Autonomous vehicles (AVs) heavily rely on LiDAR perception for environment understanding and navigation. LiDAR intensity provides valuable information about the reflected laser signals and plays a crucial role in enhancing the perception capabilities of AVs. However, accurately simulating LiDAR intensity remains a challenge due to the unavailability of material properties of the objects in the environment, and complex interactions between the laser beam and the environment. The proposed method aims to improve the accuracy of intensity simulation by incorporating physics-based modalities within the deep learning framework. One of the key entities that captures the interaction between the laser beam and the objects is the angle of incidence. In this work we demonstrate that the addition of the LiDAR incidence angle as a separate input to the deep neural networks significantly enhances the results. We present a comparative study between two prominent deep learning architectures: U-NET a Convolutional Neural Network (CNN), and Pix2Pix a Generative Adversarial Network (GAN). We implemented these two architectures for the intensity prediction task and used SemanticKITTI and VoxelScape datasets for experiments. The comparative analysis reveals that both architectures benefit from the incidence angle as an additional input. Moreover, the Pix2Pix architecture outperforms U-NET, especially when the incidence angle is incorporated.
Emotion decoding using Electroencephalography (EEG)-based affective brain-computer interfaces (aBCIs) plays a crucial role in affective computing but is limited by challenges such as EEG's non-stationarity, individual variability, and the high cost of large labeled datasets. While deep learning methods are effective, they require extensive computational resources and large data volumes, limiting their practical application. To overcome these issues, we propose Manifold-based Domain Adaptation with Dynamic Distribution (M3D), a lightweight, non-deep transfer learning framework. M3D consists of four key modules: manifold feature transformation, dynamic distribution alignment, classifier learning, and ensemble learning. The data is mapped to an optimal Grassmann manifold space, enabling dynamic alignment of source and target domains. This alignment is designed to prioritize both marginal and conditional distributions, improving adaptation efficiency across diverse datasets. In classifier learning, the principle of structural risk minimization is applied to build robust classification models. Additionally, dynamic distribution alignment iteratively refines the classifier. The ensemble learning module aggregates classifiers from different optimization stages to leverage diversity and enhance prediction accuracy. M3D is evaluated on two EEG emotion recognition datasets using two validation protocols (cross-subject single-session and cross-subject cross-session) and a clinical EEG dataset for Major Depressive Disorder (MDD). Experimental results show that M3D outperforms traditional non-deep learning methods with a 4.47% average improvement and achieves deep learning-level performance with reduced data and computational requirements, demonstrating its potential for real-world aBCI applications.
Many data distributions in the real world are hardly uniform. Instead, skewed and long-tailed distributions of various kinds are commonly observed. This poses an interesting problem for machine learning, where most algorithms assume or work well with uniformly distributed data. The problem is further exacerbated by current state-of-the-art deep learning models requiring large volumes of training data. As such, learning from imbalanced data remains a challenging research problem and a problem that must be solved as we move towards more real-world applications of deep learning. In the context of class imbalance, state-of-the-art (SOTA) accuracies on standard benchmark datasets for classification typically fall less than 75%, even for less challenging datasets such as CIFAR100. Nonetheless, there has been progress in this niche area of deep learning. To this end, in this survey, we provide a taxonomy of various methods proposed for addressing the problem of long-tail classification, focusing on works that happened in the last few years under a single mathematical framework. We also discuss standard performance metrics, convergence studies, feature distribution and classifier analysis. We also provide a quantitative comparison of the performance of different SOTA methods and conclude the survey by discussing the remaining challenges and future research direction.
Ontologies provide formal representation of knowledge shared within Semantic Web applications. Ontology learning involves the construction of ontologies from a given corpus. In the past years, ontology learning has traversed through shallow learning and deep learning methodologies, each offering distinct advantages and limitations in the quest for knowledge extraction and representation. A new trend of these approaches is relying on large language models (LLMs) to enhance ontology learning. This paper gives a review in approaches and challenges of ontology learning. It analyzes the methodologies and limitations of shallow-learning-based and deep-learning-based techniques for ontology learning, and provides comprehensive knowledge for the frontier work of using LLMs to enhance ontology learning. In addition, it proposes several noteworthy future directions for further exploration into the integration of LLMs with ontology learning tasks.
The Kernel-Free Boundary Integral (KFBI) method presents an iterative solution to boundary integral equations arising from elliptic partial differential equations (PDEs). This method effectively addresses elliptic PDEs on irregular domains, including the modified Helmholtz, Stokes, and elasticity equations. The rapid evolution of neural networks and deep learning has invigorated the exploration of numerical PDEs. An increasing interest is observed in deep learning approaches that seamlessly integrate mathematical principles for investigating numerical PDEs. We propose a hybrid KFBI method, integrating the foundational principles of the KFBI method with the capabilities of deep learning. This approach, within the framework of the boundary integral method, designs a network to approximate the solution operator for the corresponding integral equations by mapping the parameters, inhomogeneous terms and boundary information of PDEs to the boundary density functions, which can be regarded as the solution of the integral equations. The models are trained using data generated by the Cartesian grid-based KFBI algorithm, exhibiting robust generalization capabilities. It accurately predicts density functions across diverse boundary conditions and parameters within the same class of equations. Experimental results demonstrate that the trained model can directly infer the boundary density function with satisfactory precision, obviating the need for iterative steps in solving boundary integral equations. Furthermore, applying the inference results of the model as initial values for iterations is also reasonable; this approach can retain the inherent second-order accuracy of the KFBI method while accelerating the traditional KFBI approach by reducing about 50% iterations.
Recent deep learning models such as ChatGPT utilizing the back-propagation algorithm have exhibited remarkable performance. However, the disparity between the biological brain processes and the back-propagation algorithm has been noted. The Forward-Forward algorithm, which trains deep learning models solely through the forward pass, has emerged to address this. Although the Forward-Forward algorithm cannot replace back-propagation due to limitations such as having to use special input and loss functions, it has the potential to be useful in special situations where back-propagation is difficult to use. To work around this limitation and verify usability, we propose an Unsupervised Forward-Forward algorithm. Using an unsupervised learning model enables training with usual loss functions and inputs without restriction. Through this approach, we lead to stable learning and enable versatile utilization across various datasets and tasks. From a usability perspective, given the characteristics of the Forward-Forward algorithm and the advantages of the proposed method, we anticipate its practical application even in scenarios such as federated learning, where deep learning layers need to be trained separately in physically distributed environments.
Time series (TS) data have consistently been in short supply, yet their demand remains high for training systems in prediction, modeling, classification, and various other applications. Synthesis can serve to expand the sample population, yet it is crucial to maintain the statistical characteristics between the synthesized and the original TS : this ensures consistent sampling of data for both training and testing purposes. However the time domain features of the data may not be maintained. This motivates for our work, the objective which is to preserve the following features in a synthesized TS: its fundamental statistical characteristics and important time domain features like its general shape and prominent transients. In a novel way, we first isolate important TS features into various components using a spectrogram and singular spectrum analysis. The residual signal is then randomized in a way that preserves its statistical properties. These components are then recombined for the synthetic time series. Using accelerometer data in a clinical setting, we use statistical and shape measures to compare our method to others. We show it has higher fidelity to the original signal features, has good diversity and performs better data classification in a deep learning application.
Deep neural networks (DNNs) are powerful tools for approximating the distribution of complex data. It is known that data passing through a trained DNN classifier undergoes a series of geometric and topological simplifications. While some progress has been made toward understanding these transformations in neural networks with smooth activation functions, an understanding in the more general setting of non-smooth activation functions, such as the rectified linear unit (ReLU), which tend to perform better, is required. Here we propose that the geometric transformations performed by DNNs during classification tasks have parallels to those expected under Hamilton's Ricci flow - a tool from differential geometry that evolves a manifold by smoothing its curvature, in order to identify its topology. To illustrate this idea, we present a computational framework to quantify the geometric changes that occur as data passes through successive layers of a DNN, and use this framework to motivate a notion of `global Ricci network flow' that can be used to assess a DNN's ability to disentangle complex data geometries to solve classification problems. By training more than $1,500$ DNN classifiers of different widths and depths on synthetic and real-world data, we show that the strength of global Ricci network flow-like behaviour correlates with accuracy for well-trained DNNs, independently of depth, width and data set. Our findings motivate the use of tools from differential and discrete geometry to the problem of explainability in deep learning.
Evolutionary Algorithms and Generative Deep Learning have been two of the most powerful tools for sound generation tasks. However, they have limitations: Evolutionary Algorithms require complicated designs, posing challenges in control and achieving realistic sound generation. Generative Deep Learning models often copy from the dataset and lack creativity. In this paper, we propose LVNS-RAVE, a method to combine Evolutionary Algorithms and Generative Deep Learning to produce realistic and novel sounds. We use the RAVE model as the sound generator and the VGGish model as a novelty evaluator in the Latent Vector Novelty Search (LVNS) algorithm. The reported experiments show that the method can successfully generate diversified, novel audio samples under different mutation setups using different pre-trained RAVE models. The characteristics of the generation process can be easily controlled with the mutation parameters. The proposed algorithm can be a creative tool for sound artists and musicians.
In this work, we introduce a novel deep learning-based approach to text-in-image watermarking, a method that embeds and extracts textual information within images to enhance data security and integrity. Leveraging the capabilities of deep learning, specifically through the use of Transformer-based architectures for text processing and Vision Transformers for image feature extraction, our method sets new benchmarks in the domain. The proposed method represents the first application of deep learning in text-in-image watermarking that improves adaptivity, allowing the model to intelligently adjust to specific image characteristics and emerging threats. Through testing and evaluation, our method has demonstrated superior robustness compared to traditional watermarking techniques, achieving enhanced imperceptibility that ensures the watermark remains undetectable across various image contents.
Point cloud registration involves determining a rigid transformation to align a source point cloud with a target point cloud. This alignment is fundamental in applications such as autonomous driving, robotics, and medical imaging, where precise spatial correspondence is essential. Deep learning has greatly advanced point cloud registration by providing robust and efficient methods that address the limitations of traditional approaches, including sensitivity to noise, outliers, and initialization. However, a well-constructed taxonomy for these methods is still lacking, making it difficult to systematically classify and compare the various approaches. In this paper, we present a comprehensive survey and taxonomy on deep learning-based point cloud registration (DL-PCR). We begin with a formal description of the point cloud registration problem, followed by an overview of the datasets, evaluation metrics, and loss functions commonly used in DL-PCR. Next, we categorize existing DL-PCR methods into supervised and unsupervised approaches, as they focus on significantly different key aspects. For supervised DL-PCR methods, we organize the discussion based on key aspects, including the registration procedure, optimization strategy, learning paradigm, network enhancement, and integration with traditional methods; For unsupervised DL-PCR methods, we classify them into correspondence-based and correspondence-free approaches, depending on whether they require explicit identification of point-to-point correspondences. To facilitate a more comprehensive and fair comparison, we conduct quantitative evaluations of all recent state-of-the-art approaches, using a unified training setting and consistent data partitioning strategy. Lastly, we highlight the open challenges and discuss potential directions for future study. A comprehensive collection is available at https://github.com/yxzhang15/PCR.
Nasal Cytology is a new and efficient clinical technique to diagnose rhinitis and allergies that is not much widespread due to the time-consuming nature of cell counting; that is why AI-aided counting could be a turning point for the diffusion of this technique. In this article we present the first dataset of rhino-cytological field images: the NCD (Nasal Cytology Dataset), aimed to train and deploy Object Detection models to support physicians and biologists during clinical practice. The real distribution of the cytotypes, populating the nasal mucosa has been replicated, sampling images from slides of clinical patients, and manually annotating each cell found on them. The correspondent object detection task presents non'trivial issues associated with the strong class imbalancement, involving the rarest cell types. This work contributes to some of open challenges by presenting a novel machine learning-based approach to aid the automated detection and classification of nasal mucosa cells: the DETR and YOLO models shown good performance in detecting cells and classifying them correctly, revealing great potential to accelerate the work of rhinology experts.
This study explores the application of deep learning technologies in software development processes, particularly in automating code reviews, error prediction, and test generation to enhance code quality and development efficiency. Through a series of empirical studies, experimental groups using deep learning tools and control groups using traditional methods were compared in terms of code error rates and project completion times. The results demonstrated significant improvements in the experimental group, validating the effectiveness of deep learning technologies. The research also discusses potential optimization points, methodologies, and technical challenges of deep learning in software development, as well as how to integrate these technologies into existing software development workflows.
This study introduces an innovative approach to classifying various types of Persian rice using image-based deep learning techniques, highlighting the practical application of everyday technology in food categorization. Recognizing the diversity of Persian rice and its culinary significance, we leveraged the capabilities of convolutional neural networks (CNNs), specifically by fine-tuning a ResNet model for accurate identification of different rice varieties and employing a U-Net architecture for precise segmentation of rice grains in bulk images. This dual-methodology framework allows for both individual grain classification and comprehensive analysis of bulk rice samples, addressing two crucial aspects of rice quality assessment. Utilizing images captured with consumer-grade cell phones reflects a realistic scenario in which individuals can leverage this technology for assistance with grocery shopping and meal preparation. The dataset, comprising various rice types photographed under natural conditions without professional lighting or equipment, presents a challenging yet practical classification problem. Our findings demonstrate the feasibility of using non-professional images for food classification and the potential of deep learning models, like ResNet and U-Net, to adapt to the nuances of everyday objects and textures. This study contributes to the field by providing insights into the applicability of image-based deep learning in daily life, specifically for enhancing consumer experiences and knowledge in food selection. Furthermore, it opens avenues for extending this approach to other food categories and practical applications, emphasizing the role of accessible technology in bridging the gap between sophisticated computational methods and everyday tasks.
The rapid advancement of machine learning techniques has led to their widespread application in various domains including water resources. However, snowmelt modeling remains an area that has not been extensively explored. In this study, we propose a state-of-the-art (SOTA) deep learning sequential model, leveraging the Temporal Convolutional Network (TCN), for snowmelt-driven discharge modeling in the Himalayan basin of the Hindu Kush Himalayan Region. To evaluate the performance of our proposed model, we conducted a comparative analysis with other popular models including Support Vector Regression (SVR), Long Short Term Memory (LSTM), and Transformer. Furthermore, Nested cross-validation (CV) is used with five outer folds and three inner folds, and hyper-parameter tuning is performed on the inner folds. To evaluate the performance of the model mean absolute error (MAE), root mean square error (RMSE), R square ($R^{2}$), Kling-Gupta Efficiency (KGE), and Nash-Sutcliffe Efficiency (NSE) are computed for each outer fold. The average metrics revealed that TCN outperformed the other models, with an average MAE of 0.011, RMSE of 0.023, $R^{2}$ of 0.991, KGE of 0.992, and NSE of 0.991. The findings of this study demonstrate the effectiveness of the deep learning model as compared to traditional machine learning approaches for snowmelt-driven streamflow forecasting. Moreover, the superior performance of TCN highlights its potential as a promising deep learning model for similar hydrological applications.
This paper introduces the Token Space framework, a novel mathematical construct designed to enhance the interpretability and effectiveness of deep learning models through the application of category theory. By establishing a categorical structure at the Token level, we provide a new lens through which AI computations can be understood, emphasizing the relationships between tokens, such as grouping, order, and parameter types. We explore the foundational methodologies of the Token Space, detailing its construction, the role of construction operators and initial categories, and its application in analyzing deep learning models, specifically focusing on attention mechanisms and Transformer architectures. The integration of category theory into AI research offers a unified framework to describe and analyze computational structures, enabling new research paths and development possibilities. Our investigation reveals that the Token Space framework not only facilitates a deeper theoretical understanding of deep learning models but also opens avenues for the design of more efficient, interpretable, and innovative models, illustrating the significant role of category theory in advancing computational models.
Deep learning has been widely applied to solve partial differential equations (PDEs) in computational fluid dynamics. Recent research proposed a PDE correction framework that leverages deep learning to correct the solution obtained by a PDE solver on a coarse mesh. However, end-to-end training of such a PDE correction model over both solver-dependent parameters such as mesh parameters and neural network parameters requires the PDE solver to support automatic differentiation through the iterative numerical process. Such a feature is not readily available in many existing solvers. In this study, we explore the feasibility of end-to-end training of a hybrid model with a black-box PDE solver and a deep learning model for fluid flow prediction. Specifically, we investigate a hybrid model that integrates a black-box PDE solver into a differentiable deep graph neural network. To train this model, we use a zeroth-order gradient estimator to differentiate the PDE solver via forward propagation. Although experiments show that the proposed approach based on zeroth-order gradient estimation underperforms the baseline that computes exact derivatives using automatic differentiation, our proposed method outperforms the baseline trained with a frozen input mesh to the solver. Moreover, with a simple warm-start on the neural network parameters, we show that models trained by these zeroth-order algorithms achieve an accelerated convergence and improved generalization performance.
Knowledge of tree species distribution is fundamental to managing forests. New deep learning approaches promise significant accuracy gains for forest mapping, and are becoming a critical tool for mapping multiple tree species at scale. To advance the field, deep learning researchers need large benchmark datasets with high-quality annotations. To this end, we present the PureForest dataset: a large-scale, open, multimodal dataset designed for tree species classification from both Aerial Lidar Scanning (ALS) point clouds and Very High Resolution (VHR) aerial images. Most current public Lidar datasets for tree species classification have low diversity as they only span a small area of a few dozen annotated hectares at most. In contrast, PureForest has 18 tree species grouped into 13 semantic classes, and spans 339 km$^2$ across 449 distinct monospecific forests, and is to date the largest and most comprehensive Lidar dataset for the identification of tree species. By making PureForest publicly available, we hope to provide a challenging benchmark dataset to support the development of deep learning approaches for tree species identification from Lidar and/or aerial imagery. In this data paper, we describe the annotation workflow, the dataset, the recommended evaluation methodology, and establish a baseline performance from both 3D and 2D modalities.
The goal of temporal image forensic is to approximate the age of a digital image relative to images from the same device. Usually, this is based on traces left during the image acquisition pipeline. For example, several methods exist that exploit the presence of in-field sensor defects for this purpose. In addition to these 'classical' methods, there is also an approach in which a Convolutional Neural Network (CNN) is trained to approximate the image age. One advantage of a CNN is that it independently learns the age features used. This would make it possible to exploit other (different) age traces in addition to the known ones (i.e., in-field sensor defects). In a previous work, we have shown that the presence of strong in-field sensor defects is irrelevant for a CNN to predict the age class. Based on this observation, the question arises how device (in)dependent the learned features are. In this work, we empirically asses this by training a network on images from a single device and then apply the trained model to images from different devices. This evaluation is performed on 14 different devices, including 10 devices from the publicly available 'Northumbria Temporal Image Forensics' database. These 10 different devices are based on five different device pairs (i.e., with the identical camera model).
Endotracheal intubation (ETI) is an emergency procedure performed in civilian and combat casualty care settings to establish an airway. Objective and automated assessment of ETI skills is essential for the training and certification of healthcare providers. However, the current approach is based on manual feedback by an expert, which is subjective, time- and resource-intensive, and is prone to poor inter-rater reliability and halo effects. This work proposes a framework to evaluate ETI skills using single and multi-view videos. The framework consists of two stages. First, a 2D convolutional autoencoder (AE) and a pre-trained self-supervision network extract features from videos. Second, a 1D convolutional enhanced with a cross-view attention module takes the features from the AE as input and outputs predictions for skill evaluation. The ETI datasets were collected in two phases. In the first phase, ETI is performed by two subject cohorts: Experts and Novices. In the second phase, novice subjects perform ETI under time pressure, and the outcome is either Successful or Unsuccessful. A third dataset of videos from a single head-mounted camera for Experts and Novices is also analyzed. The study achieved an accuracy of 100% in identifying Expert/Novice trials in the initial phase. In the second phase, the model showed 85% accuracy in classifying Successful/Unsuccessful procedures. Using head-mounted cameras alone, the model showed a 96% accuracy on Expert and Novice classification while maintaining an accuracy of 85% on classifying successful and unsuccessful. In addition, GradCAMs are presented to explain the differences between Expert and Novice behavior and Successful and Unsuccessful trials. The approach offers a reliable and objective method for automated assessment of ETI skills.