MOTIVATION: Accurate demultiplexing of pooled single-cell RNA-seq (scRNA-seq) data is critical for large-scale studies. However, existing methods like vireo, while effective up to ∼16 donors, often struggle with poor clustering due to local optima as donor numbers rise. In high-donor scenarios, overlapping genotypes, a dense genotype space, and increased doublet formation make demultiplexing challenging, requiring methods that are robust to sparse, high-dimensional data and maintain reliable accuracy even as sample complexity grows. RESULTS: We present an enhanced version of souporcell capable of demultiplexing up to 64 donors. The method uses 10× merge for initialization, K-Harmonic Means for robust clustering, and iterative refinement with reinitialization of low-quality clusters and locking of high-quality ones. Compared to vireo, overclustered vireo, and the original souporcell, our approach completely eliminates incorrectly merged clusters and achieves consistently high Adjusted Rand Index (ARI) scores across various doublet rates, demonstrating improved accuracy and scalability. AVAILABILITY AND IMPLEMENTATION: Souporcell3 is freely available under the MIT open-source license at https://github.com/wheaton5/souporcell.

Abstract Skeleton‐based human action recognition has emerged recently thanks to its compactness and robustness to appearance variations. Although impressive results have been obtained in recent years, the performance of skeleton‐based action recognition methods has to be improved to be deployed in real‐time applications. Recently, a lightweight network structure named Double‐feature Double‐motion Network (DD‐Net) has been proposed for the skeleton‐based human action recognition. With high speed, the DD‐Net achieves state‐of‐the‐art performance on hand and body actions. The DD‐Net could not distinguish actions if they have a weak connection with the global trajectories. However, the DD‐Net is suitable for human action recognition where actions strongly correlate to the global trajectories. In this paper, the authors propose TD‐Net, an improved version of the DD‐Net in which a new branch is added. The new branch takes the normalised coordinates of joints (NCJ) to enrich the spatial information. On five datasets for skeleton‐based human activity recognition that are MSR‐Action3D, CMDFall, JHMDB, FPHAB, and NTU RGB + D, the TD‐Net consistently obtains superior performance compared with the baseline model DD‐Net. The proposed method outperforms different state‐of‐the‐art methods, including both hand‐designed and deep learning‐based methods on four datasets (MSR‐Action3D, CMDFall, JHMDB, and FPHAB). Furthermore, the generalisation of the proposed method is confirmed through cross‐dataset evaluation. To illustrate the potential use of the model for real‐time human action recognition, the authors have deployed an application on an edge device. The experimental result shows that the application can process up to 40 fps for pose estimation using MediaPipe. It takes only 0.04 ms to recognise an action from skeleton sequences.

In this paper, a complete indoor navigation assistance system for visually impaired people is introduced. Different multimedia technologies are integrated in a single system in order to provide a precise, safe and friendly navigation service. First, the environment is modeled and represented. After that, the user location is determined by combining Wi-Fi and vision information. This combination offers some benefits in comparison with single technology systems such as setup cost, computational time and accuracy. Finally, the interaction between users and the system is performed through natural Vietnamese language with the support of Vietnamese voice synthesis and recognition. The proposed the system has been successfully deployed in a school for visually impaired pupils. Evaluation with various criteria on visually impaired pupils reveals the feasibility of the solution.

This paper describes and extensively evaluates a visual-based system that autonomously operators for both building a map and localization tasks. The proposed system is to assist mapping services to the visually impaired/blind people in small or mid-scale environments such as inside a building or campus of school, hospital. Toward this end, the proposed approaches solely rely on visual data thanks to a self-designed image acquisition system. On one hand, a robust visual odometry method is utilized to create a map of the environments. On the other hand, the proposed approaches utilize FAB-MAP algorithm that is maybe the most successful for learning places in the environments. Map building and learning places in an environment are processed in an off-line phase. Through a matching place procedure, online captured images are continuously positioned on the map. Furthermore, we utilize a Kaiman Filter that combines the matching results of current observation and the estimation of robot states based on its kinematic model. We evaluate performances of the proposed system through experimental schemes. The results show that the constructed map coincides with ground truth, and matching image-to-map is high confidence. The evaluations also contain scenarios which the blind pupils move following Robot. The experimental results confirmed that proposed system feasibly navigating blind pupils in indoor environments.

Segmenting reddish lesions in capsule endoscopy (CE) images is an initial step for further computer-assisted applications such as image enhancement, abnormal measurement/tracking, and so on. In this paper, we propose an automatic segmentation method that is successful even with CE image including unclear reddish lesions. To obtain this, the proposed method seeks good features to discriminate the reddish lesions from normal tissues. For implementations, we first extract only meaningful regions in a CE image through a pre-segmentation step. The proposed features then are extracted for the meaningful regions in stead of the whole image. We approaches segmentation task through considering a statistical operator for the extracted features, that is local mean image. Candidates of the abnormal regions are located in the local mean image with assistants of a diffusion process. Evaluations in the experiments confirm effectiveness of the proposed method with both qualitative and quantitative measurement.

The interpretive skills of medical doctors and medical technologists who examine video capsule endoscopy (VCE) in clinical practice are usually improved through hands-on courses. Such courses require that a large volume of cases be undertaken as part of the training, and they thus consume a considerable amount of the trainees' time. This paper describes an e-learning system that reduces the training time in addition to enhancing the quality of the educational process with regard to reading VCE. To achieve this goal, we focused on organizing training courses in order to appropriate for the laborious conditions that exist when reading VCE. The designed courses help the trainees acquire knowledge of abnormal regions and become familiar with reading VCE before taking examinations under conditions similar to those actual clinical practice. The proposed training modality was developed as an e-learning application on the World Wide Web. Thus, it can be easily extended to a wide range of trainees. In the experiments, 20 participants completed the self-learning training procedures in approximately 3 hours. The proposed system is much faster than conventional hands-on courses, which require a minimum of 8 hours. Furthermore, the trainees' learning performances in the final examinations confirmed that the proposed system is particularly effective for inexperienced examining doctors.

Counting tender tea shoots in a sampled area is required before making a decision for plucking. However, it is a tedious task and requires a large amount of time. In this paper, we propose a vision-based method for automatically detecting and counting the number of tea shoots in an image acquired from a tea field. First, we build a parametric model of a tea-shoot's color distribution in order to roughly separate Regions-of-Interest (ROIs) of tea shoots from a complicated background. For each ROI, we then extract supportive (local) features with expectations that these features will only appear around an apical bud of tea shoots thanks to two measurements: the density of edge pixels and a statistic of gradient directions. Consequently, the extracted features are put into a mean shift cluster to locate the position of tea shoots. The proposed method is evaluated on a set of testing images with different species of tea plants and ages. The results show 86% correct tea shoots detected, whereas 25% of a false alarm rate exists. It offers an elegant way to build an assisting tool for tea harvesting.

This paper presents an efficient method for automatically segmenting the digestive organs in a Video Capsule Endoscopy (VCE) sequence. The method is based on unique characteristics of color tones of the digestive organs. We first introduce a color model of the gastrointestinal (GI) tract containing the color components of GI wall and non-wall regions. Based on the wall regions extracted from images, the distribution along the time dimension for each color component is exploited to learn the dominant colors that are candidates for discriminating digestive organs. The strongest candidates are then combined to construct a representative signal to detect the boundary of two adjacent regions. The results of experiments are comparable with previous works, but computation cost is more efficient.

We investigate performance improvements through TCP window size optimisation achievable when TCP Reno is used over a highly heterogeneous network, such as an 802.11b wireless LAN or a GPRS-based internet connection. Initially, our modelling focuses on a constant rate, buffered access link, based on a loss-less wireless channel and with a bandwidth at least one order of magnitude less than its fixed-network continuation into the core. We implement the model guidelines on wireless LAN and GPRS access links, confirming that TCP throughput can be increased by optimising the TCP receiver window size to the link characteristics, and more significantly, that there exists a broad range of near-optimal awnd values.