Abstract Tuberculosis and COVID-19 diseases are both lung-infected diseases. While tuberculosis is a bacterial infection, COVID-19 is a virus infection. Both diseases are deadly but can be treated if detected early. Several researchers have employed the analysis of lung CT scans in the diagnosis and detection of both diseases. In this paper, we address the segmentation of tuberculosis and COVID-19-infected lung areas and the severity assessment of the diseases. DAvoU-Net, a 3D-Unet segmentation network, was first used to segment the affected areas of the lung CT scans. Afterwards, a 3D CNN model was employed to extract the spatial image features from tuberculosis and COVID-19 datasets. The extracted spatial features from the 3D CNN were fused with sequential features extracted by a Bi-LSTM model. An improved weighted average fusion method merged the spatial and sequential features from the 3D-CNN and Bi-LSTM models. The comparative performance of the novel improved weighted average fusion method with previously used fusion methods shows that it outperformed the previously used fusion methods. It generated an overall classification accuracy of 94.5% and 97.2% on tuberculosis and COVID-19 datasets, respectively.

Neural Image Compression (NIC) has achieved superior compression performance by modeling images as implicit feature representations, yet its practical deployment is severely hindered by computational overhead. Recently, GaussianImage was proposed as a computationally efficient explicit image representation paradigm, which renders images from 2D Gaussians. However, it suffers from inferior compression performance relative to mainstream NIC frameworks, mainly due to low compressibility and representation capability of explicit Gaussian parameters. To this end, we propose Pixel-Aligned Generalized 2D Splatting (PA-G2DS) as a computation-efficient and compression-friendly image representation format. Specifically, we deploy a learnable rendering function with implicit coefficients to enhance the reconstructed image quality and improve the compression ratio over explicit Gaussian coefficients. Incorporating the proposed PA-G2DS as a computationally efficient decoder, we further develop a suite of image codecs optimized for either compression ratios or flexible deployment scenarios. Experiments prove that the proposed codecs could achieve 30ms compression latency and millisecond-level decompression latency, reducing the performance and efficiency gap between implicit and explicit image representation. Furthermore, the proposed codec opens potential applications for NIC such as JPEG-like sequential decompression and random-access during decompression.

While deep neural networks possess the capability to perform semantic segmentation, producing a single deterministic output limits reliability in safety-critical applications, caused by uncertainty and annotation variability. To address this, stochastic segmentation models using Conditional Variational Autoencoders (CVAE), Bayesian networks, and diffusion have been explored. However, existing approaches suffer from limited latent expressiveness and interpretability. Furthermore, our experiments showed that models like Probabilistic U-Net rely excessively on high latent variance, leading to posterior collapse. This work propose a novel framework by integrating Gaussian Mixture Model (GMM) with Normalizing Flow (NF) in CVAE for stochastic segmentation. GMM structures the latent space into meaningful semantic clusters, while NF captures feature deformations with quantified uncertainty. Our method stabilizes latent distributions through constrained variance and mean ranges. Experiments on LIDC, Crack500, and Cityscapes datasets show that our approach outperformed state-of-the-art in curvilinear structure and medical image segmentation.

The advent of high-throughput sequencing technologies, such as DNA microarray and DNA sequencing, has enabled effective analysis of cancer subtypes and targeted treatment. Furthermore, numerous studies have highlighted the capability of graph neural networks (GNN) to model complex biological systems and capture non-linear interactions in high-throughput data. GNN has proven to be useful in leveraging multiple types of omics data, including prior biological knowledge from various sources, such as transcriptomics, genomics, proteomics, and metabolomics, to improve cancer classification. However, current works do not fully utilize the non-linear learning potential of GNN and lack of the integration ability to analyse high-throughput multi-omics data simultaneously with prior biological knowledge. Nevertheless, relying on limited prior knowledge in generating gene graphs might lead to less accurate classification due to undiscovered significant gene-gene interactions, which may require expert intervention and can be time-consuming. Hence, this study proposes a graph classification model called associative multi-omics graph embedding learning (AMOGEL) to effectively integrate multi-omics datasets and prior knowledge through GNN coupled with association rule mining (ARM). AMOGEL employs an early fusion technique using ARM to mine intra-omics and inter-omics relationships, forming a multi-omics synthetic information graph before the model training. Moreover, AMOGEL introduces multi-dimensional edges, with multi-omics gene associations or edges as the main contributors and prior knowledge edges as auxiliary contributors. Additionally, it uses a gene ranking technique based on attention scores, considering the relationships between neighbouring genes. Several experiments were performed on BRCA and KIPAN cancer subtypes to demonstrate the integration of multi-omics datasets (miRNA, mRNA, and DNA methylation) with prior biological knowledge of protein-protein interactions, KEGG pathways and Gene Ontology. The experimental results showed that the AMOGEL outperformed the current state-of-the-art models in terms of classification accuracy, F1 score and AUC score. The findings of this study represent a crucial step forward in advancing the effective integration of multi-omics data and prior knowledge to improve cancer subtype classification.

Continual learning aims to acquire new knowledge while retaining past information. Class-incremental learning (CIL) presents a challenging scenario where classes are introduced sequentially. For video data, the task becomes more complex than image data because it requires learning and preserving both spatial appearance and temporal action involvement. To address this challenge, we propose a novel exemplar-free framework that equips separate spatiotemporal adapters to learn new class patterns, accommodating the incremental information representation requirements unique to each class. While separate adapters are proven to mitigate forgetting and fit unique requirements, naively applying them hinders the intrinsic connection between spatial and temporal information increments, affecting the efficiency of representing newly learned class information. Motivated by this, we introduce two key innovations from a causal perspective. First, a causal distillation module is devised to maintain the relation between spatial-temporal knowledge for a more efficient representation. Second, a causal compensation mechanism is proposed to reduce the conflicts during increment and memorization between different types of information. Extensive experiments conducted on benchmark datasets demonstrate that our framework can achieve new state-of-the-art results, surpassing current example-based methods by 4.2% in accuracy on average. The codes are accessible in https://github.com/tychen-SJTU/CSTA.

Recent research in the field of Human Activity Recognition has shown that an improvement in prediction performance can be achieved by reducing the number of LSTM layers. However, this kind of enhancement is only significant on monolithic architectures, and when it runs on large-scale distributed training, data security and privacy issues will be reconsidered, and its prediction performance is unknown. In this paper, we introduce a novel framework: FedBChain, which integrates the federated learning paradigm based on a modified DeepConvLSTM architecture with a single LSTM layer. This framework performs comparative tests of prediction performance on three different real-world datasets based on three different hidden layer units (128, 256, and 512) combined with five different federated learning strategies, respectively. The results show that our architecture has significant improvements in Precision, Recall and F1-score compared to the centralized training approach on all datasets with all hidden layer units for all strategies: FedAvg strategy improves on average by 4.54%, FedProx improves on average by 4.57%, FedTrimmedAvg improves on average by 4.35%, Krum improves by 4.18% on average, and FedAvgM improves by 4.46% on average. Based on our results, it can be seen that FedBChain not only improves in performance, but also guarantees the security and privacy of user data compared to centralized training methods during the training process. The code for our experiments is publicly available (https://github.com/Glen909/FedBChain).

While tuberculosis (TB) is a deadly disease, the coronavirus (COVID-19) has caused more rapid death since its discovery in 2019. Studies have shown that the recovery rate of COVID-19 patients with TB has been discovered to be extremely low. With this, analyzing lung Computed Tomography (CT) images of patients with TB or COVID-19 disease is a considerable way of assisting in diagnosing and treating. However, previous segmentation methods have challenges segmenting noisy images such as CT scans. This study proposed a novel technique, namely an enhanced 3-dimensional OTSU (E3D-OTSU) algorithm for segmenting TB and COVID-19-infected areas in lung CT images. It is experimentally proven to be efficient on TB and COVID-19 datasets. The evaluation results using dice co-efficient, accuracy, and sensitivity metrics showed that the proposed E3D-OTSU outperformed two previously employed OTSU algorithms on both datasets. Nonetheless, it achieved the highest dice co-efficient values of 97.78% and 98.58% on TB and COVID-19 datasets respectively.

A resurgence of research interest in recommender systems can be attributed to the widely publicized Netflix competition with the grand prize of USD 1 million. The competition enabled the promising collaborative filtering algorithms to come to prominence due to the availability of a large dataset and from it, the growth in the use of matrix factorization. There have been many recommender system projects centered around use of matrix factorization, with the co-SVD approach being one of the most promising. However, the field is chaotic using different benchmarks and evaluation metrics. Not only the performance metrics reported are not consistent, but it is difficult to reproduce existing research when details of the data processing and hyperparameters lack clarity. This paper is to address these shortcomings and provide researchers in this field with a current baseline through the provision of detailed implementation of the co-SVD approach. To facilitate progress for future researchers, it will also provide results from an up-to-date dataset using pertinent evaluation metrics such as the top-N recommendations and the normalized discounted cumulative gain measures.

Following the rising popularity of YouTube, there is an emerging problem on this platform called clickbait, which provokes users to click on videos using attractive titles and thumbnails. As a result, users ended up watching a video that does not have the content as publicized in the title. This issue is addressed in this study by proposing an algorithm called BaitRadar, which uses a deep learning technique where six inference models are jointly consulted to make the final classification decision. These models focus on different attributes of the video, including title, comments, thumbnail, tags, video statistics and audio transcript. The final classification is attained by computing the average of multiple models to provide a robust and accurate output even in situation where there is missing data. The proposed method is tested on 1,400 YouTube videos. On average, a test accuracy of 98% is achieved with an inference time of ≤ 2s.

Ambiguity or uncertainty is a pervasive element of many real-world decision-making processes. Variation in decisions is a norm in this situation when the same problem is posed to different subjects. Psychological and metaphysical research has proven that decision making by humans is subjective. It is influenced by many factors such as experience, age, background, etc. Scene understanding is one of the computer vision problems that fall into this category. Conventional methods relax this problem by assuming that scene images are mutually exclusive; therefore, they focus on developing different approaches to perform the binary classification tasks. In this paper, we show that scene images are nonmutually exclusive and propose the fuzzy qualitative rank classifier (FQRC) to tackle the aforementioned problems. The proposed FQRC provides a ranking interpretation instead of binary decision. Evaluations in terms of qualitative and quantitative measurements using large numbers and challenging public scene datasets have shown the effectiveness of our proposed method in modeling the nonmutually exclusive scene images.

To be able to perform human action recognition from multiple views is a great challenge in the field of computer vision. State-of-the-art solutions have been focusing on building a 3D action model from multiple views in a multi, calibrated cameras' environment. Promising results were achieved; however, these approaches tend to assume that human action is performed frontal-parallel to each of the multiple cameras. In a real world scenario, this is not always true and the overlapping regions in such systems are very limited. In this paper, we proposed a fuzzy action recognition framework for multiple views within a single camera. We adopted fuzzy quantity space in the framework and introduced a new concept called the Signature Action Behaviour to model an action from multiple views and represent it as fuzzy descriptor. Then, distance measure is applied to deduce an action. Experimental results showed the efficiency of our proposed framework in modeling the actions from different viewpoints and styles.

Scene classification has been studied extensively in the recent past. Most of the state-of-the-art solutions assumed that scene classes are mutually exclusive. However, this is not true as a scene image may belongs to multiple classes and different people are tend to respond inconsistently even given a same scene image. In this paper, we propose a fuzzy qualitative approach to address this problem. That is, we first adopted the fuzzy quantity space to model the training data. Secondly, we present a novel weight function, w to train a fuzzy qualitative scene model in the fuzzy qualitative states. Finally, we introduce fuzzy qualitative partition to perform the scene classification. Empirical results using a standard dataset and a comparison with K-nearest neighbour has shown the effectiveness and robustness of the proposed method.

Depth information is a very important cue to understand human motion. In this paper, we establish that, even with no real depth camera, the concept of obtaining depth information is applicable for human motion detection. We propose a new motion detection method based on the concept of a real world video surveillance system enhanced with depth cameras. It is developed for detecting and analysing human motion. First, it imitates depth measuring process of a depth camera. Specially chosen in the image during the initialization process, view points play the role of cameras, whereas the depth is measured as a distance from these points to the human figure in the image. Initially, the body is partitioned into four segments to obtain the information about which part of the body is moving. Then, in course of the working cycle of the method, the received depth values are constantly subtracted from the previously obtained values, and the intensity of the body motion is calculated using root mean square. The method has been tested on actions taken from a standard motion dataset (IXMAS). It proved to be stable and reliable.