Search

Since 2000, there have been more than 8000 publications on radiology artificial intelligence (AI). AI breakthroughs allow complex tasks to be automated and even performed beyond human capabilities. However, the lack of details on the methods and algorithm code undercuts its scientific value. Many science subfields have recently faced a reproducibility crisis, eroding trust in processes and results, and influencing the rise in retractions of scientific papers. For the same reasons, conducting research in deep learning (DL) also requires reproducibility. Although several valuable manuscript checklists for AI in medical imaging exist, they are not focused specifically on reproducibility. In this study, we conducted a systematic review of recently published papers in the field of DL to evaluate if the description of their methodology could allow the reproducibility of their findings. We focused on the Journal of Digital Imaging (JDI), a specialized journal that publishes papers on AI and medical imaging. We used the keyword "Deep Learning" and collected the articles published between January 2020 and January 2022. We screened all the articles and included the ones which reported the development of a DL tool in medical imaging. We extracted the reported details about the dataset, data handling steps, data splitting, model details, and performance metrics of each included article. We found 148 articles. Eighty were included after screening for articles that reported developing a DL model for medical image analysis. Five studies have made their code publicly available, and 35 studies have utilized publicly available datasets. We provided figures to show the ratio and absolute count of reported items from included studies. According to our cross-sectional study, in JDI publications on DL in medical imaging, authors infrequently report the key elements of their study to make it reproducible. [ABSTRACT FROM AUTHOR]

The increasing ubiquity of machine learning (ML) motivates research on algorithms to "explain" models and their predictions—so-called Explainable Artificial Intelligence (XAI). Despite many publications and discussions, the goals and capabilities of such algorithms are far from being well understood. We argue that this is because of a problematic reasoning scheme in the literature: Such algorithms are said to complement machine learning models with desired capabilities, such as interpretability or explainability. These capabilities are in turn assumed to contribute to a goal, such as trust in a system. But most capabilities lack precise definitions and their relationship to such goals is far from obvious. The result is a reasoning scheme that obfuscates research results and leaves an important question unanswered: What can one expect from XAI algorithms? In this paper, we clarify the modest capabilities of these algorithms from a concrete perspective: that of their users. We show that current algorithms can only answer user questions that can be traced back to the question: "How can one represent an ML model as a simple function that uses interpreted attributes?". Answering this core question can be trivial, difficult or even impossible, depending on the application. The result of the paper is the identification of two key challenges for XAI research: the approximation and the translation of ML models. [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]

This paper thoroughly explores the role of object detection in smart cities, specifically focusing on advancements in deep learning-based methods. Deep learning models gain popularity for their autonomous feature learning, surpassing traditional approaches. Despite progress, challenges remain, such as achieving high accuracy in urban scenes and meeting real-time requirements. The study aims to contribute by analyzing state-of-the-art deep learning algorithms, identifying accurate models for smart cities, and evaluating real-time performance using the Average Precision at Medium Intersection over Union (IoU) metric. The reported results showcase various algorithms' performance, with Dynamic Head (DyHead) emerging as the top scorer, excelling in accurately localizing and classifying objects. Its high precision and recall at medium IoU thresholds signify robustness. The paper suggests considering the mean Average Precision (mAP) metric for a comprehensive evaluation across IoU thresholds, if available. Despite this, DyHead stands out as the superior algorithm, particularly at medium IoU thresholds, making it suitable for precise object detection in smart city applications. The performance analysis using Average Precision at Medium IoU is reinforced by the Average Precision at Low IoU (APL), consistently depicting DyHead's superiority. These findings provide valuable insights for researchers and practitioners, guiding them toward employing DyHead for tasks prioritizing accurate object localization and classification in smart cities. Overall, the paper navigates through the complexities of object detection in urban environments, presenting DyHead as a leading solution with robust performance metrics. [ABSTRACT FROM AUTHOR]

In recent times, video inpainting techniques have intended to fill the missing areas or gaps in a video by utilizing known pixels. The variety in brightness or difference of the patches causes the state-of-the-art video inpainting techniques to exhibit high computation complexity and create seams in the target areas. To resolve these issues, this paper introduces a novel video inpainting technique that employs the Morphological Haar Wavelet Transform combined with the Krill Herd based Criminisi algorithm (MHWT-KHCA) to address the challenges of high computational demand and visible seam artifacts in current inpainting practices. The proposed MHWT-KHCA algorithm strategically reduces computation times and enhances the seamlessness of the inpainting process in videos. Through a series of experiments, the technique is validated against standard metrics such as peak signal-to-noise ratio (PSNR) and structural similarity index (SSIM), where it demonstrates superior performance compared to existing methods. Additionally, the paper outlines potential real-world applications ranging from video restoration to real-time surveillance enhancement, highlighting the technique's versatility and effectiveness. Future research directions include optimizing the algorithm for diverse video formats and integrating machine learning models to advance its capabilities further. [ABSTRACT FROM AUTHOR]

Collecting and analyzing data from all devices to improve the efficiency of business processes is an important task of Industrial Internet of Things (IIoT). In the age of data explosion, extensive text data generated by the IIoT have given birth to a variety of text representation methods. The task of text representation is to convert the natural language to a form that computer can understand with retaining the original semantics. However, these methods are difficult to effectively extract the semantic features among words and distinguish polysemy in natural language. Combining the advantages of convolutional neural network (CNN) and variational autoencoder (VAE), this paper proposes an intelligent CNN-VAE text representation algorithm as an advanced learning method for social big data within next-generation IIoT, which help users identify the information collected by sensors and perform further processing. This method employs the convolution layer to capture the local features of the context and uses the variational technique to reconstruct feature space to make it conform to the normal distribution. In addition, the improved word2vec model based on topical word embedding (TWE) is utilized to add topical information to word vectors to distinguish polysemy. This paper takes the social big data as an example to illustrate the way of the proposed algorithm applied in the next-generation IIoT and utilizes Cnews dataset to verify the performance of proposed method with four evaluating metrics (i.e., recall, accuracy, precision, and F1-score). Experimental results indicate that the proposed method outperforms word2vec-avg and CNN-AE in K-nearest neighbor (KNN), random forest (RF), and support vector machine (SVM) classifiers and distinguishes polysemy effectively. [ABSTRACT FROM AUTHOR]

Machine learning is frequently being leveraged to tackle problems in the health sector including utilization for clinical decision-support. Its use has historically been focused on single modal data. Attempts to improve prediction and mimic the multimodal nature of clinical expert decision-making has been met in the biomedical field of machine learning by fusing disparate data. This review was conducted to summarize the current studies in this field and identify topics ripe for future research. We conducted this review in accordance with the PRISMA extension for Scoping Reviews to characterize multi-modal data fusion in health. Search strings were established and used in databases: PubMed, Google Scholar, and IEEEXplore from 2011 to 2021. A final set of 128 articles were included in the analysis. The most common health areas utilizing multi-modal methods were neurology and oncology. Early fusion was the most common data merging strategy. Notably, there was an improvement in predictive performance when using data fusion. Lacking from the papers were clear clinical deployment strategies, FDA-approval, and analysis of how using multimodal approaches from diverse sub-populations may improve biases and healthcare disparities. These findings provide a summary on multimodal data fusion as applied to health diagnosis/prognosis problems. Few papers compared the outputs of a multimodal approach with a unimodal prediction. However, those that did achieved an average increase of 6.4% in predictive accuracy. Multi-modal machine learning, while more robust in its estimations over unimodal methods, has drawbacks in its scalability and the time-consuming nature of information concatenation. [ABSTRACT FROM AUTHOR]

To improve the effect of commercial insurance risk decision, this paper applies neural network algorithms to commercial insurance risk decision under the guidance of machine learning ideas, and selects the neural network algorithm based on the actual situation. Moreover, this paper analyzes the nature of risks of commercial insurance, analyzes the types of risks and risk relevance, constructs a commercial insurance risk decision model based on neural network algorithms, and determines the system process. In addition, this paper uses a combination method of qualitative and quantitative to identify the influencing factors of risk estimation to obtain relevant influencing factors, and verify the model proposed in this paper in combination with experimental research. From the experimental research results, it can be seen that the commercial insurance risk decision system based on neural network algorithm is very good in terms of decision effect. [ABSTRACT FROM AUTHOR]

The rising and continuous pollution of the soil from anthropogenic activities is of great concern. Owing to this concern, the advent of digital soil mapping (DSM) has been a tool that soil scientists use in this era to predict the potentially toxic element (PTE) content in the soil. The purpose of this paper was to conduct a review of articles, summarize and analyse the spatial prediction of potentially toxic elements, determine and compare the models' usage as well as their performance over time. Through Scopus, the Web of Science and Google Scholar, we collected papers between the year 2001 and the first quarter of 2019, which were tailored towards the spatial PTE prediction using DSM approaches. The results indicated that soil pollution emanates from diverse sources. However, it provided reasons why the authors investigate a piece of land or area, highlighting the uncertainties in mapping, number of publications per journal and continental efforts to research as well as published on trending issues regarding DSM. This paper reveals the complementary role machine learning algorithms and the geostatistical models play in DSM. Nevertheless, geostatistical approaches remain the most preferred model compared to machine learning algorithms. [ABSTRACT FROM AUTHOR]

After 70 years of intricate development, machine learning, represented by deep learning, is based on the multilevel structure of the human brain and the layer-by-layer analysis and processing mechanism of neuron connection and interaction information. The powerful parallel information processing ability of self-adaptation and self-learning has allowed for breakthroughs in many fields, among which the most representative is image recognition. Therefore, this paper proposed optimizing the RBF algorithm with machine learning (ML) to improve the recognition rate of spectrum sensing. The results showed that the average detection success rates of the RBF algorithm were 93.62%, 95.07%, 96.91%, 98.78% and 99.37% when the SNRs were − 8 dB, − 4 dB, 0 dB, 4 dB and 8 dB, respectively, and the other conditions were kept the same. The average detection success rates of the SVM/RBF algorithm were 97.65%, 99.63%, 99.76%, 99.91% and 99.88%, respectively. The average detection success rate of the SVM/RBF algorithm was significantly higher than that of the RBF algorithm. This indicates that analyzing the RBF neural network algorithm through ML can improve the success rate of spectrum sensing, which highlights a new direction for the application of ML and neural networks. [ABSTRACT FROM AUTHOR]

As an important indicator of the surface quality of workpieces, surface roughness has a great impact on production costs and the quality performance of the finished components. Effective surface roughness prediction can not only increase productivity but also reduce costs. However, the current methods for surface roughness prediction have some limitations. On the one hand, the prediction accuracy of classical experimental and statistical-based surface roughness prediction methods is low. On the other hand, the results of deep learning-based surface roughness prediction methods are uninterpretable due to their black-box learning mechanism. Therefore, this paper presents an ensemble learning with a differential evolution algorithm, applies it to the prediction of surface roughness of abrasive water jet polishing (AWJP), and conducts an interpretability analysis to identify key factors contributing to the prediction accuracy of surface roughness. First, we proposed automatically constructing features by an Evolution Forest algorithm to train the base regression models. The differential evolution algorithm with a simplified encoding mechanism was then used to search for the best weighted-ensemble to integrate the base regression models for obtaining highly accurate prediction results. Extensive experiments have been conducted on AWJP to validate the effectiveness of our proposed methods. The results show that the prediction accuracy of our proposed method is higher than the existing machine learning algorithms. In addition, this is the first of its time for the contributions of machining parameters (i.e., features) on surface roughness prediction by using interpretable analysis methods. The analysis results can provide a reference basis for subsequent experiments and studies. [ABSTRACT FROM AUTHOR]

Intrusion Detection Systems (IDSs) are crucial for safeguarding modern IoT communication networks against cyberattacks. IDSs must exhibit exceptional performance, low false positive rates, and significant flexibility in constructing attack patterns to efficiently identify and neutralize these attacks. This research paper discusses the use of an Extreme Learning Machine (ELM) as a new technique to enhance the performance of IDSs. The study utilizes two standard IDS-based IoT network datasets: NSL-KDD 2009 via Distilled-Kitsune 2021. Both datasets are used to assess the effectiveness of ELM in a conventional supervised learning setting. The study investigates the capacity of the ELM algorithm to handle high-dimensional and unbalanced data, indicating the potential to enhance IDS accuracy and efficiency. The research also examines the setup of ELM for both NSL_KDD and Kitsune using Python and Google COLAB to do binary and multi-class classification. The experimental evaluation revealed the proficient performance of the proposed ELM-based IDS among other implemented supervised learning-based IDSs and other state-of-the-art models in the same study area. [ABSTRACT FROM AUTHOR]

Over the years the number of research publications per year is growing exponentially. Finding research papers of quality from the massive literature of relevant articles is a challenging and time-consuming task. The approaches in the latest literature address citation recommendation by utilizing large bibliographic information and use machine learning and deep learning methods for the task. These techniques clearly require a large amount of training data as well as machines with high processing power. To overcome these issues, we propose a novel method by modifying the popular hyperlink induced topic search (HITS), a web page ranking algorithm, as citation recommendation using hyperlink induced topic search (CR-HITS) that works on a directed and weighted heterogeneous bibliographic network containing diverse types of nodes and edges. We define effective scoring schemes for nodes and edges based on basic bibliographic information like citations of papers, number of publications of an author, etc. Given a few seed papers, the citation recommendation algorithm CR-HITS is run on small neighborhoods of the seed papers and hence the time taken by the execution is very small to yield the final recommendations. To the best of our knowledge, HITS has been used for the first time for the citation recommendation problem. We perform extensive experimentation on DBLP (version-11) and ACM (version-9) datasets and compare the results with many baseline methods in terms of MAP, MRR, and recall@N measures. The performance of the proposed algorithms is superior with respect to the MAP metric and matches the second best for the other two metrics. Since the top two algorithms use deep learning methods and use much larger bibliographic information including abstracts of the papers, we claim that our approach utilizes very low resources, yet yields recommendations that are very close to the top recommendations. [ABSTRACT FROM AUTHOR]

Applying parallel-in-time algorithms to multiscale Hamiltonian systems to obtain stable long-time simulations is very challenging. In this paper, we present novel data-driven methods aimed at improving the standard parareal algorithm developed by Lions et al. in 2001, for multiscale Hamiltonian systems. The first method involves constructing a correction operator to improve a given inaccurate coarse solver through solving a Procrustes problem using data collected online along parareal trajectories. The second method involves constructing an efficient, high-fidelity solver by a neural network trained with offline generated data. For the second method, we address the issues of effective data generation and proper loss function design based on the Hamiltonian function. We show proof-of-concept by applying the proposed methods to a Fermi-Pasta-Ulam (FPU) problem. The numerical results demonstrate that the Procrustes parareal method is able to produce solutions that are more stable in energy compared to the standard parareal. The neural network solver can achieve comparable or better runtime performance compared to numerical solvers of similar accuracy. When combined with the standard parareal algorithm, the improved neural network solutions are slightly more stable in energy than the improved numerical coarse solutions. [ABSTRACT FROM AUTHOR]

The ship tracking and mapping capabilities that geospatial technology provides create an opportunity to observe fishing vessels as they move through established maritime boundaries. This paper connects data availability to ground-truthing research and explores the limits of vessel movement mapping in representing worker abuse at sea through three related themes. First, a conceptual background links the advancements in maritime remote sensing to critical GIS scholarship and provides a background on worker abuse aboard Taiwanese fishing vessels. Second, the paper examines the potential of machine learning algorithms to represent worker abuse at sea, arguing that more extensive ground-truthing research with workers could help address variations in the data and limited data sets. Third, I use remote sensing data to identify and unpack Taiwanese fishing across the three EEZs with the most concentrated Taiwanese fishing activity: starting with Taiwan, followed by the Falkland Islands, and Seychelles. I argue that fishing activity and the digital representation of vessel movements are governed by terrestrial geopolitics and subject to manipulation by ship captains. Finally, the conclusion offers recommendations for how future research can capitalize on the capabilities of AIS, particularly with respect to addressing problems of working conditions and abuse at sea. [ABSTRACT FROM AUTHOR]

We consider the problem of generating balanced training samples from an unlabeled data set with an unknown class distribution. While random sampling works well when the data are balanced, it is very ineffective for unbalanced data. Other approaches, such as active learning and cost-sensitive learning, are also suboptimal as they are classifier-dependent and require misclassification costs and labeled samples, respectively. We propose a new strategy for generating training samples, which is independent of the underlying class distribution of the data and the classifier that will be trained using the labeled data. Our methods are iterative and can be seen as variants of active learning, where we use semi-supervised clustering at each iteration to perform biased sampling from the clusters. We provide several strategies to estimate the underlying class distributions in the clusters and to increase the balancedness in the training samples. Experiments with both highly skewed and balanced data from the UCI repository and a private data set show that our algorithm produces much more balanced samples than random sampling or uncertainty sampling. Further, our sampling strategy is substantially more efficient than active learning methods. The experiments also validate that, with more balanced training data, classifiers trained with our samples outperform classifiers trained with random sampling or active learning. [ABSTRACT FROM AUTHOR]

Today according to social media, the internet, Etc. Data is rapidly produced and occupies a large space in systems that have resulted in enormous data warehouses; the progress in information technology has significantly increased the speed and ease of data flow.text mining is one of the most important methods for extracting a useful model through extracting and adapting knowledge from data sets. However, many studies have been conducted based on the usage of deep learning for text processing and text mining issues.The idea and method of text mining are one of the fields that seek to extract useful information from unstructured textual data that is used very today. Deep learning and machine learning techniques in classification and text mining and their type are discussed in this paper as well. Neural networks of various kinds, namely, ANN, RNN, CNN, and LSTM, are the subject of study to select the best technique. In this study, we conducted a Systematic Literature Review to extract and associate the algorithms and features that have been used in this area. Based on our search criteria, we retrieved 130 relevant studies from electronic databases between 1997 and 2021; we have selected 43 studies for further analysis using inclusion and exclusion criteria in Section 3.2. According to this study, hybrid LSTM is the most widely used deep learning algorithm in these studies, and SVM in machine learning method high accuracy in result shown. [ABSTRACT FROM AUTHOR]

Distributed optimization has a rich history. It has demonstrated its effectiveness in many machine learning applications, etc. In this paper we study a subclass of distributed optimization, namely decentralized optimization in a non-smooth setting. Decentralized means that m agents (machines) working in parallel on one problem communicate only with the neighbors agents (machines), i.e. there is no (central) server through which agents communicate. And by non-smooth setting we mean that each agent has a convex stochastic non-smooth function, that is, agents can hold and communicate information only about the value of the objective function, which corresponds to a gradient-free oracle. In this paper, to minimize the global objective function, which consists of the sum of the functions of each agent, we create a gradient-free algorithm by applying a smoothing scheme via l 2 randomization. We also verify in experiments the obtained theoretical convergence results of the gradient-free algorithm proposed in this paper. [ABSTRACT FROM AUTHOR]

As the scale and complexity of networks grow rapidly, management, maintenance, and optimization of them are becoming increasingly challenging tasks for network administrators. Software-Defined Networking (SDN) was introduced to facilitate these tasks as it offers logically centralized control, a global view of the network, and software-based traffic analysis, thus, it is widely adopted of SDN to manage large-scale networks. On the other hand, SDN is not immune to cyber attacks. In fact, its centralized architecture makes it more vulnerable to certain types of attacks, such as denial of service. Various attack mitigation strategies are proposed to strengthen the security of SDNs including statistical, threshold-based, and Machine Learning (ML) methods. Among them, Deep Learning (DL)-based models attained the best results as they were able to extract the complex relationship between input parameters and output that could not be achieved with other solutions. Hence, this paper presents a comprehensive survey of the literature on the utilization of different DL algorithms for the security of SDN. We first explain the types of attacks that SDNs are exposed to, then present papers that applied DL to detect and/or mitigate these attacks. We further discuss the public datasets used to train DL models and evaluate their advantages and disadvantages. Finally, we share insights into future research directions to improve the efficiency of DL methods for SDN security. [ABSTRACT FROM AUTHOR]

The new generation versatile video coding (VVC) standard brings extremely high compression efficiency. Meanwhile, the complexity of the encoder is also greatly increased. In view of this, this paper proposes a fast algorithm for all zero block detection to speed up the quantization process, thereby reducing the complexity of the encoder. The method proposed in this paper consists of three parts. Firstly, genuine all zero blocks are detected based on a fixed threshold which is derived by hard decision quantization formula. Secondly, parts of pseudo all zero blocks are detected based on an adaptive threshold which is derived by analyzing the positions of transform coefficients under a certain condition. Finally, for the remaining pseudo all zero blocks, machine learning is introduced and the decision is made through the fully connected neural network. Experimental results show that the proposed fast algorithm achieves up to 7.505% and 7.049% coding time saving under Low Delay B and Random Access configurations with only 0.470% and 0.578% performance loss on average, respectively. [ABSTRACT FROM AUTHOR]

Ensuring the transparency of machine learning models is vital for their ethical application in various industries. There has been a concurrent trend of distributed machine learning designed to limit access to training data for privacy concerns. Such models, trained over horizontally or vertically partitioned data, present a challenge for explainable AI because the explaining party may have a biased view of background data or a partial view of the feature space. As a result, explanations obtained from different participants of distributed machine learning might not be consistent with one another, undermining trust in the product. This paper presents an Explainable Data Collaboration Framework based on a model-agnostic additive feature attribution algorithm (KernelSHAP) and Data Collaboration method of privacy-preserving distributed machine learning. In particular, we present three algorithms for different scenarios of explainability in Data Collaboration and verify their consistency with experiments on open-access datasets. Our results demonstrated a significant (by at least a factor of 1.75) decrease in feature attribution discrepancies among the users of distributed machine learning. The proposed method improves consistency among explanations obtained from different participants, which can enhance trust in the product and enable ethical application in various industries. [ABSTRACT FROM AUTHOR]

Theoretically, the Super-Resolution (SR) reconstruction scheme is a method which is performed by many applications nowadays for the purpose of generating a High-Resolution (HR) image using the input Low-Resolution (LR) images by filling in the missing high frequency information. In addition, the SR reconstruction implemented based on the theory of sparse representation techniques is known as an effective way to produce HR images using images patches generated from the LR images. In order to improve the quality of denoised images produced by using the sparse representation techniques, a scheme called dictionary learning algorithms could be considered. Thus, the objective of this paper is to provide a performance comparison on the effectiveness of applying the dictionary learning steps with sparse representation algorithms in producing a better denoised image. In this case, the average Peak Signal-to-Noise ratio (PSNR) and Structural Similarity Index Metric (SSIM) values of the denoised image obtained by using Algorithms 1, 2, and 3 which combined the use of dictionary learning and sparse representation algorithms were compared with the values obtained from images produced by applying only sparse regularisation methods. As a conclusion, the denoised images produced by Algorithm 1 in this paper had the greatest average PSNR and SSIM values. Hence, the algorithm with the implementation of the dictionary learning process with sparse representation methods is able to achieve a better result in enhancing the low-resolution images. [ABSTRACT FROM AUTHOR]

Focusing on non-iterative approaches in training feed-forward neural networks, this special issue includes 12 papers to share the latest progress, current challenges, and potential applications of this topic. This editorial presents a background of the special issue and a brief introduction to the 12 contributions. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) and machine learning (ML) tools play a significant role in the recent evolution of smart systems. AI solutions are pushing towards a significant shift in many fields such as healthcare, autonomous airplanes and vehicles, security, marketing customer profiling and other diverse areas. One of the main challenges hindering the AI potential is the demand for high-performance computation resources. Recently, hardware accelerators are developed in order to provide the needed computational power for the AI and ML tools. In the literature, hardware accelerators are built using FPGAs, GPUs and ASICs to accelerate computationally intensive tasks. These accelerators provide high-performance hardware while preserving the required accuracy. In this work, we present a systematic literature review that focuses on exploring the available hardware accelerators for the AI and ML tools. More than 169 different research papers published between the years 2009 and 2019 are studied and analysed. [ABSTRACT FROM AUTHOR]

Hierarchical temporal memory (HTM) is a promising unsupervised machine-learning algorithm that models key principles of neocortical computation. One of the main components of HTM is the spatial pooler (SP), which encodes binary input streams into sparse distributed representations (SDRs). In this paper, we propose an information-theoretic framework for the performance comparison of HTM-spatial pooler (SP) algorithms, specifically, for quantifying the similarities and differences between sparse distributed representations in SP algorithms. We evaluate SP's standalone performance, as well as HTM's overall performance. Our comparison of various SP algorithms using Renyi mutual information, Renyi divergence, and Henze–Penrose divergence measures reveals that the SP algorithm with learning and a logarithmic boosting function yields the most effective and useful data representation. Moreover, the most effective SP algorithm leads to superior HTM results. In addition, we utilize our proposed framework to compare HTM with other state-of-the-art sequential learning algorithms. We illustrate that HTM exhibits superior adaptability to pattern changes over time than long short term memory (LSTM), gated recurrent unit (GRU) and online sequential extreme learning machine (OS-ELM) algorithms. This superiority is evident from the lower Renyi divergence of HTM (0.23) compared to LSTM6000 (0.33), LSTM3000 (0.38), GRU (0.41), and OS-ELM (0.49). HTM also achieved the highest Renyi mutual information value of 0.79, outperforming LSTM6000 (0.73), LSTM3000 (0.71), GRU (0.68), and OS-ELM (0.62). These findings not only confirm the numerous advantages of HTM over other sequential learning algorithm, but also demonstrate the effectiveness of our proposed information-theoretic approach as a powerful framework for comparing and evaluating various learning algorithms. [ABSTRACT FROM AUTHOR]

Federated learning (FL) represents a promising distributed machine learning paradigm for resolving data isolation due to data privacy concerns. Nevertheless, most vanilla FL algorithms, which depend on a server, encounter the problem of reliability and a high communication burden in real cases. Decentralized federated learning (DFL) that does not follow the star topology faces the challenges of weight divergence and inferior communication efficiency. In this paper, a novel DFL framework called federated incremental subgradient-proximal (FedISP) is proposed that utilizes the incremental method to perform model updates to alleviate weight divergence. In our setup, multiple clients are distributed in a ring topology and communicate in a cyclic manner, which significantly mitigates the communication load. A convergence guarantee is given under the convex condition to demonstrate the impact of the learning rate on our algorithms, which further improves the performance of FedISP. Extensive experiments on benchmark datasets validate the effectiveness of the proposed approach in both independent and identically distributed (IID) and non-IID settings while illustrating the advantages of the FedISP algorithm in achieving model consensus and saving communication costs. [ABSTRACT FROM AUTHOR]

What are the best methods of capturing thematic similarity between literary texts? Knowing the answer to this question would be useful for automatic clustering of book genres, or any other thematic grouping. This paper compares a variety of algorithms for unsupervised learning of thematic similarities between texts, which we call "computational thematics". These algorithms belong to three steps of analysis: text pre-processing, extraction of text features, and measuring distances between the lists of features. Each of these steps includes a variety of options. We test all the possible combinations of these options. Every combination of algorithms is given a task to cluster a corpus of books belonging to four pre-tagged genres of fiction. This clustering is then validated against the "ground truth" genre labels. Such comparison of algorithms allows us to learn the best and the worst combinations for computational thematic analysis. To illustrate the difference between the best and the worst methods, we then cluster 5000 random novels from the HathiTrust corpus of fiction. [ABSTRACT FROM AUTHOR]

Whenever a new supervised machine learning (ML) algorithm or solution is developed, it is imperative to evaluate the predictive performance it attains for diverse datasets. This is done in order to stress test the strengths and weaknesses of the novel algorithms and provide evidence for situations in which they are most useful. A common practice is to gather some datasets from public benchmark repositories for such an evaluation. But little or no specific criteria are used in the selection of these datasets, which is often ad-hoc. In this paper, the importance of gathering a diverse benchmark of datasets in order to properly evaluate ML models and really understand their capabilities is investigated. Leveraging from meta-learning studies evaluating the diversity of public repositories of datasets, this paper introduces an optimization method to choose varied classification and regression datasets from a pool of candidate datasets. The method is based on maximum coverage, circular packing, and the meta-heuristic Lichtenberg Algorithm for ensuring that diverse datasets able to challenge the ML algorithms more broadly are chosen. The selections were compared experimentally with a random selection of datasets and with clustering by k-medoids and proved to be more effective regarding the diversity of the chosen benchmarks and the ability to challenge the ML algorithms at different levels. [ABSTRACT FROM AUTHOR]

Machine learning techniques aim to mimic the human ability to automatically learn how to perform tasks through training examples. They have proven capable of tasks such as prediction, learning and adaptation based on experience and can be used in virtually any scientific application, ranging from biomedical, robotic, to business decision applications, and others. However, the lack of domain knowledge for a particular application can make feature extraction ineffective or even unattainable. Furthermore, even in the presence of pre-processed datasets, the iterative process of optimizing Machine Learning parameters, which do not translate from one domain to another, maybe difficult for inexperienced practitioners. To address these issues, we present in this paper a Vectorized Automated ML Pre-processIng and post-pRocEssing framework, approximately named (VAMPIRE), which implements feature extraction algorithms capable of converting large time-series recordings into datasets. Also, it introduces a new concept, the Activation Engine, which is attached to the output of a Multi Layer Perceptron and extracts the optimal threshold to apply binary classification. Moreover, a tree-based algorithm is used to achieve multi-class classification using the Activation Engine. Furthermore, the internet of things gives rise to new applications such as remote sensing and communications, so consequently applying Machine Learning to improve operation accuracy, latency, and reliability is beneficial in such systems. Therefore, all classifications in this paper were performed on the edge in order to reach high accuracy with limited resources. Moreover, forecasts were applied on three unrelated biomedical datasets, and on two other pre-processed urban and activity detection datasets. Features were extracted when required, and training and testing were performed on the Raspberry Pi remotely, where high accuracy and inference speed were achieved in every experiment. Additionally, the board remained competitive in terms of power consumption when compared with a laptop which was optimized using a Graphical Processing Unit. [ABSTRACT FROM AUTHOR]

In order to solve the problems of low learning efficiency and slow convergence speed when mobile robot uses reinforcement learning method for path planning in complex environment, a reinforcement learning method based on each round path planning result is proposed. Firstly, the algorithm adds obstacle learning matrix to improve the success rate of path planning; and introduces heuristic reward to speed up the learning process by reducing the search space; then proposes a method of dynamically adjusting the exploration factor to balance the exploration and utilization in path planning, so as to further improve the performance of the algorithm. Finally, the simulation experiment in grid environment shows that compared with Q-learning algorithm, the improved algorithm not only shortens the average path length of the robot to reach the target position, but also speeds up the learning efficiency of the algorithm, so that the robot can find the optimal path more quickly. The code of EPRQL algorithm proposed in this paper has been published to GitHub: https://github.com/panpanpanguoguoqian/mypaper1.git. [ABSTRACT FROM AUTHOR]

A recognition model named the SVM-NP is proposed in this paper to address the multi-attribute overlap in radar working recognition. The model is based on the K-NN boundary preselection algorithm and SVM-BP algorithm. Traditional classifiers tend to neglect the overlap of samples' attributes in classification, which leads to the low accuracy of classifiers. The K-NN boundary preselection can quickly select boundary samples from the total ones and reduce the whole samples' attribute overlap. The SVM-BP algorithm is improved based on the SVM-RFE algorithm, and the boundary samples with high attribute overlap are divided into many planes for training and testing. Compared with traditional methods, the overlap of sample attributes can be reduced twice in this model. Theoretical analysis and experimental results verify that the model proposed in this paper displays better performance in classification when appropriate parameters are provided. [ABSTRACT FROM AUTHOR]

Fungal keratitis (FK) is a common and severe corneal disease, which is widely spread in tropical and subtropical areas. Early diagnosis and treatment are vital for patients, with confocal microscopy cornea imaging being one of the most effective methods for the diagnosis of FK. However, most cases are currently diagnosed by the subjective judgment of ophthalmologists, which is time-consuming and heavily depends on the experience of the ophthalmologists. In this paper, we introduce a novel structure-aware automatic diagnosis algorithm based on deep convolutional neural networks for the accurate diagnosis of FK. Specifically, a two-stream convolutional network is deployed, combining GoogLeNet and VGGNet, which are two commonly used networks in computer vision architectures. The main stream is used for feature extraction of the input image, while the auxiliary stream is used for feature discrimination and enhancement of the hyphae structure. Then, the features are combined by concatenating the channel dimension to obtain the final output, i.e., normal or abnormal. The results showed that the proposed method achieved accuracy, sensitivity, and specificity of 97.73%, 97.02%, and 98.54%, respectively. These results suggest that the proposed neural network could be a promising computer-aided FK diagnosis solution. [ABSTRACT FROM AUTHOR]

Due to the large number of stock companies, complex stock categories and inconsistent evaluation standards of market value, it is not conducive to the choice of investors. Based on the theory and practice of traditional stock performance evaluation model, this paper integrates the algorithm thought structure of Fama–French five-factor model and proposes a machine learning algorithm model for stock performance research. In addition, this paper also builds a model that can evaluate the style and timing ability of fund managers to improve the fund performance evaluation system to a greater extent. With the help of the performance evaluation updating function of the model, it provides a new experience material in the empirical research composition of the fund performance field. In the system test module, the former prediction data and the actual experimental data are integrated, and the two are sorted out and compared, which proves the feasibility and effectiveness of the proposed algorithm model. The final experimental results verify the usefulness of the model in stock return prediction and analysis of influencing factors. [ABSTRACT FROM AUTHOR]

Rib segmentation based on chest X-ray images is essential in the computer-aided diagnosis systems of lung cancer, which serves as an important step in the quantitative analysis of various types of lung diseases. However, the traditional methods are unable to segment ribs effectively due to the unclear edges and overlapping regions in X-ray images. A novel rib segmentation framework based on Unpaired Sample Augmentation and Multi-Scale Network is presented in this paper, aiming to improve the accuracy of ribs segmentation with limited labeled samples. First, the algorithm learns pneumonia-related texture changes via unpaired chest x-ray images and generates various augmented samples. Then, a multi-scale network attempts to learn hierarchical features using global supervision. Finally, the refined segmentation result of each organ is achieved by using a deep separation module and a comprehensive loss function. Specifically, the hierarchical features can greatly improve the robustness of multi-organ segmentation networks. The complex multi-organ segmentation task with limited labeled data is simplified with the designed deep separation module. We justify the proposed framework through extensive experiments. It achieves good performance with DSC, Precision, Recall, and Jaccard of 88.03, 88.25, 88.36, and 79.02%, respectively. The DSC value increases nearly by 3% compared to other popular methods. The experimental results show that our algorithm presents better segmentation performance for the overlapping region and fuzzy region of multiple organs, which holds research value and prospects for application. [ABSTRACT FROM AUTHOR]

Label-specific features learning can effectively exploit the unique features of each label, which alleviates the high dimensionality and improves the classification performance of multi-label. However, most existing label-specific features learning algorithms assume that label space is complete, ignoring the effect of missing labels on the classification accuracy. Some methods try to recover the missing labels first and then learn the mapping between the completed label matrix and the feature matrix. However, early intervention in the recovery of missing labels may affect the distribution of original labels to a certain extent. In this paper, feature-label dual-mapping for missing label-specific features learning is proposed. According to the information that the label depends on the feature, the dual-mapping weight of the complete feature space and the missing label space is jointly learned. Therefore, the proposed algorithm is to conduct latent missing labels recovery by feature-label dual-mapping to directly obtain target weight in this paper, avoiding the negative influence of early label recovery intervention. Compared with several state-of-the-art methods in 10 benchmark multi-label data sets, the results show that the proposed algorithm is reasonable and effective. [ABSTRACT FROM AUTHOR]

This paper proposes a collaborative filtering algorithm based on user group interest. A novel co-clustering method (BalClust) and various weighted non-negative matrix factorization algorithms are used in the proposed method. The BalClust method is used to divide the raw rating matrix into clusters, which are smaller than the original matrix. Then, the balance factor is introduced to consider the user weight and the item-based CF (collaborative filtering). To predict the rating of the unknown items in the cluster, the non-negative matrix factorization algorithm was used. The proposed method achieves higher predicting accuracy and efficiency on low dimensional and homogeneous sub-matrices, and the method also reduces the computational complexity by combining the user and item-based CF. Based on the proposed method, this paper proposed an incremental learning method to ensure data accuracy and timeliness to overcome the problem brought by data updates. The experimental results show the proposed methods outperformed traditional CF algorithms, and the completion time is reduced. [ABSTRACT FROM AUTHOR]

With the birth of the IoT era, it is evident that the existing number of devices is going to rise exponentially. Any two devices will communicate with each other using the same frequency band with limited availability. Therefore, it is of vital importance that this frequency band used for communication be used efficiently to accommodate the maximum number of devices with the available radio resources. Cognitive radio (CR) technology serves this exact purpose. The stated one is an intelligent radio that is made to automatically identify the optimal wireless channel in the available wireless spectrum at a given instant. An important functionality of CR is spectrum sensing. Energy detection is a very popular algorithm used for spectrum sensing in CR technology for efficient allocation of radio resources to the devices intended to communicate with each other. Energy detection detects the presence of a primary user (PU) signal by continuously monitoring a selected frequency bandwidth. The conventional energy detection technique is known to perform poorly in lower SNR ranges. This paper works towards the improvement of the energy detection algorithm with the help of machine learning (ML). The ML model uses the general properties of the signal as training data and classifies between a PU signal and noise at very low SNR ranges (− 25 to − 10 dB). In this research, a K-nearest neighbours (KNN) model is selected for its versatility and simplicity. Upon testing the model with an out-of-sample dataset, the KNN model produced a detection accuracy of 94.5%. [ABSTRACT FROM AUTHOR]

Manual term extraction is similar to literal meaning: A translator browses text, classifies words, and prepares for translation. Terminology, as a centralized carrier of expertise, creation, popularization, and disappearance, dynamically reflects the development and evolution of an industry. The automatic extraction of terminology is a key technology for creating a professional terminology database, and it is also a key topic in the field of natural language processing. The purpose of this paper is to study how to analyse a term extraction algorithm based on machine learning and a comprehensive feature strategy. Focusing on the problems of poor generality and single statistical features of current term extraction algorithms, this paper proposes an improved domain ontology term extraction algorithm based on a comprehensive feature strategy. Moreover, automatic term extraction experiments based on a word-based maximum entropy model and a conditional random field model based on machine learning are conducted in this paper. Its word-based conditional random field model outperforms the maximum entropy model. The experimental results show that the algorithm based on the comprehensive feature strategy improves the accuracy by 8.6% compared with the TF-IDF algorithm and the C-value term extraction algorithm. This algorithm can be used to effectively extract the terms in a text and has good generality. [ABSTRACT FROM AUTHOR]

Present-day demand and supply of connectivity necessitate the rapid production of Microwave (MW) filter units. The production of these filters is then followed by the step of utmost importance in the assembly line, viz., the 'tuning of the filter', as tuning is crucial to meeting the selectivity requirements of the band. Since the advent of filters, tuning has always been done manually, and hence it is considered a bottleneck by experts in the field. Thus, the need to automate the system is highly implied. The goal of the current work is to outline various MW filter tuning techniques that have been advocated by the community of researchers. The limitations of the said research works and their comparative analysis are also encapsulated in tabular form in the present paper. The paper ends with the implementation of an Expert-Based Hybrid Deep Learning Algorithm to fully automate the filter tuning process. [ABSTRACT FROM AUTHOR]

In the era of big data, the demand for multivariate time series prediction has surged, drawing increased attention to feature selection and neural networks in machine learning. However, certain feature selection methods neglect the alignment between actual data sample differences and clustering results, while neural networks lack automatic parameter adjustment in response to changing target features. This paper presents the MBSSA-Bi-AESN model, a Bi-directional Adaptive Echo State Network that utilizes the modified salp swarm algorithm (MBSSA) and feature selection to address the limitations of manually set parameters. Initial feature subset selection involves assigning weights based on the consistency of clustering results with differences. Subsequently, the four critical parameters in the Bi-AESN model are optimized using MBSSA. The optimized Bi-AESN model and selected feature subset are then integrated for simultaneous model learning and optimal feature subset selection. Experimental analysis on eight datasets demonstrates the superior prediction accuracy of the MBSSA-Bi-AESN model compared to benchmark models, underscoring its feasibility, validity, and universality. [ABSTRACT FROM AUTHOR]

Twin support vector regression (TSVR) has been widely applied in regression problems. TSVR seeks a pair of ε -insensitive proximal planes by solving two support vector machine type problems. TSVR assumes that the matrices appearing in the dual formulation are positive definite. However, in real-world scenarios, such an assumption may not be fulfilled and, hence, leads to suboptimal performance. ε -Twin support vector regression (ε -TSVR) improved the TSVR by introducing the regularisation term to avoid the singularity issues. Most of the twin support vector machine models involve the computation of matrix inverses. Also, TSVR implements the empirical risk minimization principle. In this paper, we propose an improved twin support vector regression (ITSVR) for brain age estimation by introducing different Lagrangian functions for the primal problems of the TSVR. The proposed ITSVR implements the structural risk minimization principle and avoids the computation of the matrix inverses. To solve the optimization problem more efficiently, we used successive overrelaxation (SOR) technique. We evaluated the proposed ITSVR on cognitively healthy subjects, mild cognitive impairment subjects and Alzheimer's disease subjects. The experimental results demonstrate that the proposed ITSVR has superior performance compared to the baseline models for brain age estimation. [ABSTRACT FROM AUTHOR]

Today, robotic arms are widely used in industry. Reinforcement learning algorithms are used frequently for controlling robotic arms in complex environments. One of the customs off-policy model-free actor-critic deep reinforcement learning for continuous action spaces is deep deterministic policy gradient (DDPG). This algorithm has achieved significant results when applied to control robotic arms with high degrees of freedom. But, it also has limitations. DDPG is prone to instability and divergence in complex tasks due to the high dimensional continuous action spaces. In this paper, in order to increase the reliability and convergence speed of the DDPG algorithm, a new modified convergence DDPG (MCDDPG) algorithm is presented. By saving and reusing desirable parameters of the previous actor and critic networks, the proposed algorithm has shown a significant enhancement in training time and stability of the model compared to the conventional DDPG. We evaluate our method on the PR2's right arm which is a 7-DoF manipulator, and simulations demonstrate that our MCDDPG outperforms state-of-the-art algorithms such as DDPG and normalized advantage function in learning complex robotic tasks. [ABSTRACT FROM AUTHOR]

An inherent problem in software engineering is that competing prediction systems have been found to produce conflicting results. Yet accurate prediction is crucial because the complexity and quality of software requirements have dramatically changed in recent years, and consumers have become considerably more demanding in terms of the cost, timeframe, and quality of software solutions. Moreover, these variables may also be in direct conflict and can only be resolved by the optimum development of software by using reliable software engineering strategies. In this paper, a novel method based on the integration of the mine blast algorithm (MBA) and the simulated annealing (SA) algorithm is used to create input connection weights and biases for a back propagation neural network (BPNN) for the purpose of addressing the software fault prediction problem (SFP). The aim of hybridizing the MBA and SA is to find a way to efficiently explore and manipulate the search space. The proposed MBA-SA was tested on 18 datasets for SFP. The results indicated that the MBA-SA outperformed the MBA on all datasets. These results were subjected to additional statistical validity, boxplot distribution, and convergence analysis. Furthermore, a comparative evaluation of MBA-SA against twenty state-of-the-art methods for various output metrics was performed, and the result indicated that the hybrid MBA-SA outperformed most other state-of-the-art methods in the majority of datasets. [ABSTRACT FROM AUTHOR]

The problem that I present in this paper concerns the issue of ethical evaluation of algorithms, especially those used in social media and which create profiles of users of these media and new technologies that have recently emerged and are intended to change the functioning of technologies used in data management. Systems such as Overton, SambaNova or Snorkel were created to help engineers create data management models, but they are based on different assumptions than the previous approach in machine learning and deep learning. There is a need to analyze both deep learning algorithms and new technologies in database management in terms of their actions towards a person who leaves their digital footprints, on which these technologies work. Then, the possibilities of applying the existing deep learning technology and new Big Data systems in the economy will be shown. The opportunities offered by the systems mentioned above seem to be promising for many companies and—if implemented on a larger scale—they will affect the functioning of the free market. [ABSTRACT FROM AUTHOR]

The salp swarm algorithm (SSA) is a well-known optimization algorithm that is increasingly being utilized to solve many sorts of optimization problems. However, SSA may converge to sub-optimal solutions when it is applied to discrete problems such as the feature selection (FS) problem. This paper presents the enhanced opposition-based learning salp swarm algorithm (EOSSA), which is an improved SSA algorithm for solving the FS problem in intrusion detection systems (IDS). EOSSA incorporates four improvements into the original SSA algorithm. Firstly, the opposition-based learning (OBL) method is used in the initialization step of SSA to boost its population diversity. Secondly, the Elite opposition-based learning (EOBL) is used in the improvement loop of SSA to improve its exploration ability. Third, a variable neighborhood search (VNS) method is used in the improvement loop of SSA to improve its exploration mechanism to improve the local search space. Lastly, the Sigmoid binary transform function is used to convert the continuous candidate solutions produced by SSA into discrete binary solutions. EOSSA was evaluated against eighteen popular optimization algorithms (e.g., improved salp swarm algorithm based on opposition-based learning (ISSA), SSA, particle swarm algorithm (PSO), cuckoo search (CS), bat algorithm (BA), and Harris Hawk Optimization (HHO)) using eleven popular intrusion detection datasets (CICIDS2017, CSE-CIC-IDS2018, CICDDOS2019, CIRA-CIC-DoH, Intrusion detection 2018, UNSW-NB15, NSL-KDD, Phishing Legitimate, Malmem2022, IoT, and LUFlow Network) to Detect IoT Botnet Attacks. Moreover, EOSSA was compared with four machine learning algorithms (Decision Tree (DT), logistic regression (LR), Naive Bayes (NB), and K-Nearest Neighborhood (KNN)). The overall simulation results suggested that the proposed method is superior to the other algorithms in terms of the accuracy and number of selected features. The statistical analysis of the simulation results using the Friedman and Wilcoxon signed-rank test confirms the superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Research in computer analysis of medical images bears many promises to improve patients' health. However, a number of systematic challenges are slowing down the progress of the field, from limitations of the data, such as biases, to research incentives, such as optimizing for publication. In this paper we review roadblocks to developing and assessing methods. Building our analysis on evidence from the literature and data challenges, we show that at every step, potential biases can creep in. On a positive note, we also discuss on-going efforts to counteract these problems. Finally we provide recommendations on how to further address these problems in the future. [ABSTRACT FROM AUTHOR]

In Machine Learning (ML), Feature Selection (FS) plays a crucial part in reducing data's dimensionality and enhancing any proposed framework's performance. However, in real-world applications, FS work suffers from high dimensionality, computational and storage complexity, noisy or ambiguous nature, high performance, etc. The area of FS is very vast and challenging in its nature. There are lots of work that have been reported on FS over the various area of applications. This paper has discussed FS's framework and the multiple models of FS with detailed descriptions. We have also classified the various FS algorithms with respect to the data, i.e., structured or labeled data and unstructured data for the different applications of ML. We have also discussed what essential features are, the commonly used FS methods, the widely used datasets, and the widely used work done in the various ML fields for the FS task. Here we try to view the multiple comparison experimental results of FS work in different result discussions. This paper draws a descriptive survey on FS with the associated area of real-world problem domains. This paper's main objective is to understand the main idea of FS work and identify the core idea of how FS will be applicable in various problem domains. [ABSTRACT FROM AUTHOR]

Multimarginal Optimal Transport (MOT) has attracted significant interest due to applications in machine learning, statistics, and the sciences. However, in most applications, the success of MOT is severely limited by a lack of efficient algorithms. Indeed, MOT in general requires exponential time in the number of marginals k and their support sizes n. This paper develops a general theory about what "structure" makes MOT solvable in poly (n , k) time. We develop a unified algorithmic framework for solving MOT in poly (n , k) time by characterizing the structure that different algorithms require in terms of simple variants of the dual feasibility oracle. This framework has several benefits. First, it enables us to show that the Sinkhorn algorithm, which is currently the most popular MOT algorithm, requires strictly more structure than other algorithms do to solve MOT in poly (n , k) time. Second, our framework makes it much simpler to develop poly (n , k) time algorithms for a given MOT problem. In particular, it is necessary and sufficient to (approximately) solve the dual feasibility oracle—which is much more amenable to standard algorithmic techniques. We illustrate this ease-of-use by developing poly (n , k) -time algorithms for three general classes of MOT cost structures: (1) graphical structure; (2) set-optimization structure; and (3) low-rank plus sparse structure. For structure (1), we recover the known result that Sinkhorn has poly (n , k) runtime; moreover, we provide the first poly (n , k) time algorithms for computing solutions that are exact and sparse. For structures (2)-(3), we give the first poly (n , k) time algorithms, even for approximate computation. Together, these three structures encompass many—if not most—current applications of MOT. [ABSTRACT FROM AUTHOR]