Large-Kernel Attention for 3D Medical Image Segmentation.

Automated segmentation of multiple organs and tumors from 3D medical images such as magnetic resonance imaging (MRI) and computed tomography (CT) scans using deep learning methods can aid in diagnosing and treating cancer. However, organs often overlap and are complexly connected, characterized by extensive anatomical variation and low contrast. In addition, the diversity of tumor shape, location, and appearance, coupled with the dominance of background voxels, makes accurate 3D medical image segmentation difficult. In this paper, a novel 3D large-kernel (LK) attention module is proposed to address these problems to achieve accurate multi-organ segmentation and tumor segmentation. The advantages of biologically inspired self-attention and convolution are combined in the proposed LK attention module, including local contextual information, long-range dependencies, and channel adaptation. The module also decomposes the LK convolution to optimize the computational cost and can be easily incorporated into CNNs such as U-Net. Comprehensive ablation experiments demonstrated the feasibility of convolutional decomposition and explored the most efficient and effective network design. Among them, the best Mid-type 3D LK attention-based U-Net network was evaluated on CT-ORG and BraTS 2020 datasets, achieving state-of-the-art segmentation performance when compared to avant-garde CNN and Transformer-based methods for medical image segmentation. The performance improvement due to the proposed 3D LK attention module was statistically validated.

Toward Fully Automated Inspection of Critical Assets Supported by Autonomous Mobile Robots, Vision Sensors, and Artificial Intelligence.

Robotic inspection is advancing in performance capabilities and is now being considered for industrial applications beyond laboratory experiments. As industries increasingly rely on complex machinery, pipelines, and structures, the need for precise and reliable inspection methods becomes paramount to ensure operational integrity and mitigate risks. AI-assisted autonomous mobile robots offer the potential to automate inspection processes, reduce human error, and provide real-time insights into asset conditions. A primary concern is the necessity to validate the performance of these systems under real-world conditions. While laboratory tests and simulations can provide valuable insights, the true efficacy of AI algorithms and robotic platforms can only be determined through rigorous field testing and validation. This paper aligns with this need by evaluating the performance of one-stage models for object detection in tasks that support and enhance the perception capabilities of autonomous mobile robots. The evaluation addresses both the execution of assigned tasks and the robot's own navigation. Our benchmark of classification models for robotic inspection considers three real-world transportation and logistics use cases, as well as several generations of the well-known YOLO architecture. The performance results from field tests using real robotic devices equipped with such object detection capabilities are promising, and expose the enormous potential and actionability of autonomous robotic systems for fully automated inspection and maintenance in open-world settings.

Region-based evidential deep learning to quantify uncertainty and improve robustness of brain tumor segmentation.

Despite recent advances in the accuracy of brain tumor segmentation, the results still suffer from low reliability and robustness. Uncertainty estimation is an efficient solution to this problem, as it provides a measure of confidence in the segmentation results. The current uncertainty estimation methods based on quantile regression, Bayesian neural network, ensemble, and Monte Carlo dropout are limited by their high computational cost and inconsistency. In order to overcome these challenges, Evidential Deep Learning (EDL) was developed in recent work but primarily for natural image classification and showed inferior segmentation results. In this paper, we proposed a region-based EDL segmentation framework that can generate reliable uncertainty maps and accurate segmentation results, which is robust to noise and image corruption. We used the Theory of Evidence to interpret the output of a neural network as evidence values gathered from input features. Following Subjective Logic, evidence was parameterized as a Dirichlet distribution, and predicted probabilities were treated as subjective opinions. To evaluate the performance of our model on segmentation and uncertainty estimation, we conducted quantitative and qualitative experiments on the BraTS 2020 dataset. The results demonstrated the top performance of the proposed method in quantifying segmentation uncertainty and robustly segmenting tumors. Furthermore, our proposed new framework maintained the advantages of low computational cost and easy implementation and showed the potential for clinical application.

Modelling Electricity Consumption During the COVID19 Pandemic: Datasets, Models, Results and a Research Agenda.

The COVID19 pandemic has impacted the global economy, social activities, and Electricity Consumption (EC), affecting the performance of historical data-based Electricity Load Forecasting (ELF) algorithms. This study thoroughly analyses the pandemic's impact on these models and develop a hybrid model with better prediction accuracy using COVID19 data. Existing datasets are reviewed, and their limited generalization potential for the COVID19 period is highlighted. A dataset of 96 residential customers, comprising 36 and six months before and after the pandemic, is collected, posing significant challenges for current models. The proposed model employs convolutional layers for feature extraction, gated recurrent nets for temporal feature learning, and a self-attention module for feature selection, leading to better generalization for predicting EC patterns. Our proposed model outperforms existing models, as demonstrated by a detailed ablation study using our dataset. For instance, it achieves an average reduction of 0.56% & 3.46% in MSE, 1.5% & 5.07% in RMSE, and 11.81% & 13.19% in MAPE over the pre- and post-pandemic data, respectively. However, further research is required to address the varied nature of the data. These findings have significant implications for improving ELF algorithms during pandemics and other significant events that disrupt historical data patterns.

EvoPruneDeepTL: An evolutionary pruning model for transfer learning based deep neural networks.

In recent years, Deep Learning models have shown a great performance in complex optimization problems. They generally require large training datasets, which is a limitation in most practical cases. Transfer learning allows importing the first layers of a pre-trained architecture and connecting them to fully-connected layers to adapt them to a new problem. Consequently, the configuration of the these layers becomes crucial for the performance of the model. Unfortunately, the optimization of these models is usually a computationally demanding task. One strategy to optimize Deep Learning models is the pruning scheme. Pruning methods are focused on reducing the complexity of the network, assuming an expected performance penalty of the model once pruned. However, the pruning could potentially be used to improve the performance, using an optimization algorithm to identify and eventually remove unnecessary connections among neurons. This work proposes EvoPruneDeepTL, an evolutionary pruning model for Transfer Learning based Deep Neural Networks which replaces the last fully-connected layers with sparse layers optimized by a genetic algorithm. Depending on its solution encoding strategy, our proposed model can either perform optimized pruning or feature selection over the densely connected part of the neural network. We carry out different experiments with several datasets to assess the benefits of our proposal. Results show the contribution of EvoPruneDeepTL and feature selection to the overall computational efficiency of the network as a result of the optimization process. In particular, the accuracy is improved, reducing at the same time the number of active neurons in the final layers.

Edge-enhanced dual discriminator generative adversarial network for fast MRI with parallel imaging using multi-view information.

In clinical medicine, magnetic resonance imaging (MRI) is one of the most important tools for diagnosis, triage, prognosis, and treatment planning. However, MRI suffers from an inherent slow data acquisition process because data is collected sequentially in k-space. In recent years, most MRI reconstruction methods proposed in the literature focus on holistic image reconstruction rather than enhancing the edge information. This work steps aside this general trend by elaborating on the enhancement of edge information. Specifically, we introduce a novel parallel imaging coupled dual discriminator generative adversarial network (PIDD-GAN) for fast multi-channel MRI reconstruction by incorporating multi-view information. The dual discriminator design aims to improve the edge information in MRI reconstruction. One discriminator is used for holistic image reconstruction, whereas the other one is responsible for enhancing edge information. An improved U-Net with local and global residual learning is proposed for the generator. Frequency channel attention blocks (FCA Blocks) are embedded in the generator for incorporating attention mechanisms. Content loss is introduced to train the generator for better reconstruction quality. We performed comprehensive experiments on Calgary-Campinas public brain MR dataset and compared our method with state-of-the-art MRI reconstruction methods. Ablation studies of residual learning were conducted on the MICCAI13 dataset to validate the proposed modules. Results show that our PIDD-GAN provides high-quality reconstructed MR images, with well-preserved edge information. The time of single-image reconstruction is below 5ms, which meets the demand of faster processing.

AI-based medical e-diagnosis for fast and automatic ventricular volume measurement in patients with normal pressure hydrocephalus.

Based on CT and MRI images acquired from normal pressure hydrocephalus (NPH) patients, using machine learning methods, we aim to establish a multimodal and high-performance automatic ventricle segmentation method to achieve an efficient and accurate automatic measurement of the ventricular volume. First, we extract the brain CT and MRI images of 143 definite NPH patients. Second, we manually label the ventricular volume (VV) and intracranial volume (ICV). Then, we use the machine learning method to extract features and establish automatic ventricle segmentation model. Finally, we verify the reliability of the model and achieved automatic measurement of VV and ICV. In CT images, the Dice similarity coefficient (DSC), intraclass correlation coefficient (ICC), Pearson correlation, and Bland-Altman analysis of the automatic and manual segmentation result of the VV were 0.95, 0.99, 0.99, and 4.2 ± 2.6, respectively. The results of ICV were 0.96, 0.99, 0.99, and 6.0 ± 3.8, respectively. The whole process takes 3.4 ± 0.3 s. In MRI images, the DSC, ICC, Pearson correlation, and Bland-Altman analysis of the automatic and manual segmentation result of the VV were 0.94, 0.99, 0.99, and 2.0 ± 0.6, respectively. The results of ICV were 0.93, 0.99, 0.99, and 7.9 ± 3.8, respectively. The whole process took 1.9 ± 0.1 s. We have established a multimodal and high-performance automatic ventricle segmentation method to achieve efficient and accurate automatic measurement of the ventricular volume of NPH patients. This can help clinicians quickly and accurately understand the situation of NPH patient's ventricles.

Bio-inspired computation for big data fusion, storage, processing, learning and visualization: state of the art and future directions.

This overview gravitates on research achievements that have recently emerged from the confluence between Big Data technologies and bio-inspired computation. A manifold of reasons can be identified for the profitable synergy between these two paradigms, all rooted on the adaptability, intelligence and robustness that biologically inspired principles can provide to technologies aimed to manage, retrieve, fuse and process Big Data efficiently. We delve into this research field by first analyzing in depth the existing literature, with a focus on advances reported in the last few years. This prior literature analysis is complemented by an identification of the new trends and open challenges in Big Data that remain unsolved to date, and that can be effectively addressed by bio-inspired algorithms. As a second contribution, this work elaborates on how bio-inspired algorithms need to be adapted for their use in a Big Data context, in which data fusion becomes crucial as a previous step to allow processing and mining several and potentially heterogeneous data sources. This analysis allows exploring and comparing the scope and efficiency of existing approaches across different problems and domains, with the purpose of identifying new potential applications and research niches. Finally, this survey highlights open issues that remain unsolved to date in this research avenue, alongside a prescription of recommendations for future research.

Unsupervised Anomaly Detection in Stream Data with Online Evolving Spiking Neural Networks.

Unsupervised anomaly discovery in stream data is a research topic with many practical applications. However, in many cases, it is not easy to collect enough training data with labeled anomalies for supervised learning of an anomaly detector in order to deploy it later for identification of real anomalies in streaming data. It is thus important to design anomalies detectors that can correctly detect anomalies without access to labeled training data. Our idea is to adapt the Online evolving Spiking Neural Network (OeSNN) classifier to the anomaly detection task. As a result, we offer an Online evolving Spiking Neural Network for Unsupervised Anomaly Detection algorithm (OeSNN-UAD), which, unlike OeSNN, works in an unsupervised way and does not separate output neurons into disjoint decision classes. OeSNN-UAD uses our proposed new two-step anomaly detection method. Also, we derive new theoretical properties of neuronal model and input layer encoding of OeSNN, which enable more effective and efficient detection of anomalies in our OeSNN-UAD approach. The proposed OeSNN-UAD detector was experimentally compared with state-of-the-art unsupervised and semi-supervised detectors of anomalies in stream data from the Numenta Anomaly Benchmark and Yahoo Anomaly Datasets repositories. Our approach outperforms the other solutions provided in the literature in the case of data streams from the Numenta Anomaly Benchmark repository. Also, in the case of real data files of the Yahoo Anomaly Benchmark repository, OeSNN-UAD outperforms other selected algorithms, whereas in the case of Yahoo Anomaly Benchmark synthetic data files, it provides competitive results to the results recently reported in the literature.

From Data to Actions in Intelligent Transportation Systems: A Prescription of Functional Requirements for Model Actionability.

Advances in Data Science permeate every field of Transportation Science and Engineering, resulting in developments in the transportation sector that are data-driven. Nowadays, Intelligent Transportation Systems (ITS) could be arguably approached as a "story" intensively producing and consuming large amounts of data. A diversity of sensing devices densely spread over the infrastructure, vehicles or the travelers' personal devices act as sources of data flows that are eventually fed into software running on automatic devices, actuators or control systems producing, in turn, complex information flows among users, traffic managers, data analysts, traffic modeling scientists, etc. These information flows provide enormous opportunities to improve model development and decision-making. This work aims to describe how data, coming from diverse ITS sources, can be used to learn and adapt data-driven models for efficiently operating ITS assets, systems and processes; in other words, for data-based models to fully become actionable. Grounded in this described data modeling pipeline for ITS, we define the characteristics, engineering requisites and challenges intrinsic to its three compounding stages, namely, data fusion, adaptive learning and model evaluation. We deliberately generalize model learning to be adaptive, since, in the core of our paper is the firm conviction that most learners will have to adapt to the ever-changing phenomenon scenario underlying the majority of ITS applications. Finally, we provide a prospect of current research lines within Data Science that can bring notable advances to data-based ITS modeling, which will eventually bridge the gap towards the practicality and actionability of such models.

PADL: A Modeling and Deployment Language for Advanced Analytical Services.

In the smart city context, Big Data analytics plays an important role in processing the data collected through IoT devices. The analysis of the information gathered by sensors favors the generation of specific services and systems that not only improve the quality of life of the citizens, but also optimize the city resources. However, the difficulties of implementing this entire process in real scenarios are manifold, including the huge amount and heterogeneity of the devices, their geographical distribution, and the complexity of the necessary IT infrastructures. For this reason, the main contribution of this paper is the PADL description language, which has been specifically tailored to assist in the definition and operationalization phases of the machine learning life cycle. It provides annotations that serve as an abstraction layer from the underlying infrastructure and technologies, hence facilitating the work of data scientists and engineers. Due to its proficiency in the operationalization of distributed pipelines over edge, fog, and cloud layers, it is particularly useful in the complex and heterogeneous environments of smart cities. For this purpose, PADL contains functionalities for the specification of monitoring, notifications, and actuation capabilities. In addition, we provide tools that facilitate its adoption in production environments. Finally, we showcase the usefulness of the language by showing the definition of PADL-compliant analytical pipelines over two uses cases in a smart city context (flood control and waste management), demonstrating that its adoption is simple and beneficial for the definition of information and process flows in such environments.

Robust image classification against adversarial attacks using elastic similarity measures between edge count sequences.

Due to their unprecedented capacity to learn patterns from raw data, deep neural networks have become the de facto modeling choice to address complex machine learning tasks. However, recent works have emphasized the vulnerability of deep neural networks when being fed with intelligently manipulated adversarial data instances tailored to confuse the model. In order to overcome this issue, a major effort has been made to find methods capable of making deep learning models robust against adversarial inputs. This work presents a new perspective for improving the robustness of deep neural networks in image classification. In computer vision scenarios, adversarial images are crafted by manipulating legitimate inputs so that the target classifier is eventually fooled, but the manipulation is not visually distinguishable by an external observer. The reason for the imperceptibility of the attack is that the human visual system fails to detect minor variations in color space, but excels at detecting anomalies in geometric shapes. We capitalize on this fact by extracting color gradient features from input images at multiple sensitivity levels to detect possible manipulations. We resort to a deep neural classifier to predict the category of unseen images, whereas a discrimination model analyzes the extracted color gradient features with time series techniques to determine the legitimacy of input images. The performance of our method is assessed over experiments comprising state-of-the-art techniques for crafting adversarial attacks. Results corroborate the increased robustness of the classifier when using our discrimination module, yielding drastically reduced success rates of adversarial attacks that operate on the whole image rather than on localized regions or around the existing shapes of the image. Future research is outlined towards improving the detection accuracy of the proposed method for more general attack strategies.

Spiking Neural Networks and online learning: An overview and perspectives.

Applications that generate huge amounts of data in the form of fast streams are becoming increasingly prevalent, being therefore necessary to learn in an online manner. These conditions usually impose memory and processing time restrictions, and they often turn into evolving environments where a change may affect the input data distribution. Such a change causes that predictive models trained over these stream data become obsolete and do not adapt suitably to new distributions. Specially in these non-stationary scenarios, there is a pressing need for new algorithms that adapt to these changes as fast as possible, while maintaining good performance scores. Unfortunately, most off-the-shelf classification models need to be retrained if they are used in changing environments, and fail to scale properly. Spiking Neural Networks have revealed themselves as one of the most successful approaches to model the behavior and learning potential of the brain, and exploit them to undertake practical online learning tasks. Besides, some specific flavors of Spiking Neural Networks can overcome the necessity of retraining after a drift occurs. This work intends to merge both fields by serving as a comprehensive overview, motivating further developments that embrace Spiking Neural Networks for online learning scenarios, and being a friendly entry point for non-experts.

Exploiting the stimuli encoding scheme of evolving Spiking Neural Networks for stream learning.

Stream data processing has lately gained momentum with the arrival of new Big Data scenarios and applications dealing with continuously produced information flows. Unfortunately, traditional machine learning algorithms are not prepared to tackle the specific challenges imposed by data stream processing, such as the need for learning incrementally, limited memory and processing time requirements, and adaptation to non-stationary data, among others. To face these paradigms, Spiking Neural Networks have emerged as one of the most promising stream learning techniques, with variants such as Evolving Spiking Neural Networks capable of efficiently addressing many of these challenges. Interestingly, these networks resort to a particular population encoding scheme - Gaussian Receptive Fields - to transform the incoming stimuli into temporal spikes. The study presented in this manuscript sheds light on the predictive potential of this encoding scheme, focusing on how it can be applied as a computationally lightweight, model-agnostic preprocessing step for data stream learning. We provide informed intuition to unveil under which circumstances the aforementioned population encoding method yields effective prediction gains in data stream classification with respect to the case where no preprocessing is performed. Results obtained for a variety of stream learning models and both synthetic and real stream datasets are discussed to empirically buttress the capability of Gaussian Receptive Fields to boost the predictive performance of stream learning methods, spanning further research towards extrapolating our findings to other machine learning problems.

ECG-based pulse detection during cardiac arrest using random forest classifier.

Sudden cardiac arrest is one of the leading causes of death in the industrialized world. Pulse detection is essential for the recognition of the arrest and the recognition of return of spontaneous circulation during therapy, and it is therefore crucial for the survival of the patient. This paper introduces the first method based exclusively on the ECG for the automatic detection of pulse during cardiopulmonary resuscitation. Random forest classifier is used to efficiently combine up to nine features from the time, frequency, slope, and regularity analysis of the ECG. Data from 191 cardiac arrest patients was used, and 1177 ECG segments were processed, 796 with pulse and 381 without pulse. A leave-one-patient out cross validation approach was used to train and test the algorithm. The statistical distributions of sensitivity (SE) and specificity (SP) for pulse detection were estimated using 500 patient-wise bootstrap partitions. The mean (std) SE/SP for nine-feature classifier was 88.4 (1.8) %/89.7 (1.4) %, respectively. The designed algorithm only requires 4-s-long ECG segments and could be integrated in any commercial automated external defibrillator. The method permits to detect the presence of pulse accurately, minimizing interruptions in cardiopulmonary resuscitation therapy, and could contribute to improve survival from cardiac arrest.

Evolving Spiking Neural Networks for online learning over drifting data streams.

Nowadays huge volumes of data are produced in the form of fast streams, which are further affected by non-stationary phenomena. The resulting lack of stationarity in the distribution of the produced data calls for efficient and scalable algorithms for online analysis capable of adapting to such changes (concept drift). The online learning field has lately turned its focus on this challenging scenario, by designing incremental learning algorithms that avoid becoming obsolete after a concept drift occurs. Despite the noted activity in the literature, a need for new efficient and scalable algorithms that adapt to the drift still prevails as a research topic deserving further effort. Surprisingly, Spiking Neural Networks, one of the major exponents of the third generation of artificial neural networks, have not been thoroughly studied as an online learning approach, even though they are naturally suited to easily and quickly adapting to changing environments. This work covers this research gap by adapting Spiking Neural Networks to meet the processing requirements that online learning scenarios impose. In particular the work focuses on limiting the size of the neuron repository and making the most of this limited size by resorting to data reduction techniques. Experiments with synthetic and real data sets are discussed, leading to the empirically validated assertion that, by virtue of a tailored exploitation of the neuron repository, Spiking Neural Networks adapt better to drifts, obtaining higher accuracy scores than naive versions of Spiking Neural Networks for online learning environments.

Underwater Robot Task Planning Using Multi-Objective Meta-Heuristics.

Robotics deployed in the underwater medium are subject to stringent operational conditions that impose a high degree of criticality on the allocation of resources and the schedule of operations in mission planning. In this context the so-called cost of a mission must be considered as an additional criterion when designing optimal task schedules within the mission at hand. Such a cost can be conceived as the impact of the mission on the robotic resources themselves, which range from the consumption of battery to other negative effects such as mechanic erosion. This manuscript focuses on this issue by devising three heuristic solvers aimed at efficiently scheduling tasks in robotic swarms, which collaborate together to accomplish a mission, and by presenting experimental results obtained over realistic scenarios in the underwater environment. The heuristic techniques resort to a Random-Keys encoding strategy to represent the allocation of robots to tasks and the relative execution order of such tasks within the schedule of certain robots. The obtained results reveal interesting differences in terms of Pareto optimality and spread between the algorithms considered in the benchmark, which are insightful for the selection of a proper task scheduler in real underwater campaigns.