Accurate identification of pathogens-especially those with pandemic potential-remains a significant challenge, particularly when traditional sequence alignment methods fail. While recent genome sequence identification methods have shown promise, most do not account for the hierarchical structure of biological taxonomy or the varying informativeness of genomic features across classification levels. To address these limitations, we propose HieRMVir (Hierarchical Random forest and Mutual information-based Viral genome classifier), a novel hierarchical deep learning framework that integrates random forest (RF)-based feature weighting with mutual information (MI)-guided attention regularization for interpretable and accurate viral sequence classification. HieRMVir performs classification across three levels and leverages feature importance scores from RF to scale input features, while MI scores are used to guide the attention mechanism towards statistically informative k-mer patterns through regularized loss. Experimental results on over one million genome sequences demonstrate that HieRMVir achieves an average accuracy of 95.8% (95% CI: 95.3-96.4%), outperforming existing methods on multiple metrics. Evaluation using hierarchical performance metrics and the analysis of learned attention weights further highlight the biological relevance and interpretability of HieRMVir.

In the field of the Internet of Medical Things (IoMT), efficiently deploying deep learning models for breast cancer pathological diagnosis is both important and challenging. Traditional cloud computing stores data on a central server, which poses a risk of data leakage. Although conventional federated learning can protect data privacy, it still faces limitations in computing resources. In addition, most existing pathological image segmentation methods use single-resolution features, making it difficult to jointly represent both global context and local lesion details. To address these challenges, we introduce a Breast Cancer Pathological Diagnosis Cloud-Edge-Collaborative Platform based on split federated learning. We developed a lightweight edge device that is built upon the Jetson Nano deep learning computing platform. The model uses heatmap-guided region search to efficiently discover and examine ROIs over histopathological images, which simulates the expert observation process by pathologists. The platform enables collaborative learning of global and local information without leaking out sensitive patients’ data. Our method ensures data security and privacy while significantly improving model accuracy. Experimental results show that our model achieves Dice scores of 81.31% on the public Breast Cancer Semantic Segmentation (BCSS) dataset and 87.03% on clinical data collected from the Chinese People’s Liberation Army (PLA) General Hospital, improving the Dice score from 79.36% to 81.31% on BCSS, and from 86.18% to 87.03% on our clinical dataset. These results outperform existing models, advancing a meaningful step towards the distributed pathological diagnosis of breast cancer.

ABSTRACT Learning path recommendation is crucial for guiding learners through a series of courses in a logical sequence based on their previous learning experiences. This is particularly important for improving learning outcomes in massive open online courses (MOOCs) for diverse learners. Because both the historical learning courses and recommended learning paths can be represented as sequential patterns (SPs); it is reasonable to approach this problem through SP mining (SPM). In addition to support, we incorporate three factors, that is, course learning days, grades and engagement, to model frequent high‐utility SPs (FHUSPs). When recommending a learning path, FHUSPs that align with the target user's learning history and are common among successful learners, while rare among less successful ones, are prioritised. If there are insufficient matching FHUSPs, we address this by recommending additional courses based on the joint competency and complementarity of learners similar to the target learner. Experimental results on a real‐world dataset demonstrate that our method provides highly accurate and relevant recommendations.

The aim of sequential pattern mining (SPM) is to discover potentially useful information from a given sequence. Although various SPM methods have been investigated, most of these focus on mining all of the patterns. However, users sometimes want to mine patterns with the same specific prefix pattern, called co-occurrence pattern. Since sequential rule mining can make better use of the results of SPM, and obtain better recommendation performance, this paper addresses the issue of maximal co-occurrence nonoverlapping sequential rule (MCoR) mining and proposes the MCoR-Miner algorithm. To improve the efficiency of support calculation, MCoR-Miner employs depth-first search and backtracking strategies equipped with an indexing mechanism to avoid the use of sequential searching. To obviate useless support calculations for some sequences, MCoR-Miner adopts a filtering strategy to prune the sequences without the prefix pattern. To reduce the number of candidate patterns, MCoR-Miner applies the frequent item and binomial enumeration tree strategies. To avoid searching for the maximal rules through brute force, MCoR-Miner uses a screening strategy. To validate the performance of MCoR-Miner, eleven competitive algorithms were conducted on eight sequences. Our experimental results showed that MCoR-Miner outperformed other competitive algorithms, and yielded better recommendation performance than frequent co-occurrence pattern mining. All algorithms and datasets can be downloaded fromhttps://github.com/wuc567/Pattern-Mining/tree/master/MCoR-Miner.

Environmental perception provides the necessary information for unmanned ground vehicles to recognize and interact with surrounding objects. Velodyne light detection and ranging (LiDAR) is widely used for this purpose due to its significant advantages such as high precision and being uninfluenced by varying illuminations. However, the unstructured distribution of LiDAR point clouds always affects the performance of feature extraction and object recognition. Moreover, the numbers of parameters in most deep learning models of object recognition are very large and the training process costs lots of computation consumption. This paper proposes a broad learning system (BLS) variant with a unified space autoencoder (USAE) as a lightweight model to recognize 3D objects. When the proposed method was evaluated on the LiDAR point cloud dataset and ModelNet10 dataset, the experimental results indicated that the recognition accuracy of our USAE-BLS model was similar to that of state-of-the-art 3D object recognition models. Moreover, the USAE-BLS has a much smaller model size and shorter training time than that of the deep learning models.

Scientists have explored the human body for hundreds of years, and yet more relationships between the behaviors and health are still to be discovered. With the development of data mining, artificial intelligence technology, and human posture detection, it is much more possible to figure out how behaviors and movements influence people’s health and life and how to adjust the relationship between work and rest, which is needed urgently for modern people against this high-speed lifestyle. Using smart technology and daily behaviors to supervise or predict people’s health is a key part of a smart city. In a smart city, these applications involve large groups and high-frequency use, so the system must have low energy consumption, a portable system, and a low cost for long-term detection. To meet these requirements, this paper proposes a posture recognition method based on multisensor and using LoRa technology to build a long-term posture detection system. LoRa WAN technology has the advantages of low cost and long transmission distances. Combining the LoRa transmitting module and sensors, this paper designs wearable clothing to make people comfortable in any given posture. Aiming at LoRa’s low transmitting frequency and small size of data transmission, this paper proposes a multiprocessing method, including data denoising, data enlarging based on sliding windows, feature extraction, and feature selection using Random Forest, to make 4 values retain the most information about 125 data from 9 axes of sensors. The result shows an accuracy of 99.38% of extracted features and 95.06% of selected features with the training of 3239 groups of datasets. To verify the performance of the proposed algorithm, three testers created 500 groups of datasets and the results showed good performance. Hence, due to the energy sustainability of LoRa and the accuracy of recognition, this proposed posture recognition using multisensor and LoRa can work well when facing long-term detection and LoRa fits smart city well when facing long-distance transmission.

There exists an electromagnetic shielding effect on radio signals in a tunnel, which results in no satellite positioning signal in the tunnel scenario. Moreover, because vehicles always drive at a high speed on the highway, the real-time localization system (RTLS) has a bottleneck in a highway scenario. Thus, the navigation and positioning service in tunnel and highway is an important technology difficulty in the construction of a smart transportation system. In this paper, a new technology combined downlink time difference of arrival (DL-TDoA) is proposed to realize precise and automated RTLS in tunnel and highway scenarios. The DL-TDoA inherits ultra-wideband (UWB) technology to measure the time difference of radio signal propagation between the location tag and four different location base stations, to obtain the distance differences between the location tag and four groups of location base stations. The proposed solution achieves a higher positioning efficiency and positioning capacity to achieve dynamic RTLS. The DL-TDoA technology based on UWB has several advantages in precise positioning and navigation, such as positioning accuracy, security, anti-interference, and power consumption. In the final experiments on both static and dynamic tests, DL-TDoA represents high accuracy and the mean errors of 11.96 cm, 37.11 cm, 50.06 cm, and 87.03 cm in the scenarios of static tests and 30 km/h, 60 km/h, and 80 km/h in dynamic tests, respectively, which satisfy the requirements of RTLS.

Mining high utility itemsets is an interesting research problem in data mining and knowledge discovery. Most high utility itemset discovery algorithms seek patterns in a single table, but few are dedicated to processing data stored using a multi-dimensional model. In this paper, the problem of mini ng high utility itemsets in multi-relational databases is investigated, and two algorithms, RHUI-Mine and RHUI-Growth, are proposed for star schema-based data warehouses. In the RHUI-Mine algorithm, the search space is traversed in a level-wise manner, and an item index and transaction index are proposed to represent item and transaction information, respectively. The RHUI-Growth algorithm traverses the search space recursively using a pattern growth approach, and a dimensional tree and relational tree are used to compress the original data. Neither algorithm materializes the join operation between tables, thus making use of the star schema properties. Experiments show that both RHUI-Mine and RHUI-Growth are effective approaches for mining high utility itemsets in multi-relational data.

The objective of this study is to solve the problem of user data not being precisely received from sensors because of sensing region limitations in invoked reality (IR) space, distortion of colors or patterns by lighting, and blocking or overlapping of a user by other users. The sensing scope range is thus expanded using multiple sensors in the IR space. Moreover, user feature data are accurately identified by user sensing. Specifically, multiple sensors are employed when not all of user data are sensed because they overlap with data of other users. In the proposed approach, all clients share the user feature data from multiple sensors. Accordingly, each client recognizes that the user is the same individual on the basis of the shared data. Furthermore, the identification accuracy is improved by identifying the user features based on colors and patterns that are less affected by lighting. Therefore, accurate identification of the user feature data is enabled, even under lighting changes. The proposed system was implemented based on system performance analysis standards. The practicality and system performance in identifying the same person using the proposed method were verified through an experiment.

Face detection and recognition is an important topic in security. Currently, ubiquitous monitoring has received a large amount of attention. This paper proposes a cloud-based ubiquitous monitoring system via face recognition. It consists of a monitoring client module for face detection and recognition and a cloud storage module for data visualization. In the monitoring client module, the center-symmetric local Gabor binary pattern feature extraction method is proposed for face recognition, which combines improved multi-scale Gabor and center-symmetric local binary pattern (CS-LBP) features. This method maintains crucial local features, reduces the Gabor filter complexity, and adds rotational invariance and more precise texture information. A large number of experiments on the ORL, Yale-B, and Yale databases show that the proposed method obtains significantly better recognition rates than the LBP, CS-LBP, and Scale Gabor methods. Furthermore, we propose a Web browser-based data visualization that renders the geographic locations of the face detection and recognition results.

High utility itemset mining has recently emerged to address the limitations of frequent itemset mining. It entails relevance measures to reflect both statistical significance and user expectations. Whether breadth-first or depth-first search algorithms are employed, most methods generate new candid ates by 1-extension of existing itemsets (i.e., by adding only one item to verified itemsets to generate new potential candidates). As an alternative to 1-extension, we introduce an expansion method based on binary partition. We then define the transaction utility list and key support count and discuss a new pruning strategy. Based on the new itemset expansion method and pruning strategy, we propose an efficient high utility itemset mining algorithm called BPHUI-Mine (Binary Partition-based High Utility Itemsets Mine). Tests on publicly available datasets show that the proposed algorithm outperforms other state-of-the-art algorithms.

It is essential for smart house researchers to have large datasets from actual environments. However, not all researchers have sufficient budgets to build test beds. These researchers need a simulator that can synthesize realistic sensory datasets. To solve this problem, we propose the 'UbiSim' simulator for activity recognition research. UbiSim provides a 3D graphical user interface to enable spatial perception using multiple sensors, including those that detect motion, pressure, vibration, temperature, and contact, along with RFID tags and receivers. The sensors are designed to verify collisions in a virtual space as a means to operate with minimal computational costs. Our proposed methods were tested in a virtual environment. The results show that the smart house simulator achieves real-time performance.

Since the birth of Natural User Interface (NUI) concept, the NUI has become widely used. NUI-based applications have grown rapidly, particularly those using gestures, which have come to occupy a pivotal place in technology. The ever-popular Smartphone is one of the best examples. Recently, video conferencing has also begun adopting gesture-based NUIs with augmented reality (AR) technology. The NUI and AR have greatly enriched and facilitated human experience. In addition, path planning has been a popular topic in research area. Traditional path planning uses automatic navigation to solve problems, it cannot practically interact with people. Its algorithm calculates complexly, moreover, in certain extenuating circumstances, automatic real-time processing is much less efficient than human path modification. Therefore, considering such extenuating circumstances, we present a solution that employs NUI technology for 3D path modification in real time. In our proposed solution, users can manually operate and edit their own paths. The core method is based on 3D point detection to change paths. We did a simulation experiment about city path modification. Experiment resulted that computer can accurately identify a valid gesture. By using gesture it can effectively change the path. Among other applications, this solution can be used in virtual military maps and car navigation.

The sheer size of all frequent itemsets is one challenging problem in data mining research. Based on both closed itemset and maximal itemset, meta itemset which is a new concise representation of frequent itemset is proposed. It is proved that both closed itemset and maximal itemset are special cases of meta itemset. The set of all closed itemsets and the set of all maximal itemsets form the upper bound and the lower bound of the set of all meta itemsets. Then, property and pruning strategies of meta itemset are discussed. Finally, an efficient algorithm for mining meta itemset is proposed. Experimental results show that the proposed algorithm is effective and efficient.