Search

The pulp and paper industry is critical to global industrial and economic development. Recently, India's pulp and paper industries have been facing severe competitive challenges. The challenges have impaired the environmental performance and resulted in the closure of several operations. Assessment and prediction of the performance of the Indian pulp and paper industry using various parameters is a critical task for researchers. This study proposes a framework for performance assessment and prediction based on Data Envelopment Analysis (DEA), Artificial Neural Networks, and Deep Learning (DL) to assist industry administration and decision-making. We presented a case study based on eight industries to demonstrate the methodology's applicability. This study analyses and predicts industry performance based on sample data observations over 30 years. The result suggests the DEA-DL-based efficiency prediction has an overall MSE of 0.08 compared with the actual efficiency. Furthermore, the efficiency rankings are compared between the three techniques. The results suggest that the integrated DEA-DL method is primarily accurate in most scenarios with the actual values. The findings of this study provide a comprehensive analysis of environmental performance for policymakers. [ABSTRACT FROM AUTHOR]

Purpose: Paper-based artifacts hold significant cultural and social values. However, paper is intrinsically fragile to microorganisms, such as mold, due to its cellulose composition, which can serve as a microorganisms' nutrient source. Mold not only can damage papers' structural integrity and pose significant challenges to conservation works but also may subject individuals attending the contaminated artifacts to health risks. Current approaches for strain identification usually require extensive training, prolonged time for analysis, expensive operation costs, and higher risks of secondary damage due to sampling. Thus, in current conservation practices with mold-contaminated artifacts, little pre-screening or strain identification was performed before mold removal, and the cleaning techniques are usually broad-spectrum rather than strain-specific. With deep learning showing promising applications across various domains, this study investigated the feasibility of using a convolutional neural network (CNN) for fast in-situ recognition and classification of mold on paper. Methods: Molds were first non-invasively sampled from ancient Xuan Paper-based Chinese books from the Qing and Ming dynasties. Strains were identified using molecular biology methods and the four most prevalent strains were inoculated on Xuan paper to create mockups for image collection. Microscopic images of the molds as well as their stains situated on paper were collected using a compound microscope and commercial microscope lens for cell phone cameras, which were then used for training CNN models with a transfer learning scheme to perform the classification of mold. To enable involvement and contribution from the research community, a web interface that actuates the process while providing interactive features for users to learn about the information of the classified strain was constructed. Moreover, a feedback functionality in the web interface was embedded for catching potential classification errors, adding additional training images, or introducing new strains, all to refine the generalizability and robustness of the model. Results & Conclusion: In the study, we have constructed a suite of high-confidence classification CNN models for the diagnostic process for mold contamination in conservation. At the same time, a web interface was constructed that allows recurrently refining the model with human feedback through engaging the research community. Overall, the proposed framework opens new avenues for effective and timely identification of mold, thus enabling proactive and targeted mold remediation strategies in conservation. [ABSTRACT FROM AUTHOR]

The integration of artificial intelligence (AI) in ophthalmology has promoted the development of the discipline, offering opportunities for enhancing diagnostic accuracy, patient care, and treatment outcomes. This paper aims to provide a foundational understanding of AI applications in ophthalmology, with a focus on interpreting studies related to AI-driven diagnostics. The core of our discussion is to explore various AI methods, including deep learning (DL) frameworks for detecting and quantifying ophthalmic features in imaging data, as well as using transfer learning for effective model training in limited datasets. The paper highlights the importance of high-quality, diverse datasets for training AI models and the need for transparent reporting of methodologies to ensure reproducibility and reliability in AI studies. Furthermore, we address the clinical implications of AI diagnostics, emphasizing the balance between minimizing false negatives to avoid missed diagnoses and reducing false positives to prevent unnecessary interventions. The paper also discusses the ethical considerations and potential biases in AI models, underscoring the importance of continuous monitoring and improvement of AI systems in clinical settings. In conclusion, this paper serves as a primer for ophthalmologists seeking to understand the basics of AI in their field, guiding them through the critical aspects of interpreting AI studies and the practical considerations for integrating AI into clinical practice. [ABSTRACT FROM AUTHOR]

De-mining operations are of critical importance for humanitarian efforts and safety in conflict-affected regions. In this paper, we address the challenge of enhancing the accuracy and efficiency of mine detection systems. We present an innovative Deep Learning architecture tailored for pulse induction-based Metallic Mine Detectors (MMD), so called DL-MMD. Our methodology leverages deep neural networks to distinguish amongst nine distinct materials with an exceptional validation accuracy of 93.5%. This high level of precision enables us not only to differentiate between anti-personnel mines, without metal plates but also to detect minuscule 0.2-g vertical paper pins in both mineralized soil and non-mineralized environments. Moreover, through comparative analysis, we demonstrate a substantial 3% and 7% improvement (approx.) in accuracy performance compared to the traditional K-Nearest Neighbors and Support Vector Machine classifiers, respectively. The fusion of deep neural networks with the pulse induction-based MMD not only presents a cost-effective solution but also significantly expedites decision-making processes in de-mining operations, ultimately contributing to improved safety and effectiveness in these critical endeavors. [ABSTRACT FROM AUTHOR]

Accurate atom mapping, which establishes correspondences between atoms in reactants and products, is a crucial step in analyzing chemical reactions. In this paper, we present a novel end-to-end approach that formulates the atom mapping problem as a deep graph matching task. Our proposed model, AMNet (Atom Matching Network), utilizes molecular graph representations and employs various atom and bond features using graph neural networks to capture the intricate structural characteristics of molecules, ensuring precise atom correspondence predictions. Notably, AMNet incorporates the consideration of molecule symmetry, enhancing accuracy while simultaneously reducing computational complexity. The integration of the Weisfeiler-Lehman isomorphism test for symmetry identification refines the model's predictions. Furthermore, our model maps the entire atom set in a chemical reaction, offering a comprehensive approach beyond focusing solely on the main molecules in reactions. We evaluated AMNet's performance on a subset of USPTO reaction datasets, addressing various tasks, including assessing the impact of molecular symmetry identification, understanding the influence of feature selection on AMNet performance, and comparing its performance with the state-of-the-art method. The result reveals an average accuracy of 97.3% on mapped atoms, with 99.7% of reactions correctly mapped when the correct mapped atom is within the top 10 predicted atoms. Scientific contribution The paper introduces a novel end-to-end deep graph matching model for atom mapping, utilizing molecular graph representations to capture structural characteristics effectively. It enhances accuracy by integrating symmetry detection through the Weisfeiler-Lehman test, reducing the number of possible mappings and improving efficiency. Unlike previous methods, it maps the entire reaction, not just main components, providing a comprehensive view. Additionally, by integrating efficient graph matching techniques, it reduces computational complexity, making atom mapping more feasible. [ABSTRACT FROM AUTHOR]

With a significant number of mechanical products approaching the retirement phase, the batch recycling of discarded mechanical parts necessitates a preliminary assessment of their surface condition. However, the presence of surface rust poses a challenge to defect identification. Therefore, this paper proposes a method for detecting heavily rusted surface defects based on an improved YOLOv8n network. In the Backbone, the C2f-DBB module of re-parameterized deep feature extraction was introduced, and the attention module was designed to improve the accuracy of information extraction. In the Neck part, a Bi-Afpn multiscale feature fusion strategy is designed to facilitate information exchange between features at different scales. Finally, Focal-CIoU is employed as the bounding box loss function to enhance the network's localization performance and accuracy for defects. Experimentally, it is proved that the improved network in this paper improves the Recall, Precision, and mAP0.5 by 1.2%, 2.1%, and 1.9%, respectively, on the original basis, which is better than other network models. [ABSTRACT FROM AUTHOR]

Programmed death-ligand 1 (PD-L1) expression is currently used in the clinic to assess eligibility for immune-checkpoint inhibitors via the tumor proportion score (TPS), but its efficacy is limited by high interobserver variability. Multiple papers have presented systems for the automatic quantification of TPS, but none report on the task of determining cell-level PD-L1 expression and often reserve their evaluation to a single PD-L1 monoclonal antibody or clinical center. In this paper, we report on a deep learning algorithm for detecting PD-L1 negative and positive tumor cells at a cellular level and evaluate it on a cell-level reference standard established by six readers on a multi-centric, multi PD-L1 assay dataset. This reference standard also provides for the first time a benchmark for computer vision algorithms. In addition, in line with other papers, we also evaluate our algorithm at slide-level by measuring the agreement between the algorithm and six pathologists on TPS quantification. We find a moderately low interobserver agreement at cell-level level (mean reader-reader F1 score = 0.68) which our algorithm sits slightly under (mean reader-AI F1 score = 0.55), especially for cases from the clinical center not included in the training set. Despite this, we find good AI-pathologist agreement on quantifying TPS compared to the interobserver agreement (mean reader-reader Cohen's kappa = 0.54, 95% CI 0.26–0.81, mean reader-AI kappa = 0.49, 95% CI 0.27—0.72). In conclusion, our deep learning algorithm demonstrates promise in detecting PD-L1 expression at a cellular level and exhibits favorable agreement with pathologists in quantifying the tumor proportion score (TPS). We publicly release our models for use via the Grand-Challenge platform. [ABSTRACT FROM AUTHOR]

Context: With the union of machine learning (ML) and quantum chemistry, amid the debate between machine-learned functionals and human-designed functionals in density functional theory (DFT), this paper aims to demonstrate the generation of potential energy surfaces using computations with machine-learned density functional approximation (ML-DFA). A recent research trend is the application of ML in quantum sciences in the design of density functionals such as DeepMind's Deep Learning model (DeepMind21, DM21). Though science reported the state-of-the-art performance of DM21, the opportunity to utilize DeepMind's pretrained DM21 neural networks in computations in quantum chemistry has not yet been tapped. So far in the literature, the Deep Learning density functionals (DM21) have not been applied to generate potential energy surfaces. While the superior accuracy of DM21 has been reported, there is still a scarcity of publications that apply DM21 in calculations in the field. In this context, for the first time in literature, neural density functionals inferring 2D potential energy surfaces (ML-DFA-PES) based on machine-learned DFA-based computational method is contributed in this paper. This paper reports the ML-DFA-generated PES for C4H8, H2O, H2, and H2+ by employing a pretrained DM21m TensorFlow model with cc-pVDZ basis set. In addition, we also analyze the long-range behavior of DM21 based PES to investigate the ability to describe a system at long ranges. Furthermore, we compare PES diagrams from DM21 with popular DFT functionals (b3lyp/ PW6B95) and CCSD(T). Methods: In this method, 2D potential energy surfaces are obtained using a method that relies upon the neural network's ability to accurately learn the mapping between 3D electron density and exchange–correlation potential. By inserting Deep Learning inference in DFT with a pretrained neural network, self-consistent field (SCF) energy at different geometries along the coordinates of interest is computed, and then, potential energy surfaces are plotted. In this method, first, the electron density is computed mathematically, and this computed 3D electron density is used as a ML feature vector to predict the exchange correlation potential as a ML inference computed by a forward pass of pre-trained DM21 TensorFlow computational graph, followed by the computation of self-consistent field energy at multiple geometries, and then, SCF energies at different bond lengths/angles are plotted as 2D PES. We implement this in a python source code using frameworks such as PySCF and DM21. This paper contributes this implementation in open source. The source code and DM21-DFA-based PES are contributed at https://sites.google.com/view/MLfunctionals-DeepMind-PES. [ABSTRACT FROM AUTHOR]

Forecasting of load is essential for operating power systems. India recently witnessed one of the worst power crisis with the highest ever power demand of 207 GW on April 29, 2022. The demand in the month of May and June 2022 was estimated to reach 215 GW. The peak demand this year 2023, according to the electricity ministry, is predicted to be around 230 GW from April to June. The inability to meet certain fundamental issues as power can take a toll on any country's economy. Proper prediction helps in proper decision making and planning. The main objective of this paper is to predict day ahead electrical load demand for Assam. Statistical and Machine Learning Algorithms has been studied. The study has been carried out using real-time data for the years 2016, 2017 and 2018. The paper presents a detailed analysis of the different hyper parameters of the deep learning models and their effect is seen on the learning efficiency. A novel stacked forecasting model is proposed using neural networks as base learners and CatBoost as the meta-learner. The performance of the proposed model has been evaluated and compared with individual models in terms of training time and accuracy using different error metrics namely MAE, MSE, RMSE, MAPE and R2 score. A comparison of the proposed prediction model with the prediction models available in literature has been presented. The conclusion states that both the statistical and machine learning algorithms used in this study act as useful tools for daily load forecasting with considerable accuracy; yet machine learning algorithm outperforms the statistical methods. The entire work has been done in Google Colaboratory using Python as the programming language. [ABSTRACT FROM AUTHOR]

When traditional EEG signals are collected based on the Nyquist theorem, long-time recordings of EEG signals will produce a large amount of data. At the same time, limited bandwidth, end-to-end delay, and memory space will bring great pressure on the effective transmission of data. The birth of compressed sensing alleviates this transmission pressure. However, using an iterative compressed sensing reconstruction algorithm for EEG signal reconstruction faces complex calculation problems and slow data processing speed, limiting the application of compressed sensing in EEG signal rapid monitoring systems. As such, this paper presents a non-iterative and fast algorithm for reconstructing EEG signals using compressed sensing and deep learning techniques. This algorithm uses the improved residual network model, extracts the feature information of the EEG signal by one-dimensional dilated convolution, directly learns the nonlinear mapping relationship between the measured value and the original signal, and can quickly and accurately reconstruct the EEG signal. The method proposed in this paper has been verified by simulation on the open BCI contest dataset. Overall, it is proved that the proposed method has higher reconstruction accuracy and faster reconstruction speed than the traditional CS reconstruction algorithm and the existing deep learning reconstruction algorithm. In addition, it can realize the rapid reconstruction of EEG signals. [ABSTRACT FROM AUTHOR]

With the rapid development of information transfer technology and the influence of complex electromagnetic environment, the signal components in communication systems are becoming more and more complex, and the spectrum congestion is further aggravated, which seriously affects the performance of communication systems. Single-channel blind source separation technology is an effective solution, but the existing algorithms are deficient in terms of estimation accuracy, time delay and computational complexity. Based on the powerful feature extraction capability and timing signal processing capability of deep learning, this paper proposes an end-to-end time-domain blind separation convolutional network structure, including three parts: encoder, separation module and decoder. The attention mechanism module is also introduced into the encoding layer of the network to enhance the deep feature extraction ability of the network, highlight the influence of important timing features of communication signals, further improve the separation performance and enhance the practicality of the network. The experimental results show that the algorithm has superior performance and can effectively separate the mixed communication signal of various modulation types, and it can also extract own-side communication signals from high-power masked signals. Compared with the existing algorithms, the network in this paper has high separation accuracy and low computational complexity, which breaks the bottleneck of traditional single-channel blind separation algorithms in complex communication electromagnetic environment. [ABSTRACT FROM AUTHOR]

Automated and accurate detection of power quality (PQ) events is important from the point of view of safety as well as maintaining the reliability of the power transmission and distribution network. However, detection of multiple PQ events in a noisy environment is challenging task. Another important issue is the choice of meaningful features that can directly influence the accuracy of PQ detection. Considering these two aforesaid facts, this paper presents a novel framework for automated classification of PQ signals in a noisy environment employing cross Stockwell Transform (XST). The XST proposed in this paper has better noise suppression capability compared to conventional Stockwell Transform. Here, XST was used to convert 1D PQ signals to 2D time–frequency (T–F) images. To improve the accuracy of PQ detection, an automated feature extraction method employing deep learning is implemented in this work. The noise free T–F images obtained using XST were fed as inputs to several pre-trained convolutional neural networks (CNNs) for deep feature extraction. Transfer learning technique was implemented to reduce the computational cost. The extracted deep features were further undergone selection using one-way analysis of variance test followed by false discovery rate correction. The statistically significant deep features were subsequently fed to three benchmark machine learning classifiers for classification of PQ signals. In addition, tests were also carried out on real-life PQ signals to verify the practicability of the proposed framework. Investigations revealed that the proposed method returned mean accuracy of 99.72% and 96.45% for classification of simulated and real-life PQ signals, respectively. [ABSTRACT FROM AUTHOR]

Increasing the integration of distributed generation (DG) into distribution networks provides many technological benefits, including improving system security, performance, and reliability. The intermittent nature of renewable DGs poses certain difficulties for this integration. Moreover, the large integration of DGs will lead to islanding conditions in the power system. In the islanded operation, the microgrid keeps power injection into the network. The islanding event can occur intentionally or unintentionally; the former is controllable and required for maintaining the main utility, whereas the latter is uncontrollable, caused by regular faults. However, islanding detection is important for ensuring the system's reliability and operation. Hence, a comprehensive review is made in this paper to examine different methods for islanding detection in the power system. Unlike the previous review papers, the proposed review paper focused on different types of islanding detection methods, including active, reactive, hybrid active–passive methods, deep learning and machine learning techniques. All of these methods have their advantage and disadvantages. Moreover, the complexities in power systems increased with the increasing penetration of DGs. Thus, the rapid islanding detection technique is necessary for improving the system's performance. This review has provided some recent literature for signal processing, which includes the recent feature selection and advance finding for islanding occurrences. From the comparative analysis, it is found that the Non-detection zone (NDZ) is more in the passive method is higher than in the active and hybrid active–passive methods. At the same time, the remote islanding detection methods are NDZ free, but it has computational complexities when compared with existing methods. Moreover, the DL based methods have higher computational time due to large training and testing data. It is found that hybrid methods are more feasible for providing accurate results in islanding detection. In addition to that, a feasible and economical solution in terms of recent research trends is provided. [ABSTRACT FROM AUTHOR]

Leukemia is a severe blood disorder that poses a threat to the life and well-being of patients. Accurate diagnosis of leukemia typing is crucial for treatment and prognosis. However, manual diagnosis requires significant resources and is subject to observer variation. Computer-aided diagnostic (CAD) technologies have emerged as a promising approach to complement manual diagnosis and alleviate the workload of specialized physicians. With the recent advances in deep learning, the performance of CAD has been substantially enhanced. In this paper, we propose a novel classification model, AMLNet, for acute myeloid leukemia (AML) cells. AMLNet is a lightweight model based on the ShuffleNet V2 architecture. We first validate the performance of the convolutional neural network and Transformer architecture models on the largest AML cell dataset to date. Then, we enhance the data augmentation approach and model structure of the ShuffleNet V2 model to develop AMLNet. The AUC, sensitivity, and accuracy of AMLNet are up to 0.9935%, 63.91%, and 96.43%, respectively, which achieves the optimal classification performance. Finally, the classification performance of AMLNet is verified on other public datasets, which is superior to other methods. AMLNet presents a promising solution for practical diagnosis scenarios since the end devices of assisted diagnosis often have limited computational power. The proposed AMLNet model effectively improves the classification performance of ShuffleNet V2 while offering the advantages of high performance and low computational consumption. Overall, our study demonstrates the potential of lightweight deep learning models in improving the accuracy of leukemia typing and reducing the workload of specialized physicians. [ABSTRACT FROM AUTHOR]

Fraud detection and prevention has received a lot of attention from the research community due to its high impact on financial institutions' revenues and reputation. The increased use of the web and the provision of online services open up the pathway for exposing these systems to numerous threats and jeopardizing their effective functioning. Naturally, financial frauds are increased in number and form imposing various requirements for their efficient and immediate detection. These requirements are related to the performance of the adopted models as well as the timely response of the decision-making mechanism. Machine learning and data mining are two research domains that can provide a number of techniques/algorithms for fraud detection and setup the road for mitigation actions. However, these methods still need to be improved with respect to the detection of unknown fraud patterns and the incorporation of big data processing mechanisms. This paper presents our attempt to build a hybrid system, i.e., a sequential scheme for combining two deep learning models and efficiently detecting potential financial frauds. We elaborate on the combination of an autoencoder and a Long Short-Term Memory Recurrent Neural Network trained upon datasets which are processed through the use of an oversampling technique. Oversampling is adopted to handle heavily imbalanced datasets which is the 'natural' scenario due to the limited number of frauds compared to the humongous volumes of transactions. The proposed approach tends to capture much more fraud events in comparison with other conventional ML techniques. Our experimental evaluation exposes that our model exhibits a good performance in terms of recall and precision. [ABSTRACT FROM AUTHOR]

In the era of heterogeneous computing, a new paradigm called accelerator level parallelism (ALP) has emerged. In ALP, accelerators are used concurrently to provide unprecedented levels of performance and energy efficiency. To reach that there are many problems to be solved, one of the most challenging being co-execution. In this paper, we present a new scheduling framework called POAS, a general method for providing co-execution to applications. Our proposal consists of four steps: predict, optimize, adapt and schedule. With POAS, an unseen application can be executed concurrently in ALP with little effort. We evaluate POAS on a heterogeneous environment consisting of CPUs, GPUs (CUDA cores), and XPUs (Tensor cores) on two different fields, namely linear algebra (matrix multiplication benchmark) and deep learning (convolution benchmark). Our experiments prove that POAS provides excellent performance and completes the tasks within a time very close to the optimal time for the hardware and applications used, with a negligible execution time overhead. Moreover, the POAS predictor performed exceptionally well, achieving very low RMSE values for both use cases. Therefore, POAS can be a valuable tool for fully exploiting ALP and improving overall performance over offloading in heterogeneous settings. [ABSTRACT FROM AUTHOR]

The term "Internet of Things" (IoT) encompasses an entire group of gadgets that are capable of connecting to the Internet in order to gather and share data. The IoT paradigm is being pushed into computer networks by numerous highly advanced intrusions. Cloud computing greatly enhances the success of the IoT by enabling users to perform computing tasks using Internet-based services accessed through connected devices. This seamless integration of cloud technology and the IoT has become a powerful catalyst, revolutionizing the way we operate. The adoption of a distributed architecture, such as cloud computing, exposes the system to potential threats like Distributed Denial of Service (DDoS) and Denial of Service (DoS) attacks. To mitigate these risks, the concept of an intrusion detection system (IDS) has been introduced within the cloud environment. Various machine learning (ML) and deep learning (DL) algorithms have been proposed and implemented to effectively detect and respond to such malicious traffic in the cloud system. For dimension reduction during the training process of those algorithms, multiple independent and hybrid techniques have been proposed. This study presents an efficient ML-based real-time IDS framework with proposed hybrid feature selection techniques. Additionally, in this study, a concise comparative analysis has been conducted using five well-known public datasets. The findings presented in this paper reveal that our proposed IDS achieved a maximum accuracy of 99.98% in identifying malicious traffic. [ABSTRACT FROM AUTHOR]

The accurate and automated segmentation of neurons in electron microscopy (EM) images presents a challenging problem in neuroscience. In this paper, we propose a deep learning (DL)-based neuron segmentation approach using a relatively shallow residual deconvolutional neural network (DNN) as the core. Our proposed segmentation framework differs from most EM image segmentation networks that use original images as input, as we suggest using modified morphological features with attention characteristics as input instead. We calculate Bhattacharyya distances in morphology feature space to provide attention features, which are then concatenated with the original image and used as input to the segmentation network. By attending to membrane pixels, our network efficiently highlights the discrimination between membrane boundaries and background pixels. To remove noise pixels in the segmentation map while preserving membrane boundaries in the final result, the dilated version of the output is then processed using a guided filtering scenario. Our proposed model outperforms several competing DL methods such as DeepLabv3 as well as different versions of deconvolutional neural networks on the ISBI 2012 dataset in terms of various image segmentation metrics. The proposed attention-based morphological guided framework can help advance research in neuroscience by providing an automated and accurate segmentation of neurons in EM images. [ABSTRACT FROM AUTHOR]

The rapid growth of Internet of Things (IoT) devices has changed human interactions with the environment. IoT networks require specialized defense strategies distinct from traditional corporate contexts. Security measures such as anti-malware software, firewalls, authentication protocols, and encryption techniques are established but face limitations against evolving attack strategies. Therefore, this study proposes an intrusion detection approach for a realistic IoT environment, employing various variants of deep learning models such as deep neural networks (DNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs). The research tested three variants for each model: DNN1, DNN2, DNN3, CNN1, CNN2, CNN3, RNN1, RNN2, RNN3. All these variants are customized and tuned differently to analyze the efficacy of the suggested methodology. Likewise, notable observation highlights the significance of aligning training and validation accuracy curves that indicate controlled overfitting, validating the model's reliability in accurately predicting intrusion and benign network traffic in IoT settings. Results reveal that RNN1 achieves the best results: accuracy of 98.61%, precision of 98.55%, recall of 98.61%, and F1-score of 98.57% compared with other DNN and CNN architectures and benchmark papers. This study advances intrusion detection within IoT networks through a comprehensive evaluation of deep learning models and inspires ongoing research to enhance intrusion detection systems' resilience in dynamic IoT environments. [ABSTRACT FROM AUTHOR]

General matrix multiplication (gemm) is a fundamental kernel in scientific computing and current frameworks for deep learning. Modern realisations of gemm are mostly written in C, on top of a small, highly tuned micro-kernel that is usually encoded in assembly. The high performance realisation of gemm in linear algebra libraries in general include a single micro-kernel per architecture, usually implemented by an expert. In this paper, we explore a couple of paths to automatically generate gemm micro-kernels, either using C++ templates with vector intrinsics or high-level Python scripts that directly produce assembly code. Both solutions can integrate high performance software techniques, such as loop unrolling and software pipelining, accommodate any data type, and easily generate micro-kernels of any requested dimension. The performance of this solution is tested on three ARM-based cores and compared with state-of-the-art libraries for these processors: BLIS, OpenBLAS and ArmPL. The experimental results show that the auto-generation approach is highly competitive, mainly due to the possibility of adapting the micro-kernel to the problem dimensions. [ABSTRACT FROM AUTHOR]

Lung cancer is an uncontrolled growth of tissue causing a lump in the human lung. If lung cancer can be detected early, it can increase the survival rate. Therefore, a multi-classification approach of lung nodule detection with high computational effectiveness is required. In this paper, a multi-classification approach of lung nodule detection and classification is proposed using artificial intelligence on computed tomography (CT) scan images. Different preprocessing steps are applied for resizing, smoothing, and enhancement of the CT images. Then, two different approaches for feature extraction using VGG16 transfer learning and morphological segmentation are proposed. Morphological segmentation and feature extraction are applied for the segmentation of the region of interest and to extract the distinct features. Finally, the proposed deep learning architecture and seven different machine learning algorithms are applied on the preprocessed data and the extracted features for the classification of lung nodules into three classes: malignant, benign, and normal. It is observed that the stacked ensemble model of deep learning convolutional neural network (CNN) and VGG16 transfer learning models (CNN+VGG16) can achieve 99.55% accuracy using preprocessed data. It is also observed that all the ML algorithms perform with reasonably high accuracy using the low-dimensional morphological features. It is observed from the fivefold cross-validation results that logistic regression performs with 99.36% accuracy in 23.71 s time using the preprocessed data. Whereas, using the morphological features, k-nearest neighbor, and the support vector machine perform with the highest accuracy of 99.76% with very reduced computational time of 0.017 and 0.008 s, respectively. [ABSTRACT FROM AUTHOR]

In this paper, we address the problem of spatially-varying illumination-aware indoor harmonization. Existing image harmonization works either focus on extracting no more than 2D information (e.g., low-level statistics or image filters) from the background image or rely on the non-linear representations of deep neural networks to adjust the foreground appearance. However, from a physical point of view, realistic image harmonization requires the perception of illumination at the foreground position in the scene (i.e., Spatially-Varying (SV) illumination), especially for indoor scenes. To solve indoor harmonization, we present a novel learning-based framework, which attempts to mimic the physical model of image formation. The proposed framework consists of a new neural harmonization architecture with four compact neural modules, which jointly learn SV illumination, shading, albedo, and rendering. In particular, a multilayer perceptron-based neural illumination field is designed to recover the illumination with finer details. Besides, we construct the first large-scale synthetic indoor harmonization benchmark dataset in which the foreground focuses on humans and is rendered and perturbed by SV illuminations. An object placement formula is also derived to ensure that the foreground object is placed in the background at a reasonable size. Extensive experiments on synthetic and real data demonstrate that our proposed approach achieves better results than prior works. [ABSTRACT FROM AUTHOR]

Image and video inpainting is a classic problem in computer vision and computer graphics, aiming to fill in the plausible and realistic content in the missing areas of images and videos. With the advance of deep learning, this problem has achieved significant progress recently. The goal of this paper is to comprehensively review the deep learning-based methods for image and video inpainting. Specifically, we sort existing methods into different categories from the perspective of their high-level inpainting pipeline, present different deep learning architectures, including CNN, VAE, GAN, diffusion models, etc., and summarize techniques for module design. We review the training objectives and the common benchmark datasets. We present evaluation metrics for low-level pixel and high-level perceptional similarity, conduct a performance evaluation, and discuss the strengths and weaknesses of representative inpainting methods. We also discuss related real-world applications. Finally, we discuss open challenges and suggest potential future research directions. [ABSTRACT FROM AUTHOR]

Thunderstorm gusts are a common form of severe convective weather in the warm season in North China, and it is of great importance to correctly forecast them. At present, the forecasting of thunderstorm gusts is mainly based on traditional subjective methods, which fails to achieve high-resolution and high-frequency gridded forecasts based on multiple observation sources. In this paper, we propose a deep learning method called Thunderstorm Gusts TransU-net (TG-TransUnet) to forecast thunderstorm gusts in North China based on multi-source gridded product data from the Institute of Urban Meteorology (IUM) with a lead time of 1 to 6 h. To determine the specific range of thunderstorm gusts, we combine three meteorological variables: radar reflectivity factor, lightning location, and 1-h maximum instantaneous wind speed from automatic weather stations (AWSs), and obtain a reasonable ground truth of thunderstorm gusts. Then, we transform the forecasting problem into an image-to-image problem in deep learning under the TG-TransUnet architecture, which is based on convolutional neural networks and a transformer. The analysis and forecast data of the enriched multi-source gridded comprehensive forecasting system for the period 2021–23 are then used as training, validation, and testing datasets. Finally, the performance of TG-TransUnet is compared with other methods. The results show that TG-TransUnet has the best prediction results at 1–6 h. The IUM is currently using this model to support the forecasting of thunderstorm gusts in North China. [ABSTRACT FROM AUTHOR]

As an all-in-one process that blended design, materials, and manufacturing, additive manufacturing (AM) adopted a bottom-up stacking approach, thereby avoiding excessive infrastructure and complex production steps. However, the different process stages of AM were influenced by multi-scale factors such as material characteristics, parameter settings, and process stability, resulting in uncertainty. Therefore, the effective containment and accurate evaluation of automated production processes were crucial. With the rapid development and widespread application of artificial intelligence (AI) technologies in the Industry 4.0 era, computer vision (CV) techniques, as an important component, could achieve multi-level understanding of the real world through traditional machine learning (ML) and efficient deep learning (DL) approaches based on information-dense cross-media data such as images, videos, and three-dimensional models. Hence, the organic integration of CV and AM was of great significance for the virtual simulation, global perception, real-time monitoring, and quality measurement of the machining processes. According to the chronological order and logical relationship of manufacturing engineering, this paper organized and summarized the application of CV techniques in material characteristics perception and stacking process simulation before the implementation of projects, in situ inspection, and law exploration during the manufacturing processes, as well as product evaluation and defect detection after processing, which demonstrated its powerful performance and great potential in the intelligence and integration of AM. [ABSTRACT FROM AUTHOR]

As the integration of mechanical engineering and deep learning fields becomes increasingly intertwined, the application of experimental thermal error modeling in intelligent manufacturing has gained significant importance. In this paper, the issue of spindle thermal error is treated as a multivariate time series problem due to the thermal transfer characteristics. This study aims to address the challenge of modeling intermittent multivariate time series spindle thermal errors under a wide range of environmental temperatures and various operational scenarios. To tackle this challenge, a substantial volume of experimental data, capable of effectively reflecting the patterns of spindle thermal error variations, was collected through experiments conducted at multiple speeds and under various operational scenarios. Subsequently, the acquired thermal error data underwent intermittent multivariate time series transformation (IMTS) to suit the serialized deep learning model. The study introduces the Crossformer model into the field of thermal error modeling for the first time, which is a variant of the Transformer model. The Crossformer model exhibits remarkable adaptability to temporal aspects while effectively maintaining its focus on data features. Ultimately, this study resulted in the development of the IMTS-CrossformerR experimental thermal error model. Throughout the research, a comprehensive examination of various models was undertaken, including two traditional Transformer models and other thermal error deep learning and machine learning models. The results indicate that the proposed model outperforms its counterparts across multiple model metrics and predictive capabilities. Particularly noteworthy is its substantial improvement in the range (± 5) ratio of residual fluctuations reaching 95.7%, a key engineering metric. [ABSTRACT FROM AUTHOR]

This research paper presents a comprehensive investigation into the utilization of color image processing technologies and deep learning algorithms in the development of a robot vision system specifically designed for 8-ball billiards. The sport of billiards, with its various games and ball arrangements, presents unique challenges for robotic vision systems. The proposed methodology addresses these challenges through two main components: object detection and ball pattern recognition. Initially, a robust algorithm is employed to detect the billiard balls using color space transformation and thresholding techniques. This is followed by determining the position of the billiard table through strategic cropping and isolation of the primary table area. The crucial phase involves the intricate task of recognizing ball patterns to differentiate between solid and striped balls. To achieve this, a modified convolutional neural network is utilized, leveraging the Xception network optimized by an innovative algorithm known as the Improved Chaos African Vulture Optimization (ICAVO) algorithm. The ICAVO algorithm enhances the Xception network's performance by efficiently exploring the solution space and avoiding local optima. The results of this study demonstrate a significant enhancement in recognition accuracy, with the Xception/ICAVO model achieving remarkable recognition rates for both solid and striped balls. This paves the way for the development of more sophisticated and efficient billiards robots. The implications of this research extend beyond 8-ball billiards, highlighting the potential for advanced robotic vision systems in various applications. The successful integration of color image processing, deep learning, and optimization algorithms shows the effectiveness of the proposed methodology. This research has far-reaching implications that go beyond just billiards. The cutting-edge robotic vision technology can be utilized for detecting and tracking objects in different sectors, transforming industrial automation and surveillance setups. By combining color image processing, deep learning, and optimization algorithms, the system proves its effectiveness and flexibility. The innovative approach sets the stage for creating advanced and productive robotic vision systems in various industries. [ABSTRACT FROM AUTHOR]

In the globalization trend, China's cultural heritage is in danger of gradually disappearing. The protection and inheritance of these precious cultural resources has become a critical task. This paper focuses on the Miao batik culture in Guizhou Province, China, and explores the application of knowledge graphs, natural language processing, and deep learning techniques in the promotion and protection of batik culture. We propose a dual-channel mechanism that integrates semantic and visual information, aiming to connect batik pattern features with cultural connotations. First, we use natural language processing techniques to automatically extract batik-related entities and relationships from the literature, and construct and visualize a structured batik pattern knowledge graph. Based on this knowledge graph, users can textually search and understand the images, meanings, taboos, and other cultural information of specific patterns. Second, for the batik pattern classification, we propose an improved ResNet34 model. By embedding average pooling and convolutional operations into the residual blocks and introducing long-range residual connections, the classification performance is enhanced. By inputting pattern images into this model, their categories can be accurately identified, and then the underlying cultural connotations can be understood. Experimental results show that our model outperforms other mainstream models in evaluation metrics such as accuracy, precision, recall, and F1-score, achieving 94.46%, 94.47%, 93.62%, and 93.8%, respectively. This research provides new ideas for the digital protection of batik culture and demonstrates the great potential of artificial intelligence technology in cultural heritage protection. [ABSTRACT FROM AUTHOR]

Accurate power load forecasting is crucial for the sustainable operation of smart grids. However, the complexity and uncertainty of load, along with the large-scale and high-dimensional energy information, present challenges in handling intricate dynamic features and long-term dependencies. This paper proposes a computational approach to address these challenges in short-term power load forecasting and energy information management, with the goal of accurately predicting future load demand. The study introduces a hybrid method that combines multiple deep learning models, the Gated Recurrent Unit (GRU) is employed to capture long-term dependencies in time series data, while the Temporal Convolutional Network (TCN) efficiently learns patterns and features in load data. Additionally, the attention mechanism is incorporated to automatically focus on the input components most relevant to the load prediction task, further enhancing model performance. According to the experimental evaluation conducted on four public datasets, including GEFCom2014, the proposed algorithm outperforms the baseline models on various metrics such as prediction accuracy, efficiency, and stability. Notably, on the GEFCom2014 dataset, FLOP is reduced by over 48.8%, inference time is shortened by more than 46.7%, and MAPE is improved by 39%. The proposed method significantly enhances the reliability, stability, and cost-effectiveness of smart grids, which facilitates risk assessment optimization and operational planning under the context of information management for smart grid systems. [ABSTRACT FROM AUTHOR]

The recent adoption of deep learning-based models for the processing and coding of multimedia signals has brought noticeable gains in performance, which have established deep learning-based solutions as the uncontested state-of-the-art both for computer vision tasks, targeting machine consumption, as well as, more recently, coding applications, targeting human visualization. Traditionally, applications requiring both coding and computer vision processing require first decoding the bitstream and then applying the computer vision methods to the decompressed multimedia signals. However, the adoption of deep learning-based solutions enables the use of compressed domain computer vision processing, with gains in performance and computational complexity over the decompressed domain approach. For point clouds (PCs), these gains have been demonstrated in the single available compressed domain computer vision processing solution, named Compressed Domain PC Classifier, which processes JPEG Pleno PC coding (PCC) compressed streams using a PC classifier largely compatible with the state-of-the-art spatial domain PointGrid classifier. However, the available Compressed Domain PC Classifier presents strong limitations by imposing a single, specific input size which is associated to specific JPEG Pleno PCC configurations; this limits the compression performance as these configurations are not ideal for all PCs due to their different characteristics, notably density. To overcome these limitations, this paper proposes the first Adaptive Compressed Domain PC Classifier solution which includes a novel adaptive bridge model that allows to process the JPEG Pleno PCC encoded bit streams using different coding configurations, now maximizing the compression efficiency. Experimental results show that the novel Adaptive Compressed Domain PC Classifier allows JPEG PCC to achieve better compression performance by not imposing a single, specific coding configuration for all PCs, regardless of its different characteristics. Moreover, the added adaptability power can achieve slightly better PC classification performance than the previous Compressed Domain PC Classifier and largely better PC classification performance (and lower number of weights) than the PointGrid PC classifier working in the decompressed domain. [ABSTRACT FROM AUTHOR]

In this paper, a method based on transfer learning is proposed to recover the three-dimensional shape of cultural relics faces from a single old photo. It can simultaneously reconstruct the three-dimensional facial structure and align the texture of the cultural relics with fewer training samples. The UV position map is used to represent the three-dimensional shape in space and act as the output of the network. A convolutional neural network is used to reconstruct the UV position map from a single 2D image. In the training process, the human face data is used for pre-training, and then a small amount of artifact data is used for fine-tuning. A deep learning model with strong generalization ability is trained with fewer artifact data, and a three-dimensional model of the cultural relic face can be reconstructed from a single old photograph. The methods can train more complex deep networks without a large amount of cultural relic data, and no over-fitting phenomenon occurs, which effectively solves the problem of fewer cultural relic samples. The method is verified by restoring a Chinese Terracotta Warrior with facial cracks and a Buddha with a broken nose. Other applications can be used in the fields such as texture recovery, facial feature extraction, and three-dimensional model estimation of the damaged cultural relics or sculptures in the photos. [ABSTRACT FROM AUTHOR]

Over the past decades, the software industry has expanded to include all industries. Since stakeholders tend to use it to get their work done, software houses seek to estimate the cost of the software, which includes calculating the effort, time, and resources required. Although many researchers have worked to estimate it, the prediction accuracy results are still inaccurate and unstable. Estimating it requires a lot of effort. Therefore, there is an urgent need for modern techniques that contribute to cost estimation. This paper seeks to present a model based on deep learning and machine learning techniques by combining convolutional neural networks (CNN) and the particle swarm algorithm (PSO) in the context of time series forecasting, which enables feature extraction and automatic tuning of hyperparameters, which reduces the manual effort of selecting parameters and contributes to fine-tuning. The use of PSO also enhances the robustness and generalization ability of the CNN model and its iterative nature allows for efficient discovery of hyperparameter similarity. The model was trained and tested on 13 different benchmark datasets and evaluated through six metrics: mean absolute error (MAE), mean square error (MSE), mean magnitude relative error (MMRE), root mean square error (RMSE), median magnitude relative error (MdMRE), and prediction accuracy (PRED). Comparative results reveal that the performance of the proposed model is better than other methods for all datasets and evaluation criteria. The results were very promising for predicting software cost estimation. [ABSTRACT FROM AUTHOR]

The prevalence of cardiovascular disease (CVD) has surged in recent years, making it the foremost cause of mortality among humans. The Electrocardiogram (ECG), being one of the pivotal diagnostic tools for cardiovascular diseases, is increasingly gaining prominence in the field of machine learning. However, prevailing neural network models frequently disregard the spatial dimension features inherent in ECG signals. In this paper, we propose an ECG autoencoder network architecture incorporating low-rank attention (LRA-autoencoder). It is designed to capture potential spatial features of ECG signals by interpreting the signals from a spatial perspective and extracting correlations between different signal points. Additionally, the low-rank attention block (LRA-block) obtains spatial features of electrocardiogram signals through singular value decomposition, and then assigns these spatial features as weights to the electrocardiogram signals, thereby enhancing the differentiation of features among different categories. Finally, we utilize the ResNet-18 network classifier to assess the performance of the LRA-autoencoder on both the MIT-BIH Arrhythmia and PhysioNet Challenge 2017 datasets. The experimental results reveal that the proposed method demonstrates superior classification performance. The mean accuracy on the MIT-BIH Arrhythmia dataset is as high as 0.997, and the mean accuracy and F 1 -score on the PhysioNet Challenge 2017 dataset are 0.850 and 0.843. [ABSTRACT FROM AUTHOR]

The magnetic flux leakage (MFL) technique is widely employed for nondestructive testing of ferromagnetic specimens and materials, including wire ropes, bridge cables, and pipelines. As regards the MFL testing, extracting features from MFL signals is crucial for defect recognition and estimation of corresponding widths. Deep learning has been extensively used for feature extraction, but it often performs inadequately on a small sample dataset. To address this limitation, this paper develops a network framework that combines the Wavelet Scattering Transform (WST) and Neural Networks (NN) for defect width estimation. The WST is a knowledge-based feature extraction technique with a structure similar to convolutional neural networks. It offers a translation-invariant representation of signal features using a redundant dictionary of wavelets. The NN then maps the WST feature representation to the defect width information. Experiments on real steel plates with defects are carried out to validate the effectiveness of the proposed framework. Quantitative comparisons of the experimental results demonstrate that the proposed framework achieves better estimation performance in handling MFL signals and has superiority in scenarios with limited training samples. [ABSTRACT FROM AUTHOR]

This paper delves into the methodology employed in examining lean premixed turbulent flame fronts extracted from Planar Laser Induced Fluorescence (PLIF) images at elevated pressures. In such flow regimes, the PLIF signal suffers from significant collisional quenching, typically resulting in image data with low signal-to-noise ratio (SNR). This poses severe difficulties for conventional flame front extraction algorithms based on intensity gradients and requires intense user intervention to yield acceptable results. In this work, we propose Convolutional Neural Network (CNN)-based Deep Learning (DL) models as an alternative to problem specific conventional methods. The pretrained DL models were fine-tuned, employing data augmentation, on a small annotated dataset including a variety of conditions between SNR ≈ 1.6 to 2.6 and subsequently evaluated. All DL models significantly outperformed the best-scoring conventional implementation both quantitatively and visually, while having similar inference times. IoU-scores and Recall values were found to be up to a factor ≈ 1.2 and ≈ 2.5 higher, respectively, with ≈ 1.15 times improved Precision. Small-scale structures were captured much better with fewer erroneous predictions, becoming particularly pronounced for the lower SNR data investigated. Moreover, by applying artificially modeled noise, it was shown that the range of image conditions in terms of SNR that can be reliably processed extends well beyond the images included in the training data, and satisfactory segmentation performances were found for SNR as low as ≈ 1.1. The presented DL-based flame front detection algorithm marks a methodology with significantly increased detection performance, while a similar computational effort for inference is achieved and the need for user-based parameter tuning is eliminated. It enables a very accurate extraction of instantaneous flame fronts in large image datasets where supervised processing is infeasible, unlocking unprecedented possibilities for the study of flame dynamics and instability mechanisms at industry-relevant conditions. [ABSTRACT FROM AUTHOR]

In aerial image detection, difficulties in feature extraction and low detection accuracy arise due to background interference, occlusion, and the presence of multiple small objects. This paper proposes a DM-YOLOX aerial object target detection method with intensive attention mechanism. Firstly, the proposed approach incorporates coordinate attention (CA) and a dense connection method into the backbone network architecture, enabling adaptive channel weighting throughout the feature extraction process. This facilitates the enhancement of significant features while suppressing less relevant ones, thereby augmenting the network's capacity to represent object features and ensuring retention and reinforcement of key features. Secondly, the multibranch extraction module (MBE) is incorporated into the feature fusion network to enhance the network's ability in extracting multi-scale feature information from images with extensive coverage, thereby enhancing the detection accuracy and efficiency of small- and medium-sized objects in complex scenes. Finally, the utilization of SIoU instead of IoU as the bounding box loss function effectively addresses the issue of mismatch between real and predicted boxes, leading to accelerated network convergence and improved performance during model training. After training and testing on the VisDrone 2019 dataset, this method effectively detects small objects in complex environments. The DM-YOLOX model shows a significant improvement of 2.7% in mAP compared to the baseline network, while achieving an 8% increase in frames per second (FPS). [ABSTRACT FROM AUTHOR]

Recurrent neural networks (RNNs) are widely utilized in neural network research to capture spatiotemporal features in video data. However, their effectiveness heavily relies on the spatial features upon which they trained. This paper introduces innovative ensembles of features for constructing frame-wise structures by employing impactful neural network models with innovative training pipelines. These features are designed to enhance the recognition of hand gesture videos using RNN by leveraging temporal information. Recognizing hand gestures from videos is a complex task that presents considerable challenges. One notable challenge is the overlap in gesture motion, where different gesture categories exhibit similar hand poses within a single video clip. To overcome this issue, we were motivated to develop extensive and diverse features that offer a more comprehensive description of the gesture video clips, thereby mitigating recognition problems caused by images overlapping. Overall, our efforts to generate diverse features have yielded promising results in enhancing the recognition of hand gestures from videos, particularly in scenarios where overlap poses a significant challenge. We have combined the extracted features from a deep neural network trained from scratch with features obtained from various standard neural networks (Self-Organizing Map, Radial Base Function) that are trained to enhance the deep-trained features. The mutual arrangement for combining the shared features has configured new frame-wise image features. Furthermore, we have provided a performance comparison of the newly constructed frame-wise features through time-sharing to train RNN for recognition. The proposed models have been evaluated on two-hand gesture video datasets, where a preserving gesture sequence is crucial due to overlapping motions. Our work demonstrates a significant improvement in performance for both datasets. [ABSTRACT FROM AUTHOR]

With the massive amount of data available on the Internet, many users face problems when they need access to the information and goods they need. Adapting information to user needs has become a complex and time-consuming process. Recommender systems are powerful tools for guiding users in electronic settings to information, services, and goods of interest. With the ability to identify users and predict their preferences, recommender systems can extract information likely to be of interest to users from vast amounts of data and save time and energy by providing them with relevant recommendations. Therefore, in this paper, a framework for a recommender system is proposed, which consists of four main phases. In the first phase, the preprocessing operation is performed. The purpose of this phase is to create an ontology model for products based on the convolutional neural network method. Data collection operations are carried out in the second phase. The purpose of this phase is to receive and store user information based on behavior and different criteria. The third phase is related to creating an ontology. The purpose of this phase is to create an ontology model for user behavior using OWL libraries. Finally, in the last phase, finding similarities and presented a proposal. The purpose of this phase is the necessary calculations of the proposed framework in the similarity finding section using ontology models. Simulation results show that the proposed framework measures MAE (more than 10 and 15%), RMSE (more than 12 and 16%), precision (less than 10 and 13%), recall (more than 25 and 28%), F1-score (higher than 25 and 30%) and Score of User (higher than 15 and 17%) outperform two related approaches, namely CF and CF+ Ontology, respectively. [ABSTRACT FROM AUTHOR]

One of the most important strategies used to mitigate the adverse impacts of traffic growth on mobile networks is caching. By caching at the edge, the backhaul traffic load is reduced, and the quality of service for the user is increased. Developing an effective caching algorithm requires accurate prediction of the future popularity of the content, which is a challenging issue. In recent years, deep learning models have achieved high predictive accuracy due to advancements in data availability and increased computing power. In this paper, we present a caching algorithm called the user preference-aware content caching algorithm (UPACA). This algorithm is specifically designed for an edge content delivery platform where users can access content services provided by a remote content provider. UPACA operates in two steps. In the first step, the proposed collaborative filtering-based popularity prediction algorithm (CFPA) is used to predict future content popularities. CFPA utilizes a gated residual variational autoencoder collaborative filtering model to predict users' future preferences and calculate the future popularity of content. This algorithm considers the popularity of the content as well as the number and timing of content requests. Experimental results demonstrate that UPACA outperforms previous methods in terms of cache hit rates and user utilities. [ABSTRACT FROM AUTHOR]

Visual and audio events simultaneously occur and both attract attention. However, most existing saliency prediction works ignore the influence of audio and only consider vision modality. In this paper, we propose a multi-task learning method for audio–visual saliency prediction and sound source localization on multi-face video by leveraging visual, audio and face information. Specifically, we first introduce a large-scale database of multi-face video in visual-audio condition, containing eye-tracking data and sound source annotations. Using this database, we find that sound influences human attention, and conversely attention offers a cue to determine sound source on multi-face video. Guided by these findings, an audio–visual multi-task network (AVM-Net) is introduced to predict saliency and locate sound source. AVM-Net consists of three branches corresponding to visual, audio and face modalities. The visual branch has a two-stream architecture to capture spatial and temporal information. Face and audio branches encode audio signals and faces, respectively. Finally, a spatio-temporal multi-modal graph is constructed to model the interaction among multiple faces. With joint optimization of these branches, the intrinsic correlation of the tasks of saliency prediction and sound source localization is utilized and their performance is boosted by each other. Experiments show that the proposed method outperforms 12 state-of-the-art saliency prediction methods, and achieves competitive results in sound source localization. [ABSTRACT FROM AUTHOR]

Medical diagnosis can be severely hindered by distorted medical images, especially in the analysis of Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) images. Therefore, enhancing the accuracy of diagnostic imaging and inpainting damaged areas are essential for medical diagnosis. Over the past decade, image inpainting techniques have advanced due to deep learning and multimedia information. In this paper, we proposed a deep convolutional autoencoder network with improved parameters as a robust method for inpainting non-anatomical objects in MRI and CT images. Traditional approaches based on the exemplar methods are much less effective than deep learning methods in capturing high-level features. However, the inpainted regions would appear blurr and with global inconsistency. To handle the fuzzy problem, we enhanced the network model by introducing skip connections between mirrored layers in the encoder and decoder stacks. This allowed the generative process of the inpainting region to directly use the low-level feature information of the processed image. To provide both pixel-accurate and local-global contents consistency, the proposed model is trained with a combination of the typical pixel-wise reconstruction loss and two adversarial losses, which makes the inpainted output seem more realistic and consistent with its surrounding contexts. As a result, the proposed approach is much faster than existing methods while providing unprecedented qualitative and quantitative evaluation with a high inpainting inception score of 10.58, peak signal-to-noise ratio (PSNR) 52.44, structural similarity index (SSIM) 0.95, universal image quality index (UQI) 0.96, and mean squared error (MSE) 40.73 for CT and MRI images. This offers a promising avenue for enhancing image fidelity, potentially advancing clinical decision-making and patient care in neuroimaging practice. [ABSTRACT FROM AUTHOR]

Conventional photography can only provide a two-dimensional image of the scene, whereas emerging imaging modalities such as light field enable the representation of higher dimensional visual information by capturing light rays from different directions. Light fields provide immersive experiences, a sense of presence in the scene, and can enhance different vision tasks. Hence, research into light field processing methods has become increasingly popular. It does, however, come at the cost of higher data volume and computational complexity. With the growing deployment of machine-learning and deep architectures in image processing applications, a paradigm shift toward learning-based approaches has also been observed in the design of light field processing methods. Various learning-based approaches are developed to process the high volume of light field data efficiently for different vision tasks while improving performance. Taking into account the diversity of light field vision tasks and the deployed learning-based frameworks, it is necessary to survey the scattered learning-based works in the domain to gain insight into the current trends and challenges. This paper aims to review the existing learning-based solutions for light field imaging and to summarize the most promising frameworks. Moreover, evaluation methods and available light field datasets are highlighted. Lastly, the review concludes with a brief outlook for future research directions. [ABSTRACT FROM AUTHOR]

In recent years, the growth spurt of medical imaging data has led to the development of various machine learning algorithms for various healthcare applications. The MedMNISTv2 dataset, a comprehensive benchmark for 2D biomedical image classification, encompasses diverse medical imaging modalities such as Fundus Camera, Breast Ultrasound, Colon Pathology, Blood Cell Microscope etc. Highly accurate classifications performed on these datasets is crucial for identification of various diseases and determining the course of treatment. This research paper presents a comprehensive analysis of four subsets within the MedMNISTv2 dataset: BloodMNIST, BreastMNIST, PathMNIST and RetinaMNIST. Each of these selected datasets is of diverse data modalities and comes with various sample sizes, and have been selected to analyze the efficiency of the model against diverse data modalities. The study explores the idea of assessing the Vision Transformer Model's ability to capture intricate patterns and features crucial for these medical image classification and thereby transcend the benchmark metrics substantially. The methodology includes pre-processing the input images which is followed by training the ViT-base-patch16-224 model on the mentioned datasets. The performance of the model is assessed using key metrices and by comparing the classification accuracies achieved with the benchmark accuracies. With the assistance of ViT, the new benchmarks achieved for BloodMNIST, BreastMNIST, PathMNIST and RetinaMNIST are 97.90%, 90.38%, 94.62% and 57%, respectively. The study highlights the promise of Vision transformer models in medical image analysis, preparing the way for their adoption and further exploration in healthcare applications, aiming to enhance diagnostic accuracy and assist medical professionals in clinical decision-making. [ABSTRACT FROM AUTHOR]

The resolution of traffic congestion and personal safety issues holds paramount importance for human’s life. The ability of an autonomous driving system to navigate complex road conditions is crucial. Deep learning has greatly facilitated machine vision perception in autonomous driving. Aiming at the problem of small target detection in traditional YOLOv5s, this paper proposes an optimized target detection algorithm. The C3 module on the algorithm’s backbone is upgraded to the CBAMC3 module, introducing a novel GELU activation function and EfficiCIoU loss function, which accelerate convergence on position loss lbox, confidence loss lobj, and classification loss lcls, enhance image learning capabilities and address the issue of inaccurate detection of small targets by improving the algorithm. Testing with a vehicle-mounted camera on a predefined route effectively identifies road vehicles and analyzes depth position information. The avoidance model, combined with Pure Pursuit and MPC control algorithms, exhibits more stable variations in vehicle speed, front-wheel steering angle, lateral acceleration, etc., compared to the non-optimized version. The robustness of the driving system's visual avoidance functionality is enhanced, further ameliorating congestion issues and ensuring personal safety. [ABSTRACT FROM AUTHOR]

Recent research has focused extensively on employing Deep Learning (DL) techniques, particularly Convolutional Neural Networks (CNN), for Speech Emotion Recognition (SER). This study addresses the burgeoning interest in leveraging DL for SER, specifically focusing on Punjabi language speakers. The paper presents a novel approach to constructing and preprocessing a labeled speech corpus using diverse social media sources. By utilizing spectrograms as the primary feature representation, the proposed algorithm effectively learns discriminative patterns for emotion recognition. The method is evaluated on a custom dataset derived from various Punjabi media sources, including films and web series. Results demonstrate that the proposed approach achieves an accuracy of 69%, surpassing traditional methods like decision trees, Naïve Bayes, and random forests, which achieved accuracies of 49%, 52%, and 61% respectively. Thus, the proposed method improves accuracy in recognizing emotions from Punjabi speech signals. [ABSTRACT FROM AUTHOR]

A neural network model needs to be manually designed for ancient mural dynasty recognition, and this paper proposes an ancient mural dynasty recognition algorithm that is based on a neural architecture search (NAS). First, the structural edge information of mural images is extracted for use by the neural network model in recognizing mural missions. Second, an NAS algorithm that is based on contrast selection (CS) simplifies the architecture search to an incremental CS and then searches for the optimal network architecture on the mural dataset. Finally, the identified optimal network architecture is used for training and testing to complete the mural dynasty recognition task. The results show that the top accuracy of the proposed method on the mural dataset is 88.10%, the recall rate is 87.52%, and the precision rate is 87.69%. Each evaluation index used by the neural network model is superior to that of classical network models such as AlexNet and ResNet-50. Compared with NAS methods such as ASNG and MIGO, the accuracy of mural dynasty recognition is higher by an average of 4.27% when using the proposed method. The proposed method is verified on CIFAR-10, CIFAR-100, ImageNet16-120 and other datasets and achieves a good recognition accuracy in the NAS-bench-201 search space, which averages 93.26%, 70.73% and 45.34%, respectively, on the abovementioned datasets. [ABSTRACT FROM AUTHOR]

Monitoring battery health is critical for electric vehicle maintenance and safety. However, existing research has limited focus on predicting capacity degradation paths for entire battery packs, representing a gap between literature and application. This paper proposes a multi-horizon time series forecasting model (MMRNet, which consists of MOSUM, flash-MUSE attention, and RNN core modules) to predict the capacity degradation paths of battery packs. First, domain knowledge (DK) extracts the features from extensive battery aging datasets. The moving sum (MOSUM) and improved flash multi-scale attention (MUSE) methods are proposed to capture capacity curve mutations and multi-scale trends. Dynamic dropout training, transposition linear architecture, residual connections, and module stacking improve model generalization and accuracy. Experiments on battery pack and cell datasets demonstrate the superior performance of MMRNet over six baseline time series models. The proposed data-driven approach effectively predicts battery degradation trajectories, with implications for condition monitoring and the safety of electric vehicles. [ABSTRACT FROM AUTHOR]

Protein-ligand binding affinity plays a pivotal role in drug development, particularly in identifying potential ligands for target disease-related proteins. Accurate affinity predictions can significantly reduce both the time and cost involved in drug development. However, highly precise affinity prediction remains a research challenge. A key to improve affinity prediction is to capture interactions between proteins and ligands effectively. Existing deep-learning-based computational approaches use 3D grids, 4D tensors, molecular graphs, or proximity-based adjacency matrices, which are either resource-intensive or do not directly represent potential interactions. In this paper, we propose atomic-level distance features and attention mechanisms to capture better specific protein-ligand interactions based on donor-acceptor relations, hydrophobicity, and π -stacking atoms. We argue that distances encompass both short-range direct and long-range indirect interaction effects while attention mechanisms capture levels of interaction effects. On the very well-known CASF-2016 dataset, our proposed method, named Distance plus Attention for Affinity Prediction (DAAP), significantly outperforms existing methods by achieving Correlation Coefficient (R) 0.909, Root Mean Squared Error (RMSE) 0.987, Mean Absolute Error (MAE) 0.745, Standard Deviation (SD) 0.988, and Concordance Index (CI) 0.876. The proposed method also shows substantial improvement, around 2% to 37%, on five other benchmark datasets. The program and data are publicly available on the website https://gitlab.com/mahnewton/daap. Scientific Contribution Statement This study innovatively introduces distance-based features to predict protein-ligand binding affinity, capitalizing on unique molecular interactions. Furthermore, the incorporation of protein sequence features of specific residues enhances the model's proficiency in capturing intricate binding patterns. The predictive capabilities are further strengthened through the use of a deep learning architecture with attention mechanisms, and an ensemble approach, averaging the outputs of five models, is implemented to ensure robust and reliable predictions. [ABSTRACT FROM AUTHOR]

This paper aims to propose a prediction method based on Deep Learning (DL) and Internet of Things (IoT) technology, focusing on the ecological security and tourist satisfaction of Ice-and-Snow Tourism (IST) to solve practical problems in this field. Accurate predictions of ecological security and tourist satisfaction in IST have been achieved by collecting and analyzing environment and tourist behavior data and combining with DL models, such as convolutional and recurrent neural networks. The experimental results show that the proposed method has significant advantages in performance indicators, such as accuracy, F1 score, Mean Squared Error (MSE), and correlation coefficient. Compared to other similar methods, the method proposed improves accuracy by 3.2%, F1 score by 0.03, MSE by 0.006, and correlation coefficient by 0.06. These results emphasize the important role of combining DL with IoT technology in predicting ecological security and tourist satisfaction in IST. [ABSTRACT FROM AUTHOR]

The challenge of developing an Android malware detection framework that can identify malware in real-world apps is difficult for academicians and researchers. The vulnerability lies in the permission model of Android. Therefore, it has attracted the attention of various researchers to develop an Android malware detection model using permission or a set of permissions. Academicians and researchers have used all extracted features in previous studies, resulting in overburdening while creating malware detection models. But, the effectiveness of the machine learning model depends on the relevant features, which help in reducing the value of misclassification errors and have excellent discriminative power. A feature selection framework is proposed in this research paper that helps in selecting the relevant features. In the first stage of the proposed framework, t-test, and univariate logistic regression are implemented on our collected feature data set to classify their capacity for detecting malware. Multivariate linear regression stepwise forward selection and correlation analysis are implemented in the second stage to evaluate the correctness of the features selected in the first stage. Furthermore, the resulting features are used as input in the development of malware detection models using three ensemble methods and a neural network with six different machine-learning algorithms. The developed models' performance is compared using two performance parameters: F-measure and Accuracy. The experiment is performed by using half a million different Android apps. The empirical findings reveal that malware detection model developed using features selected by implementing proposed feature selection framework achieved higher detection rate as compared to the model developed using all extracted features data set. Further, when compared to previously developed frameworks or methodologies, the experimental results indicates that model developed in this study achieved an accuracy of 98.8%. [ABSTRACT FROM AUTHOR]