed method not only facilitates easier acquisition of the removal function model but also significantly enhances the accuracy of computer-aided processing software predictions, thereby better guiding ultra-precision machining processes. • Proposed a CNN-BiLSTM hybrid neural network to predict material removal rates. • First to construct a small grinding head removal function using a BiLSTM Predictor. • Optimized the neural network parameter sets using an improved Grey Wolf algorithm. • Achieved MSE of 6.19 and R2 of 0.9949 on the PHM2016 Data Challenge dataset. • Reduced polishing residual surface PV and RMS prediction errors to 4.563 % and 4.86 %. [ABSTRACT FROM AUTHOR]

Thanks to its richness in extractable features, Hyperspectral images (HSI) find an accelerated use in medical, industrial, agricultural, and environmental fields. In this paper, we present a wavelet-based reduction technique that creates a Hypercube containing the most significant features extracted from the original HSI and representing a multi-dimensional array that is utilized for training a Convolutional Neural Network (CNN), which is designed here to classify different types of surfaces or materials. The performance of this approach is tested and proved using two distinct datasets. Then, we compare the same approach with the PCA, a widely used reduction method. The most important contribution of this paper is the implementation of an FPGA-based parallel accelerator to train the same suggested CNN in only 10% of the computational time compared to the classical CPU-based techniques. The Microblaze will be explained and exploited here to play the role of an embedded microprocessor. • A Wavelet-based technique gives a reduced Hypercube rich in pixels spectrum features. • A CNN is designed to classify different types of surfaces or materials. • An FPGA-based parallel design is created to reduce 90% of the CNN training time. • The Microblaze is used to play the role of an embedded microprocessor. [ABSTRACT FROM AUTHOR]

In this paper, the non-uniform illumination enhancement problem of underwater images under the artificial light sources conditions is investigated based on Convolution Neural Network (CNN). First, we propose a trainable end-to-end enhancer called NUIENet, for enhancing the non-uniform illumination of underwater images. The proposed model consists of correction network and fusion layers. The correction network adopts the encoder–decoder structure with skip connections to enhance the features of different channels in the HSV domain, and then these enhanced features are fused by the fusion layers to obtain the desired high-quality images. Second, we built an underwater images dataset using Generative Adversarial Network (GAN) and Gaussian Function. Finally, both qualitative and quantitative experimental results show that the proposed method can produce better performance compared to other state-of-the-art enhancement methods on both real-word and synthetic underwater dataset. • This paper proposes a non-uniform illumination enhancer CNN-based which uses the encoder–decoder structure with skip connections to enhance the underwater images with NUI to the desired high-quality images. • To boost underwater imaging processing, we construct a dataset of the underwater image with NUI based on the GAN and Gaussian function which contains NUI images and their corresponding high-quality reference image. • Compared with other state-of-the-art NUIE methods, the proposed network achieves a nature color correction and superior or equivalent visibility improvement. [Display omitted] [ABSTRACT FROM AUTHOR]

Voice cloning methods have been used in a range of ways, from customized speech interfaces for marketing to video games. Current voice cloning systems are smart enough to learn speech characteristics from a few samples and produce perceptually unrecognizable speech. These systems pose new protection and privacy risks to voice-driven interfaces. Fake audio has been used for malicious purposes and is difficult to classify what is real and fake during a digital forensic investigation. This paper reviews the issue of deep-fake audio classification and evaluates the current methods of deep-fake audio detection for forensic investigation. Audio file features were extracted and visually presented using MFCC, Mel-spectrum, Chromagram, and spectrogram representations to further study the differences. Harnessing the different deep learning techniques from existing literature were compared using five iterative tests to determine the mean accuracy and the effects thereof. The results showed a Custom Architecture gave better results for the Chromagram, Spectrogram, and Me-Spectrum images and the VGG-16 architecture gave the best results for the MFCC image feature. This paper contributes to further assisting forensic investigators in differentiating between synthetic and real voices. [ABSTRACT FROM AUTHOR]

The term "crowd counting" refers to the practise of counting the number of people present in a certain area. Urban planning, medical services, emergency preparedness, public security, strategic planning, and defence all seem to be domains where this method may be used. Occlusion, size and perspective distortion, and non-uniform distribution are all problems that crowd counting approaches face. As the population density grows, so does the complexity of the calculations. Great advances in deep convolution neural networks (CNNs) and datasets are largely responsible for the tremendous development in crowd count approaches seen in the past few years. In this paper we assess recent efforts and provide a complete evaluation of modern deep learning-based crowd counting systems. This paper discusses some classic and deep learning-based crowd counting approaches. We examine detection-based, regression-based, and classic density estimation approaches briefly. For the purpose of estimating the crowd density and count for the provided crowd scene image, we have evaluated the recent 10 publications on crowd counting using deep learning. We also go through the most widely used datasets. In conclusion, these investigations demonstrated a high degree of precision and offered good illustrations of the potential of AI in crowd counting. From paper to paper, there were significant differences in the approaches and algorithms used to address the crowd counting and density mapping challenge. We also examine the possible uses of crowd counting as well as the difficulties associated with it. As a result, fresh study is being conducted in this area. [ABSTRACT FROM AUTHOR]

Image Synthesis or generation is evolving at a high rate helping from diagnosis of diseases to traffic control. Deep Learning has touched a new height in which domains like Computer Vision have successfully developed Deep learning models for image generation. Recent improvements in deep learning enabled Generative Adversarial Networks or GANs to achieve a remarkable level of success in image synthesis. GANs help in generating significant and relevant outcomes from convoluted patterns as input. This piece of research aims at making a call towards conservation of tribal art culture through deploying neural models and computer vision techniques, in line with Warli tribal human synthetic stick figures of Asian tribes. This paper presents several methods for synthesizing human stick figures in Asian Tribal Art using modified GAN architecture. The modified GANs were quite different in terms of layers as well as the range and distribution of latent vector space. To provide input data for the training process, a customized data set was created based on spherical polar coordinates and the laws of coordinate geometry. The process of training the GAN architecture involves insertion of random vector points, and addition of neural layers, to generate outputs of higher and better resolution. The paper includes training of Generator and Discriminator following the concepts of Transfer learning and providing relevant affirmation to draw conclusions that the generated samples exhibit similarities and resemble the original input sample. Further work extends towards using of different color space data set images for generating outputs with better accuracy through the modified GAN models. The final generated output images along with other visualizations are also attached with this work to provide evidence for the fact that the output samples are analogous to the actual data. This piece of research tries to open a gate way of using artificial intelligence in terms of cultivating and protecting the traditional art cultures of various tribes across the globe. The proposed methodology performed quite well in terms of producing warli figures from given latent vector space, which is vindicated by the comparison of images at pixel level and image histograms. [ABSTRACT FROM AUTHOR]

Synthetic Aperture Radar (SAR) is a high-resolution radar extensively used for aerial and terrestrial images in numerous applications. The SAR images are all weather and day/night capable. It is extensively used in defense/military systems for surveillance, target detection and target tracking. In current times, the need for deep learning algorithms has increased due to its capability of generating SAR images, as it is very intensive and expensive task for the acquisition and formation of SAR images through sensors. Thus, alternative methods are required to produce SAR image data. In this paper, generative adversarial networks (GAN) are used to generate SAR images from a limited pre-existing dataset. This paper presents a novel way of translating optical images to SAR images, for the generation of paired, unpaired data set. Due to the unavailability of an open-source paired, unpaired image dataset, a synthetic paired image dataset is created for proving the concepts of CycleGAN and Pix-to-Pix algorithm by fine tuning the algorithms using generated datasets. The paper tried tackling this problem in two ways, both paired and unpaired image-to-image translation. [ABSTRACT FROM AUTHOR]

Identification of human actions from video has gathered much attention in past few years. Most of the computer vision tasks such as Health Care Activity Detection, Suspicious Activity detection, Human Computer Interactions etc. are based on the principle of activity detection. Automatic labelling of activity from videos frames is known as activity detection. With the introduction of deep networks, the process of activity detection is clustered into two groups known as hand-crafted feature based approach and automatic feature extraction approach. This paper focuses on various approaches used in recent literature based on traditional and automatic approach. Moreover, hierarchy for different approaches under them such as space based, motion based, genetic based, fuzzy based, dictionary based are discussed. With introduction of Convolutional Neural Networks and Recurrent Neural Networks, automatic learning capability from input modality makes them first choice to be implemented for activity recognition. In this paper various approaches have been analyzed according to methodology, accuracy, classifier and datasets. [ABSTRACT FROM AUTHOR]

Natural Language processing (NLP) includes the task of classifying texts. The proposed paper uses the ability and power of machine learning and deep learning techniques for sentiment analysis on restaurant reviews. With the increasing use of social media, classification of reviews has significant role in the development of public opinion. This work has extensive applications from client opinion study, market research and social media monitoring. The machine learning algorithms and NLP techniques are used classifying reviews and the results are rigorously analysed. It was noted that results obtained from logistic regression and multinomial naïve bayes algorithms are better than other machine learning models. Hence these two algorithms are selected to optimize further. After tuning the hyperparameters by grid search technique, the best accuracy obtained by logistic regression and multinomial naive bayes on validation dataset was 89.9% and 89.6% respectively. Deep learning architectures were also utilized for reviews classification. The accuracy obtained by Convolutional Neural Net (CNN) and Bi-Directional Long-short-term-memory (Bi-LSTM) was 89% and 90% respectively. [ABSTRACT FROM AUTHOR]

In recent years, one of the deadliest malignancies is skin cancer. If it is not detected and treated in a timely manner, it is expected to spread to other body parts. An accurate automated system for skin lesion recognition is essential for early detection to save human lives. Although there are many other forms of skin cancer, basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and melanoma are the three most prevalent. With early identification and appropriate treatment, these three kinds of skin cancer can be successfully treated by using deep learning techniques. One of the main benefits of using deep learning for skin cancer detection is its ability to accurately classify images with subtle differences. In this paper, Image pre-processing is employed at an initial diagnosis for removing the artifacts present in the raw dataset and further Convolutional Neural Network (CNN) is employed to improve classification and detection of skin cancer with improved accuracy. For analyzing enormous volumes of data, R-CNN algorithms are proved to be incredibly effective in terms of accuracy of 84.32%. Due to its precision, effectiveness, objectivity, and accessibility, R-CNN algorithm have proven to be very helpful in the identification and categorization of skin cancer. [ABSTRACT FROM AUTHOR]

One of the buzz words in current research depends for a weather forecast is the atmospheric temperature, and this value may change at any time. Predicting air temperature exactly is necessary since it is particularly important for various communities and events. In today's world of massive amounts of data and unforeseen data fluctuations, long-short term memory (LSTM), a sort of neural network method, is becoming more and more popular. The present work employed a sequence to sequence LSTM autoencoder to forecast Indian weather patterns. The prediction model was trained using historical data obtained from the Khordha district administration. The proposed method primarily emphasizes two phases of the procedure. The present study involves an examination of a proposed model, wherein a comparison is made between four distinct variants of LSTM techniques: vanilla LSTM, stacked LSTM, bidirectional LSTM, and convLSTM. The objective of this analysis is to predict temperature patterns. Additionally, this paper utilizes an LSTM autoencoder model to forecast the temperature for the subsequent two-year period in the Khordha district of Odisha, India. The experimental investigation demonstrates that the utilization of Stacking encoder-decoders with bidirectional LSTM cells leads to a notable enhancement in the accuracy of the model, resulting in maximum efficacy. A notably lower Mean Absolute Error (MAE) result suggests that the 9-layer stacked autoencoder model has superior performance in predicting both the minimum and maximum temperature. [ABSTRACT FROM AUTHOR]

Brain tumors pose a significant medical challenge, demanding early detection and diagnosis to enhance patient outcomes. However, existing brain tumor detection methods often suffer from inefficiency and inaccuracy. Presently, deep learning models have gained prominence in classifying brain MRI images due to their superior accuracy compared to traditional classifiers. Nonetheless, optimizing hyperparameters manually to achieve precise image classification is a daunting and time-consuming task. To address these challenges, we present a novel approach in this paper—the Manta Ray Foraging Optimized Convolutional Neural Network (MRFO-CNN) model to classify brain MRIs into tumorous and non-tumorous categories. We leverage the Manta Ray Foraging Optimization technique to automatically determine the optimal hyperparameters, specifically batch size and epoch settings. Our model is trained on a dataset comprising 3000 brain MR images and validated on an additional 351 brain MR images. The results unequivocally demonstrate the superiority of our proposed MRFO-CNN model over conventional CNN approaches, achieving an impressive training accuracy of 99.3% and a validation accuracy of 98.7%. This research not only showcases the potential of deep learning in brain tumours classification but also underscores the efficiency and effectiveness of automated hyperparameter optimization in medical image analysis. [ABSTRACT FROM AUTHOR]

Stress is a psychological or emotional strain that occurs due to adverse experiences in human life. This paper showcases the application of deep learning in detecting stress levels in continuous audio signals in the Distress Analysis Interview Corpus Wizard of Oz (DAIC-WOZ) database. The features that have been experimented with are Gammatone Frequency Cepstral Coefficients (GFCC), Log Filter Bank (Log-Filter Bank), Mel Frequency Cepstral Coefficients (MFCC), chroma, and Linear Predictive Coding (LPC). Five deep learning models were evaluated: Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Bidirectional LSTM (Bi-LSTM), k-fold CNN with the k value as 5, and a fusion model of CNN, LSTM, and attention. Upon evaluating the performance metrics of all the models, it is concluded that the k-fold CNN model with k as 5 performs well with continuous audio signals. The model has achieved an accuracy of 80% when it is trained on MFCC, GFCC, and Log-F Bank features which are observed to be the optimal features in the stress analysis. [ABSTRACT FROM AUTHOR]

The concept of predictions has gained much attention over the last few years. Research on prediction based on experience is error-prone. Usually, a lot of data has been available with multiple variables, but not all features are relevant. This work uses different feature selection techniques and their combinations to select the best possible feature subset. This paper uses feature selection techniques for time series data prediction with deep learning models. In this work, we have used filter, wrapper, and embedded methods for feature selection. We combine these techniques and compare their performance with single feature selection techniques. We found that the embedded method alone performs well with fewer features, but its performance deteriorates when the number of features increases. We input these reduced feature sets into deep learning models such as recurrent neural networks (RNN), long short-term memory (LSTM), and 1d Convolutional with LSTM (1d CNN-LSTM). We assess the performance of different deep-learning models with reduced features. Our results analysis found that the right feature subset may help increase the performance of deep learning models for time series prediction. Performance improvement is specific to the dataset, feature selection techniques, and the deployed DL models; performance improvement varies on average, from a few percent to fifty percent. [ABSTRACT FROM AUTHOR]

Breast cancer diagnosis from mammographic scans is a complex challenge, demanding accurate and efficient methodologies. Existing approaches often rely on time-consuming manual feature extraction or lack scalability when employed with diverse clinical image sets. To address these limitations, this paper presents an innovative solution: the MPC2EL (Multiple Phased Convolution model for Pre-emption of Breast Cancer via Extensive Learning Operations). The core problem tackled by this research is the need for improved breast cancer detection, especially concerning scalability, accuracy, and practicality. To achieve this, MPC2EL leverages extensive learning operations and multiple phased convolutions to process extensive clinical datasets containing both cancerous and benign images. Our novel approach begins with the conversion of these images into multimodal feature sets, encompassing frequency, cosine, wavelet, and Gabor domains. These feature sets enable enhanced classification of images into different cancer stages. The proposed methodology lies in a Dual 1D Convolutional Neural Network (D1D CNN) architecture, capable of categorizing images initially into malignant and benign types and subsequently refining classification for malignant images. Experimental results reveal a substantial 5.9% increase in classification accuracy and a 4.5% improvement in recall compared to conventional deep learning methods. Moreover, the model demonstrates lower processing delay and higher precision, making it a promising candidate for real-world clinical deployment. [ABSTRACT FROM AUTHOR]

The high variety in the forms of the Arabic words creates significant complexity related challenges in Natural Language Processing (NLP) tasks for Arabic text. These challenges can be dealt with by using different techniques for semantic representation, such as word embedding methods. In addition, approaches for reducing the diversity in Arabic morphologies can also be employed, for example using appropriate word normalisation for Arabic texts. Deep learning has proven to be very popular in solving different NLP tasks in recent years as well. This paper proposes an approach that combines Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks to improve sentiment classification, by excluding the max-pooling layer from the CNN. This layer reduces the length of generated feature vectors after convolving the filters on the input data. As such, the LSTM networks will receive well-captured vectors from the feature maps. In addition, the paper investigated different effective approaches for preparing and representing the text features in order to increase the accuracy of Arabic sentiment classification. [ABSTRACT FROM AUTHOR]

• The paper fills the gap in the literature by reviewing and analyzing the current studies that apply deep learning for Covid-19 forecasting. • The initial search identified 152 studies of which 53 passed the quality control. • The existing literature is categorized using a model-based taxonomy. • The description of the models along with their performance evaluation is presented. • Recommendations for future improvements are provided. The Covid-19 pandemic has galvanized scientists to apply machine learning methods to help combat the crisis. Despite the significant amount of research there exists no comprehensive survey devoted specifically to examining deep learning methods for Covid-19 forecasting. In this paper, we fill the gap in the literature by reviewing and analyzing the current studies that use deep learning for Covid-19 forecasting. In our review, all published papers and preprints, discoverable through Google Scholar, for the period from Apr 1, 2020 to Feb 20, 2022 which describe deep learning approaches to forecasting Covid-19 were considered. Our search identified 152 studies, of which 53 passed the initial quality screening and were included in our survey. We propose a model-based taxonomy to categorize the literature. We describe each model and highlight its performance. Finally, the deficiencies of the existing approaches are identified and the necessary improvements for future research are elucidated. The study provides a gateway for researchers who are interested in forecasting Covid-19 using deep learning. [ABSTRACT FROM AUTHOR]

• The classification of brain tumors (BTs) is an expensive intricate challenge in the section of clinical image analysis. Radiologists were able to reliably detect tumors using machine learning (ML) algorithms without the need for extensive surgery. • The efficacy of this paper is examined using classification accuracy. • The suggested model demonstrated its advantage over the currently used approaches for classifying BTs from MR images. The classification of brain tumors (BTs) is an expensive intricate challenge in the section of clinical image analysis. Radiologists were able to reliably detect tumors using machine learning (ML) algorithms without the need for extensive surgery. Hand-crafted features are necessary for the conventional ML classifiers, which take a lot of effort. Deep Learning (DL), on the other hand, has gained popularity recently for identification and categorization-based functionalities because of its effective feature extraction capabilities. Creating the most precise DL architecture for classifying BTs is a huge task. These challenges inspired us to develop a cutting-edge and highly accurate framework based on DL and computational methods that evolve to effectively create the hybrid framework automatically for categorizing three distinct types of brain cancers on a vast library of MR images. We present a unique EBT Deep Net DL model that uses a substantial convolutional neural network (CNN) technique for the classification of three distinct forms of brain cancers: gliomas, tumors in brain meningeal tissue, and tumors in pituitary glands. Pretrained deep CNN models like ResNet50V2, ResNet152, DenseNet201, MobileNetV3, and VGG19 were used to extract deep features. The efficacy of this paper is examined using classification accuracy. In comparison to the most recent classification findings from ResNet50V2, ResNet152, DenseNet201, MobileNetV3, and VGG19, the proposed methodology had the greatest accuracy. The models' respective accuracy on a classification test is as follows: VGG19 scored 97.46 %, ResNet152 scored 98 %, DenseNet201 scored 95.44 %, ResNet50V2 scored 90.04 %, MobileNetV3 scored 97.15 %, and the ensemble model outperformed all of them with an accuracy of 98.8 %. The suggested model demonstrated its advantage over the currently used approaches for classifying BTs from MR images. [ABSTRACT FROM AUTHOR]

Big data, AI, and machine learning have ushered in a transformative era in computer processing and application. AI's capacity to emulate human cognition spans a spectrum of industries, from rudimentary tasks to intricate decision-making processes. Projections indicate that within a short span, AI technology will bestow computers with human-like capabilities, rendering it indispensable. This advancement has substantially bolstered industry autonomy, fortifying security and safety through the integration of electronics, internet connectivity, advanced algorithms, and cutting-edge processing chips. In this context, Automated Guided Vehicles (AGVs) leverage AI-powered systems and sensors to optimize performance and proactively thwart potential failures. Going beyond Advanced Driver Assistance Systems (ADAS), this review scrutinizes the broader spectrum of AI applications. Specifically, it synthesizes pertinent studies encompassing AI's impact on car emissions, predictive maintenance, security, and the realm of connected vehicles. While AGVs can utilize AI algorithms to chart emission-efficient routes and engineer energy-conservative vehicles, AI, through diverse algorithms, proficiently anticipates component failures, substantially enhancing the cost-effectiveness of predictive maintenance and bolstering vehicle reliability. Moreover, AI integrated with sensor technology safeguards vehicles against a spectrum of threats. Neural networks and machine learning further automate security measures for both cargo and passengers. Concurrently, AI and machine learning fortify traffic control and enhance vehicle communication within connected vehicle frameworks, albeit necessitating fortifications in data security, encryption, and system efficiency. This survey paper comprehensively covers the expanse of automotive AI and machine learning applications, extending beyond ADAS. It underscores that the evolving mobility landscape necessitates a thorough evaluation of network architecture, connectivity, and performance metrics, encompassing AGV technology, networking protocols, and swarm dynamics. In this vein, the paper advocates for experts to address existing literature gaps and proactively enhance automotive systems. [ABSTRACT FROM AUTHOR]

Indonesia is a tropical country that experiences forest fires every year. Forest fires occur due to a prolonged summer season. A major effect of forest fires that commonly occurred in Indonesia is the respiratory disorder and the visual impairment caused by the thick smoke that can experienced by the people who lives around the forest. The effects of forest fire fumes when the forest fire spread across the bigger land or area are also experienced by neighboring countries such as Malaysia, Singapore and Brunei Darussalam. Forest is a habitat for many animals, one of which is a bird. Birds are able to communicate with their colonies through sound. The bird sound during communication to the group can be in the form of calls, marriage invitations, and warnings of danger or threat of forest fires. This paper presents bird sounds classification study using one of Deep Learning (DL) algorithms i.e. Convolutional Neural Network (CNN) method. The CNN method is used to classify bird sounds in the two conditions: (1) under normal circumstances or conditions, and (2) under threated or panic condition. The bird sound data used in this study were collected from the local birds in Indonesia. The classification result of two bird sounds based on CNN method achieved up to 96.45%. This paper is a preliminary study for bio inspired early warning of forest fires based on the sound of birds. [ABSTRACT FROM AUTHOR]

Due to the fast progress of Deep Learning (DL) methods in remote sensing applications, many change detection (CD) algorithms have been recently proposed based on CNN networks and the mechanism of self-attention. These algorithms extract features without focusing on the temporal dependency between features. This shortcoming led to the introduction of the Transformer mechanism. In this paper, we design a convolutional transformer network with a Siamese U-shaped structure and name it CTS-Unet to solve the CD problem. We exploit the ability of the CNN to extract effective semantic features and that of the transformer to extract global information effectively. The Siamese architecture allows using CNN to simultaneously extract effective semantic features from low-resolution bi-temporal images. The transformer part contains an encoder and a decoder, all of which use the Swin transformer module as their basic unit. The encoder processes the features extracted from the CNN using patch merging and the Swin transformer module to produce semantic features. The encoder extracts the detailed information from the features using patch expansion, the Swin transformer module, and convolutional upsampling to create a CD map. The experiments were performed on the widely used LEVIR-CD and DSIFN-CD datasets. Compared with other state-of-the-art CD methods, CTS-Unet provides higher performance with F1-scores of 91.87% and 69.60% for LEVIR-CD and DSIFN-CD datasets, respectively. [ABSTRACT FROM AUTHOR]

• Accuracy of avalanche hazard analysis and prediction rely on avalanche feedback. • Convention methods of avalanche reporting are inefficient and incomplete. • UAV RGB images can provide accurate avalanche occurrence details of an area. • Detected deposits will help in avalanche analysis, characterization and modelling. Avalanche activities in the snow-covered mountainous slopes are very frequent and stochastically distributed over time and geographical extents. Conventional methods of avalanche occurrence reporting in these areas are inefficient and incomplete due to inhospitable weather and inaccessible topographic conditions. This paper presents a novel framework for the detection and analysis of avalanche deposits using UAV (Unmanned Aerial Vehicle) RGB images of snow-bound avalanche-prone areas. In the first part of the proposed framework, an OBIA-CNN (Object Based Image Analysis-Convolution Neural Network) method is applied to UAV images for the detection of avalanche deposits. Initially, the OBIA-based multi-scale multi-resolution segmentation technique is used for UAV image segmentation, then the classification of these image segments was performed using a CNN classifier to detect the avalanche deposits. The CNN-based classifier was created, trained, validated, and applied to generate the class probability maps of different classes present in the images. The post-classification refinements were then applied to the detected deposits. In the second step the detailed accuracy analysis of the detected deposits based on their count, area, size similarity, and shape similarity with respect to reference deposits has been carried out to establish the suitability of the proposed method. The avalanche deposits detected using the proposed method were found in good correlation with manually delineated deposits in terms of all four accuracy criteria. The precision of the model was found 1.0, the value of recall was 0.88 and the F-1 score was 0.93. The overall object shape matching accuracy of the detected deposits was also found high (0.92). The results of the proposed deposit detection method were also compared with the classification results of Support Vector Machine (SVM), Random Forest (RF), and UNET to evaluate the performance of the method. Finally, the surface area and snow volume-based characterization of the detected deposits was performed. The proposed framework will be useful for the automated detection of avalanche deposits and their characterization for the regions of specific interest. The study suggests that regular monitoring of avalanche activities using UAV images provides a good solution for the operational monitoring of important corridors of snowbound regions. [ABSTRACT FROM AUTHOR]

• The improved VMD and DWT are combined to denoise and reconstruct the signal under strong noise without a reference. • The selection of wavelet function and transform level in DWT is optimized by Shannon entropy to denoise the signal without a reference. • The RAPID and the CNN are used to achieve spatial localization and visualization of the composite delamination. In this paper, a damage spatial imaging approach based on novel signal extraction is suggested to reconstruct the Lamb wave response signal under strong noise and realize the spatial localization of damage. First, the Variable Mode Decomposition (VMD) parameters are optimized by the improved Grey Wolf optimization method (IGWO) to decompose the response signal. To rebuild the response signal, the correlation coefficient is used to choose the optimal modal component and the residual. To give the best wavelet function and transform level for adaptive denoising of the reconstructed signal without a reference signal, an enhanced Discrete Wavelet Transform (DWT) based on Shannon entropy is proposed. To achieve damage localization imaging, a damage spatial localization model is built utilizing a reconstruction algorithm for probabilistic inspection of damage (RAPID) approach and a convolutional neural network (CNN). The suggested method may successfully increase the signal-to-noise ratio (SNR) of the reconstructed response signal and lower the error of spatial localization under strong noise through experiments. The spatial localization of composite damage using Lamb wave under strong noise is expanded in this paper. [ABSTRACT FROM AUTHOR]

With the rapid development of blockchain and digital currencies, cybercrimes targeting blockchain transactions are proliferating. Various abnormal transaction behaviors caused by malicious nodes and malicious transactions have emerged in blockchain systems. Therefore, blockchain transaction security research is a hot issue in blockchain research. Deep learning has made remarkable achievements in image and audio. However, deep learning is less effective when processing text-like data than tree-based models. Therefore, for the highly unbalanced textual financial dataset, this paper designs a deep learning anomaly detection method called 1D SA-Inception by combining CNN with Transformer structure on the basis of traditional one-dimensional CNN (1D-CNN), introduces the Inception structure to learn the information of different scales of tabular data, and introduces the Transformer (self-attention) self-attention mechanism for the research of blockchain anomaly transaction detection technology, effectively improving the prediction effect. Finally, by conducting experiments on the extreme class imbalance dataset, the results show that the 1D SA-Inception designed in this paper outperforms the traditional CNN with AUC, G-mean, and F1 indexes of 91.05 %, 84.95 %, and 83.52 %, respectively, on the textual dataset. This method can more efficiently achieve the detection of abnormal transaction behavior, safeguard consumer rights and interests, and ensure the safe development of the financial sector. [ABSTRACT FROM AUTHOR]

High-resolution (HR) MR images provide rich structural detail to assist physicians in clinical diagnosis and treatment plan. However, it is arduous to acquire HR MRI due to equipment limitations, scanning time or patient comfort. Instead, HR MRI could be obtained through a number of computer assisted post-processing methods that have proven to be effective and reliable. This paper aims to develop a convolutional neural network (CNN) based super-resolution reconstruction framework for low-resolution (LR) T2w images. In this paper, we propose a novel multi-modal HR MRI generation framework based on deep learning techniques. Specifically, we construct a CNN based on multi-resolution analysis to learn an end-to-end mapping between LR T2w and HR T2w, where HR T1w is fed into the network to offer detailed a priori information to help generate HR T2w. Furthermore, a low-frequency filtering module is introduced to filter out the interference from HR-T1w during high-frequency information extraction. Based on the idea of multi-resolution analysis, detailed features extracted from HR T1w and LR T2w are fused at two scales in the network and then HR T2w is reconstructed by upsampling and dense connectivity module. Extensive quantitative and qualitative evaluations demonstrate that the proposed method enhances the recovered HR T2w details and outperforms other state-of-the-art methods. In addition, the experimental results also suggest that our network has a lightweight structure and favorable generalization performance. The results show that the proposed method is capable of reconstructing HR T2w with higher accuracy. Meanwhile, the super-resolution reconstruction results on other dataset illustrate the excellent generalization ability of the method. [ABSTRACT FROM AUTHOR]

Cardiac arrhythmia is one of the prime reasons for death globally. Early diagnosis of heart arrhythmia is crucial to provide timely medical treatment. Heart arrhythmias are diagnosed by analyzing the electrocardiogram (ECG) of patients. Manual analysis of ECG is time-consuming and challenging. Hence, effective automated detection of heart arrhythmias is important to produce reliable results. Different deep-learning techniques to detect heart arrhythmias such as Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Transformer, and Hybrid CNN–LSTM were proposed. However, these techniques, when used individually, are not sufficient to effectively learn multiple features from the ECG signal. The fusion of CNN and LSTM overcomes the limitations of CNN in the existing studies as CNN–LSTM hybrids can extract spatiotemporal features. However, LSTMs suffer from long-range dependency issues due to which certain features may be ignored. Hence, to compensate for the drawbacks of the existing models, this paper proposes a more comprehensive feature fusion technique by merging CNN, LSTM, and Transformer models. The fusion of these models facilitates learning spatial, temporal, and long-range dependency features, hence, helping to capture different attributes of the ECG signal. These features are subsequently passed to a majority voting classifier equipped with three traditional base learners. The traditional learners are enriched with deep features instead of handcrafted features. Experiments are performed on the MIT-BIH arrhythmias database and the model performance is compared with that of the state-of-art models. Results reveal that the proposed model performs better than the existing models yielding an accuracy of 99.56%. • This paper proposes a rich feature fusion technique for cardiac arrhythmia detection from ECG by merging three deep learning models, namely, CNN, CNN–LSTM, and Transformer. • Integrating these models combines the advantages of all these individual models, overcomes their limitations, and learns significant features from the input ECG signal. • The deep spatial, temporal, and long-range dependency patterns learned by the aforementioned models are fused via concatenation and fed to a majority voting classifier with three traditional base learners: SVM, LR, and RF. • MIT-BIH Arrhythmia database is used for experimentation. A comparison of the results with the baseline models and state-of-the-art models shows that the proposed model outdoes the existing models achieving an accuracy of 95.56% and an F-score of 99.34%. • The results show that the proposed model outperforms the existing models in terms of precision, recall, F-score, and accuracy. [ABSTRACT FROM AUTHOR]

Using deep learning in three-phase induction motor fault diagnosis has gained increasing interest nowadays. This paper proposes a Convolutional Neural Network (CNN) model to diagnose induction motor faults during the starting period. The model is able to detect various faults (locked-rotor, overload, voltage-unbalance, overvoltage, and undervoltage) under three loading levels (Light, Normal, and Heavy loads). The proposed model has high reliability as it depends on image data from multiple motor signals (voltages, currents, torque, and speed). The transient response of the motor starting period, makes it challenging to diagnose faults depending on raw time-domain images only. Therefore, the measured signals are additionally represented as d-q, and Lissajous images to focus on the effect of using these representations on the model performance. With multi-signals data, two forms of data (single- and multi-channel input-shape) can be implemented and evaluated to figure out the form that can capture the related fault features more efficiently. Experiments are performed using simulated machine model, to investigate the best signal representation and the best input shape for the proposed fault diagnosis system. Eight distinct datasets are generated from the motor data to be used in training and testing the CNN model. For the comparison of signals representations, the best accuracy is achieved with datasets containing both voltage and current d-q signals representation. They performed better than the other representations in the range from (0.03%) to (3.57%). For the comparison of input shapes, all multi-channels datasets proved to have better performance than single-channel datasets in the range from (0.77%) to (4.06%). [ABSTRACT FROM AUTHOR]

With the continuous development of social economy, the road traffic system as one of the basis of national economy is also increasingly developed, which is followed by the traffic safety problems are increasingly prominent. Among them, driving violations such as not obeying traffic signs are the main cause of traffic accidents. In this research, Traffic Sign Recognition (TSR) has become a hot research topic. The research status and application field of traffic sign detection and recognition technology are introduced and analyzed in detail, and the improvement of traffic sign database is introduced. After that, the application of CNN in image processing and traffic sign recognition is introduced, and the existing problems in traffic sign recognition are analyzed. The CNN deep learning network used in this paper can conduct training while identifying targets, effectively improve the recognition accuracy of traffic signs under complex natural conditions and reduce the time consumption. [ABSTRACT FROM AUTHOR]

• Deep and handcrafted features are extracted from 2D depth images and 3D scans respectively. • The extracted features are embedded into a covariance pooling for the dimensionality reduction. • Deep covariance learning is carried out using two additional layers to enhance their discrimination power. • The Gaussian kernel is used to generalize the radial basis function to the manifold space for SVM classification. • High classification performance is achieved on two challenging datasets. Facial emotion recognition (FER) methods have been proposed mainly using 2D images. These methods suffer from many problems caused by the difficult conditions of unconstrained environments such as light conditions and view variations. In this paper, we aim to recognize the emotional facial expressions independently of their identity using the 3D data and 2D depth images. Since the 3D FER is a very fine-grained recognition task, mapping the 3D images into 2D depth images may lack some geometric characteristics of the expressive face and decay the FER performance. Convolutional Neural Networks (CNN), however, have been successfully applied to the 2D depth images and improved handcrafted-based methods in computer vision and pattern recognition applications. For this reason, we combine in this paper two types of features; handcrafted and deep learning features and prove their complementarity for 3D FER. Favorably, covariance descriptors have proven a very good ability to combine features from different types into a compact representation. Therefore, we propose to use the covariance matrices of features (handcrafted and deep ones), instead of the features independently. Since covariance matrices belong to one of the manifold space types, formed by SPD (Symmetric Positive Definite) matrices, we mainly focus on the generalization of the RBF kernel to the manifold space for 3D FER using a supervised SVM classification. The achieved performance of the proposed method on the Bosphorus and BU-3DFE datasets outperforms similar state-of-the-arts. [ABSTRACT FROM AUTHOR]

With the development of modern cities, urban rail transit has become an indispensable part of residents' travelling mode, and accurate prediction of urban rail transit passenger flow is particularly important. However, due to the non-linearity and non-stability of passenger flow, the low quality of big data and the lack of data make it more and more difficult to predict the passenger flow of urban rail transit. In this paper, we propose a unique model structure that ingeniously integrates Gated Recurrent Units (GRU), Convolutional Neural Networks (CNN) with fused residual network connections, and a self-attention mechanism. The design of this model is primarily to effectively handle complex and low-quality data, which is often prevalent in passenger flow prediction scenarios. To validate the effectiveness of the proposed model, we used data from the Beijing urban rail transit in 2016 for prediction. In the experiments, we performed comparison study and ablation study. The experimental results show that the model proposed in this paper has significantly improved prediction accuracy in both horizontal and vertical comparisons. This outcome substantiates that the proposed model can not only effectively handle complex and low-quality data but also extract short-term features and long-term dependency features of passenger flow well, thereby achieving more accurate predictions. • Integration of GRU, CNN with fused residual connections, and self-attention mechanism constitutes a novel model. • The model is capable of handling complex and lower-quality data, significantly improving the accuracy of predictions. • The model can simultaneously extract short-term features and long-term dependency features from time series. [ABSTRACT FROM AUTHOR]

The task of accurately classifying defect types and pinpointing their locations in the domain of industrial product defect detection remains a formidable challenge. This paper introduces an advanced industrial defect detection framework, named YOLOv7-SiamFF, which utilizes the YOLOv7 as a feature extraction and detection backbone with three feature reinforcement modules. Firstly, we employ a parallel Siamese network, facilitating differential feature extraction through dual-stream feature extraction channels, aimed at better highlighting defect features and suppressing background interference. Additionally, we introduce a depth information feature fusion module, which effectively integrates high and low-level features in the Siamese network, thus enhancing the model's detection accuracy for small target defects. Finally, an attention mechanism is integrated into the feature extraction network, further enhancing the model's precision in identifying defect-specific features. In the simulation experiment, a specialized visual dataset was created for object detection tasks focusing on industrial defects, dubbed the BC-DD dataset. Additionally, the effectiveness of the proposed model has been validated in this paper using the aforementioned dataset. [ABSTRACT FROM AUTHOR]

Evolutionary computation is derived from the simulation of natural selection and genetic processes in biological evolution. This approach provides a method for optimizing the structure and parameters of neural networks. When combined with neural networks, forming what's termed as evolutionary computation based neural networks, it offers a systematic approach to optimize neural network models in diverse applications. In this study, we introduce a method that employs differential evolution algorithms to optimize parameters of convolutional neural network (CNN) for music emotion recognition tasks. This method optimizes the initial weights of the CNN, aiming to achieve near-global optimal solutions and expedite network convergence. Comparative experiments indicate that the proposed approach effectively identifies optimal parameters and structures for CNN, suggesting potential advancements in automated music emotion recognition. • This paper improves differential evolution algorithm via combining five key operations. • This paper employs differential evolution algorithm to optimize parameters of CNNs for music emotion recognition tasks. • The proposed DE-CNN approach effectively identifies optimal parameters and structures for CNNs. [ABSTRACT FROM AUTHOR]

Automatic detection of Diabetic Retinopathy (DR) is critically important, as it is the primary reason of irreversible loss of vision in the economically active populations in the developed countries. Early detection of the onset of Diabetic Retinopathy can greatly benefit clinical treatment; although several different feature extraction methods have been proposed, the task of retinal image classification remains tedious even for trained clinicians. This paper emphasizes on Diabetic Retinopathy detection as well as the analysis of the different stages of DR, performed on fundus images using Deep Learning algorithms. Fundus images of the patient were provided as input to the developed model evaluated using the real-time dataset of the hospital. The proposed ResNet-18 architecture with swish function has achieved an accuracy of 93.51%, sensitivity of 93.42%, precision of 93.77% and F1-score of 93.59%. The paper concludes with a comparative study of Simple CNN, VGGNet-16, MobileNet-V2 and ResNet architectures and other state-of-art approaches, which highlights ResNet-18 with Swish as the most effective deep learning classifier model for DR detection. • Deep learning outperforms traditional screening for Diabetic Retinopathy, reducing ophthalmologists' workload. • ResNet18's residual connections mitigate the vanishing gradient problem and enable effective retinal image pattern learning. • Swish activation in ResNet18 enhances Diabetic Retinopathy detection with improved accuracy and faster training convergence. [ABSTRACT FROM AUTHOR]

The increasing number of articles available in the digital library will require quite a long time and accuracy in sorting articles according to needs. The use of artificial neural networks in finding the right articles as needed through topic segmentation applications will helps this process in terms of speed and accuracy. Several neural network models used in segmentation topic applications include Recurrent Neural Networks (RNN), Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM). The Transformer model since its introduction in 2017 for Natural Language Processing (NLP) has a better level of accuracy compared to the RNN, CNN and LSTM models. Transformer model research for segmentation topic applications, especially articles in Indonesian language, is still very limited. This paper will discuss the use of the Transformer model in segmentation topic applications for Indonesian-language articles. The experimental results found that the accuracy produced by the Transformer model was higher than previous LSTM model with the WindowDiff value generated by the model proposed using Transformer is 0.249 and the LSTM baseline model is 0.363, while the while the Pk value generated by the proposed model is 0.279 and the LSTM baseline model is 0.394. [ABSTRACT FROM AUTHOR]

• A novel deep learning-based registration network • A novel smooth constraints function • Two-stage skip connections obtain richer local information • Proposed method can be easily transferred to various applications Medical image registration can establish the spatial consistency of the corresponding anatomical structures between different medical images, which is important in medical image analysis. In recent years, with the rapid development of deep learning, the image registration methods based on deep learning greatly improve the speed, accuracy, and robustness of registration. Regrettably, these methods typically do not work well for large deformations and complex deformations in the image, and neglect to preserve the topological properties of the image during deformation. Aiming at these problems, we propose a new network TS-Net that learns deformation from coarse to fine and transmits information of different scales in the two stages. Two-stage network learning deformation from coarse to fine can gradually learn the large and complex deformations in images. In the second stage, the feature maps downsampled in the first stage for skip connection can expand the local receptive field and obtain more local information. The smooth constraints function used in the past is to impose the same restriction on the global, which is not targeted. In this paper, we propose a new smooth constraints function for each voxel deformation, which can better ensure the smoothness of the transformation and maintain the topological properties of the image. The experiments on brain datasets with complex deformations and heart datasets with large deformations show that our proposed method achieves better results while maintaining the topological properties of deformations compared to existing deep learning-based registration methods. [ABSTRACT FROM AUTHOR]

• A new approach for PD detection based on CNN deep features and i-vector features. • The impact of effective use of dynamic features for PD classification. • The significance of CNN deep features and i-vector features in terms of PD detection. Parkinson's disease (PD) corresponds to one of the most common neurological diseases in the world, which is mainly manifested by motor, cognitive, and language disorders. The change in the patient's voice is one of the most striking clinical signs and proves to be an element of interest to support the diagnosis and the assessment of PD. In this research paper, a new approach based on speech signal analysis is set forward to automatically detect Parkinson's disease. The approach evaluates two learning techniques, namely Support Vector Machines (SVM) and Convolutional Neural Networks (CNN), to classify data obtained from speech tasks. Two input data,i.e., the raw speech signal's values and the i-vector features of dimensions 100, 200 and 300 are extracted in this study. Eventually, an evaluation step is undertaken through the use of five evaluation metrics which are accuracy, precision, recall/sensitivity, specificity and f -score. The most pertinent obtained results for a test dataset composed of 28 participants are recorded as follows: an accuracy of 100%, precision of 0.99, recall/sensitivity of 0.98, specificity of 0.96 and f -score of 0.98. These findings corroborate that our approach can help in terms of PD detection. [ABSTRACT FROM AUTHOR]

• An automatic energy leakage detection for district heating systems based on UAV Infrared (IR) images is presented. • A deep learning-based model and 8 different ML classifiers have been developed and evaluated for detection of leakages. • A region extraction algorithm has been incorporated to extract potential leakages enabling the ML analysis. • The proposed ML methods have been applied to ca. 13.4 million image patches and achieved an actual detection rate of 98.6%. In this paper, we propose automatic energy leakage detection in underground pipes of district heating systems based on Infrared (IR) images, captured by an Unmanned Aerial Vehicle (UAV). Hot water or steam is distributed to homes and industries through underground pipes from a central power plan. Leakages in underground pipes pose a very common problem, which can occur for many reasons, e.g. unprofessional installation and end of service life. Potentially, a leakage remains undiscovered for a very long period of time. Therefore, it is of great interest for power supply companies to monitor district heating networks to identify leakages. In this paper, the original IR images are captured in a 16 bit format by a UAV. On ground, potential leakages are extracted using a region extraction algorithm. Thereafter a Convolutional Neural Network (CNN) as well as eight conventional Machine Learning (ML) classifiers are applied on these regions to classify whether or not it is a leakage. In total, twelve UAV sequences are captured at different cities in Denmark. Based on these, around 13.4 million samples of image patches of district heating systems are extracted. Eleven sequences are used for training and the remaining one for testing. This was performed on all splits in the leave-one-out testing. The deep learning CNN achieved an average weighted accuracy of 0.872 with a false positive and negative rate of 12.7 % and 10.4 %, respectively. This CNN model detected around 98.6 % of the true leakages. In comparison, conventional ML classifiers, i.e. Adaboost (AB), Random Forest (RF), etc. provide lower average weighted accuracy, but on the other hand they require less computational resources. We have compared our method with a state-of-art method and the result shows that the proposed method is very competitive. [ABSTRACT FROM AUTHOR]

This paper presents a new proposal of an efficient computational model of face recognition which uses cues from the distributed face recognition mechanism of the brain, and by gathering engineering equivalent of these cues from existing literature. Three distinct and widely used features – Histogram of Oriented Gradients (HOG), Local Binary Patterns (LBP), and Principal components (PCs) extracted from target images are used in a manner which is simple, and yet effective. The HOG and LBP features further undergo Principal Component Analysis (PCA) for dimensionality reduction. Our model uses multi-layer perceptrons (MLP) to classify these three features and fuse them to form a sparsely connected model. A computational theory is first developed by using concepts from the information processing mechanism of the brain. Extensive experiments are carried out using eight publicly available face datasets to validate our proposed model's performance in recognizing faces with extreme variation of illumination, pose angle, expression, and background. We also investigate the same mechanism because of reasons discussed later, on object recognition tasks as well. Results obtained are extremely promising when compared with other face and object recognition algorithms including CNN and deep learning-based methods. This highlights that simple computational processes, if clubbed properly, can produce competing performance with best algorithms. [ABSTRACT FROM AUTHOR]

Medical image segmentation is one of the most challenging tasks in medical image analysis which aims to extract effective information and improve the level of clinical diagnosis. In last decades, automatic segmentation based on Deep Learning (DL) models such as U-Net and CNN architectures have been widely used to automatically extract organs or lesions contours in order to overcome manual segmentation limitations. In this paper, we performed a comparative study between CNN and U-Net performance for medical image segmentation applied to cardiac-MRI segmentation using U-Net from short-axis MRI images of ACDC database. The adopted architecture was trained and tested with and without data augmentation. The obtained results show a strong agreement between the labelled masks and the predicted ones with a mean DSC that reached 97,9% and a mean Hausdorrf Distance (HD) that reached 5.318 mm. A quantitative comparison was made on two levels. The first one is an intra-comparison made between the adopted model and methods based on the same architecture and having been trained and tested using the same database which proved that our method reached the highest performance and can be considered as a promising tool for medical image segmentation. The second one is an inter-comparison made between U-Net and CNN performance which proved that U-Net is more suitable for carrying out this task since it takes less time for training as it does not have a fully connected layer and offers a fairly significant similarity to ground truth compared to CNN. [ABSTRACT FROM AUTHOR]

In the last two decades, improvement in artificial intelligence and medical imaging technology have made healthcare sector to achieve some remarkable achievements in diseases analysis and prediction. Due to advancement in medical imaging technology the brain images are taken in different modalities, that gives 3D view of different sections of brain for tumor diagnosis. The ability to extract relevant characteristics from magnetic resonance imaging (MRI) scans is a crucial step for brain tumor classifiers. As a result, several studies have proposed various strategies to extract relevant features from different modalities of MRI to predict the growth of abnormal tumor. Most of techniques used conventional techniques of image processing for feature extraction and machine learning for classification. More recently, the use deep learning algorithms in medical imaging has resulted in significant improvements in the classification and diagnosis of brain tumor. Since tumors are located at different regions of brain, the localizing the tumor and classifying it to particular category is challenging task. In this paper, we have solved this problem by designing deep ensemble model. In the proposed approach, first shallow convolutional neural network (SCNN) and VGG16 network were designed with T1C modality MRI image and subsequently loss and accuracy were examined. To improve the performance of model in terms accuracy and loss information, the extracted features from both the deep learning model were fused to improve the classification accuracy of three types of tumors. The obtained results from ensemble deep convolutional neural network model (EDCNN), proved that the fusion of deep learning model improves the accuracy of multiclass classification problem and also tries to address the problem of overfitting of model for imbalance dataset. The proposed model tries to give classification accuracy up to 97.77%. Furthermore, the proposed framework, achieves competitive results when compared with other state of art studies. [ABSTRACT FROM AUTHOR]