Analyzing long text data such as customer call transcripts is a cost-intensive and tedious task. Machine learning methods, namely Transformers, are leveraged to model agent-customer interactions. Unfortunately, Transformers adhere to fixed-length architectures and their self-attention mechanism scales quadratically with input length. Such limitations make it challenging to leverage traditional Transformers for long sequence tasks, such as conversational understanding, especially in real-time use cases. In this paper we explore and evaluate recently proposed efficient Transformer variants (e.g. Performer, Reformer) and a CNN-based architecture for real-time and near real-time long conversational understanding tasks. We show that CNN-based models are dynamic, ~2.6x faster to train, ~80% faster inference and ~72% more memory efficient compared to Transformers on average. Additionally, we evaluate the CNN model using the Long Range Arena benchmark to demonstrate competitiveness in general long document analysis.

Diabetic Retinopathy DR is a severe complication of diabetes. Damaged or abnormal blood vessels can cause loss of vision. The need for massive screening of a large population of diabetic patients has generated an interest in a computer-aided fully automatic diagnosis of DR. In the realm of Deep learning frameworks, particularly convolutional neural networks CNNs, have shown great interest and promise in detecting DR by analyzing retinal images. However, several challenges have been faced in the application of deep learning in this domain. High-quality, annotated datasets are scarce, and the variations in image quality and class imbalances pose significant hurdles in developing a dependable model. In this paper, we demonstrate the proficiency of two Convolutional Neural Networks CNNs based models, UNET and Stacked UNET utilizing the APTOS Asia Pacific Tele-Ophthalmology Society Dataset. This system achieves an accuracy of 92.81% for the UNET and 93.32% for the stacked UNET architecture. The architecture classifies the images into five categories ranging from 0 to 4, where 0 is no DR and 4 is proliferative DR.

Speech emotion recognition (SER) classifies human emotions in speech with a computer model. Recently, performance in SER has steadily increased as deep learning techniques have adapted. However, unlike many domains that use speech data, data for training in the SER model is insufficient. This causes overfitting of training of the neural network, resulting in performance degradation. In fact, successful emotion recognition requires an effective preprocessing method and a model structure that efficiently uses the number of weight parameters. In this study, we propose using eight dataset versions with different frequency-time resolutions to search for an effective emotional speech preprocessing method. We propose a 6-layer convolutional neural network (CNN) model with efficient channel attention (ECA) to pursue an efficient model structure. In particular, the well-positioned ECA blocks can improve channel feature representation with only a few parameters. With the interactive emotional dyadic motion capture (IEMOCAP) dataset, increasing the frequency resolution in preprocessing emotional speech can improve emotion recognition performance. Also, ECA after the deep convolution layer can effectively increase channel feature representation. Consequently, the best result (79.37UA 79.68WA) can be obtained, exceeding the performance of previous SER models. Furthermore, to compensate for the lack of emotional speech data, we experiment with multiple preprocessing data methods that augment trainable data preprocessed with all different settings from one sample. In the experiment, we can achieve the highest result (80.28UA 80.46WA).

Location trajectories provide valuable insights for applications from urban planning to pandemic control. However, mobility data can also reveal sensitive information about individuals, such as political opinions, religious beliefs, or sexual orientations. Existing privacy-preserving approaches for publishing this data face a significant utility-privacy trade-off. Releasing synthetic trajectory data generated through deep learning offers a promising solution. Due to the trajectories' sequential nature, most existing models are based on recurrent neural networks (RNNs). However, research in generative adversarial networks (GANs) largely employs convolutional neural networks (CNNs) for image generation. This discrepancy raises the question of whether advances in computer vision can be applied to trajectory generation. In this work, we introduce a Reversible Trajectory-to-CNN Transformation (RTCT) that adapts trajectories into a format suitable for CNN-based models. We integrated this transformation with the well-known DCGAN in a proof-of-concept (PoC) and evaluated its performance against an RNN-based trajectory GAN using four metrics across two datasets. The PoC was superior in capturing spatial distributions compared to the RNN model but had difficulty replicating sequential and temporal properties. Although the PoC's utility is not sufficient for practical applications, the results demonstrate the transformation's potential to facilitate the use of CNNs for trajectory generation, opening up avenues for future research. To support continued research, all source code has been made available under an open-source license.

Tabular data have been extensively used in different knowledge domains. Convolutional neural networks (CNNs) have been successfully used in many applications where important information about data is embedded in the order of features (images), outperforming predictive results of traditional models. Recently, several researchers have proposed transforming tabular data into images to leverage the potential of CNNs and obtain high results in predictive tasks such as classification and regression. In this paper, we present a novel and effective approach for transforming tabular data into images, addressing the inherent limitations associated with low-dimensional and mixed-type datasets. Our method, named Low Mixed-Image Generator for Tabular Data (LM-IGTD), integrates a stochastic feature generation process and a modified version of the IGTD. We introduce an automatic and interpretable end-to-end pipeline, enabling the creation of images from tabular data. A mapping between original features and the generated images is established, and post hoc interpretability methods are employed to identify crucial areas of these images, enhancing interpretability for predictive tasks. An extensive evaluation of the tabular-to-image generation approach proposed on 12 low-dimensional and mixed-type datasets, including binary and multi-class classification scenarios. In particular, our method outperformed all traditional ML models trained on tabular data in five out of twelve datasets when using images generated with LM-IGTD and CNN. In the remaining datasets, LM-IGTD images and CNN consistently surpassed three out of four traditional ML models, achieving similar results to the fourth model.

Monocular depth estimation has been widely studied, and significant improvements in performance have been recently reported. However, most previous works are evaluated on a few benchmark datasets, such as KITTI datasets, and none of the works provide an in-depth analysis of the generalization performance of monocular depth estimation. In this paper, we deeply investigate the various backbone networks (e.g.CNN and Transformer models) toward the generalization of monocular depth estimation. First, we evaluate state-of-the-art models on both in-distribution and out-of-distribution datasets, which have never been seen during network training. Then, we investigate the internal properties of the representations from the intermediate layers of CNN-/Transformer-based models using synthetic texture-shifted datasets. Through extensive experiments, we observe that the Transformers exhibit a strong shape-bias rather than CNNs, which have a strong texture-bias. We also discover that texture-biased models exhibit worse generalization performance for monocular depth estimation than shape-biased models. We demonstrate that similar aspects are observed in real-world driving datasets captured under diverse environments. Lastly, we conduct a dense ablation study with various backbone networks which are utilized in modern strategies. The experiments demonstrate that the intrinsic locality of the CNNs and the self-attention of the Transformers induce texture-bias and shape-bias, respectively.

In recent days, Deep Learning (DL) techniques have become an emerging transformation in the field of machine learning, artificial intelligence, computer vision, and so on. Subsequently, researchers and industries have been highly endorsed in the medical field, predicting and controlling diverse diseases at specific intervals. Liver tumor prediction is a vital chore in analyzing and treating liver diseases. This paper proposes a novel approach for predicting liver tumors using Convolutional Neural Networks (CNN) and a depth-based variant search algorithm with advanced attention mechanisms (CNN-DS-AM). The proposed work aims to improve accuracy and robustness in diagnosing and treating liver diseases. The anticipated model is assessed on a Computed Tomography (CT) scan dataset containing both benign and malignant liver tumors. The proposed approach achieved high accuracy in predicting liver tumors, outperforming other state-of-the-art methods. Additionally, advanced attention mechanisms were incorporated into the CNN model to enable the identification and highlighting of regions of the CT scans most relevant to predicting liver tumors. The results suggest that incorporating attention mechanisms and a depth-based variant search algorithm into the CNN model is a promising approach for improving the accuracy and robustness of liver tumor prediction. It can assist radiologists in their diagnosis and treatment planning. The proposed system achieved a high accuracy of 95.5% in predicting liver tumors, outperforming other state-of-the-art methods.

This work leverages the recent advancements of deep learning in image processing to find optimal locations that present the important characteristics of a field. The data for training are collected at different fields in local farms with five features: aspect, flow accumulation, slope, NDVI (normalized difference vegetation index), and yield. The soil sampling dataset is challenging because the ground truth is highly imbalanced binary images. Therefore, we approached the problem with two methods, the first approach involves utilizing a state-of-the-art model with the convolutional neural network (CNN) backbone, while the second is to innovate a deep-learning design grounded in the concepts of transformer and self-attention. Our framework is constructed with an encoder-decoder architecture with the self-attention mechanism as the backbone. In the encoder, the self-attention mechanism is the key feature extractor, which produces feature maps. In the decoder, we introduce atrous convolution networks to concatenate, fuse the extracted features, and then export the optimal locations for soil sampling. Currently, the model has achieved impressive results on the testing dataset, with a mean accuracy of 99.52%, a mean Intersection over Union (IoU) of 57.35%, and a mean Dice Coefficient of 71.47%, while the performance metrics of the state-of-the-art CNN-based model are 66.08%, 3.85%, and 1.98%, respectively. This indicates that our proposed model outperforms the CNN-based method on the soil-sampling dataset. To the best of our knowledge, our work is the first to provide a soil-sampling dataset with multiple attributes and leverage deep learning techniques to enable the automatic selection of soil-sampling sites. This work lays a foundation for novel applications of data science and machine-learning technologies to solve other emerging agricultural problems.

In recent years, the traditional feature engineering process for training machine learning models is being automated by the feature extraction layers integrated in deep learning architectures. In wireless networks, many studies were conducted in automatic learning of feature representations for domain-related challenges. However, most of the existing works assume some supervision along the learning process by using labels to optimize the model. In this paper, we investigate an approach to learning feature representations for wireless transmission clustering in a completely unsupervised manner, i.e. requiring no labels in the process. We propose a model based on convolutional neural networks that automatically learns a reduced dimensionality representation of the input data with 99.3% less components compared to a baseline principal component analysis (PCA). We show that the automatic representation learning is able to extract fine-grained clusters containing the shapes of the wireless transmission bursts, while the baseline enables only general separability of the data based on the background noise.

This report presents the technical details of our submission to the 2023 Epic-Kitchen EPIC-SOUNDS Audio-Based Interaction Recognition Challenge. The task is to learn the mapping from audio samples to their corresponding action labels. To achieve this goal, we propose a simple yet effective single-stream CNN-based architecture called AudioInceptionNeXt that operates on the time-frequency log-mel-spectrogram of the audio samples. Motivated by the design of the InceptionNeXt, we propose parallel multi-scale depthwise separable convolutional kernels in the AudioInceptionNeXt block, which enable the model to learn the time and frequency information more effectively. The large-scale separable kernels capture the long duration of activities and the global frequency semantic information, while the small-scale separable kernels capture the short duration of activities and local details of frequency information. Our approach achieved 55.43% of top-1 accuracy on the challenge test set, ranked as 1st on the public leaderboard. Codes are available anonymously at https://github.com/StevenLauHKHK/AudioInceptionNeXt.git.