Despite significant advancements in deep learning-based sparse-view computed tomography (SVCT) reconstruction algorithms, these methods still encounter two primary limitations: (I) It is challenging to explicitly prove that the prior networks of deep unfolding algorithms satisfy Lipschitz constraints due to their empirically designed nature. (II) The substantial storage costs of training a separate model for each setting in the case of multiple views hinder practical clinical applications. To address these issues, we elaborate an explicitly provable Lipschitz-constrained network, dubbed LipNet, and integrate an explicit prompt module to provide discriminative knowledge of different sparse sampling settings, enabling the treatment of multiple sparse view configurations within a single model. Furthermore, we develop a storage-saving deep unfolding framework for multiple-in-one SVCT reconstruction, termed PromptCT, which embeds LipNet as its prior network to ensure the convergence of its corresponding iterative algorithm. In simulated and real data experiments, PromptCT outperforms benchmark reconstruction algorithms in multiple-in-one SVCT reconstruction, achieving higher-quality reconstructions with lower storage costs. On the theoretical side, we explicitly demonstrate that LipNet satisfies boundary property, further proving its Lipschitz continuity and subsequently analyzing the convergence of the proposed iterative algorithms. The data and code are publicly available at https://github.com/shibaoshun/PromptCT.

Optical motion capture is a foundational technology driving advancements in cutting-edge fields such as virtual reality and film production. However, system performance suffers severely under large-scale marker occlusions common in real-world applications. An in-depth analysis identifies two primary limitations of current models: (i) the lack of training datasets accurately reflecting realistic marker occlusion patterns, and (ii) the absence of training strategies designed to capture long-range dependencies among markers. To tackle these challenges, we introduce the CMU-Occlu dataset, which incorporates ray tracing techniques to realistically simulate practical marker occlusion patterns. Furthermore, we propose OpenMoCap, a novel motion-solving model designed specifically for robust motion capture in environments with significant occlusions. Leveraging a marker-joint chain inference mechanism, OpenMoCap enables simultaneous optimization and construction of deep constraints between markers and joints. Extensive comparative experiments demonstrate that OpenMoCap consistently outperforms competing methods across diverse scenarios, while the CMU-Occlu dataset opens the door for future studies in robust motion solving. The proposed OpenMoCap is integrated into the MoSen MoCap system for practical deployment. The code is released at: https://github.com/qianchen214/OpenMoCap.

Android is the most popular mobile operating system. However, Android development requires extensive coding, especially for unique features such as lifecycle callbacks and UI widgets. Existing code completion methods typically utilize Retrieval-Augmented Generation (RAG) to provide contextual information for pre-trained code large language models (Code LLMs) to perform completion. Despite considerable progress in these methods, their effectiveness in Android development remains limited. This is because the features of Android development make it challenging for existing retrieval mechanisms to extract sufficient context effectively. In response, we propose DroidCoder, a novel Android code completion framework that employs Android development features and contextual information of code snippets to enrich RAG. It also incorporates a specifically designed loss function to fine-tune the model, enabling it to better utilize context-enhanced RAG for Android code completion. We evaluated our method on three base models and different types of applications, comparing it with two state-of-the-art code completion methods. The experimental results demonstrate that our method significantly outperforms the baselines at line-level and multi-line-level code completion and improves the quality of the completed code.

In remote sensing images, detecting aeroplanes of special shapes is difficult due to limited number of samples. Without enough training samples, most supervised learning based algorithms will fail. Focusing on the specially-shaped aeroplanes in high-resolution optical remote sensing imagery, this paper presents a single-sample approach. The proposed approach takes one sample as input and directly searches for similar matches from the image. Unlike the supervised learning algorithms which extracts information from positive and negative samples, the hyperspectral algorithm estimates the statistics of background by analyzing the global information of the target image, needless to provide negative samples. Furthermore, this algorithm tries to find a hyperplane projected on which the background is compressed while the target is preserved, making it more data-adaptive than the conventional similarity measurements. Experiments on real data have presented the robustness of the proposed method.

Malaria remains one of the most important public health concerns worldwide. It causes nearly half a million deaths every year, and about 40% of the world's population lives in the endemic regions of malaria. A major hurdle in antimalarial development is our limited understanding of the dynamic cellular networks in the malaria parasite. In this study, by coupling RNA-Seq analysis and network mining using a PageRank-based algorithm, we investigated the temporal-specific expression of parasite genes during the 48-hour red blood cycle, and identified genes that may play influential roles in parasite development and invasion. The just-in-time mechanism for gene expression may contribute to a dynamic yet effective adaptive strategy of the malaria parasite.

Malaria is one of the most deadly infectious diseases in the world. The malaria burden is characterized by 207 million cases and over 627,000 deaths annually. The consistent morbidity and mortality underscore an urgent need for the development of next-generation antimalarials. In this paper, we propose a network mining approach to uncover the protein-protein associations that are implicated in important cellular processes including DNA repair, genome integrity, transcriptional regulation, and pathogenesis.

Ship detection in high-resolution optical imagery is a challenging task due to the variable appearances of ships and background. This paper aims at further investigating this problem and presents an approach to detect ships in a “coarse-to-fine” manner. First, to increase the separability between ships and background, we concentrate on the pixels in the vicinities of ships. We rearrange the spatially adjacent pixels into a vector, transforming the panchromatic image into a “fake” hyperspectral form. Through this procedure, each produced vector is endowed with some contextual information, which amplifies the separability between ships and background. Afterward, for the “fake” hyperspectral image, a hyperspectral algorithm is applied to extract ship candidates preliminarily and quickly by regarding ships as anomalies. Finally, to validate real ships out of ship candidates, an extra feature is provided with histograms of oriented gradients (HOGs) to generate a hypothesis using AdaBoost algorithm. This extra feature focuses on the gray values rather than the gradients of an image and includes some information generated by very near but not closely adjacent pixels, which can reinforce HOG to some degree. Experimental results on real database indicate that the hyperspectral algorithm is robust, even for the ships with low contrast. In addition, in terms of the shape of ships, the extended HOG feature turns out to be better than HOG itself as well as some other features such as local binary pattern.

Due to the importance of Frequent Pattern Mining (FPM) in bioinformatics, web mining, social networks and so on, researchers have been paying significant attention to FPM and its various forms. In this study, we introduce a new form that we call super-sequence pattern mining. In contrast to frequent sub-sequence pattern mining studied significantly in the literature, frequent super-sequence mining requires to identify super-sequences that may contain sequential parts from different sequences and that have the total support larger than a given threshold. In essence, finding frequent super-sequence patterns turns out to be related to the well-known NP-hard longest path problem in graphs. Accordingly, we transform a given sequential dataset into a sequence graph and formulate the problem as k-hop longest path problem. We then propose a heuristic algorithm using dynamic programming techniques. The running time of our solution is depending on the number of different items in the sequence set but not on the size of the dataset. Through experiments, we demonstrate the effectiveness of the proposed solution. We also illustrate its use on an actual web log dataset and find out some interesting facts based on the identified frequent super-sequences on the web log dataset.

Advances in biotechnology have given rise to rapid production of biomedical data and the creation of a wide variety of biomedical and bioinformatics ontologies which serve as a primary impetus for the creation of new ontological similarity measures. A new IC ontological similarity measure, a variation of a standard fuzzy set similarity measure, is presented. This new IC ontological similarity measure has never been used in bioinformatics studies. It is compared with two standard IC ontological similarity measures, Resnik and Lin, and also an existing modification of Lin's measure by analyzing the results when used on a set of concepts pairs selected from the cellular component sub-ontology of the Gene Ontology. As part of this experiment, several different methods of calculating IC for an ontological concept are also investigated. These results for the cellular component sub-ontology confirm the results of a previous study on WordNet showing that ontology-based IC measures corresponded closely with corpus-based IC measures.