Retailers must have accurate sales forecasts to operate their businesses efficiently and effectively and to remain competitive in the marketplace. Global forecasting models like RNNs can be a powerful tool for forecasting in retail settings, where multiple time series are often interrelated and influenced by a variety of external factors. By including covariates in a forecasting model, we can better capture the various factors that can influence sales in a retail setting. This can help improve the accuracy of our forecasts and enable better decision-making for inventory management, purchasing, and other operational decisions. In this study we investigate how the accuracy of global forecasting models is affected by the inclusion of different potential demand covariates. To ensure the significance of the study's findings, we used the M5 forecasting competition's openly accessible and well-established dataset. The results obtained from the DeepAR models, which were trained on various combinations of features including time, price, events, and IDs, suggest that individually only the features corresponding to IDs improve the baseline model. However, when all the features are used together, the best performance is achieved, indicating that the individual relevance of each feature is emphasized when the information is given jointly. Comparing the model with features to the model without features, there is an improvement of 1.76\% for MRMSSE and 6.47\% for MMASE.

Sometimes when diabetic retinopathy (DR) is found and treated quickly, vision loss can indeed be spared. This study deploys a deep learning (DL) model that can discover all 5 stages of DR more accurately than other methods. The proposed methodology shows two cases scenarios: case 1 with image enhancement using CLAHE and ESRGAN, and case 2 without image enhancement. Augmentation techniques are then employed to produce a balanced dataset with the identical criteria for both scenarios. The generated model using DenseNet-121 on the APTOS dataset outperformed other approaches for locating the 5 stages of DR, with an accuracy of 98.7 percent for case 1 and 81.2 percent for case 2. Using CLAHE and ESRGAN was shown to improve a model's performance and ability to learn.

Using machine learning or deep learning to solve the problem of garbage recognition and classification is an important application in computer vision, but due to the incomplete establishment of garbage datasets and the poor performance of complex network models on smart terminal devices, the existing garbage classification models The effect is not good.This paper presents a waste classification and identification method base on transfer learning and lightweight neural network. By migrating the lightweight neural network MobileNetV2 and rebuild it, The reconstructed network is used for feature extraction, and the extracted features are introduced into the SVM to realize the identification of 6 types of garbage. The model was trained and verified by using 2527 pieces of garbage labeled data in the TrashNet dataset, which ultimately resulted in a classification accuracy of 98.4% of the method, which proves that the method can effectively improve the classification accuracy and time and overcome the problem of weak data and less labeling. The over-fitting phenomenon encountered by small data sets in deep learning makes the model robust.

Hybrid forecasting methods have emerged as a solution surpassing the limitations of both statistical and deep learning approaches. While the first emphasize the significance of variables, they often produce worse forecasting results when compared to newer techniques. In contrast, deep learning models remain enigmatic "black boxes" in terms of interpretability, although achieving better results in forecasting. This article introduces the Comprehensive Cross-Correlation and Lagged Linear Regression Deep Learning (CCLR-DL) framework, designed to harness the best of both approaches, enhancing forecasting accuracy while retaining model interpretability through a feature selection process. CCLR-DL blens cross-correlation analysis, lagged multiple linear regression and granger's causality procedures with deep learning architectures based on LSTM. In a practical demonstration, CCLR-DL was applied to a real database of clinical visits associated to diagnoses in Catalonia, Spain (tracking a population of 6.3 million patients during 10 years). Predicting visits enables the healthcare managers to be ready for future demand shifts. Results demonstrate a consistent and substantial improvement over standalone statistical and deep learning methods when predicting healthcare demand. This hybrid approach not only showcases its efficacy but also offers a promising solution to the challenge of balancing predictive accuracy with model explicability. In this context, this work aims to design and validate a method for feature selection and forecasting of multivariate high dimensional time series datasets not only to improve prediction accuracy but also to model transparency by identifying a subset of variables that improve predictions and G-cause the target variable.

Pakistan is an agricultural country, and an exporter of crops in many countries. The crop production is an important factor to earn revenue for the country. But the agriculture of Pakistan is still not revolutionized and no modern system has been deployed commonly. Whereas the farmers face difficulty in growing some crops because those crops needs more care and calculated steps. Moreover the farmers face difficulty at different stages of the crop growth like to check fertility of soil and if the soil is non-fertile then which chemical property is lacking. The objective of this research is to provide digitize the agriculture of Pakistan. An emerging technology IoT and Deep learning based system will be developed. The IoT part contains some devices like sensors,gateways and communication technologies whereas the software part consists of Deep learning models that can make predictions about the fertility of the soil. The motive of this system is to provide best results in term of accuracy. Whereas the dataset used is publicly available on kaggle but it was of non-fertile values, so data augmentation is also performed to generate data for fertile values. We have implemented LSTM,RNN,CNN among them LSTM performed best for the prediction of soil fertility.

Artificial intelligence methods and application have recently shown great contribution in modeling and prediction of the hydrological processes, climate change, and earth systems. Among them, deep learning and machine learning methods mainly have reported being essential for achieving higher accuracy, robustness, efficiency, computation cost, and overall model performance. This paper presents the state of the art of machine learning and deep learning methods and applications in this realm and the current state, and future trends are discussed. The survey of the advances in machine learning and deep learning are presented through a novel classification of methods. The paper concludes that deep learning is still in the first stages of development, and the research is still progressing. On the other hand, machine learning methods are already established in the fields, and novel methods with higher performance are emerging through ensemble techniques and hybridization.

Alzheimer’s is a degenerative brain condition brought on by intricate brain changes after cell injury. The prevalence of Alzheimer’s disease is highest in those over 65. Presently, AD is detected by manual examination of a patient’s Magnetic Resonance Imaging (MRI) scan and neuropsychological assessments. Due to its subpar accuracy and performance, solutions based on artificial intelligence (AI) have not been made more widely available. This paper proposes a deep Convolutional Neural Network (CNN) with the pre-trained MobileNet-V2 architecture as the model’s base for feature extraction and reducing the parameter size and training time. The proposed model accurately classifies various early stages of AD. The proposed approach visualizes the class activation maps in the form of a heat map on brain MRI scans via the Grad-CAM algorithm that lifts the black-box nature of the deep model. To handle the imbalance problem of the AD data set acquired from Kaggle, the oversampling algorithm SMOTE interpolates new images to even the class samples. The proposed multi-class classification deep model is named Bio-AD and evaluated using different quality metrics. The Bio-AD model has the following values for evaluation metrics: 97.92%, 99.87%, 97.87%, 98%, 98%, and 0.0646 for accuracy, Area Under the Curve (AUC), F1-score, Precision, Recall, and loss respectively. The proposed Bio-AD model is compared with DenseNet-169, VGG-19, and InceptionResNet-V2 using different quality metrics and outperformed in comparison with all other models using the AD data set.

Polar Mesospheric Summer Echoes (PMSEs) are radar echoes that are observed in the mesosphere during the Arctic summer months in the polar regions. By studying PMSE, researchers can gain insights into physical and chemical processes that occur in the upper atmosphere specifically in the 80 to 90 km altitude range. In this paper, we employ fully convolutional networks such as UNET and UNET++ for the purposes of segmenting PMSE from the EISCAT VHF dataset. First, experiments are performed to find suitable weights and hyperparameters for UNET and UNET++. Second, different loss functions are tested to find one suitable for our task. Third, as the number of PMSE samples used is relatively small that can lead to poor generalization. To address this, image-level and object-level augmentation methods are employed. Four, we briefly explain our findings by employing layerwise relevance propagation.

This study compares the performance of existing studies on multimodal emotion recognition, and proposes a model that fuses two modalities with the speaker's text and voice signals as input values and detects depression. Based on the DAIC-WOZ dataset, voice features were extracted using CNN, text features were extracted using Transformers, and two modalities were fused through a tensor fusion network. We also build a model to detect whether the speaker is depressed or not using LSTM in the final layer. This study suggests the possibility of increasing access to mental illness diagnosis by enabling patients to detect depression on their own in daily conversations. If the model proposed in this study is developed and the voice conversation system is connected, it will be easier for patients who cannot visit the hospital periodically or who are reluctant to visit the hospital to check their condition and seek recovery. Furthermore, it can be expanded to multi-label classification for various mental diseases and used as a simple self-mental disease diagnosis tool.

Now when the whole world is still under COVID-19 pandemic, many schools have transferred the teaching from physical classroom to online platforms. It is highly important for schools and online learning platforms to investigate the feedback to get valuable insights about online teaching process so that both platforms and teachers are able to learn which aspect they can improve to achieve better teaching performance. But handling reviews expressed by students would be a pretty laborious work if they were handled manually as well as it is unrealistic to handle large-scale feedback from e-learning platform. In order to address this problem, both machine learning algorithms and deep learning models are used in recent research to automatically process students' review getting the opinion, sentiment and attitudes expressed by the students. Such studies may play a crucial role in improving various interactive online learning platforms by incorporating automatic analysis of feedback. Therefore, we conduct an overview study of sentiment analysis in educational field presented in recent research, to help people grasp an overall understanding of the sentiment analysis research. Besides, according to the literature review, we identify three future directions that researchers can focus on in automatically feedback processing: high-level entity extraction, multi-lingual sentiment analysis, and handling of figurative language.

The exponential growth of biomedical data in recent years urged the application of numerous machine learning techniques to address emerging problems in biology and clinical research. By enabling automatic feature extraction, selection and generation of predictive models, these methods can be used to efficiently study complex biological systems. Machine learning techniques are frequently integrated with bioinformatic methods, as well as curated databases and biological networks, to enhance training and validation, identify the best interpretable features, and enable feature and model investigation. Here, we review recently developed methods that incorporate machine learning within the same framework with techniques from molecular evolution, protein structure analysis, systems biology and disease genomics. We outline the challenges posed for machine learning, and in particular, deep learning in biomedicine and suggest unique opportunities for machine learning techniques integrated with established bioinformatics approaches to overcome some of these challenges.

Accurate forecasting and efficient management of commodities are crucial for stakeholders in the industry, given the volatile nature of these markets. This study addresses these needs by leveraging advanced forecasting techniques and machine learning models to predict prices and enhance supply chain efficiency. TThe focus is on utilizing ARIMA, SARIMAX, and LSTM models to analyze historical trading data for commodities such as cocoa, coffee, and sugar sourced from Kaggle’s comprehensive dataset. The research applies ARIMA and SARIMAX models to forecast price trends, overcoming initial challenges related to data index frequency and seasonality. LSTM models are employed for more nuanced demand forecasting, particularly for random-length lumber, demonstrating the model's capability to predict future market trends accurately. The study highlights significant improvements in prediction accuracy and supply chain management through meticulous feature engineering and model optimization, offering valuable insights for strategic decision-making in the supply chain sector.

A hybrid smart process and material design system for nanoimprinting is proposed, which combines with a learning system based on experimental and numerical simulation results. Instead of carrying out extensive learning experiments for various condition, the simulation learning results are partially complimented where the results can be theoretically predicted by numerical simulation. In other word, the lacking data in experimental learning are complimented by simulation-based learning results. Therefore, the prediction of nanoimprint results under various conditions without experimental learning could be realized even for unknown materials. In this study, material and process design for a low-temperature nanoimprint process using glycerol-containing polyvinyl alcohol are demonstrated. Experimental results under limited conditions are learned to investigate optimum Glycerol concentrations and process temperatures. On the other hand, simulation-based learning is used to predict the dependence on press pressure and shape parameters. The prediction results for unknown Glycerol concentrations agreed well with the follow-up experiments.

Deep learning has taken over - both in problems beyond the realm of traditional, hand-crafted machine learning paradigms as well as in capturing the imagination of the practitioner sitting on top of petabytes of data. While the public perception about the efficacy of deep neural architectures in complex pattern recognition tasks grows, sequentially up-to-date primers on the current state of affairs must follow. In this review, we seek to present a refresher of the many different stacked, connectionist networks that make up the deep learning architectures followed by automatic architecture optimization protocols using multi-agent approaches. Further, since guaranteeing system uptime is fast becoming an indispensable asset across multiple industrial modalities, we include an investigative section on testing neural networks for fault detection and subsequent mitigation. This is followed by an exploratory survey of several application areas where deep learning has emerged as a game-changing technology - be it anomalous behavior detection in financial applications or financial time-series forecasting, predictive and prescriptive analytics, medical imaging, natural language processing or power systems research. The thrust of this review is on outlining emerging areas of application-oriented research within the deep learning community as well as to provide a handy reference to researchers seeking to embrace deep learning in their work for what it is: statistical pattern recognizers with unparalleled hierarchical structure learning capacity with the ability to scale with information.

By 2024, artificial intelligence (AI) will have had a revolutionary impact on cyber security, putting the sector at a critical turning point. This article explores the significant influence AI has had on cyber security procedures, outlining the progress made as well as the difficulties faced. artificial intelligence (AI) has transformed threat detection and response systems, allowing for proactive security tactics against a constantly changing array of cyber threats. By utilizing neural networks and machine learning algorithms, artificial intelligence (AI) systems can predict possible security breaches, detect unusual trends, and automatically reduce risks in real-time. These capabilities are unparalleled. Nevertheless, despite these impressive advancements, worries about data privacy, adversarial attacks, and ethical ramifications remain significant. Moreover, the never-ending game of cat and mouse between cyber attackers and defenders continues, requiring constant innovation and adaptability in cyber security strategies driven by Artificial Intelligence. In addition to providing insights into its implications for protecting digital assets and bolstering resilience against cyber threats in the changing cyber security scenario of 2024, this paper summarizes the current state of the artificial intelligence revolution in cyber security.

Tremendous progress has been witnessed in artificial intelligence within the domain of neural network backed deep learning systems and its applications. As we approach the post Moore’s Law era, the limit of semiconductor fabrication technology along with a rapid increase in data generation rates have lead to an impending growing challenge of tackling newer and more modern machine learning problems. In parallel, quantum computing has exhibited rapid development in recent years. Due to the potential of a quantum speedup, quantum based learning applications have become an area of significant interest, in hopes that we can leverage quantum systems to solve classical problems. In this work, we propose a quantum deep learning architecture; we demonstrate our quantum neural network architecture on tasks ranging from binary and multi-class classification to generative modelling. Powered by a modified quantum differentiation function along with a hybrid quantum-classic design, our architecture encodes the data with a reduced number of qubits and generates a quantum circuit, loading it onto a quantum platform where the model learns the optimal states iteratively. We conduct intensive experiments on both the local computing environment and IBM-Q quantum platform. The evaluation results demonstrate that our architecture is able to outperform Tensorflow-Quantum by up to 12.51% and 11.71% for a comparable classic deep neural network on the task of classification trained with the same network settings. Furthermore, our GAN architecture runs the discriminator and the generator purely on quantum hardware and utilizes the swap test on qubits to calculate the values of loss functions. In comparing our quantum GAN, we note our architecture is able to achieve similar performance with 98.5% reduction on the parameter set when compared to classical GANs. With the same number of parameters, additionally, QuGAN outperforms other quantum based GANs in the literature for up to 125.0% in terms of similarity between generated distributions and original data sets.

Background: Albumin has a pivotal role in the homeostasis of osmotic pressure and is associated with cardiovascular, nephrotic, hepatic, and nutritional diseases. The detection of hypoalbuminemia is a cornerstone for diagnosis of hidden diseases and patient deterioration. We developed and validated a deep-learning-based model (DLM) for detection of hypoalbuminemia using electrocardiography (ECG). Methods: This historical cohort study included data from consecutive patients from two hospitals. The patient data in one hospital were divided into development (82,499 ECGs from 54,248 patients) and internal validation (20,664 ECGs from 20,664 patients) datasets, whereas the patient data in the other hospital were included in only an external validation (37,421 ECGs from 37,421 patients) dataset. An DLM was developed using a 12-lead ECG signal, age, and sex from the development dataset. The endpoint was hypoalbuminemia, defined by serum albumin concentration below 3.5 g/dL. Results: During the internal and external validations, the areas under the receiver operating characteristic curve of the DLM for the detection of hypoalbuminemia were 0.887 (0.877–0.897) and 0.888 (0.880–0.896), respectively. Among the 27,400 individuals without hypoalbuminemia at the initial laboratory exam, those identified by the DLM as higher-risk patients had a significantly larger change in developing hypoalbuminemia than those in the low-risk group (7.09% vs. 1.01%, p < 0.001) during 24 months. The sensitivity map showed that the DLM focused on the T wave and QRS complex for the detection of hypoalbuminemia. Conclusions: The DLM exhibited a high accuracy for hypoalbuminemia detection and prediction using 12-, 6-, and single-lead ECGs.

Image registration (IR) is a process that deforms images to align them with respect to a reference space, making it easier for medical practitioners to examine various medical images in a standardized reference frame, such as having the same rotation and scale. This document introduces image registration using a simple numeric example. It provides a definition of image registration along with a space-oriented symbolic representation. This review covers various aspects of image transformations, including affine, deformable, invertible, and bidirectional transformations, as well as medical image registration algorithms such as Voxelmorph, Demons, SyN, Iterative Closest Point, and SynthMorph. It also explores atlas-based registration and multistage image registration techniques, including coarse-fine and pyramid approaches. Furthermore, this survey paper discusses medical image registration taxonomies, datasets, evaluation measures, such as correlation-based metrics, segmentation-based metrics, processing time, and model size. It also explores applications in image-guided surgery, motion tracking, and tumor diagnosis. Finally, the document addresses future research directions, including the further development of transformers.

Dynamic adaptive video streaming over HTTP (DASH) plays a crucial role in video transmission across networks. Traditional adaptive bitrate (ABR) algorithms adjust the quality of video segments based on network conditions and buffer occupancy. However, these algorithms rely on fixed rules within a complex environment, making it challenging to achieve optimal decisions considering the overall context. In this paper, we propose a novel Deep Reinforcement Learning-based approach for streaming DASH, focusing on maintaining consistent perceived video quality throughout the streaming session to enhance user experience. Our approach optimizes the Quality of Experience (QoE) by dynamically controlling the quality distance factor between consecutive video segments. We evaluate this approach through a simulation model that encompasses diverse wireless network environments and various video sequences. Additionally, we compare our proposed approach with state-of-the-art methods. The experimental results demonstrate significant improvements in QoE, ensuring users enjoy stable, high-quality video streaming sessions.

Initial choice of Learning Rate is a key part of gradient based methods and has a great effect on the performance of the Deep Learning Model.This paper studies the behavior of multiple gradient based optimization algorithm which are commonly used in Deep Learning and compare their performance on various learning rate. As observed popular choice of optimization algorithms are highly sensitive to various choice of learning rates. Our goal is to find which optimizer has an edge over others for a specific setting. We look at two datasets namely MNIST and CIFAR10 for benchmarking. The results are quite surprising, and it will help us to choose a learning rate more efficiently.

Considering animal welfare, the free-range laying hen farming model is increasingly gaining attention. However, in some countries, large-scale farming still relies on the cage-rearing model, making the focus on the welfare of caged laying hens equally important. To evaluate the health status of caged laying hens, a dataset comprising visible light and thermal infrared images was established for analyses, including morphological, thermographic, comb, and behavioural as-sessments, enabling a comprehensive evaluation of the hens' health, behaviour, and population counts. To address the issue of insufficient data samples in the health detection process for indi-vidual and group hens, a dataset named BClayinghens was constructed containing 61,133 images of visible light and thermal infrared images. The BClayinghens dataset was completed using three types of devices: smartphones, visible light cameras, and infrared thermal cameras. All thermal infrared images correspond to visible light images and have achieved positional alignment through coordinate correction. Additionally, the visible light images were annotated with chicken head labels, obtaining 63,693 chicken head labels, which can be directly used for training deep learning models for chicken head object detection and combined with corresponding thermal infrared data to analyze the temperature of the chicken heads. To enable the constructed deep-learning object detection and recognition models to adapt to different breeding environ-ments, various data enhancement methods such as rotation, shearing, colour enhancement, and noise addition were used for image processing. The BClayinghens dataset is important for ap-plying visible light images and corresponding thermal infrared images in the health detection, behavioural analysis, and counting of caged laying hens under large-scale farming.

Many works have recently identified the need to combine deep learning with extreme learning to strike a performance balance with accuracy especially in the domain of multimedia applications. Considering this new paradigm, namely convolutional extreme learning machine (CELM), we present a systematic review that investigates alternative deep learning architectures that use extreme learning machine (ELM) for a faster training to solve problems based on image analysis. We detail each of the architectures found in the literature, application scenarios, benchmark datasets, main results, advantages, and present the open challenges for CELM. We follow a well structured methodology and establish relevant research questions that guide our findings. We hope that the observation and classification of such works can leverage the CELM research area providing a good starting point to cope with some of the current problems in the image-based computer vision analysis.

The advent of deep learning has completely reshaped our world. Now, our daily life is fulfilled with many well-known applications that adopt deep learning techniques, such as self-driving cars and face recognition. Furthermore, robotics developed more forms of technology which share the same principle with face recognition, such as hand pose recognition and fingerprint recognition. Image recognition technology requires a huge database and various learning algorithms, such as convolutional neural network and recurrent neural network, that requires lots of computational power, such as CPUs and GPUs. Thus, clients could not be satisfied with the computational resource of the local machine. The cloud resource platform emerged at a historic moment. Docker containers play a significant role of microservices-based applications in the next generation. However, it could not guarantee the quality of service. From clients’ perspective, they have to balance the budget and quality of experiences (e.g. response time). The budget leans on individual business owners and the required Quality of Experience (QoE) depends on usage scenarios of different applications, for instance, an autonomous vehicle requires real-time response, but, unlocking your smartphone can tolerate delays. Plenty of on-going projects developed user-oriented optimization resource allocation to improve the quality of the service. Considering the users’ specifications, including accelerating the training process and specifying the quality of experience, this thesis proposes two differentiate containers scheduling for deep learning applications: TRADL and DQoES .

Deep learning techniques, such as convolutional neural networks (CNN), generative adversarial networks (GAN), and graph neural networks (GNN), have over the past decade changed the ac-curacy of prediction in many diverse fields. In recent years, the application of deep learning tech-niques in computer vision tasks in pathology demonstrated extraordinary potential in assisting clinicians, automating diagnosis, and reducing costs for patients. Formerly unknown pathologi-cal evidence, such as morphological features related to specific biomarkers, copy number varia-tions, and other molecular features, were also able to be captured by deep learning models. In this paper, we review popular deep learning methods and some recent publications about their appli-cations in pathology.

Data sets for medical images are generally imbalanced and limited in sample size because of high data collection costs, time-consuming annotations, and patient privacy concerns. The training of deep neural network classification models on these data sets to improve the generalization ability does not produce the desired results for classifying the medical condition accurately and often overfit the data on the majority of class samples. To address the issue, we propose a framework for improving the classification performance metrics of deep neural network classification models using transfer learning: pre-trained models, such as Xception, InceptionResNet, DenseNet along with the Generative Adversarial Network (GAN) – based data augmentation. Then, we trained the network by combining traditional data augmentation techniques, such as randomly flipping the image left to right and GAN-based data augmentation, and then fine-tuned the hyper-parameters of the transfer learning models, such as the learning rate, batch size, and the number of epochs. With these configurations, the Xception model outperformed all other pre-trained models achieving a test accuracy of 98.7%, the precision of 99%, recall of 99.3%, f1-score of 99.1%, receiver operating characteristic (ROC) - area under the curve (AUC) of 98.2%.

This paper presents a new method : HIVEC to learn latent vector representations of graphs in a manner that captures the semantic dependencies of sub-structures. The representations can then be used in machine learning algorithms for tasks such as graph classification, clustering etcetera. The method proposed is unsupervised and uses the information of co-occurrence of sub-structures. It introduces a notion of hierarchical embeddings that allows us to avoid repetitive learning of sub-structures for every new graph. As an alternative to deep learning methods, the edit distance similarity between sub-structures is also used to learn vector representations. We compare the performance of these methods against previous work.

To identify objects in images, a complex set of skills is needed that includes understanding the context and being able to determine the borders of objects. In computer vision, this task is known as semantic segmentation and it involves categorizing each pixel in an image. It is crucial in many real-world situations: for autonomous vehicles, it enables the identification of objects in the surrounding area; in medical diagnosis, it enhances the ability to detect dangerous pathologies early, thereby reducing the risk of serious consequences. In this study, we compare the performance of various ensembles of convolutional and transformer neural networks. Ensembles can be created, e.g, by varying the loss function, data augmentation method or the learning rate strategy. Our proposed ensemble, which is based on the simple average rule, demonstrates exceptional performance on several datasets. All the resources used in this study are available online at the following GitHub repository: https://github.com/LorisNanni.

Breast cancer is a common malignant tumour and studies have shown that early and accurate detection is crucial for patients. With the maturity of medical imaging and deep learning development, significant progress has been made in breast cancer classification, which greatly improves the accuracy and efficiency of classification. This review focuses on deep learning, migration learning, GAN, and lifelong learning to elaborate and summarise the important roles arising from breast cancer detection. This review also examines the dataset and labeling issues required for breast cancer classification. In conclusion, at the end of the article, we look at future directions for breast cancer classification research, including cross-migration learning, multimodal data fusion, model interpretability, and lifelong learning, and also explore how to provide personalized treatment plans for patients.

This research aims to explore the integration method of deep learning and large language models in speech recognition to improve the system’s recognition accuracy and ability to handle complex contexts. Deep neural network (DNN), convolutional neural network (CNN), long short-term memory network (LSTM) and Transformer-based large language model are used to build an integrated acoustic and language model framework. Experiments on TIMIT, LibriSpeech and Common Voice datasets show that the ensemble model shows significant improvements in both word error rate (WER) and real-time factor (RTF) compared to traditional models. Especially in terms of adaptability to multiple languages and accent changes, the model shows superior performance. The conclusion shows that through technology integration, the performance of the speech recognition system in complex environments can be effectively improved, providing a new direction for the future development of speech recognition technology.

Our daily activities hinge on the flexibility of our fingers, and a fractured finger can significantly disrupt these routines. The finger bones enable us to bend and fold the fingers and thumb to pick up or grasp objects and do all of our daily activities. A broken finger can cause adverse effects on our daily life activities. It is important to treat broken finger as soon as possible. Swift and precise treatment begins with capturing multiple X-rays, followed by the critical step of fracture detection in these images. Relying on the naked eye for this task carries the risk of overlooking small fractures. To address this issue an automated diagnoses of fractured fingers from images is required for which the current research employs advanced deep learning models—ResNet34, ResNet50, ResNet101, ResNet152, VGG-16, and VGG-19—to classify finger images from the Musculoskeletal Radiographs (MURA) dataset as either fractured or non-fractured. The results emphasize the consistently strong performance of ResNet models, attaining an impressive accuracy of 81.9%. This surpasses VGG models by 3.4% and establishes ResNet as the new benchmark for state-of-the-art accuracy.

This study discusses the application of deep learning technology in network intrusion detection systems (IDS) and focuses on a new model named CNN-Focal. First, through the review of traditional IDS technology, it analyzes its limitations in dealing with complex network traffic. Then, the design principle of the CNN-Focal model is described in detail, which uses threshold convolution and SoftMax multi-class classification technology to effectively improve abnormal traffic detection's accuracy and efficiency. The experimental results show that CNN-Focal performs well on the open data set, demonstrating the potential and advantages of its application in the natural network environment and providing a new perspective and method for further research of deep learning in the field of network security in the future.

Deep learning image reconstruction (DLIR) algorithms employs convolutional neural networks (CNNs) for CT image reconstruction to produce CT images with a very low noise level, even at low radiation dose. The aim of this study was to assess whether the DLIR algorithm reduces the CT effective dose (ED) and im-proves CT image quality in comparison with filtered back projection (FBP) and iterative reconstruction (IR) algorithms in intensive care unit (ICU) patients. We identified all consecutive patients referred to the ICU of a single hospital who underwent at least two consecutive chest and/or abdominal contrast-enhanced CT scans within a time period of 30 days using DLIR and subsequently FBP or IR algorithm (Advanced Mod-eled Iterative Reconstruction model-based algorithm [ADMIRE], or Adaptive Iterative Dose Reduction 3D [AIDR 3D]) for CT image reconstruction. The radiation ED, noise level, and signal-to-noise ratio (SNR) were compared between the different CT scanners. The non-parametric Wilcoxon test was used for statistical comparison. Statistical significance was set at p < 0.05. A total of 83 patients (mean age, 59 ± 15 years [standard deviation]; 56 men) were included. DLIR vs FBP reduced ED (18.45 ± 13.16 mSv vs 22.06 ± 9.55 mSv, P < 0.05), while DLIR vs FBP and vs ADMIRE and AIDR 3D IR algorithms reduced image noise (8.45 ± 3.24 vs 14.85 ± 2.73 vs 14.77 ± 32.77 and 11.17 ± 32.77\, P < 0.05) and increased SNR (11.53 ± 9.28 vs 3.99 ± 1.23 vs 5.84 ± 2.74 and 3.58 ± 2.74, P < 0.05). CT scanners employing DLIR reduced radiation ED and im-proved SNR compared to CT scanners using FBP, whereas CT scanners using DLIR improved SNR com-pared to CT scanners using FBP or IR algorithms in ICU patients.

Coffee is one of the most valuable agricultural products worldwide, and it is crucial to have efficient tools to obtain reliable information about production. This study aims to estimate coffee plantation production using segmentation and deep learning techniques in RGB images. Photographs of coffee plants were taken in Tabaconas, San Ignacio-Cajamarca, to create a dataset of crops during the harvest stage. The images were segmented to detect coffee fruits. A deep learning method was developed with YOLOv5 to detect the fruits and OpenCV to count them. The results showed that YOLOv5 achieved an accuracy of 97.25%, a recall of 95.77%, and an F1-Score of 96.37%, demonstrating high reliability in detecting coffee fruits. The average detection time per image was 17.9 seconds. The metrics were evaluated using a confusion matrix, highlighting the model's good performance. In conclusion, segmentation and deep learning techniques, along with counting algorithms developed with OpenCV, proved effective for estimating coffee production. This approach provides a valuable tool for farmers, improving crop management and facilitating decision-making in precision agriculture.

Scaffoldings play a critical role as temporary structures in supporting construction processes. Accidents at construction sites frequently stem from issues related to scaffoldings, including insufficient support caused by deviations from the construction design, insecure rod connections, or absence of cross bracing, which result in uneven loading and potential collapse, leading to casualties. In this study, we introduce a deep-learning-based, augmented reality (AR)-enabled system called scaffolding assembly deficiency detection system (SADDS) to assist field inspectors in identifying deficiencies in scaffolding assemblies. Inspectors have the flexibility to utilize SADDS through various devices, such as video cameras, mobile phones, or AR goggles (i.e., Microsoft HoloLens 2), for automated detection of deficiencies in scaffolding assemblies. The training test yielded satisfactory results, with a mean average precision of 0.89 and individual precision values of 0.96, 0.82, 0.90, and 0.89 for “qualified” frames and frames with the “missing cross-tie rod,” “missing lower-tie rod,” and “missing footboard” deficiencies, respectively. Field tests conducted at two construction sites demonstrated improved system performance compared to that in the training test. However, these field tests also revealed certain limitations of the SADDS system.

COVID-19 was a terrible worldwide pandemic that caused a global public health crisis, with numerous deaths and a severe economic depression. To suppress the spread of COVID-19 and initiate patient isolation and contact tracing to reduce its effect, early diagnosis was required, with real-time reverse transcriptase polymerase chain reaction (RT-PCR) swab test being the most widely used. However, the RT-PCR test was sometimes found to be lengthy and inaccurate and; for that reason, in many cases of severe complications of COVID-19 pneumonia, chest screening with radiography imaging was preferred. In this paper, we carried out a study for COVID-19 detection from computed tomography images, and compared the obtained results using deep learning (DL) and support vector machine (SVM). The findings showed that, despite the excellent results shown by deep learning, the accuracy in predicting COVID-19 using SVM, in the presence of small databases, was slightly higher than DL. The execution time using SVM was also shorter

Over the past decade, Deep Learning (DL) had been applied in a large number of optical sensors’ applications. DL algorithms can improve the accuracy and reduce the noise level in optical sensors. Optical sensors are considered as promise technology for the modern intelligent sensing platforms. These sensors are widely used to process monitoring, quality prediction, pollution, defense, security and many other applications. However, they suffer major challenges such as the large generated data and low processing speed for that data and moreover the much cost of these sensor. These challenges can be mitigated by integrating deep learning system with the optical sensor technologies. This paper presents recent studies that integrate DL algorithms with optical sensors applications. This paper also highlights several of DL algorithms directions that promise a considerable impact on use for optical sensor applications. Moreover, this study provides new directions for the future related research development.

Machine learning (ML) has emerged as a critical tool for making sense of the growing amount of genetic and genomic data available because of its ability to find complex patterns in high dimensional and heterogeneous data. While the complexity of ML models is what makes them powerful, it also makes them difficult to interpret. Fortunately, recent efforts to develop approaches that make the inner workings of ML models understandable to humans have improved our ability to make novel biological insights using ML. Here we discuss the importance of interpretable ML, different strategies for interpreting ML models, and examples of how these strategies have been applied. Finally, we identify challenges and promising future directions for interpretable ML in genetics and genomics.

Continuous greenhouse gas emissions are causing global warming and impacting the habitats of many animals. Researchers in the field of electric power are making efforts to mitigate this situation. Operating and maintaining the power grid in an economic, low-carbon, and stable is challenging. To address the issue, we propose a grid dispatching technique that combines prediction technology, reinforcement learning, and optimization technology. Prediction technology can forecast future power demand and solar power generation, while reinforcement learning and optimization technology can make charging and discharging decisions for energy storage devices based on current and future grid conditions. In the power system, the aggregation of distributed energy resources increases uncertainty, particularly due to the fluctuating generation of renewable energy. This requires the use of advanced predictive control techniques to ensure long-term economic and decarbonization goals. In this paper, we present a real-time dispatching framework that integrates deep learning-based prediction, reinforcement learning-based decision-making, and stochastic optimization techniques. The framework can rapidly adapt to target uncertainty caused by various factors in real-time data distribution and control processes. The proposed framework achieved global Champion in the NeurIPS Challenge 2022 competition and demonstrated its effectiveness in practical scenarios of intelligent building energy management.

Pulsed thermography is a vital technique in the nondestructive evaluation field. However, its data analysis can be complex and requires skilled experts. Advances in deep learning have yielded exceptional results, including image segmentation. Therefore, many efforts have been made to apply deep learning methods to data processing for nondestructive evaluation. Despite this, there is currently no public Pulsed thermographic dataset available for evaluating various spatial-temporal deep methods of segmenting pulsed thermographic data. This article aims to provide such a dataset and assess the performance of commonly used deep learning-based instance segmentation models on it. Additionally, the impact of the number of frames and data transformations on model performance is examined. The findings suggest that suitable preprocessing methods can effectively reduce the data size without compromising the deep models’ performance.

Magnetic resonance imaging (MRI) is crucial for its superior soft tissue contrast and high spatial resolution. Integrating deep learning algorithms into MRI reconstruction enhances image quality and efficiency, but a comprehensive review of optimization-based deep learning models for MRI reconstruction has been missing. This study fills that gap by examining the latest optimization-based algorithms in deep learning for MRI reconstruction, including gradient descent algorithms, proximal gradient descent algorithms, ADMM, PDHG, and diffusion models combined with gradient descent. Learnable optimization algorithms (LOA) are highlighted for their ability to map optimization processes to structured neural networks, improving model interpretability and performance. The study demonstrates significant advancements in MRI reconstruction through deep learning, with successful clinical applications. These findings provide valuable insights and resources for researchers aiming to advance medical imaging using innovative deep learning techniques.

In recent years the field of computer science has experienced great changes, due to the incredible advances in the field of artificial intelligence. Deep Learning models are responsible for most of them since the biggest milestones occurred in 2012 when AlexNet won the image classification challenge called ImageNet. These models have demonstrated great performances in different types of complex tasks like image restoration, medical diagnosis or object recognition. Their disadvantages are related to their high data dependency, which forces experts in the field to follow a precise methodology to obtain accurate models. In this paper, we describe a complete workflow that begins with the management of the raw data until the in-depth interpretation of the performance of the models. This should be taken as a high-level consultation document describing good practices that should be applied. Apart from the step-by-step methodology, we present different use cases that correspond to the two main problems of the field: classification and regression.

The betatron tune in the Large Hadron Collider (LHC) is measured using a Base-Band Tune (BBQ) system. The processing of these BBQ signals is often perturbed by 50 Hz noise harmonics present in the beam. This causes the tune measurement algorithm, currently based on peak detection, to provide incorrect tune estimates during the acceleration cycle with values that oscillate between neighbouring harmonics. The LHC tune feedback (QFB) cannot be used to its full extent in these conditions as it relies on stable and reliable tune estimates. In this work we propose new tune estimation algorithms, designed to mitigate this problem through different techniques. As ground-truth of the real tune measurement does not exist, we developed a surrogate model, which allowed us to perform a comparative analysis of a simple weighted moving average, Gaussian Processes and different deep learning techniques. The simulated dataset used to train the deep models was also improved using a variant of Generative Adversarial Networks (GANs) called SimGAN. In addition we demonstrate how these methods perform with respect to the present tune estimation algorithm.

Intracranial hemorrhage is a serious medical problem that requires rapid and often intensive medical care. Identifying the location and type of any hemorrhage present is a critical step in the treatment of the patient. Diagnosis requires an urgent procedure, and the detection of hemorrhage is a difficult and time-consuming process for human experts. In this paper, we propose methods based on EfficientDet’s deep-learning technology that can be applied to the diagnosis of hemorrhages and thus become a decision-support system. Our proposal is two-fold. On the one hand, the proposed technique classifies slices of computed tomography scans for the presence hemorrhage or its lack, achieving 92.7% accuracy and 0.978 ROC-AUC. On the other hand, our methodology provides visual explanations of the classification chosen using the Grad-CAM methodology.

Investigation of functional magnetic resonance imaging (fMRI) data with machine learning (ML) techniques, including also deep learning (DL) methods, have been widely used to study Autism Spectrum Disorder (ASD). This disorder is characterized by symptoms that affect the individual’s behavioral aspects and social relationships. Early diagnosis is crucial for intervention, but the complexity of ASD poses challenges for treatment development. This study compares traditional ML techniques with deep learning (DL) methods in the analysis of functional connectivity measures obtained from the time series of multicentric ABIDE dataset. Specifically, Support Vector Machines (SVM) classifiers, with both linear and Radial Basis Function (RBF) kernels, as well as eXtreme Gradient Boosting (XGBoost) classifiers, are compared against the TabNet classifier, which is a DL architecture customized for tabular data analysis and a Multi Layer Perceptron (MLP). The findings suggest that DL classifiers may not be optimal for the type of data analyzed, as their performance trails behind that of standard classifiers. SVMs achieve performances, in terms of AUC, around 75%, compared to the best TabNet and MLP results, which are 65% and 71%, respectively. Additionally, this work investigates the brain regions that contribute most to the classification task, which are found to be those primarily responsible for sensory and spatial perception, as well as attention modulation, known to be altered in ASD.

Accurate segmentation of the Left Ventricle (LV) in Echocardiogram (Echo) images is essential for cardiovascular analysis. Conventional techniques are labor-intensive and exhibit inter-observer variability. Deep learning has emerged as a powerful tool for automated medical image segmentation, offering advantages in speed and potentially superior accuracy. This study explores the efficacy of employing the YOLO (You Only Look Once) segmentation model for automated LV segmentation in Echo images. YOLO, a cutting-edge object detection model, achieves exceptional speed-accuracy balance through its well-designed architecture. It utilizes efficient dilated convolutional layers and bottleneck blocks for feature extraction, while incorporating innovations like path aggregation and spatial attention mechanisms. These attributes make YOLO a compelling candidate for adaptation to LV segmentation in Echo images. We posit that by fine-tuning a pre-trained YOLO based model on a well-annotated Echo image dataset, we can leverage the model's strengths in real-time processing and precise object localization to achieve robust LV segmentation. The proposed approach entails fine-tuning a pre-trained YOLO model on a rigorously labeled Echo image dataset. Model performance has been evaluated using established metrics such as mean Average Precision (mAP) at an Intersection over Union (IoU) threshold of 50% (mAP50) with 98.31%and across a range of IoU thresholds from 50% to 95% (mAP50:95) with 75.27%. Successful implementation of YOLO for LV segmentation has the potential to significantly expedite and standardize Echo image analysis. This advancement could translate to improved clinical decision-making and enhanced patient care.

Unmanned aerial vehicle (UAV) photogrammetry allows the generation of orthophoto and digital surface model (DSM) rasters of a terrain. However, DSMs of water bodies mapped using this technique often reveal distortions in the water surface, thereby impeding the accurate sampling of water surface elevation (WSE) from DSMs. This study investigates the capability of deep neural networks to accommodate the aforementioned perturbations and effectively estimate WSE from photogrammetric rasters. Convolutional neural networks (CNNs) were employed for this purpose. Two regression approaches utilizing CNNs were explored: direct regression employing an encoder and solution based on prediction of the weight mask by an encoder-decoder architecture, subse-quently used to sample values from the photogrammetric DSM. The dataset employed in this study comprises data collected from five case studies of small lowland streams in Poland and Denmark, consisting of 322 DSM and orthophoto raster samples. Each sample corresponds to a 10 by 10 meter area of the stream channel and adjacent land. A grid search was employed to identify the optimal combination of encoder, mask generation architecture, and batch size among multiple candidates. Solutions were evaluated using two cross-validation methods: stratified k-fold cross-validation, where validation subsets maintained the same proportion of samples from all case studies, and leave-one-case-out cross-validation, where the validation dataset originates entirely from a single case study, and the training set consists of samples from other case studies. The proposed solution was compared with existing methods for measuring WSE in small streams using a drone. The results indicate that the solution outperforms previous photogrammetry-based methods and is second only to the radar-based method, which is considered the most accurate method available. The solution is characterized by a high degree of explainability and generalization.

The use of Attitude and Heading Reference Systems (AHRS) for orientation estimation is now common practice in a wide range of applications, e.g., robotics and human motion tracking, aerial vehicles and aerospace, gaming and virtual reality, indoor pedestrian navigation and maritime navigation. The integration of the high-rate measurements can provide very accurate estimates, but these can suffer from errors accumulation due to the sensors drift over longer time scales. To overcome this issue, inertial sensors are typically combined with additional sensors and techniques. As an example, camera-based solutions have drawn a large attention by the community, thanks to their low-costs and easy hardware setup; moreover, impressive results have been demonstrated in the context of Deep Learning. This work presents the preliminary results obtained by DOES , a supportive Deep Learning method specifically designed for maritime navigation, which aims at improving the roll and pitch estimations obtained by common AHRS. DOES recovers these estimations through the analysis of the frames acquired by a low-cost camera pointing the horizon at sea. The training has been performed on the novel ROPIS dataset, presented in the context of this work, acquired using the FrameWO application developed for the scope. Promising results encourage to test other network backbones and to further expand the dataset, improving the accuracy of the results and the range of applications of the method.

Data collection and analysis are becoming more and more important in a variety of application domains as long as the novel technologies advance. At the same time, we are experiencing a growing need for human-machine interaction with expert systems pushing research through new knowledge representation models and interaction paradigms. In particular, in the last years eHealth - that indicates all the health-care practices supported by electronic elaboration and remote communications - calls for the availability of smart environment and big computational resources. The aim of this paper is to introduce the HOLMeS (Health On-Line Medical Suggestions) framework. The introduced system proposes to change the eHealth paradigm where a trained machine learning algorithm, deployed on a cluster-computing environment, provides medical suggestion via both chat-bot and web-app modules. The chat-bot, based on deep learning approaches, is able to overcome the limitation of biased interaction between users and software, exhibiting a human-like behavior. Results demonstrate the effectiveness of the machine learning algorithms showing 74.65% of Area Under ROC Curve (AUC) when first-level features are used to assess the occurrence of different prevention pathways. When disease-specific features are added, HOLMeS shows 86.78% of AUC achieving a more specific prevention pathway evaluation.

The impact of financial risks extends beyond the normal operation and survival of industrial and commercial enterprises and financial institutions. They also have the potential to impede the stable development of a country's and even the world's financial economy. This is clearly demonstrated by the severe consequences of the frequent financial crises that have occurred in recent years. It thus follows that the prevention of financial risks has become one of the core tasks of the operation and management of industrial and commercial enterprises and financial institutions. Portfolio optimization techniques are employed in the construction of a variety of asset allocation models, with reinforcement learning algorithms used to dynamically adjust investment strategies with the objective of maximizing returns and minimizing risks. The preliminary construction of an asset allocation model is achieved through the utilization of a genetic algorithm. Genetic algorithms emulate the processes of natural selection and genetic variation to identify the optimal portfolio of assets that will yield the greatest returns at a pre-established level of risk. Subsequently, the Deep Q-Learning algorithm is introduced to facilitate dynamic adjustments and optimization of the asset allocation, based on the initial construction. Deep Q-learning employs deep neural networks to forecast the prospective returns of disparate investment strategies, thereby optimizing the decision-making process through continuous learning and updating. The combination of genetic algorithms and deep Q-learning enables the system to identify the optimal investment strategy under a diverse range of initial conditions and to adapt it in real-time to respond to market fluctuations and uncertainties. The experimental analysis demonstrates that the proposed method exhibits an exemplary capacity for risk control and a robust ability to generate stable income growth across diverse market environments. In simulation experiments, portfolios constructed using this method demonstrate lower volatility and higher average returns than those generated through traditional methods.

This paper explores the use of different deep learning models for predicting precipitation in 56 meteorological stations in Jilin Province, China. The models used include Stacked-LSTM, Transformer, and SVR, and Gaussian noise is added to the data to improve their robustness. Results show that the Stacked-LSTM model performs the best, achieving high prediction accuracy and stability. The study also conducts variable attribution analysis using LightGBM and finds that temperature, dew point, precipitation in previous days, and air pressure are the most important factors affecting precipitation prediction, which is consistent with traditional meteorological theory. The paper provides detailed information on the data processing, model training, and parameter settings, which can serve as a reference for future precipitation prediction tasks. The findings suggest that adding Gaussian noise to the dataset can improve the model's generalization ability, especially for predicting days with zero precipitation. Overall, this study provides useful insights into the application of deep learning models in precipitation prediction and can contribute to the development of meteorological forecasting and applications.

Automatic and real-time pose estimation is important in monitoring animal behavior, health and welfare. In this paper, we utilized pose estimation for monitoring farrowing process to prevent piglet mortality and preserve the health and welfare of sow. State-of-the-art Deep Learning (DL) methods have lately been used for animal pose estimation. The aim of this paper was to probe the generalization ability of five common DL networks (ResNet50, ResNet101, MobileNet, EfficientNet and DLCRNet) for sow and piglet pose estimation. These architectures predict body parts of several piglets and the sow directly from input video sequences. Real farrowing data from a commercial farm was used for training and validation of the proposed networks. The experimental results demonstrated that MobileNet was able to detect seven body parts of the sow with median test error of 0.61 pixels.

Skin cancer is an uncommon but serious malignancy. Dermoscopic images examination and biopsy are required for cancer detection. Deep learning (DL) is extremely effective in learning characteristics and predicting malignancies. However, DL requires a large number of images to train. Image augmentation and transferring learning were employed to overcome the lack of images issue. In this study we divided images into two categories: benign and malignant. To train and test our models, we used the public ISIC 2020 database. Melanoma is classified as malignant in the ISIC 2020 dataset. Along with categorization, the dataset was studied to demonstrate variation. The performance of three top pretrained models was then benchmarked in terms of training and validation accuracy. Three optimizers were employed to optimize the loss: RMSProp, SGD, and ADAM. Using ResNet, VGG16, and MobileNetV2, we obtained training accuracy of 98.73%, 99.12%, and 99.76%, respectively. Using these three pretrained models, we attained a validation accuracy of 98.39%.

Clinicians are often very sceptical about applying automatic image processing approaches, especially deep learning based methods, in practice. One main reason for this is the black-box nature of these approaches and the inherent problem of missing insights of the automatically derived decisions. In order to increase trust in these methods, this paper presents approaches that help to interpret and explain the results of deep learning algorithms by depicting the anatomical areas which influence the decision of the algorithm most. Moreover, this research presents a unified framework, TorchEsegeta, for applying various interpretability and explainability techniques for deep learning models and generate visual interpretations and explanations for clinicians to corroborate their clinical findings. In addition, this will aid in gaining confidence in such methods. The framework builds on existing interpretability and explainability techniques that are currently focusing on classification models, extending them to segmentation tasks. In addition, these methods have been adapted to 3D models for volumetric analysis. The proposed framework provides methods to quantitatively compare visual explanations using infidelity and sensitivity metrics. This framework can be used by data scientists to perform post-hoc interpretations and explanations of their models, develop more explainable tools and present the findings to clinicians to increase their faith in such models. The proposed framework was evaluated based on a use case scenario of vessel segmentation models trained on Time-of-fight (TOF) Magnetic Resonance Angiogram (MRA) images of the human brain. Quantitative and qualitative results of a comparative study of different models and interpretability methods are presented. Furthermore, this paper provides an extensive overview of several existing interpretability and explainability methods.

Mineral identification is an important part of geological analysis. Traditional identification methods rely on either the experiences of the appraisers or the various measuring instruments and the methods are either easily influenced by the experiences or need too much work. To solve the above problems, there have been studies using image recognition and intelligent algorithms to identify minerals. But the current studies can not identify many minerals, and the accuracy is low. To increase the number of identified mineral categories and the accuracy, we proposed the method that uses both the mineral images and the Mohs hardness in the deep neural networks to identify the minerals. The experimental results showed that the method can reach 94.0% Top-1 accuracy and 99.9% Top-5 accuracy for 28 common minerals. The model that combines image and Mohs hardness together can identify more minerals and increase the accuracy using less training data.

During the last few years, several approaches have been proposed to improve early warning systems for reducing rock-fall risk. In this regard, this paper introduces a Deep learning-and (IoT) based Framework for Rock-fall Early Warning, devoted to reducing the rock-fall risk with high accuracy. In this framework, the prediction accuracy was augmented by eliminating the uncertainties and confusion plaguing the prediction model. In order to achieve augmented prediction accuracy, this framework fused the prediction model-based deep learning with a detection model-based Internet of Things. In order to determine the framework’s performance, this study adopted parameters, namely overall prediction performance measures, based on a confusion matrix and the ability to reduce the risk. The result indicates an increase in prediction model accuracy from 86% to 98.8%. In addition, a framework reduced the risk probability from (1.51 ×10-3) to (8.57 ×10-9). Our results indicate the framework’s high prediction accuracy; it also provides a robust decision-making process for delivering early warning and lowering the rock-fall risk probability.

This study presents the development and evaluation of a Multi-Task Long Short-Term Memory (LSTM) model with an Attention Mechanism designed to predict students' academic performance. The model concurrently addresses two tasks: predicting overall performance (total score) as a regression task and categorizing performance levels (remarks) as a classification task. By processing both tasks simultaneously, the model optimizes computational efficiency and resource use. The dataset includes detailed student performance records across various metrics such as Continuous Assessment, Practical Skills, Demeanor, Presentation Quality, Attendance, and Participation. The model's performance was evaluated using comprehensive metrics. For the regression task, it achieved a Mean Absolute Error (MAE) of 0.0249, Mean Squared Error (MSE) of 0.0012, and Root Mean Squared Error (RMSE) of 0.0346. For the classification task, it attained perfect scores with an accuracy, precision, recall, and F1 score of 1.0. These results highlight the model's high accuracy and robustness in predicting both continuous and categorical outcomes. The Attention Mechanism enhances the model's capabilities by identifying and focusing on the most relevant features. This study demonstrates the effectiveness of the Multi-Task LSTM with Attention Mechanism in educational data analysis, offering a reliable tool for predicting student performance and potential broader applications in similar multi-task learning contexts. Future work will explore further enhancements and wider applications to improve predictive accuracy and efficiency.

The steep rise in reinforcement learning (RL) in various applications in energy as well as the penetration of home automation in recent years are the motivation for this article. It surveys the use of RL in various home energy management system (HEMS) applications. There is a focus on deep neural network (DNN) models in RL. The article provides an overview of reinforcement learning. This is followed with discussions on state-of-the-art methods for value, policy, and actor–critic methods in deep reinforcement learning (DRL). In order to make the published literature in reinforcement learning more accessible to the HEMS community, verbal descriptions are accompanied with explanatory figures as well as mathematical expressions using standard machine learning terminology. Next, a detailed survey of how reinforcement learning is used in different HEMS domains is described. The survey also considers what kind of reinforcement learning algorithms are used in each HEMS application. It suggests that research in this direction is still in its infancy. Lastly, the article proposes four performance metrics to evaluate RL methods.

Estimating precipitation is of critical importance to climate systems and decision-making processes. This paper presents Espresso, a deep learning model designed for estimating precipitation from satellite observations on a global scale. Conventional methods, like ground-based radars, are limited in terms of spatial coverage. Satellite observations, on the other hand, allow global coverage. Combined with deep learning methods these observations offer the opportunity to address the challenge of estimating precicpation on a global scale. This research paper presents the development of a deep learning model using geostationary satellite data as input and generating instantaneous rainfall rates, calibrated using data from the Global Precipitation Measurement Core Observatory (GPMCO). The performance impact of various input data configurations on Espresso was investigated. These configurations include a sequence of four images from geostationary satellites and the optimal selection of channels. Additional descriptive features were explored to enhance the model’s robustness for global aplications. When evaluated against the GPMCO test set, Espresso demonstrated highly accurate precipitation estimation, especially within equatorial regions. A comparison against six other operational products using multiple metrics indicated its competitive performance. The model’s superior storm localization and intensity estimation were further confirmed through visual comparisons in case studies. Espresso has been incorporated as an operational product at Météo-France, delivering high-quality, real-time global precipitation estimates every 30 minutes.

Sentiment analysis is a process of extracting opinions into the positive, negative, or neutral categories from a pool of text using Natural Language Processing (NLP). In the recent era, our society is swiftly moving towards virtual platforms by joining virtual communities. Social media such as Facebook, Twitter, WhatsApp, etc are playing a very vital role in developing virtual communities. A pandemic situation like COVID-19 accelerated people's involvement in social sites to express their concerns or views regarding crucial issues. Mining public sentiment from these social sites especially from Twitter will help various organizations to understand the people's thoughts about the COVID-19 pandemic and to take necessary steps as well. To analyze the public sentiment from COVID-19 tweets is the main objective of our study. We proposed a deep learning architecture based on Bidirectional Gated Recurrent Unit (BiGRU) to accomplish our objective. We developed two different corpora from unlabelled and labeled COVID-19 tweets and use the unlabelled corpus to build an improved labeled corpus. Our proposed architecture draws a better accuracy of 87% on the improved labeled corpus for mining public sentiment from COVID-19 tweets.

Sentiment analysis of public opinion expressed in social networks has been developed into various applications, especially in English. Hybrid approaches are potential models for reducing sentiment errors on increasingly complex training data. This paper aims to test some hybrid deep learning models' reliability in some domains' Vietnamese language. Our research questions are to determine whether it is possible to produce hybrid models that outperform the Vietnamese language. Hybrid deep sentiment-analysis learning models are built and tested on reviews and feedback of the Vietnamese language. The hybrid models outperformed the accuracy of Vietnamese sentiment analysis on Vietnamese datasets. It contributes to the growing body of research on Vietnamese NLP, providing insights and directions for future studies in this area.

Computer vision methods have shown to be effective in classifying garbage into recycling categories for waste processing, existing methods are costly, imprecise, and unclear. To tackle this issue, we introduce MWaste, a mobile application that uses computer vision and deep learning techniques to classify waste materials as trash, plastic, paper, metal, glass or cardboard. Its effectiveness was tested on various neural network architectures and real world images, achieving an average precision of 92% on the test set. This app can help combat climate change by enabling efficient waste processing and reducing the generation of greenhouse gases caused by incorrect waste disposal.

To generate a probability density function (PDF) for fitting probability distributions of real data, this study proposes a deep learning method which consists of two stages: (1) a training stage for estimating the cumulative distribution function (CDF) and (2) a performing stage for predicting the corresponding PDF. The CDFs of common probability distributions can be adopted as activation functions in the hidden layers of the proposed deep learning model for learning actual cumulative probabilities, and the differential equation of trained deep learning model can be used to estimate the PDF. To evaluate the proposed method, numerical experiments with single and mixed distributions are performed. The experimental results show that the values of both CDF and PDF can be precisely estimated by the proposed method.

Deep Neutral Networks (DNNs) were initially proposed towards the midst of the 20th century, motivated by the neural structure and mechanism of the human brain. Thanks to major ad-vancements in computational resources, during the past decade DNN-based systems have demonstrated unprecedented performance in terms of accuracy and speed. However, recent work has shown that such models may not be sufficiently robust during the inference process. Furthermore, due to the data-driven learning nature of DNNs, designing interpretable and gen-eralizable networks is a major challenge, especially in critical applications, such as medical Computer Aided Diagnostics (CAD) and other medical imaging tasks, including classification, regression and reconstruction. Within this context, a line of physics-driven approaches for deep learning has recently emerged, aimed at improving the stability and generalization capacity of DNNs for medical imaging applications. In this paper, we review recent work focused on phys-ics-driven or prior-information learning for a variety of imaging modalities and medical applica-tions. We discuss how the inclusion of domain-related knowledge into the learning process and networks’ design supports their stability and generalization capability. In addition, we highlight current and future challenges within this scope.

The transportation industry is rapidly transitioning from Internal Combustion Engine (ICE) based vehicles to Electric Vehicles (EVs) to promote clean energy. However, large-scale adoption of EVs can compromise the reliability of the power grids by introducing large uncertainty in the demand. Demand response with a controlled charge scheduling strategy for EVs can mitigate such issues. In this paper, a deep reinforcement learning- based charge scheduling strategy is developed for individual EVs by considering user’s dynamic driving behavior and charging preferences. The temporal dynamics of user’s anxiety about charging the EV battery is rigorously addressed. A dynamic weight allocation technique is applied to continuously tune user’s priority for charging and cost-saving with respect to charging duration. The sequential charging control problem is formulated as a Markov decision process, and an episodic approach to the deep deterministic policy gradient (DDPG) algorithm with target policy smoothing and delayed policy update techniques is applied to develop the optimal charge scheduling strategy. A real-world dataset that captures user’s driving behavior, such as arrival time, departure time, and charging duration, is utilized in this study. The extensive simulation results reveal the effectiveness of the proposed algorithm in minimizing energy cost while satisfying user’s charging requirements.

The intrinsic non-linearity and complexity of suspended sediment dynamics, which are impacted by the geographical variability of basin parameters and temporal climatic patterns, make it difficult to estimate suspended sediment concentration (SSC) accurately in hydrological processes. Deep neural networks (DNNs), a cutting-edge modeling method that can capture the innate non-linearity in hydrological systems, have emerged as a solution to this problem. Using primary data on discharge, SSC, and turbidity, the long short-term memory method of DNNs was employed in this study to simulate the discharge-suspended sediment connection for the Esopus Creek, NY, USA as the first objective. To develop effective modeling strategies, multiple scenarios of feature selection, including combinations of discharge, turbidity and SSC for preceding days, were considered. Secondly, the variations in SSC and discharge between the three USGS gages along Esopus Creek that were upper stream, lower stream, and downstream, adjacent to the pourpoint were analyzed. Statistical metrics and scenarios of feature importance were used to evaluate the effectiveness of the DNN-based models. The study shows that among 24 DNN approaches feature selection is crucial in simulating the daily SSC, and discharge and presenting novel research directions for utilizing machine learning algorithms in water quality.

Face recognition is a valuable forensic tool for criminal investigators since it certainly helps in identifying individuals in scenarios of criminal activity like fugitives or child sexual abuse. It is, however, a very challenging task as it must be able to handle low-quality images of real world settings and fulfill real time requirements. Deep learning approaches for face detection have proven to be very successful but they require a large computation power and processing time. In this work, we evaluate the speed-accuracy tradeoff of three popular deep-learning-based face detectors on the WIDER Face and UFDD data sets in several CPUs and GPUs. We also develop a regression model capable to estimate the performance, both in terms of processing time and accuracy. We expect this to become a very useful tool for the end user in forensic laboratories in order to estimate the performance for different face detection options. Experimental results showed that the best speed-accuracy tradeoff is achieved with images resized to 50% of the original size in GPUs and images resized to 25% of the original size in CPUs. Moreover, performance can be estimated using multiple linear regression models with a Mean Absolute Error (MAE) of 0.113 what is very promising for the forensic field.

This last decade, the amount of data exchanged in the Internet increased by over a staggering factor of 100, and is expected to exceed well over the 500 exabytes by 2020. This phenomenon is mainly due to the evolution of high speed broadband Internet and, more specifically, the popularization and wide spread use of smartphones and associated accessible data plans. Although 4G with its long-term evolution (LTE) technology is seen as a mature technology, there is continual improvement to its radio technology and architecture such as in the scope of the LTE Advanced standard, a major enhancement of LTE. But for the long run, the next generation of telecommunication (5G) is considered and is gaining considerable momentum from both industry and researchers. In addition, with the deployment of the Internet of Things (IoT) applications, smart cities, vehicular networks, e-health systems, and Industry 4.0, a new plethora of 5G services has emerged with very diverging and technologically challenging design requirements. These include: high mobile data volume per area, high number of devices connected per area, high data rates, longer battery life for low-power devices, and reduced end-to-end latency. Several technologies are being developed to meet these new requirements. Among these we list ultra-densification, millimeter Wave usage, antennas with massive multiple-input multiple-output (MIMO), antenna beamforming to increase spacial diversity, edge/fog computing, among others. Each of these technologies brings its own design issues and challenges. For instance, ultra-densification and MIMO will increase the complexity to estimate channel condition and traditional channel state information (CSI) estimation techniques are no longer suitable due to the complexity of the new scenarios. As a result, new approaches to evaluate network condition such as by continuously collecting and monitoring key performance indicators become necessary. Timely decisions are needed to ensure the correct operation of such network. In this context, deep learning (DL) models could be seen as one of the main tools that can be used to process monitoring data and automate decisions. As these models are able to extract relevant features from raw data (images, texts, and other types of unstructured data), the integration between 5G and DL looks promising and one that requires exploring. As main contributions, this paper presents a systematic review about how DL is being applied to solve some 5G issues. We examine data from the last decade and the works that addressed diverse 5G problems, such as physical medium state estimation, network traffic prediction, user device location prediction, self network management, among others. We also discuss the main research challenges when using DL models in 5G scenarios and identify several issues that deserve further consideration.

Clinically, knowing the number of red blood cells (RBCs) and white blood cells (WBCs) helps doctors to make the better decision on accurate diagnosis of numerous diseases. The manual cell counting is a very time-consuming and expensive process, and it depends on the experience of specialists. Therefore, a completely automatic method supporting cell counting is a viable solution for clinical laboratories. This paper proposes a novel blood cell counting procedure to address this challenge. The proposed method adopts SegNet - a deep learning semantic segmentation to simultaneously segment RBCs and WBCs. The global accuracy of the segmentation of WBCs, RBCs, and the background of peripheral blood smear images obtains 89% when segment WBCs and RBCs from the background of blood smear images. Moreover, an effective solution to separate grouped or overlapping cells and cell count is presented using Euclidean distance transform, local maxima, and connected component labeling. The counting result of the proposed procedure achieves an accuracy of 93.3% for red blood cell count using dataset 1 and 97.38% for white blood cell count using dataset 2.

Recently, generative adversarial networks (GANs) can be used to generate the photo-realistic image from a low-dimension random noise. It is very dangerous that the synthesized or generated image is used on inappropriate contents in social media network. In order to successfully detect such fake image, an effective and efficient image forgery detector is desired. However, conventional image forgery detectors are failed to recognize the synthesized or generated images by using GAN-based generator since they are all generated but manipulation from the source. Therefore, we propose a deep learning-based approach to detect the fake image by combining the contrastive loss. First, several state-of-the-art GANs will be collected to generate the fake-real image pairs. Then, the contrastive will be used on the proposed common fake feature network (CFFN)to learn the discriminative feature between the fake image and real image (i.e., paired information). Finally, a smaller network will be concatenated to the CFFN to determine whether the feature of the input image is fake or real. Experimental results demonstrated that the proposed method significantly outperforms other state-of-the-art fake image detectors.

Ultrasound (US) is commonly used for the diagnosis of liver masses. Ensemble learning has been widely used for image classification, but its methods have not been fully optimized. This study was performed to investigate the usefulness of ensemble learning and compare a number of ensemble learning techniques using multiple convolutional neural network (CNN)-trained models for image classification of liver masses in US images. The US imaging data set was classified into four categories: benign liver tumor (BLT, 6320 images), liver cyst (LCY, 2320 images), metastatic liver cancer (MLC, 9720 images), and primary liver cancer (PLC, 7840 images). In this study, 250 test images were randomly selected for each class, for a total of 1000 images, and the remaining images were used for training. Sixteen different CNNs were used for to train and test the US images. All four types of ensemble learning—soft voting (SV), stacking (ST), weighted average voting (WAV), and weighted hard voting (WHV)—showed greater accuracy than the single CNN. All four types also showed significantly better deep learning performance than ResNeXt101 alone. For image classification of liver masses using US images, ensemble learning improved the performance of deep learning over a single CNN.

Advances in computing technology provide an opportunity to grow and develop an effective crop protection system. This study is a new way of diagnosing plant diseases using a deep and convolutional neural network. Deep learning is the strengthened method of machine learning. It uses a neural network that imitates like a human brain and gains certain information. Although powerful, its training process necessitates millions of tagged data points. The study's Methodology consists of three key stages: data acquisition, pre-processing, and Model Building.

In this review we summarize existing trends of flow control used to improve the aerodynamic efficiency of wings. We first discuss active methods to control turbulence, starting with flat-plate geometries and building towards the more complicated flow around wings. Then, we discuss active approaches to control separation, a crucial aspect towards achieving high aerodynamic efficiency. Furthermore, we highlight methods relying on turbulence simulation, and discuss various levels of modelling. Finally, we thoroughly revise data-driven methods, their application to flow control, and focus on deep reinforcement learning (DRL). We conclude that this methodology has the potential to discover novel control strategies in complex turbulent flows of aerodynamic relevance.

PurposeThe purpose of this research was the development and evaluation of an intelligent assistive classification system for the recognition of endometriosis and the improvement of the accuracy of laparoscopic imaging in diagnosis. The research was developed with the use of Deep Learning approaches. Methods Data from 4448 laparoscopy images were used in a retrospective chart analysis. The data were divided into two folders, healthy and pathological including 2157 healthy and 2291 pathological images. Based on simple clinical and imaging information and criteria such as the diagnosis of endometriosis (included in an open-source dataset GLENDA of Kaggle repository), data mining algorithms were used to improve laparoscopic imaging accuracy. Results The final developed computer system based on the ResNet50 algorithm predicted the best outcome for all participants who had laparoscopic surgical therapy. The Keras tool was used and the generated code was implemented in Python programming language providing a mean accuracy of > 95 %. Conclusion The intelligent approach revealed better performance than the commonly used imaging criteria in predicting endometriosis improving the time and the total accuracy of diagnostic approaches.

The increasing use of deep learning techniques to manipulate images and videos, commonly referred to as "deepfakes," is making more and more challenging to differentiate between real and fake content. While various deepfake detection systems have been developed, they often struggle to detect deepfakes in real-world situations. In particular, these methods are often unable to effectively distinguish images or videos when these are modified using novel techniques which have not been used in the training set. In this study, we carry out an analysis of different deep learning architectures in an attempt to understand which is more capable of better generalizing the concept of deepfake. According to our results, it appears that Convolutional Neural Networks (CNNs) seem to be more capable of storing specific anomalies and thus excel in cases of datasets with a limited number of elements and manipulation methodologies. The Vision Transformer, conversely, is more effective when trained with more varied datasets, achieving more outstanding generalization capabilities than the other methods analysed. Finally, the Swin Transformer appears to be a good alternative for using an attention-based method in a more limited data regime. All the analyzed architectures seem to have a different way to look at deepfakes but since in a real-world environment, the generalization capability is essential, based on the carried out experiments the Vision Transformer seems to provide superior performances.

While visual assessment is the standard technique for burn evaluation, computer-aided diagnosis is increasingly sought due to high number of incidences globally. Patients are increasingly facing challenges which are not limited to shortage of experienced clinicians, lack of accessibility to healthcare facilities, and high diagnostic cost. Certain number of studies were proposed in discriminating burn and healthy skin using machine learning leaving a huge and important gap unaddressed; whether burns and related skin injuries can be effectively discriminated using machine learning techniques. Therefore, we specifically use pre-trained deep learning models due to deficient dataset to train a new model from scratch. Experiments were extensively conducted using three state-of-the-art pre-trained deep learning models that includes ResNet50, ResNet101 and ResNet152 for image patterns extraction via two transfer learning strategies: fine-tuning approach where dense and classification layers were modified and trained with features extracted by base layers, and in the second approach support vector machine (SVM) was used to replace top-layers of the pre-trained models, trained using off-the-shelf features from the base layers. Our proposed approach records near perfect classification accuracy of approximately 99.9%.

In the field of low power wireless networks, one of the techniques on which many researchers are putting their efforts is related to positioning methodologies such as fingerprinting in dense urban areas. This paper presents an experimental study aimed at quantifying the mean location estimation error in densely urbanized areas.Using a dataset made available by the University of Antwerp, a neural network was implemented with the aim of providing the position of the end-devices. In this way it was possible to measure the mean location estimation error in an area with high urban density. The results obtained show an accuracy in the localization of the end-device of less than 150 meters.This result would make it possible to use the fingerprint instead of alternative, energy consuming, methodologies such as GPS in IoT (Internet of Things) applications where battery life is the primary requirement to be met.

Accurate and timely prediction of Napa cabbage (Brissica rapa subsp. Perkinensis) fresh weight is crucial for optimizing harvest timing, crop management, and supply chain logistics, contributing to food security and price stabilization. Traditional manual sampling methods are labor-intensive and imprecise. This study addresses this challenge by developing a comprehensive (artificial intelligence) AI-powered model for predicting Napa cabbage fresh weight using unmanned aerial vehicle (UAV)-based multi-sensor data. High-resolution RGB, multispectral, and thermal infrared (TIR) imagery were collected over a Napa cabbage field throughout the 2020 growing season. Various vegetation indices, crop features (vegetation fraction, crop height model), and water stress indi-cators (CWSI) were extracted from the imagery. Three AI algorithms—deep neural network (DNN), support vector machine (SVM), and random forest (RF)—were trained and evaluated, with the DNN model consistently outperforming the others. The DNN model achieved the highest accuracy (R² = 0.86 for training, 0.82 for testing; root mean square error (RMSE) = 0.432 kg for training, 0.465 kg for testing) during the mid-to-late rosette growth stage (DAP 35-42), highlighting this period as crucial for fresh weight estimation due to stable leaf area and well-developed canopy structure. The model tended to underestimate the weight of Napa cabbages exceeding 5 kg, potentially due to limited samples and saturation effects of vegetation indices. However, the overall error rate was less than 5%, demonstrating the feasibility and effectiveness of this approach. Spatial analysis revealed that the model accurately captured the variability in Napa cabbage growth across different soil types and irrigation conditions, particularly reflecting the positive impact of drip irrigation on the sandy loam plot. Bias analysis indicated the DNN model's tendency to overestimate smaller Napa cabbages (2 kg), suggesting areas for future refinement. This study demonstrates the potential of UAV-based multi-sensor data and AI algorithms for accurate and non-invasive prediction of Napa cabbage fresh weight. The developed DNN model offers a promising tool for optimizing harvest timing, improving crop management practices, and en-hancing supply chain efficiency. Future research should focus on refining the model for specific weight ranges and diverse environmental conditions, as well as extending its application to other crops, to further advance precision agriculture and contribute to sustainable food production.

Deep learning (DL) and machine learning (ML) methods have recently contributed to the advancement of models in the various aspects of prediction, planning, and uncertainty analysis of smart cities and urban development. This paper presents the state of the art of DL and ML methods used in this realm. Through a novel taxonomy, the advances in model development and new application domains in urban sustainability and smart cities are presented. Findings reveal that five DL and ML methods have been most applied to address the different aspects of smart cities. These are artificial neural networks; support vector machines; decision trees; ensembles, Bayesians, hybrids, and neuro-fuzzy; and deep learning. It is also disclosed that energy, health, and urban transport are the main domains of smart cities that DL and ML methods contributed in to address their problems.

Late-onset Alzheimer’s disease (LOAD) is a dementia category disease that starts after the age of 65. Progressive problems in thinking, behaviour, learning etc. are its characteristics. Due to its progressive nature, early diagnosis is crucial. A complex pathway mechanism with different risk factors is involved in LOAD progression. A comprehensive study is done on factors causing LOAD, biomarkers used for diagnosis in clinical and preclinical stage of the disease, ML (Machine Learning) techniques to identify disease stage. We reviewed research papers on clinical and preclinical diagnosis of LOAD using ML techniques from biomarker data: MRI, PET image, MMSE, Genome / Gene expression, DNA / RNA binding sites with protein, Epigenetic expression /DNA, methylation, Speech and text. We have listed improvement scope after finding the gaps and scope of using Generative AI and SMOTE (Synthetic Minority Oversampling Technique) for data augmentation. At the end, we have elaborated current use of DL (Deep Learning) and CNN (‘Convolution Neural Network’) in Alzheimer’s disease (AD) diagnosis.

This study employs the reflection symmetry decomposition (RSD) method to extract polarization scattering features from ground object images, aiming to determine the optimal data input scheme for deep learning networks in polarimetric synthetic aperture radar classification. Eight distinct polarizing feature combinations are designed, and the classification accuracy of various approaches is evaluated using the classic convolutional neural networks(CNNs) AlexNet and VGG16. The findings reveal that the commonly employed 6-parameter input scheme, favored by many researchers, lacks the comprehensive utilization of polarization information and warrants attention. Intriguingly, leveraging the complete 9-parameter input scheme based on the polarization coherence matrix results in improved classification accuracy. Furthermore, the input scheme incorporating all 21 parameters from the RSD and polarization coherence matrix notably enhances overall accuracy and the Kappa coefficient compared to the other 7 schemes. This comprehensive approach maximizes the utilization of polarization scattering information from ground objects, emerging as the most effective CNN input data scheme in this study. Additionally, the classification performance using the second and third component total power values (P2 and P3) from the RSD surpasses the approach utilizing surface scattering power value (PS) and secondary scattering power value (PD) from the same decomposition.

In this paper, we present a novel approach for text independent phone-to-audio alignment based on phoneme recognition, representation learning and knowledge transfer. Our method leverages a self-supervised model (wav2vec2) fine-tuned for phoneme recognition using a Connectionist Temporal Classification (CTC) loss, a dimension reduction model and a frame-level phoneme classifier trained thanks to forced-alignment labels (using Montreal Forced Aligner) to produce multi-lingual phonetic representations, thus requiring minimal additional training. We evaluate our model using synthetic native data from the TIMIT dataset and the SCRIBE dataset for American and British English, respectively. Our proposed model outperforms the state-of-the-art (charsiu) in statistical metrics and has applications in language learning and speech processing systems. We leave experiments on other languages for future work but the design of the system makes it easily adaptable to other languages.

Identifying dust aerosols from passive satellite images is of great interest for many applications. In this study, we developed 5 different machine-learning (ML) and deep-learning (DL) based algorithms, including Logistic Regression, K Nearest Neighbor, Random Forest (RF), Feed Forward Neural Network (FFNN), and Convolutional Neural Network (CNN), to identify dust aerosols in the daytime satellite images from the Visible Infrared Imaging Radiometer Suite (VIIRS) under cloud-free conditions on a global scale. In order to train the ML and DL algorithms, we collocated the state-of-the-art dust detection product from the Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) with the VIIRS observations along the CALIOP track. The 16 VIIRS M-band observations with the center wavelength ranging from deep blue to thermal infrared, together with solar-viewing geometries and pixel time and locations, are used as the predictor variables. Four different sets of training input data are constructed based on different combinations of VIIRS pixel and predictor variables. The validation and comparison results based on the collocated CALIOP data indicates that the FFNN method based on all available predictor variables is the best performing one among all methods. It has an averaged dust detection accuracy of about 81 %, 89 % and 85 % over land, ocean and whole globe, respectively, compared with collocated CALIOP. When applied to off-track VIIRS pixels, the FFNN method retrieves geographical distributions of dust that are in good agreement with on-track results as well as CALIOP statistics. For further evaluation, we compared our results based on the ML and DL algorithms to NOAA’s Aerosol Detection Product (ADP) , which is a product that classifies dust, smoke and ash using physical-based methods. The comparison reveals both similarity and differences. Overall, this study demonstrates the great potential of ML and DL methods for dust detection and proves that these methods can be trained on the CALIOP track and then applied to the whole granule of VIIRS granule.

Fruit quality is a critical factor in the produce industry, affecting producers, distributors, consumers, and the economy. High-quality fruits are more appealing, nutritious, and safe, boosting consumer satisfaction and revenue for producers. Artificial Intelligence can aid in assessing the quality of the fruit using images. This paper presents a general machine-learning model for assessing fruit quality using deep image features. The model leverages the learning capabilities of the recent successful networks for image classification called Vision Transformers (ViT). The ViT model is built and trained with a combination of various fruit datasets and learned to distinguish between good and rotten fruit images. The general model demonstrated impressive results in accurately identifying the quality of various fruits such as Apples (with a 99.50% accuracy), Cucumbers (99%), Grapes (100%), Kakis (99.50%), Oranges (99.50%), Papayas (98%), Peaches (98%), Tomatoes (99.50%), and Watermelons (98%). However, it showed slightly lower performance in identifying Guavas (97%), Lemons (97%), Limes (97.50%), mangoes (97.50%), Pears (97%), and Pomegranates (97%).

Introduction: Dental segmentation in panoramic radiograph has become very relevant in dentistry, since it allows health professionals to carry out their assessments more clearly and helps them to define the best possible treatment plan for their patients. Objectives: In this work, a comparative study is carried out with four segmentation algorithms (U-Net, DCU-Net, DoubleU-Net and Nano-Net) that are prominent in the medical literature on segmentation and we evaluate their results with the current state of the art of dental segmentation in panoramic radiograph. Methods: These algorithms were tested with a dataset consisting of 1,500 images, considering experiment scenarios with and without augmentation data. Results: DoubleU-Net was the model that presented the best results among the analyzed models, reaching 96.591% accuracy and 92.886% Dice using the dataset with data augmentation. Another model that stood out was Nano-Net using the dataset without data augmentation; this model achieved results close to that of the literature with only 235 thousand trainable parameters, while the literature model (TSASNet) contains 78 million. Conclusions: The results obtained in this work are satisfactory and present paths for a better and more effective dental segmentation process.

Beyond semantic segmentation,3D instance segmentation(a process to delineate objects of interest and also classifying the objects into a set of categories) is gaining more and more interest among researchers since numerous computer vision applications need accurate segmentation processes(autonomous driving, indoor navigation, and even virtual or augmented reality systems…) This paper gives an overview and a technical comparison of the existing deep learning architectures in handling unstructured Euclidean data for the rapidly developing 3D instance segmentation. First, the authors divide the 3D point clouds based instance segmentation techniques into two major categories which are proposal based methods and proposal free methods. Then, they also introduce and compare the most used datasets with regard to 3D instance segmentation. Furthermore, they compare and analyze these techniques performance (speed, accuracy, response to noise…). Finally, this paper provides a review of the possible future directions of deep learning for 3D sensor-based information and provides insight into the most promising areas for prospective research.

The explosion of data has transformed the world since much more information is available for collection and analysis than ever before. To extract valuable information from the data in different dimensions, various deep learning models have been developed in the past years. Although these models have demonstrated their strong capability on improving products and services in various applications, training them is still a time-consuming and resource-intensive process. Presently, cloud, one of the most powerful computing infrastructures, has been used for the training. However, how to manage cloud computing resources and to perform the training efficiently is still challenging current techniques. For example, general resource scheduling approaches, such as spread priority and balanced resource schedulers, actually do not work well with deep learning workloads. Besides, the resource allocation problem on a cluster can be divide into two subproblems: (1) local resource optimization: improve resource configuration for a single machine; (2) global resource optimization: improve the cluster-wide resource allocation. In this thesis, we propose two novel container schedulers, FlowCon and SpeCon, that are designed to address these two subproblems respectively and specifically to optimize performance of short-lived deep learning applications in the cloud. FlowCon focuses on resource configuration of single-node in a cluster, as show that it efficiently improves deep learning tasks completion time and resource utilization, and reduces the completion time of a specific job by up to 42.06\% without sacrificing the overall system time. SpeCon targets on cluster-wide resource configuration that speculatively migrate slow-growing models to release resources for fast-growing ones. Based on our experiments, SpeCon improves makespan for up to 24.7\%, compared to current approaches.

The robust control of high precision electromechanical systems, such as micropositioners, is challenging in terms of the inherent high nonlinearity, the sensitivity to external interference, and the complexity of accurate identification of the model parameters. To cope with these problems, this work investigates a disturbance observer-based deep reinforcement learning control strategy to realize high robustness and precise tracking performance. Reinforcement learning has shown great potential as optimal control scheme, however, its application in micropositioning systems is still rare. Therefore, embedded with the integral differential compensator (ID), deep deterministic policy gradient (DDPG) is utilized in this work with the ability to not only decrease the state error but also improves the transient response speed. In addition, an adaptive sliding mode disturbance observer (ASMDO) is proposed to further eliminate the collective effect caused by the lumped disturbances. The sterling performance is revealed with intensive tracking simulation experiments and demonstrates the improvement in the accuracy and response time of the controller.

This paper presents a two-dimensional mathematical model of compound eye vision. Such a model is useful for solving navigation issues for autonomous mobile robots on the ground plane. The model is inspired by the insect compound eye that consists of ommatidia, which are tiny independent photoreception units, each of which combines a cornea, lens, and rhabdom. The model describes the planar binocular compound eye vision, focusing on measuring distance and azimuth to a circular feature with an arbitrary size. The model provides a necessary and sufficient condition for the visibility of a circular feature by each ommatidium. On this basis, an algorithm is built for generating a training data set to create two deep neural networks (DNN): the first detects the distance, and the second detects the azimuth to a circular feature. The hyperparameter tuning and the configurations of both networks are described. Experimental results showed that the proposed method could effectively and accurately detect the distance and azimuth to objects.

Prediction of stock groups values has always been attractive and challenging for shareholders. This paper concentrates on the future prediction of stock market groups. Four groups named diversified financials, petroleum, non-metallic minerals and basic metals from Tehran stock exchange are chosen for experimental evaluations. Data are collected for the groups based on ten years of historical records. The values predictions are created for 1, 2, 5, 10, 15, 20 and 30 days in advance. The machine learning algorithms utilized for prediction of future values of stock market groups. We employed Decision Tree, Bagging, Random Forest, Adaptive Boosting (Adaboost), Gradient Boosting and eXtreme Gradient Boosting (XGBoost), and Artificial neural network (ANN), Recurrent Neural Network (RNN) and Long short-term memory (LSTM). Ten technical indicators are selected as the inputs into each of the prediction models. Finally, the result of predictions is presented for each technique based on three metrics. Among all algorithms used in this paper, LSTM shows more accurate results with the highest model fitting ability. Also, for tree_based models, there is often an intense competition between Adaboost, Gradient Boosting and XGBoost.

Gastrointestinal (GI) tract disorders, ranging from benign polyps to aggressive forms of cancer, pose significant health challenges globally. Early detection and precise classification of these conditions are crucial for effective treatment and improving patient survival rates. This study employs the Hyper-Kvasir dataset, a comprehensive collection of endoscopic images, to develop deep learning models that harness the power of the YOLO (You Only Look Once) architecture for real-time detection and classification of GI abnormalities. The focus is on overcoming inherent challenges such as class imbalance and limited annotated data availability. Advanced machine learning strategies, including data augmentation and semi-supervised learning, are utilized to enhance the model's performance. Our experiments demonstrate notable improvements in the detection of pre-cancerous lesions and other GI abnormalities, confirming the potential of integrating AI into endoscopic practices to support clinicians, reduce diagnostic errors, and contribute to more accurate and timely diagnoses. The implications of these findings are significant, offering a pathway to more reliable diagnostic processes and ultimately, better patient management in gastroenterology.

Tropical cyclones (TC) are dangerous weather events and accurate monitoring and forecasting can provide significant early warning to reduce loss of life and property. However, the study of tropical cyclone intensity remains challenging, both in terms of theory and forecasting. ERA5 reanalysis is benchmark data set for tropical cyclone studies, yet the maximum wind speed error is very large (68 kts) and still 19 kts after simple linear correction even in the better sampled North Atlantic. Here, we develop an adaptive learning approach to correct the intensity in the ERA5 reanalysis, by optimising the inputs to overcome the problems because of the poor data quality and updating the features to improve the generalisability of the deep learning-based model. Specifically, we use TC knowledge to increase the representativeness of the inputs so that the general features can be learned with deep neural networks in the sample space, and then use domain adaptation to update the general features from the known domain with historical storms to the specific features for the unknown domain of new storms. This approach can reduce the error to only 6 kts which is within the uncertainty of the best track data in IBTrACS in the North Atlantic. The method may have wide applicability, such as extending it to the correction of intensity estimation from satellite imagery and intensity prediction from dynamical models.

Sparse reward long horizon task is a major challenge for deep reinforcement learning algorithm. One of the key barriers is data-inefficiency. Even in the simulation environment, it usually takes weeks to training the agent. In this study, a data-efficiency training framework is proposed, where a curriculum learning is design for the agent in the simulation scenario. Different distributions of the initial state are set for the agent to get more informative reward during the whole training process. A fine-tuning of the parameters in the output layer of the neural network for value function is conduct to bridge the gap between sim-to-real. An experiment of UAV maneuver control is conducted in the proposed training framework to verify the method more efficient. We demonstrate that data-efficiency is different for the same data in different training stages.

In this paper, we propose a new methodology for crack monitoring in concrete structures. This approach is based on a n this paper, we propose a new methodology for monitoring cracks in concrete structures. This approach is based on a multi-resolution analysis of a sample or a specimen of the studied material subjected to several types of solicitation. The image obtained by ultrasonic investigation and processing by a dedicated wavelet will be analyzed according to several scales in order to detect internal cracks and crack initiation. The ultimate goal of this work is to propose an automatic crack type identification scheme based on convolutional neural networks (CNN). In this context, crack propagation can be monitored without access to the concrete surface and the goal is to detect cracks before they are visible on the concrete surface. The key idea allowing such a performance is the combination of two major data analysis tools which are wavelets and Deep Learning. This original procedure allows to reach a high accuracy close to 0.90. In this work, we have also implemented another approach for automatic detection of external cracks by deep learning from publicly available datasets.

In this paper major machine learning (ML) tools and the most important applications developed elsewhere for numerical weather and climate modeling systems (NWCMS) are reviewed. NWCMSs are briefly introduced. The most important papers published in this field in recent years are reviewed. The advantages and limitations of the ML approach in applications to NWCMS are briefly discussed. Currently, this field is experiencing explosive growth. Several important papers are published every week. Thus, this paper should be considered a simple introduction to the problem.

Deep learning (DL) algorithms have recently emerged from machine learning and soft computing techniques. Since then, several deep learning (DL) algorithms have been recently introduced to scientific communities and are applied in various application domains. Today the usage of DL has become essential due to their intelligence, efficient learning, accuracy and robustness in model building. However, in the scientific literature, a comprehensive list of DL algorithms has not been introduced yet. This paper provides a list of the most popular DL algorithms, along with their applications domains.

In the rapidly evolving landscape of cybersecurity, Intrusion Detection Systems (IDS) play a critical role in safeguarding networks and systems from unauthorized access and malicious activities. Traditional IDS approaches, relying heavily on predefined rules and signature-based detection, often struggle to keep pace with the dynamic nature of modern cyber threats. Deep learning, with its ability to automatically learn complex patterns and representations from large datasets, offers a promising solution to this challenge. This paper explores the application of deep learning techniques in enhancing the effectiveness and accuracy of IDS. By leveraging advanced neural network architectures such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and autoencoders, deep learning-based IDS can detect both known and unknown (zero-day) attacks with higher precision. We discuss the advantages of deep learning in IDS, including its capability to handle large-scale data, adaptability to evolving threats, and reduced dependency on human intervention. Furthermore, this paper reviews recent advancements in deep learning for IDS, highlights the challenges associated with their implementation, and suggests future directions for research to overcome these hurdles. The integration of deep learning into IDS frameworks represents a significant step forward in the development of intelligent and autonomous cybersecurity systems.

Deep Learning is an extremely important research topic in Earth Observation. Current use-cases range from semantic image segmentation, object detection to more common problems found in computer vision such as object identification. Earth Observation is an excellent source for different types of problems and data for Machine Learning in general and Deep Learning in particular. It can be argued that both Earth Observation and Deep Learning as fields of research will benefit greatly from this recent trend of research. In this paper we take several state of the art Deep Learning network topologies and provide a detailed analysis of their performance for semantic image segmentation for building footprint detection. The dataset used is comprised of high resolution images depicting urban scenes. We focused on single model performance on simple RGB images. In most situations several methods have been applied to increase the accuracy of prediction when using deep learning such as ensembling, alternating between optimisers during training and using pretrained weights to bootstrap new models. These methods although effective, are not indicative of single model performance. Instead, in this paper, we present different topology variations of these state of the art topologies and study how these variations effect both training convergence and out of sample, single model, performance.

If the development of machine learning and artificial intelligence plays a role in many fields of research and technology today, it has a special relationship with neurosciences. Indeed, historically inspired by our knowledge of the brain, deep learning shares some vocabularies with neurosciences and can sometimes be considered a brain’s model. Taking the particular example of epileptic seizure, which can develop in any biological neural tissue, we raise the question if and how the models used for deep learning can capture or model these pathological events. This particular example is a starting point to discuss the nature, limits, and functions of these models, and what we expect from a model of the brain. Finally, we argue that a pluralistic approach leading to the integrated coexistence of different models is necessary to study the brain in all its complexity.

Rainfall retrieval using geostationary satellites provides critical means to the monitoring of extreme rainfall events. Using the relatively new Himawari 8 meteorological satellite with three times more channels than its predecessors, the deep learning framework of “convolutional autoencoder” (CAE) was applied to the extraction of cloud and precipitation features. The CAE method was incorporated into the Convolution Neural Network version of the PERSIANN precipitation retrieval that uses GOES satellites. By applying the CAE technique with the addition of Residual Blocks and other modifications of deep learning architecture, the presented derivation of PERSIANN operated at the Central Weather Bureau of Taiwan (referred to as PERSIANN-CWB) expands four extra convolution layers to fully use Himawari 8’s infrared and water vapor channels, while preventing degradation of accuracy caused by the deeper network. The development of PERSIANN-CWB was trained over Taiwan for its diverse weather systems and localized rainfall features, and the evaluation reveals an overall improvement from its CNN counterpart and superior performance over all other rainfall retrievals analyzed. Limitation of this model was found in the derivation of typhoon rainfall, an area requiring further research.

The increasing trend of studying the innate softness of robotic structures and amalgamating it with the benefits of the extensive developments in the field of embodied intelligence has led to sprouting of a relatively new yet extremely rewarding sphere of technology. The fusion of current deep reinforcement algorithms with physical advantages of a soft bio-inspired structure certainly directs us to a fruitful prospect of designing completely self-sufficient agents that are capable of learning from observations collected from their environment to achieve a task they have been assigned. For soft robotics structure possessing countless degrees of freedom, it is often not easy (something not even possible) to formulate mathematical constraints necessary for training a deep reinforcement learning (DRL) agent for the task in hand, hence, we resolve to imitation learning techniques due to ease of manually performing such tasks like manipulation that could be comfortably mimicked by our agent. Deploying current imitation learning algorithms on soft robotic systems have been observed to provide satisfactory results but there are still challenges in doing so. This review article thus posits an overview of various such algorithms along with instances of them being applied to real world scenarios and yielding state-of-the-art results followed by brief descriptions on various pristine branches of DRL research that may be centers of future research in this field of interest.