Search

One of the most widely used measures of scientific impact is the number of citations. However, due to its heavy-tailed distribution, citations are fundamentally difficult to predict but can be improved. This study was aimed at investigating the factors and parts influencing the citation number of a scientific paper in the otology field. Therefore, this work proposes a new solution that utilizes machine learning and natural language processing to process English text and provides a paper citation as the predicted results. Different algorithms are implemented in this solution, such as linear regression, boosted decision tree, decision forest, and neural networks. The application of neural network regression revealed that papers' abstracts have more influence on the citation numbers of otological articles. This new solution has been developed in visual programming using Microsoft Azure machine learning at the back end and Programming Without Coding Technology at the front end. We recommend using machine learning models to improve the abstracts of research articles to get more citations. [ABSTRACT FROM AUTHOR]

Machine learning (ML), a form of artificial intelligence (AI), is being increasingly employed in neurology. Reported performance metrics often match or exceed the efficiency of average clinicians. The neurologist is easily baffled by the underlying concepts and terminologies associated with ML studies. The superlative performance metrics of ML algorithms often hide the opaque nature of its inner workings. Questions regarding ML model's interpretability and reproducibility of its results in real-world scenarios, need emphasis. Given an abundance of time and information, the expert clinician should be able to deliver comparable predictions to ML models, a useful benchmark while evaluating its performance. Predictive performance metrics of ML models should not be confused with causal inference between its input and output. ML and clinical gestalt should compete in a randomized controlled trial before they can complement each other for screening, triaging, providing second opinions and modifying treatment. [ABSTRACT FROM AUTHOR]

As the world's transport infrastructure ages, the importance of bridge condition monitoring is becoming increasingly acknowledged. Large-scale deployment of existing inspection and monitoring techniques is infeasible due to cost and logistical challenges. The concept of using sensors located within vehicles for low cost 'drive-by' monitoring has become the focus of much attention in recent years. This paper presents a new data-driven approach for drive-by bridge monitoring. Machine learning techniques are leveraged to allow the influence of vehicle speed to be considered and the Operating Deflection Shape Ratio (ODSR) is presented as an alternative damage-sensitive feature to the commonly used frequency spectrum. Extensive laboratory experiments demonstrate that the method is capable of detecting midspan cracking and seized bearings. A statistical classification approach is adopted to classify damage indicators as either 'damaged' or 'healthy'. Classification accuracy is seen to vary between 65-96% and is similar whether using the frequency spectrum or ODSR. Based on the results of the laboratory testing, it is expected that this approach could be implemented on a large scale to act as an early warning tool for infrastructure owners to identify bridges presenting signs of distress or deterioration. [ABSTRACT FROM AUTHOR]

Simple Summary: Risk assessment in early breast cancer is critical for clinical decisions, but defining risk categories poses a significant challenge. The integration of conventional histopathology and biomarkers with artificial intelligence (AI) techniques, including machine learning and deep learning, has the potential to offer more precise information. AI applications extend beyond detection to histological subtyping, grading, and molecular feature identification. The successful integration of AI into clinical practice requires collaboration between histopathologists, molecular pathologists, computational pathologists, and oncologists to optimize patient outcomes. Effective risk assessment in early breast cancer is essential for informed clinical decision-making, yet consensus on defining risk categories remains challenging. This paper explores evolving approaches in risk stratification, encompassing histopathological, immunohistochemical, and molecular biomarkers alongside cutting-edge artificial intelligence (AI) techniques. Leveraging machine learning, deep learning, and convolutional neural networks, AI is reshaping predictive algorithms for recurrence risk, thereby revolutionizing diagnostic accuracy and treatment planning. Beyond detection, AI applications extend to histological subtyping, grading, lymph node assessment, and molecular feature identification, fostering personalized therapy decisions. With rising cancer rates, it is crucial to implement AI to accelerate breakthroughs in clinical practice, benefiting both patients and healthcare providers. However, it is important to recognize that while AI offers powerful automation and analysis tools, it lacks the nuanced understanding, clinical context, and ethical considerations inherent to human pathologists in patient care. Hence, the successful integration of AI into clinical practice demands collaborative efforts between medical experts and computational pathologists to optimize patient outcomes. [ABSTRACT FROM AUTHOR]

This paper aims to build a machine learning and a neural network model to detect the probability of money laundering in banks. The paper's data came from a simulation of actual transactions flagged for money laundering in Middle Eastern banks. The main findings highlight that criminal networks mainly use the integration stage to integrate money into the financial system. Fraudsters prefer to launder funds in the early hours, morning followed by the business day's afternoon time intervals. Additionally, the Naïve Bayes and Random Forest classifiers were identified as the two best-performing models to predict bank money laundering transactions. [ABSTRACT FROM AUTHOR]

This paper explores the different insider employee-led cyber frauds (IECF) based on the recent large-scale fraud events of prominent Indian banking institutions. Examining the different types of fraud and appropriate control measures will protect the banking industry from fraudsters. In this study, we identify and classify Cyber Fraud (CF), map the severity of the fraud on a scale of priority, test the mitigation effectiveness, and propose optimal mitigation measures. The identification and classification of CF losses were based on a literature review and focus group discussions with risk and vigilance officers and cyber cell experts. The CF was analyzed using secondary data. We predicted and prioritized CF based on machine learning-derived Random Forest (RF). An efficient fraud mitigation model was developed based on an offender-victim-centric approach. Mitigation is advised both before and after fraud occurs. Through the findings of this research, banks and fraud investigators can prevent CF by detecting it quickly and controlling it on time. This study proposes a structured, sustainable CF mitigation plan that protects banks, employees, regulators, customers, and the economy, thus saving time, resources, and money. Further, these mitigation measures will improve the reputation of the Indian banking industry and ensure its survival. [ABSTRACT FROM AUTHOR]

Many current medical image segmentation methods utilize convolutional neural networks (CNNs), with some extended U-Net-based networks relying on deep feature representations to achieve satisfactory results. However, due to the limited receptive fields of convolutional architectures, they are unable to explicitly model the varying range dependencies present in medical images. Recently, advancements in large kernel convolution have allowed for the extraction of a wider range of low frequency information, making this task more achievable. In this paper, we propose TBUnet for solving the problem of difficult to accurately segment lesions with heterogeneous structures and fuzzy borders, such as melanoma, colon polyps and breast cancer. The TBUnet is a pure convolutional network with three branches for extracting high frequency information, low frequency information, and boundary information, respectively. It is capable of extracting features in various areas. To fuse the feature maps from the three branches, TBUnet presents the FL (fusion layer) module, which is based on threshold and logical operation. We design the FE (feature enhancement) module on the skip-connection to emphasize the fine-grained features. In addition, our method varies the number of input channels in different branches at each stage of the network, so that the relationship between low and high frequency features can be learned. TBUnet yields 91.08 DSC on ISIC-2018 for melanoma segmentation, and achieves better performance than state-of-the-art medical image segmentation methods. Furthermore, experimental results with 82.48 DSC and 89.04 DSC obtained on the BUSI dataset and the Kvasir-SEG dataset show that TBUnet outperforms the advanced segmentation methods. Experiments demonstrate that TBUnet has excellent segmentation performance and generalisation capability. [ABSTRACT FROM AUTHOR]

Deficits in social verbal communication in individuals with Social Communication Disorder (SCD) is of concern and SCD in the human community is prevalent in large population throughout the globe. Deficits in verbal social communication are prevalent in a large population. This paper aimed to propose internet connected multi-system architecture which is capable to support verbal communication in a social environment for individuals with social communication deficits. Implementation methodology was included with corpus collection for specific communication, deep learning based machine training for intelligent communication, and implementation of the trained algorithm on internet connected electronic multiple social communication devices. The implemented system is smart enough to initiate and maintain two types of communication; the first type includes communication between multiple individuals on the remote location and the second type includes communication with the individual present in the physical listening range. The system was investigated in terms of its algorithmic parameters and found 97% to 100% in terms of training and testing accuracy with negligible mean squared error. Vocal-Friend analysed results based on audio-bot simulative conditions provide more than 91% accuracy, interaction rate and fallback rate. On the basis of the satisfaction analysis, above average results were noticed. In terms of technical implementations and satisfaction analysis, results found acceptable with above average score. Proposed framework is easy to use by caregivers with even having little knowledge. Support individual with deficit to learn social verbal communication skill to survive in society. Aiding parents, caregivers and professionals to understand the communication needs of individuals with communication deficits. Since technology is also grooming in the domain of rehabilitation, so this system could be used in various future applications such as social robots, social virtual assistants etc. [ABSTRACT FROM AUTHOR]

In the field of gas turbine (GT) monitoring and diagnostics, GT trip is of great concern for manufactures and users. In fact, due to the number of issues that may cause a trip, its occurrence is not infrequent, and its prediction is a quite unexplored field of research. This is demonstrated by the fact that, despite its relevance, a comprehensive study on the reliability of predicting GT trip has not been proposed yet. To fill this gap, this paper investigates the fusion of five data-driven base models by means of voting and stacking, in order to improve prediction accuracy and robustness. The five benchmark supervised machine learning and deep learning classifiers are k-nearest neighbors, support vector machine (SVM), Naïve Bayes (NB), decision trees (DTs), and long short-term memory (LSTM) neural networks. While voting just averages the predictions of base models, without providing additional pieces of information, stacking is a technique used to aggregate heterogeneous models by training an additional machine learning model (namely, stacked ensemble model) on the predictions of the base models. The analyses carried out in this paper employ filed observations of both safe operation and trip events, derived from a large fleet of industrial Siemens GTs in operation. The results demonstrate that the stacked model provides higher accuracy than base models and also outperforms voting by proving more effective, especially when the reliability of the prediction of base models is poor. [ABSTRACT FROM AUTHOR]

Simple Summary: In radiotherapy treatment, organs at risk and target volumes are contoured by the clinicians to prepare a dosimetry plan. In retrospective data, these structures are not often standardised to universal names across the patients plans, which is required to enable data mining and analysis. In this paper, a new method was proposed and evaluated to automatically standardise radiotherapy structures names using machine learning algorithms. The proposed approach was deployed over a dataset with 1613 patients collected from Liverpool & Macarthur Cancer Therapy Centres, New South Wales, Australia. It was concluded that machine learning techniques can standardise the dosimetry plan structures, taking into consideration the integration of multiple modalities representing each structure during the training process. In progressing the use of big data in health systems, standardised nomenclature is required to enable data pooling and analyses. In many radiotherapy planning systems and their data archives, target volumes (TV) and organ-at-risk (OAR) structure nomenclature has not been standardised. Machine learning (ML) has been utilised to standardise volumes nomenclature in retrospective datasets. However, only subsets of the structures have been targeted. Within this paper, we proposed a new approach for standardising all the structures nomenclature by using multi-modal artificial neural networks. A cohort consisting of 1613 breast cancer patients treated with radiotherapy was identified from Liverpool & Macarthur Cancer Therapy Centres, NSW, Australia. Four types of volume characteristics were generated to represent each target and OAR volume: textual features, geometric features, dosimetry features, and imaging data. Five datasets were created from the original cohort, the first four represented different subsets of volumes and the last one represented the whole list of volumes. For each dataset, 15 sets of combinations of features were generated to investigate the effect of using different characteristics on the standardisation performance. The best model reported 99.416% classification accuracy over the hold-out sample when used to standardise all the nomenclatures in a breast cancer radiotherapy plan into 21 classes. Our results showed that ML based automation methods can be used for standardising naming conventions in a radiotherapy plan taking into consideration the inclusion of multiple modalities to better represent each volume. [ABSTRACT FROM AUTHOR]

Simple Summary: Melanoma is the most dangerous type of skin cancer worldwide. Early detection of melanoma is crucial for better outcomes, but this often can be challenging. This research explores the use of artificial intelligence (AI) techniques combined with non-invasive imaging methods to improve melanoma detection. The authors aim to evaluate the current state of AI-based techniques using tools including dermoscopy, optical coherence tomography (OCT), and reflectance confocal microscopy (RCM). The findings demonstrate that several AI algorithms perform as well as or better than dermatologists in detecting melanoma, particularly in the analysis of dermoscopy images. This research highlights the potential of AI to enhance diagnostic accuracy, leading to improved patient outcomes. Further studies are needed to address limitations and ensure the reliability and effectiveness of AI-based techniques. Background: Melanoma, the deadliest form of skin cancer, poses a significant public health challenge worldwide. Early detection is crucial for improved patient outcomes. Non-invasive skin imaging techniques allow for improved diagnostic accuracy; however, their use is often limited due to the need for skilled practitioners trained to interpret images in a standardized fashion. Recent innovations in artificial intelligence (AI)-based techniques for skin lesion image interpretation show potential for the use of AI in the early detection of melanoma. Objective: The aim of this study was to evaluate the current state of AI-based techniques used in combination with non-invasive diagnostic imaging modalities including reflectance confocal microscopy (RCM), optical coherence tomography (OCT), and dermoscopy. We also aimed to determine whether the application of AI-based techniques can lead to improved diagnostic accuracy of melanoma. Methods: A systematic search was conducted via the Medline/PubMed, Cochrane, and Embase databases for eligible publications between 2018 and 2022. Screening methods adhered to the 2020 version of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Included studies utilized AI-based algorithms for melanoma detection and directly addressed the review objectives. Results: We retrieved 40 papers amongst the three databases. All studies directly comparing the performance of AI-based techniques with dermatologists reported the superior or equivalent performance of AI-based techniques in improving the detection of melanoma. In studies directly comparing algorithm performance on dermoscopy images to dermatologists, AI-based algorithms achieved a higher ROC (>80%) in the detection of melanoma. In these comparative studies using dermoscopic images, the mean algorithm sensitivity was 83.01% and the mean algorithm specificity was 85.58%. Studies evaluating machine learning in conjunction with OCT boasted accuracy of 95%, while studies evaluating RCM reported a mean accuracy rate of 82.72%. Conclusions: Our results demonstrate the robust potential of AI-based techniques to improve diagnostic accuracy and patient outcomes through the early identification of melanoma. Further studies are needed to assess the generalizability of these AI-based techniques across different populations and skin types, improve standardization in image processing, and further compare the performance of AI-based techniques with board-certified dermatologists to evaluate clinical applicability. [ABSTRACT FROM AUTHOR]

In this paper, we have designed an artificial neural network architecture to produce metric field of planar BTZ and quintessence black holes applying a data-driven approach andleveraging holography principle (according to AdS/DL (Anti de Sitter/Deep Learning) correspondence given by [1]). Data has been collected by choosing minimally coupled massive scalar field with quantum fluctuations and we try to process two emergent and ground-truth metrics versus the holographic parameter which plays the role of depth of the neural network. Loss or error function which shows rate of deviation of these two metrics in presence of penalty regularization term reaches to its minimum value when values of the learning rate approach to the observed steepest gradient point. Values of the regularization or penalty term of the quantum scalar field has critical role to matching this two mentioned metric. Also, we design an algorithm which helps us to find optimum value for learning parameter and finally, we understand that loss function convergence heavily depends on the number of epochs and learning rate. [ABSTRACT FROM AUTHOR]

Deep Neural Networks (DNNs) are widely regarded as the most effective learning tool for dealing with large datasets, and they have been successfully used in thousands of applications in a variety of fields. Based on these large datasets, they are trained to learn the relationships between various variables. The adaptive moment estimation (Adam) algorithm, a highly efficient adaptive optimization algorithm, is widely used as a learning algorithm in various fields for training DNN models. However, it needs to improve its generalization performance, especially when training with large-scale datasets. Therefore, in this paper, we propose HN Adam, a modified version of the Adam Algorithm, to improve its accuracy and convergence speed. The HN_Adam algorithm is modified by automatically adjusting the step size of the parameter updates over the training epochs. This automatic adjustment is based on the norm value of the parameter update formula according to the gradient values obtained during the training epochs. Furthermore, a hybrid mechanism was created by combining the standard Adam algorithm and the AMSGrad algorithm. As a result of these changes, the HN_Adam algorithm, like the stochastic gradient descent (SGD) algorithm, has good generalization performance and achieves fast convergence like other adaptive algorithms. To test the proposed HN_Adam algorithm performance, it is evaluated to train a deep convolutional neural network (CNN) model that classifies images using two different standard datasets: MNIST and CIFAR-10. The algorithm results are compared to the basic Adam algorithm and the SGD algorithm, in addition to other five recent SGD adaptive algorithms. In most comparisons, the HN Adam algorithm outperforms the compared algorithms in terms of accuracy and convergence speed. AdaBelief is the most competitive of the compared algorithms. In terms of testing accuracy and convergence speed (represented by the consumed training time), the HN-Adam algorithm outperforms the AdaBelief algorithm by an improvement of 1.0% and 0.29% for the MNIST dataset, and 0.93% and 1.68% for the CIFAR-10 dataset, respectively. [ABSTRACT FROM AUTHOR]

Simple Summary: Accurately grading gliomas, which are the most common and aggressive malignant brain tumors in adults, poses a significant challenge for radiologists. This study explores the application of Deep Learning techniques in assisting tumor grading using Magnetic Resonance Images (MRIs). By analyzing a glioma database sourced from multiple public datasets and comparing different settings, the aim of this study is to develop a robust and reliable grading system. The study demonstrates that by focusing on the tumor region of interest and augmenting the available data, there is a significant improvement in both the accuracy and confidence of tumor grade classifications. While successful in differentiating low-grade gliomas from high-grade gliomas, the accurate classification of grades 2, 3, and 4 remains challenging. The research findings have significant implications for advancing the development of a non-invasive, robust, and trustworthy data-driven system to support clinicians in the diagnosis and therapy planning of glioma patients. Glioma is the most common type of tumor in humans originating in the brain. According to the World Health Organization, gliomas can be graded on a four-stage scale, ranging from the most benign to the most malignant. The grading of these tumors from image information is a far from trivial task for radiologists and one in which they could be assisted by machine-learning-based decision support. However, the machine learning analytical pipeline is also fraught with perils stemming from different sources, such as inadvertent data leakage, adequacy of 2D image sampling, or classifier assessment biases. In this paper, we analyze a glioma database sourced from multiple datasets using a simple classifier, aiming to obtain a reliable tumor grading and, on the way, we provide a few guidelines to ensure such reliability. Our results reveal that by focusing on the tumor region of interest and using data augmentation techniques we significantly enhanced the accuracy and confidence in tumor classifications. Evaluation on an independent test set resulted in an AUC-ROC of 0.932 in the discrimination of low-grade gliomas from high-grade gliomas, and an AUC-ROC of 0.893 in the classification of grades 2, 3, and 4. The study also highlights the importance of providing, beyond generic classification performance, measures of how reliable and trustworthy the model's output is, thus assessing the model's certainty and robustness. [ABSTRACT FROM AUTHOR]

With the exponential growth of data, solving classification or regression tasks by mining time series data has become a research hotspot. Commonly used methods include machine learning, artificial neural networks, and so on. However, these methods only extract the continuous or discrete features of sequences, which have the drawbacks of low information utilization, poor robustness, and computational complexity. To solve these problems, this paper innovatively uses Wasserstein distance instead of Kullback–Leibler divergence and uses it to construct an autoencoder to learn discrete features of time series. Then, a hidden Markov model is used to learn the continuous features of the sequence. Finally, stacking is used to ensemble the two models to obtain the final model. This paper experimentally verifies that the ensemble model has lower computational complexity and is close to state-of-the-art classification accuracy. [ABSTRACT FROM AUTHOR]

Background: Auditory–perceptual assessment of voice is a subjective procedure. Artificial intelligence with deep learning (DL) may improve the consistency and accessibility of this task. It is unclear how a DL model performs on different acoustic features. Aims: To develop a generalizable DL framework for identifying dysphonia using a multidimensional acoustic feature. Methods & Procedures: Recordings of sustained phonations of /a/ and /i/ were retrospectively collected from a clinical database. Subjects contained 238 dysphonic and 223 vocally healthy speakers of Chinese Mandarin. All audio clips were split into multiple 1.5‐s segments and normalized to the same loudness level. Mel frequency cepstral coefficients and mel‐spectrogram were extracted from these standardized segments. Each set of features was used in a convolutional neural network (CNN) to perform a binary classification task. The best feature was obtained through a five‐fold cross‐validation on a random selection of 80% data. The resultant DL framework was tested on the remaining 20% data and a public German voice database. The performance of the DL framework was compared with those of two baseline machine‐learning models. Outcomes & Results: The mel‐spectrogram yielded the best model performance, with a mean area under the receiver operating characteristic curve of 0.972 and an accuracy of 92% in classifying audio segments. The resultant DL framework significantly outperformed both baseline models in detecting dysphonic subjects on both test sets. The best outcomes were achieved when classifications were made based on all segments of both vowels, with 95% accuracy, 92% recall, 98% precision and 98% specificity on the Chinese test set, and 92%, 95%, 90% and 89%, respectively, on the German set. Conclusions & Implications: This study demonstrates the feasibility of DL for automatic detection of dysphonia. The mel‐spectrogram is a preferred acoustic feature for the task. This framework may be used for vocal health screening and facilitate automatic perceptual evaluation of voice in the era of big data. WHAT THIS PAPER ADDS: What is already known on this subject: Auditory–perceptual assessment is the current gold standard in clinical evaluation of voice quality, but its value may be limited by the rater's reliability and accessibility. DL is a new method of artificial intelligence that can overcome these disadvantages and promote automatic voice assessment. This study explored the feasibility of a DL approach for automatic detection of dysphonia, along with a quantitative comparison of two common sets of acoustic features. What this study adds to existing knowledge: A CNN model is excellent at decoding multidimensional acoustic features, outperforming the baseline parameter‐based models in identifying dysphonic voices. The first 13 mel‐frequency cepstral coefficients (MFCCs) are sufficient for this task. The mel‐spectrogram results in greater performance, indicating the acoustic features are presented in a more favourable way than the MFCCs to the CNN model. What are the potential or actual clinical implications of this work?: DL is a feasible method for the detection of dysphonia. The current DL framework may be used for remote vocal health screening or documenting voice recovery after treatment. In future, DL models may potentially be used to perform auditory–perceptual tasks in an automatic, efficient, reliable and low‐cost manner. [ABSTRACT FROM AUTHOR]

Despite the existence of evidence-based rehabilitation strategies that address biomechanical deficits, the persistence of recurrent ankle problems in 70% of patients with acute ankle sprains highlights the unresolved nature of this issue. Artificial intelligence (AI) emerges as a promising tool to identify definitive predictors for ankle sprains. This paper aims to summarize the use of AI in investigating the ankle biomechanics of healthy and subjects with ankle sprains. Articles published between 2010 and 2023 were searched from five electronic databases. 59 papers were included for analysis with regards to: i). types of motion tested (functional vs. purposeful ankle movement); ii) types of biomechanical parameters measured (kinetic vs kinematic); iii) types of sensor systems used (lab-based vs field-based); and, iv) AI techniques used. Most studies (83.1%) examined biomechanics during functional motion. Single kinematic parameter, specifically ankle range of motion, could obtain accuracy up to 100% in identifying injury status. Wearable sensor exhibited high reliability for use in both laboratory and on-field/clinical settings. AI algorithms primarily utilized electromyography and joint angle information as input data. Support vector machine was the most used supervised learning algorithm (18.64%), while artificial neural network demonstrated the highest accuracy in eight studies. The potential for remote patient monitoring is evident with the adoption of field-based devices. Nevertheless, AI-based sensors are underutilized in detecting ankle motions at risk of sprain. We identify three key challenges: sensor designs, the controllability of AI models, and the integration of AI-sensor models, providing valuable insights for future research. [Display omitted] • Application of sensors and artificial intelligence to analyse ankle biomechanics. • Lab sensors predict parameters, paving the way for post-modern rehabilitation. • Field devices show potential for ankle injury prediction. • Focus on streamlined smart sensors and effective data management in the future. [ABSTRACT FROM AUTHOR]

Tactical UAV path planning under radar threat using reinforcement learning involves particular challenges ranging from modeling related difficulties to sparse feedback problem. Learning goal-directed behavior with sparse feedback from complex environments is a fundamental challenge for reinforcement learning algorithms. In this paper we extend our previous work in this area to provide a solution to the problem setting stated above, using Hierarchical Reinforcement Learning (HRL) in a novel way that involves a meta controller for higher level goal assignment and a controller that determines the lower-level actions of the agent. Our meta controller is based on a regression model trained using a state transition scheme that defines the evolution of goal designation, whereas our lower-level controller is based on a Deep Q Network (DQN) and is trained via reinforcement learning iterations. This two-layer framework ensures that an optimal plan for a complex path, organized as multiple goals, is achieved gradually, through piecewise assignment of sub-goals, and thus as a result of a staged, efficient and rigorous procedure. [ABSTRACT FROM AUTHOR]

Simple Summary: This paper presents a breast cancer detection approach where the convoluted features from a convolutional neural network are utilized to train a machine learning model. Results demonstrate that use of convoluted features yields better results than the original features to classify malignant and benign tumors. Breast cancer is a common cause of female mortality in developing countries. Screening and early diagnosis can play an important role in the prevention and treatment of these cancers. This study proposes an ensemble learning-based voting classifier that combines the logistic regression and stochastic gradient descent classifier with deep convoluted features for the accurate detection of cancerous patients. Deep convoluted features are extracted from the microscopic features and fed to the ensemble voting classifier. This idea provides an optimized framework that accurately classifies malignant and benign tumors with improved accuracy. Results obtained using the voting classifier with convoluted features demonstrate that the highest classification accuracy of 100% is achieved. The proposed approach revealed the accuracy enhancement in comparison with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

With the limitation of air traffic and the rapid increase in the number of flights, flight delay is becoming more frequent. Flight delay leads to financial and time losses for passengers and increases operating costs for airlines. Therefore, the establishment of an accurate prediction model for flight delay becomes vital to build an efficient airline transportation system. The air transportation system has a huge amount of data and complex operation modes, which is suitable for analysis by using machine learning methods. This paper discusses the factors that may affect the flight delay, and presents a new flight delay prediction model. The five warning levels are defined based on flight delay database by using K-means clustering algorithm. After extracting the key factors related to flight operation by the grey relational analysis (GRA) algorithm, an improved machine learning algorithm called GRA — Genetic algorithm (GA) — back propagation neural network, GRA-GA-BP, is introduced, which is optimized by GA. The calculation results show that, compared with models before optimization and other two algorithms in previous papers, the proposed prediction model based on GRA-GA-BP algorithm shows a higher prediction accuracy and more stability. In terms of operation efficiency and memory consumption, it also has good performance. The analysis presented in this paper indicates that this model can provide effective early warnings for flight delay, and can help airlines to intervene in flights with abnormal trend in advance. [ABSTRACT FROM AUTHOR]

This paper investigates the stochastic optimization problem focusing on developing scalable parallel algorithms for deep learning tasks. Our solution involves a reformation of the objective function for stochastic optimization in neural network models, along with a novel parallel computing strategy, coined the weighted aggregating stochastic gradient descent (WASGD). Following a theoretical analysis on the characteristics of the new objective function, WASGD introduces a decentralized weighted aggregating scheme based on the performance of local workers. Without any center variable, the new method automatically gauges the importance of local workers and accepts them by their contributions. Furthermore, we have developed an enhanced version of the method, WASGD+, by (1) implementing a designed sample order and (2) upgrading the weight evaluation function. To validate the new method, we benchmark our pipeline against several popular algorithms including the state-of-the-art deep neural network classifier training techniques (e.g., elastic averaging SGD). Comprehensive validation studies have been conducted on four classic datasets: CIFAR-100, CIFAR-10, Fashion-MNIST, and MNIST. Subsequent results have firmly validated the superiority of the WASGD scheme in accelerating the training of deep architecture. Better still, the enhanced version, WASGD+, is shown to be a significant improvement over its prototype. [ABSTRACT FROM AUTHOR]

Vehicle fault detection and diagnosis (VFDD) along with predictive maintenance (PdM) are indispensable for early diagnosis in order to prevent severe accidents due to mechanical malfunction in urban environments. This paper proposes an early voiceprint driving fault identification system using machine learning algorithms for classification. Previous studies have examined driving fault identification, but less attention has focused on using voiceprint features to locate corresponding faults. This research uses 43 different common vehicle mechanical malfunction condition voiceprint signals to construct the dataset. These datasets were filtered by linear predictive coefficient (LPC) and wavelet transform(WT). After the original voiceprint fault sounds were filtered and obtained the main fault characteristics, the deep neural network (DNN), convolutional neural network (CNN), and long short-term memory (LSTM) architectures are used for identification. The experimental results show that the accuracy of the CNN algorithm is the best for the LPC dataset. In addition, for the wavelet dataset, DNN has the best performance in terms of identification performance and training time. After cross-comparison of experimental results, the wavelet algorithm combined with DNN can improve the identification accuracy by up to 16.57% compared with other deep learning algorithms and reduce the model training time by up to 21.5% compared with other algorithms. Realizing the cross-comparison of recognition results through various machine learning methods, it is possible for the vehicle to proactively remind the driver of the real-time potential hazard of vehicle machinery failure. [ABSTRACT FROM AUTHOR]

LEarning TO Rank (LETOR) algorithms are usually trained on annotated corpora where a single relevance label is assigned to each available document‐topic pair. Within the Cranfield framework, relevance labels result from merging either multiple expertly curated or crowdsourced human assessments. In this paper, we explore how to train LETOR models with relevance judgments distributions (either real or synthetically generated) assigned to document‐topic pairs instead of single‐valued relevance labels. We propose five new probabilistic loss functions to deal with the higher expressive power provided by relevance judgments distributions and show how they can be applied both to neural and gradient boosting machine (GBM) architectures. Moreover, we show how training a LETOR model on a sampled version of the relevance judgments from certain probability distributions can improve its performance when relying either on traditional or probabilistic loss functions. Finally, we validate our hypothesis on real‐world crowdsourced relevance judgments distributions. Overall, we observe that relying on relevance judgments distributions to train different LETOR models can boost their performance and even outperform strong baselines such as LambdaMART on several test collections. [ABSTRACT FROM AUTHOR]

All organisms contain antimicrobial peptides (AMPs), which are a critical component of the innate immune system. These chemicals have the ability to suppress the growth of a variety of fungi, bacteria, and viruses. Because AMPs interact with structural components of the microbial cell membrane and have a wide range of cellular targets, bacteria are unlikely to be able to develop resistance to them in the short term. The underlying structure of AMPs is critical in determining the selectivity with which they target their respective targets. As far as we know, peptides have not been tested in a lab to see if they can fight bacteria, fungus, and viruses in real life. In this paper, we develop an artificial neural network (ANN) using a back propagation neural network (BPNN) that enables optimal classification of tendency of a peptide sequence that involves the activities of antifungal, antibacterial, or antiviral. The BPNN is trained on the datasets collected across different repositories and then the overfitting is avoided using particle swarm optimization (PSO) algorithm. Hence, at the time of testing, the BPNN clearly finds the predicted samples belonging to the same classes and this avoids the problem of finding the false positives. The simulation is conducted to test the efficacy of the model against various metrics that includes accuracy, precision, recall, and f1-measure. The effectiveness of the BPNN-PSO model in classifying instances at a faster rate than other techniques is demonstrated by its performance. The principle is straightforward, it is not difficult to programme, it converges more quickly, and it generally offers a superior solution. [ABSTRACT FROM AUTHOR]

There are many thyroid diseases affecting people all over the world. Many diseases affect the thyroid gland, like hypothyroidism, hyperthyroidism, and thyroid cancer. Thyroid inefficiency can cause severe symptoms in patients. Effective classification and machine learning play a significant role in the timely detection of thyroid diseases. This timely classification will indeed affect the timely treatment of the patients. Automatic and precise thyroid nodule detection in ultrasound pictures is critical for reducing effort and radiologists' mistake rate. Medical images have evolved into one of the most valuable and consistent data sources for machine learning generation. In this paper, various machine learning algorithms like decision tree, random forest algorithm, KNN, and artificial neural networks on the dataset create a comparative analysis to better predict the disease based on parameters established from the dataset. Also, the dataset has been manipulated for accurate prediction for the classification. The classification was performed on both the sampled and unsampled datasets for better comparison of the dataset. After dataset manipulation, we obtained the highest accuracy for the random forest algorithm, equal to 94.8% accuracy and 91% specificity. [ABSTRACT FROM AUTHOR]

Research has proven that having high level of emotional intelligence (EI) can reduce the chance of getting mental illness. EI, and its component, can be improved with training, but currently the process is less flexible and very time-consuming. Machine learning (ML), on the other hand, can analyse huge amount of data to discover useful trends and patterns in shortest time possible. Despite the benefits, ML usage in EI training is scarce. In this paper, we studied 92 journal articles to discover the trend of the ML utilisation in the study of EI and its components. This survey aims to pave way for future studies that could lead to implementation of ML in EI training, and to rope in researchers in psychology and computer science to find possibilities of having a generic ML algorithm for every EI's components. Our findings show an increasing trend to apply ML on EI components, and Support Vector Machine and Neural Network are the two most popular ML algorithms used in those researches. We also found that social skill and empathy are the least exposed EI components to ML. Finally, we provide recommendations for future research direction of ML in EI domain, and EI in ML. [ABSTRACT FROM AUTHOR]

A comprehensive systematic study was carried out in order to identify various deep learning methods developed and used for predicting student academic performance. Predicting academic performance allows for the implementation of various preventive and supportive measures earlier in order to improve academic performance and reduce failure and dropout rates. Although machine learning schemes were once popular, deep learning algorithms are now being investigated to solve difficult predictions of student performance in larger datasets with more data attributes. Deep neural network prediction methods with clear modelling and parameter measurements formulated on publicly available and recognised datasets are the focus of the research. Widely used for academic performance prediction, backpropagation algorithms have been trained and tested with various datasets, especially those related to learning management systems (LMS) and massive open online courses (MOOC). The most widely used prediction method appears to be the standard artificial neural network approach. The long-short-term memory (LSTM) approach has been reported to achieve an accuracy of around 87 percent for temporal student performance data. The number of papers that study and improve this method shows that there is a clear rise in deep learning-based academic performance prediction over the last few years. [ABSTRACT FROM AUTHOR]

Breast cancer (BC) is the leading cause of death among women worldwide. It affects in general women older than 40 years old. Medical images analysis is one of the most promising research areas since it provides facilities for diagnosis and decision-making of several diseases such as BC. This paper conducts a Structured Literature Review (SLR) of the use of Machine Learning (ML) and Image Processing (IP) techniques to deal with BC imaging. A set of 530 papers published between 2000 and August 2019 were selected and analyzed according to ten criteria: year and publication channel, empirical type, research type, medical task, machine learning techniques, datasets used, validation methods, performance measures and image processing techniques which include image pre-processing, segmentation, feature extraction and feature selection. Results showed that diagnosis was the most used medical task and that Deep Learning techniques (DL) were largely used to perform classification. Furthermore, we found out that classification was the most ML objective investigated followed by prediction and clustering. Most of the selected studies used Mammograms as imaging modalities rather than Ultrasound or Magnetic Resonance Imaging with the use of public or private datasets with MIAS as the most frequently investigated public dataset. As for image processing techniques, the majority of the selected studies pre-process their input images by reducing the noise and normalizing the colors, and some of them use segmentation to extract the region of interest with the thresholding method. For feature extraction, we note that researchers extracted the relevant features using classical feature extraction techniques (e.g. Texture features, Shape features, etc.) or DL techniques (e. g. VGG16, VGG19, ResNet, etc.), and finally few papers used feature selection techniques in particular the filter methods. [ABSTRACT FROM AUTHOR]

Fuzzy English recognition is affected by many factors, which leads to certain accuracy problems in intelligent recognition results. In order to improve the automatic recognition efficiency of fuzzy English, based on machine learning technology, this study constructs a neural network model. At the same time, this paper analyzes the research status and existing problems of handwritten character recognition, analyzes the model, and adopts multiple modules for automatic English recognition. In addition, the system is built on the basis of algorithms and model support, which makes fuzzy English recognition intelligent. Finally, in order to study the algorithm and model performance, the fuzzy English recognition is carried out through experiments. The research shows that the model constructed in this paper has certain recognition effect, which can be applied to practice, and can provide theoretical reference for subsequent related research. [ABSTRACT FROM AUTHOR]

This paper investigates how to best compare algorithms for predicting chronic homelessness for the purpose of identifying good candidates for housing programs. Predictive methods can rapidly refer potentially chronic shelter users to housing but also sometimes incorrectly identify individuals who will not become chronic (false positives). We use shelter access histories to demonstrate that these false positives are often still good candidates for housing. Using this approach, we compare a simple threshold method for predicting chronic homelessness to the more complex logistic regression and neural network algorithms. While traditional binary classification performance metrics show that the machine learning algorithms perform better than the threshold technique, an examination of the shelter access histories of the cohorts identified by the three algorithms show that they select groups with very similar characteristics. This has important implications for resource constrained not-for-profit organizations since the threshold technique can be implemented using much simpler information technology infrastructure than the machine learning algorithms. [ABSTRACT FROM AUTHOR]

In keratoconus, the cornea assumes a conical shape due to its thinning and protrusion. Early detection of keratoconus is vital in preventing vision loss or costly repairs. In corneal topography maps, curvature and steepness can be distinguished by the colour scales, with warm colours representing curved steep areas and cold colours representing flat areas. With the advent of machine learning algorithms like convolutional neural networks (CNN), the identification and classification of keratoconus from these topography maps have been made faster and more accurate. The classification and grading of keratoconus depend on the colour scales used. Artefacts and minimal variations in the corneal shape, in mild or developing keratoconus, are not represented clearly in the image gradients. Segmentation of the maps needs to be carried out for identifying the severity of the keratoconus as well as for identifying the changes in the severity. In this paper, we are considering the use of particle swarm optimisation and its modifications for segmenting the topography image. Pretrained CNN models are then trained with the dataset and tested. Results show that the performance of the system in terms of accuracy is 95.9% compared to 93%, 95.3%, and 84% available in the literature for a 3-class classification that involved mild keratoconus or forme fruste keratoconus. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is the most generally known neurodegenerative disorder, leading to a steady deterioration in cognitive ability. Deep learning models have shown outstanding performance in the diagnosis of AD, and these models do not need any handcrafted feature extraction over conventional machine learning algorithms. Since the 2012 AlexNet accomplishment, the convolutional neural network (CNN) has been progressively utilized by the medical community to assist practitioners to early diagnose AD. This paper explores the current cutting edge applications of CNN on single and multimodality (combination of two or more modalities) neuroimaging data for the classification of AD. An exhaustive systematic search is conducted on four notable databases: Google Scholar, IEEE Xplore, ACM Digital Library, and PubMed in June 2021. The objective of this study is to examine the effectiveness of classification approaches on AD to analyze different kinds of datasets, neuroimaging modalities, preprocessing techniques, and data handling methods. However, CNN has achieved great success in the classification of AD; still, there are a lot of challenges particularly due to scarcity of medical imaging data and its possible scope in this field. [ABSTRACT FROM AUTHOR]

Gradient-based algorithms are commonly used for training radial basis function neural network (RBFNN). However, it is still difficult to avoid vanishing gradient to improve the learning performance in the training process. For this reason, in this paper, an accelerated second-order learning (ASOL) algorithm is developed to train RBFNN. First, an adaptive expansion and pruning mechanism (AEPM) of gradient space, based on the integrity and orthogonality of hidden neurons, is designed. Then, the effective gradient information is constantly added to gradient space and the redundant gradient information is eliminated from gradient space. Second, with AEPM, the neurons are generated or pruned accordingly. In this way, a self-organizing RBFNN (SORBFNN) which reduces the structure complexity and improves the generalization ability is obtained. Then, the structure and parameters in the learning process can be optimized by the proposed ASOL-based SORBFNN (ASOL-SORBFNN). Third, some theoretical analyses including the efficiency of the proposed AEPM on avoiding the vanishing gradient and the stability of SORBFNN in the process of structural adjustment are given, then the successful application of the proposed ASOL-SORBFNN is guaranteed. Finally, to illustrate the advantages of the proposed ASOL-SORBFNN, several experimental studies are examined. By comparing with other existing approaches, the results show that ASOL-SORBFNN performs well in terms of both learning speed and prediction accuracy. [ABSTRACT FROM AUTHOR]

In this paper, we have proposed a novel methodology based on statistical features and different machine learning algorithms. The proposed model can be divided into three main stages, namely, preprocessing, feature extraction, and classification. In the preprocessing stage, the median filter has been used in order to remove salt-and-pepper noise because MRI images are normally affected by this type of noise, the grayscale images are also converted to RGB images in this stage. In the preprocessing stage, the histogram equalization has also been used to enhance the quality of each RGB channel. In the feature extraction stage, the three channels, namely, red, green, and blue, are extracted from the RGB images and statistical measures, namely, mean, variance, skewness, kurtosis, entropy, energy, contrast, homogeneity, and correlation, are calculated for each channel; hence, a total of 27 features, 9 for each channel, are extracted from an RGB image. After the feature extraction stage, different machine learning algorithms, such as artificial neural network, k -nearest neighbors' algorithm, decision tree, and Naïve Bayes classifiers, have been applied in the classification stage on the features extracted in the feature extraction stage. We recorded the results with all these algorithms and found that the decision tree results are better as compared to the other classification algorithms which are applied on these features. Hence, we have considered decision tree for further processing. We have also compared the results of the proposed method with some well-known algorithms in terms of simplicity and accuracy; it was noted that the proposed method outshines the existing methods. [ABSTRACT FROM AUTHOR]

Autonomous driving approaches today are mainly based on perception-planning-action modular pipelines and the End2End paradigm respectively. The End2End paradigm is a strategy that directly maps raw sensor data to vehicle control actions. This strategy is very promising and appealing because complex module design and cumbersome data labeling are avoided. Since this approach lacks a degree of interpretability, safety and practicability. we propose an autonomous driving approach based on trajectory learning using deep neural networks in this paper. In comparison to End2End algorithm, it is found that the trajectory learning algorithm performs better in autonomous driving. As for trajectory learning algorithm, the CNN_Raw-RNN network structure is established, which is verified to be more effective than the original CNN_LSTM network structure. Besides, we propose an autonomous driving architecture of a pilot and copilot combination. The pilot is responsible for trajectory prediction via imitation learning with labeled driving trajectories, while the copilot is a safety module that is employed to verify the effectiveness of the vehicle trajectory by the results of the semantic segmentation auxiliary task. The proposed autonomous driving architecture is verified with a real car on urban roads without manual intervention within 40 km. [ABSTRACT FROM AUTHOR]

As a new brain-inspired computational model of artificial neural networks, spiking neural networks transmit and process information via precisely timed spike trains. Constructing efficient learning methods is a significant research field in spiking neural networks. In this paper, we present a supervised learning algorithm for multilayer feedforward spiking neural networks; all neurons can fire multiple spikes in all layers. The feedforward network consists of spiking neurons governed by biologically plausible long-term memory spike response model, in which the effect of earlier spikes on the refractoriness is not neglected to incorporate adaptation effects. The gradient descent method is employed to derive synaptic weight updating rule for learning spike trains. The proposed algorithm is tested and verified on spatiotemporal pattern learning problems, including a set of spike train learning tasks and nonlinear pattern classification problems on four UCI datasets. Simulation results indicate that the proposed algorithm can improve learning accuracy in comparison with other supervised learning algorithms. [ABSTRACT FROM AUTHOR]

In many machine learning applications and algorithms, the algorithm performance and accuracy are highly dependent on the metric used to measure the distance between different samples. Therefore, learning a distance metric specific to the data can improve these algorithms' performance. This paper proposes an unrestricted deep metric learning framework based on neural networks' interaction for learning metrics in latent space. The proposed method is inspired by generative neural nets (GANs), in which two neural nets are working together to learn true data distribution. In our method, one network plays the role of a supervisor for another network, a feature learning auto-encoder. Its task is to learn transformation to latent space in which data have more meaningful distance and separability. i.e., the supervisor gets the output of the auto-encoder and sends feedback to modify its weights. They interact with each other interleavingly. Several experiments were conducted on four datasets, such as MNIST, GISETTE, Winnipeg Cropland Classification (WCC), and swarm behavior, from different application domains, to evaluate the proposed method's performance. The results show that we can force auto-encoder to learn label information to project data into a latent space with better separability by using our approach. In addition to better class discrimination, the proposed method is far faster than normal auto-encoders during feature learning and has much less training time in the classification phase. [ABSTRACT FROM AUTHOR]

We use a recently developed synchronous Spiking Neural Network (SNN) model to study the problem of learning hierarchically-structured concepts. We introduce an abstract data model that describes simple hierarchical concepts. We define a feed-forward layered SNN model, with learning modeled using Oja's local learning rule, a well known biologically-plausible rule for adjusting synapse weights. We define what it means for such a network to recognize hierarchical concepts; our notion of recognition is robust, in that it tolerates a bounded amount of noise. Then, we present a learning algorithm by which a layered network may learn to recognize hierarchical concepts according to our robust definition. We analyze correctness and performance rigorously; the amount of time required to learn each concept, after learning all of the sub-concepts, is approximately O 1 η k ℓmax log (k) + 1 ɛ + b log (k) , where k is the number of sub-concepts per concept, ℓmax is the maximum hierarchical depth, η is the learning rate, ɛ describes the amount of uncertainty allowed in robust recognition, and b describes the amount of weight decrease for "irrelevant" edges. An interesting feature of this algorithm is that it allows the network to learn sub-concepts in a highly interleaved manner. This algorithm assumes that the concepts are presented in a noise-free way; we also extend these results to accommodate noise in the learning process. Finally, we give a simple lower bound saying that, in order to recognize concepts with hierarchical depth two with noise-tolerance, a neural network should have at least two layers. The results in this paper represent first steps in the theoretical study of hierarchical concepts using SNNs. The cases studied here are basic, but they suggest many directions for extensions to more elaborate and realistic cases. [ABSTRACT FROM AUTHOR]

Find the global optimal solution of the model is one promising research topic in computational intelligent community. Dependent on analogies to natural processes, the evolutionary swarm intelligent algorithms are widely used for solving global optimization problems which directed by the fitness values. In this paper, we propose one efficient fractional global learning machine (Fragmachine) which includes two stages (descending and ascending) to determine the optimal search path. The neural network model is used to approach the given fitness value. Specifically, for the descending stage, the integer gradient of the network output with respect the current location is employed to find the next descending point, while for the ascending stage, the fractional gradient is implemented to climb and escape from the local optimal point. We further propose one adaptive learning rate during training which relies on both the current gradient (integer or fractional) information and the fitness value. Finally, a series of numerical experiments verify the effectiveness of the proposed algorithm, Fragmachine. [ABSTRACT FROM AUTHOR]

Machine learning methods, especially deep learning models, have achieved impressive performance in various natural language processing tasks including sentiment analysis. However, deep learning models are more demanding for training data. Data augmentation techniques are widely used to generate new instances based on modifications to existing data or relying on external knowledge bases to address annotated data scarcity, which hinders the full potential of machine learning techniques. This paper presents our work using part‐of‐speech (POS) focused lexical substitution for data augmentation (PLSDA) to enhance the performance of machine learning algorithms in sentiment analysis. We exploit POS information to identify words to be replaced and investigate different augmentation strategies to find semantically related substitutions when generating new instances. The choice of POS tags as well as a variety of strategies such as semantic‐based substitution methods and sampling methods are discussed in detail. Performance evaluation focuses on the comparison between PLSDA and two previous lexical substitution‐based data augmentation methods, one of which is thesaurus‐based, and the other is lexicon manipulation based. Our approach is tested on five English sentiment analysis benchmarks: SST‐2, MR, IMDB, Twitter, and AirRecord. Hyperparameters such as the candidate similarity threshold and number of newly generated instances are optimized. Results show that six classifiers (SVM, LSTM, BiLSTM‐AT, bidirectional encoder representations from transformers [BERT], XLNet, and RoBERTa) trained with PLSDA achieve accuracy improvement of more than 0.6% comparing to two previous lexical substitution methods averaged on five benchmarks. Introducing POS constraint and well‐designed augmentation strategies can improve the reliability of lexical data augmentation methods. Consequently, PLSDA significantly improves the performance of sentiment analysis algorithms. [ABSTRACT FROM AUTHOR]

With the rapid development of deep learning algorithms, it is gradually applied in UAV (Unmanned Aerial Vehicle) driving, visual recognition, target tracking, behavior recognition, and other fields. In the field of sports, many scientists put forward the research of target tracking and recognition technology based on deep learning algorithms for athletes' trajectory and behavior capture. Based on the target tracking algorithm, a regional proposal network RPN algorithm combined with the twin regional proposal network Siamese algorithm is proposed to study the tracking and recognition technology of athletes' behavior. Then, the adaptive updating network is used to track the behavior target of athletes, and the simulation model of behavior recognition is established. This algorithm is different from the traditional twin network algorithm. It can accurately take the athlete's behavior as the target candidate box in model training and reduce the interference of environment and other factors on model recognition. The results show that the Siamese-RPN algorithm can reduce the interference from the background and environment when tracking the athletes' target behavior trajectory. This algorithm can improve the training behavior recognition model, ignore the background interference elements of the behavior image, and improve the accuracy and overall performance of the model. Compared with the traditional twin network method for sports behavior recognition, the Siamese-RPN algorithm studied in this paper can perform offline operations and distinguish the interference factors of athletes' background environment. It can quickly capture the characteristic points of athletes' behavior as the data input of the tracking model, so it has excellent popularization and application value. [ABSTRACT FROM AUTHOR]

Accurate demand prediction of bike-sharing is an important prerequisite to reducing the cost of scheduling and improving the user satisfaction. However, it is a challenging issue due to stochasticity and non-linearity in bike-sharing systems. In this paper, a model called pseudo-double hidden layer feedforward neural networks is proposed to approximately predict actual demands of bike-sharing. Specifically, to overcome limitations in traditional back-propagation learning process, an algorithm, an extreme learning machine with improved particle swarm optimization, is designed to construct learning rules in neural networks. The performance is verified by comparing with other learning algorithms on the dataset of Streeter Dr bike-sharing station in Chicago. [ABSTRACT FROM AUTHOR]

Although tendon-driven continuum manipulators have been extensively researched, how to realize tip contact force sensing in a more general and efficient way without increasing the diameter is still a challenge. Rather than use a complex modeling approach, this paper proposes a general tip contact force-sensing method based on a recurrent neural network that takes the tendons' position and tension as the input of a recurrent neural network and the tip contact force of the continuum manipulator as the output and fits this static model by means of machine learning so that it may be used as a real-time contact force estimator. We also designed and built a corresponding three-degree-of-freedom contact force data acquisition platform based on the structure of a continuum manipulator designed in our previous studies. After obtaining training data, we built and compared the performances of a multi-layer perceptron-based contact force estimator as a baseline and three typical recurrent neural network-based contact force estimators through TensorFlow framework to verify the feasibility of this method. We also proposed a manually decoupled sub-estimators algorithm and evaluated the advantages and disadvantages of those two methods. [ABSTRACT FROM AUTHOR]

In recent decades, researches on optimizing the parameter of the artificial neural network (ANN) model has attracted significant attention from researchers. Hybridization of superior algorithms helps improving optimization performance and capable of solving complex applications. As a traditional gradient-based learning algorithm, ANN suffers from a slow learning rate and is easily trapped in local minima when training techniques such as gradient descent (GD) and back-propagation (BP) algorithm are used. The characteristics of randomization and selection of the best or near-optimal solution of metaheuristic algorithm provide an effective and robust solution; therefore, it has always been used in training of ANN to improve and overcome the above problems. New metaheuristic algorithms are proposed every year. Therefore, the review of its latest developments is essential. This article attempts to summarize the metaheuristic algorithms which have been proposed from the year 1975 to 2020 from various journals, conferences, technical papers, and books. The comparison of the popularity of the metaheuristic algorithm is presented in two time frames, such as algorithms proposed in the recent 20 years and those proposed earlier. Then, some of the popular metaheuristic algorithms and their working principle are reviewed. This article further categorizes the latest metaheuristic search algorithm in the literature to indicate their efficiency in training ANN for various industry applications. More and more researchers tend to develop new hybrid optimization tools by combining two or more metaheuristic algorithms to optimize the training parameters of ANN. Generally, the algorithm's optimal performance must be able to achieve a fine balance of their exploration and exploitation characteristics. Hence, this article tries to compare and summarize the properties of various metaheuristic algorithms in terms of their convergence rate and the ability to avoid the local minima. This information is useful for researchers working on algorithm hybridization by providing a good understanding of the convergence rate and the ability to find a global optimum. [ABSTRACT FROM AUTHOR]

We explore a new approach for training neural networks where all loss functions are replaced by hard constraints. The same approach is very successful in phase retrieval, where signals are reconstructed from magnitude constraints and general characteristics (sparsity, support, etc.). Instead of taking gradient steps, the optimizer in the constraint based approach, called relaxed–reflect–reflect (RRR), derives its steps from projections to local constraints. In neural networks one such projection makes the minimal modification to the inputs x, the associated weights w, and the pre-activation value y at each neuron, to satisfy the equation x ⋅ w = y . These projections, along with a host of other local projections (constraining pre- and post-activations, etc.) can be partitioned into two sets such that all the projections in each set can be applied concurrently—across the network and across all data in the training batch. This partitioning into two sets is analogous to the situation in phase retrieval and the setting for which the general purpose RRR optimizer was designed. Owing to the novelty of the method, this paper also serves as a self-contained tutorial. Starting with a single-layer network that performs nonnegative matrix factorization, and concluding with a generative model comprising an autoencoder and classifier, all applications and their implementations by projections are described in complete detail. Although the new approach has the potential to extend the scope of neural networks (e.g. by defining activation not through functions but constraint sets), most of the featured models are standard to allow comparison with stochastic gradient descent. [ABSTRACT FROM AUTHOR]

With the continuous development of neural network theory itself and related theories and related technologies, neural network is one of the main branches of intelligent control technology. Artificial neural network is a nonlinear and adaptive information processing composed of a large number of processing units. In this paper, an adaptive fuzzy neural network (FNN) is used to construct an intelligent system architecture for English learning, and activation function is used to apply the knowledge of computer science and linguistics to English learning. The network neural structure diagram is presented. English machine learning model framework is established based on recursive neural network. On this basis, feature vector extraction and normalization algorithm are used to meet the needs of neural network model. After acquiring the feature vectors of users' learning styles, the clustering algorithm is used to effectively form a variety of learning styles. The validity of the English learning model was verified by designing the functional flow based on tests. Accurate mastery can activate the corresponding brain regions not only to improve the efficiency of learning, but also to better facilitate language learning. [ABSTRACT FROM AUTHOR]

In this paper, we suggest basing the development of classification methods on traditional techniques but approximating them in whole or in part with artificial neural networks (ANNs). Compared to a direct ANN approach, the underlying traditional method is often easier to analyse. Classification failures can be better understood and corrected for, while at the same time faster execution can be obtained due to the parallel ANN structure. Furthermore, such a two‐step design philosophy partly eliminates the 'guesswork' associated with the design of ANNs. The expected gain is thus that the benefits from the traditional field, and the ANN field can be obtained by combining the best features from both fields. We illustrate our approach by working through an explicit example, namely, a Nearest Neighbour classifier applied to a subset of the MNIST database of handwritten digits. Two different approaches are discussed for how to translate the traditional method into an ANN. The first approach is based on a constructive implementation which directly reflects the original algorithm. The second approach uses ANNs to approximate the whole, or part of, the original method. An important part of the approach is to show how improvements can be introduced. In line with the presented philosophy, this is done by extending the traditional method in several ways followed by ANN approximation of the modified algorithms. The extensions are based on a windowed version of the nearest neighbour algorithm. We show that the improvements carry over to the ANN implementations. We further investigate the stability of the solutions by modifying the training set. It is shown that the errors do not change significantly. This also holds true for the ANN approximations providing confidence that the two‐step strategy is robust. [ABSTRACT FROM AUTHOR]

We propose a method to discover differential equations describing the long‐term dynamics of phenomena featuring a multiscale behavior in time, starting from measurements taken at the fast‐scale. Our methodology is based on a synergetic combination of data assimilation (DA), used to estimate the parameters associated with the known fast‐scale dynamics, and machine learning (ML), used to infer the laws underlying the slow‐scale dynamics. Specifically, by exploiting the scale separation between the fast and the slow dynamics, we propose a decoupling of time scales that allows to drastically lower the computational burden. Then, we propose a ML algorithm that learns a parametric mathematical model from a collection of time series coming from the phenomenon to be modeled. Moreover, we study the interpretability of the data‐driven models obtained within the black‐box learning framework proposed in this paper. In particular, we show that every model can be rewritten in infinitely many different equivalent ways, thus making intrinsically ill‐posed the problem of learning a parametric differential equation starting from time series. Hence, we propose a strategy that allows to select a unique representative model in each equivalence class, thus enhancing the interpretability of the results. We demonstrate the effectiveness and noise‐robustness of the proposed methods through several test cases, in which we reconstruct several differential models starting from time series generated through the models themselves. Finally, we show the results obtained for a test case in the cardiovascular modeling context, which sheds light on a promising field of application of the proposed methods. [ABSTRACT FROM AUTHOR]