MOTIVATION: Intratumor heterogeneity arises from ongoing somatic evolution and complicates cancer diagnosis, prognosis, and treatment. Reconstructing evolutionary dynamics typically requires spatiotemporal samples, which are often unavailable in clinical settings. Computational approaches that can infer tumor evolutionary history from single-timepoint bulk sequencing data remain limited. RESULTS: We present estimating evolutionary events through single-timepoint sequencing (TEATIME), a novel computational framework that models tumors as mixtures of two competing cell populations: an ancestral clone with baseline fitness and a derived subclone with elevated fitness. Using cross-sectional bulk sequencing data, TEATIME estimates mutation rates, timing of subclone emergence, relative fitness, and number of generations of growth. To quantify intratumor fitness asymmetries, we introduce a novel metric-fitness diversity-which captures the imbalance between competing cell populations and serves as a measure of functional intratumor heterogeneity. Applying TEATIME to 33 tumor types from The Cancer Genome Atlas, we revealed divergent as well as convergent evolutionary patterns. Notably, we found that immune-hot microenvironments constraint subclonal expansion and limit fitness diversity. Moreover, we detected temporal dependencies in mutation acquisition, where early driver mutations in ancestral clones epistatically shape the fitness landscape, predisposing specific subclones to selective advantages. These findings underscore the importance of intratumor competition and tumor-microenvironment interactions in shaping evolutionary trajectories, driving intratumor heterogeneity. Lastly, we demonstrate that TEATIME-derived evolutionary parameters and fitness diversity offer novel prognostic insights across multiple cancer types. AVAILABILITY AND IMPLEMENTATION: R implementation of TEATIME is available on GitHub (https://github.com/liliulab/TEATIME) and Zenodo (https://zenodo.org/records/17422174).

Long-range (LoRa) technology has emerged as a promising solution for Internet of Things applications due to its low power consumption and long communication range. However, its pure ALOHA-based MAC layer leads to severe packet collisions as the network scale expands, significantly degrading the system energy efficiency (EE). While careful allocation of transmission parameters such as channel (CH), transmission power (TP), and spreading factor (SF) could mitigate this issue, the complex interference patterns in multi-gateway scenarios and the time-consuming nature of EE evaluation pose significant challenges. Therefore, we propose an analytical model to calculate the system EE while fully considering the impacts of multiple gateways, duty cycling, quasi-orthogonal SFs and capture effects. Based on this model, we formulate a joint CH, SF, and TP allocation problem to optimize the system EE. To solve this NP-hard optimization problem, we decompose it into CH assignment and SF/TP assignment subproblems. A two-phase optimization framework is then designed. In the first phase, a matching-based algorithm is designed for CH assignment. In the second phase, a multi-agent reinforcement learning approach that incorporates a two-stage attention mechanism and graph convolutional networks is proposed for SF/TP assignment, which effectively captures and weights inter-ED interactions in multi-gateway scenarios. Simulation results indicate that the proposed approach well-suited for complex multi-GW LoRa network topologies and outperforms state-of-the-art algorithms.

The task of translating natural language questions into query languages has long been a central focus in semantic parsing.Recent advancements in Large Language Models (LLMs) have significantly accelerated progress in this field.However, existing studies typically focus on a single query language, resulting in methods with limited generalizability across different languages.In this paper, we formally define the Text-to-Query task paradigm, unifying semantic parsing tasks across various query languages.We identify query skeletons as a shared optimization target of Text-to-Query tasks, and propose a general dynamic data augmentation framework that explicitly diagnoses modelspecific weaknesses in handling these skeletons to synthesize targeted training data.Experiments on four Text-to-Query benchmarks demonstrate that our method achieves state-ofthe-art performance using only a small amount of synthesized data, highlighting the efficiency and generality of our approach and laying a solid foundation for unified research on Textto-Query tasks.We release our code

The advancement of multi-modal large language models (MLLMs) has significantly enhanced their capability to process and understand diverse data types, integrating text, images, and other modalities. Despite their impressive performance, evaluating the robustness of these models remains challenging due to the difficulty of aligning their text-based responses with image classification labels. Traditional approaches rely on CLIP scores or other large language models as judges, but these methods lack scientific rigor and fail to capture robustness across different semantic levels. In this paper, we propose a novel evaluation metric that systematically assesses the robustness of MLLMs in image classification using WordNet’s hierarchical structure. Specifically, we parse the text descriptions generated by MLLMs to extract all nouns, then calculate their distances to the groundtruth label in WordNet as a similarity metric. The minimum distance among all nouns is used as the similarity score between the text description and the label. By using WordNet, we can also evaluate classification performance at different semantic levels. Through extensive experiments, we demonstrate that our WordNet-based evaluation metric offers a deeper understanding of MLLMs’ robustness, paving the way for more resilient and reliable models in real-world applications.

Model inversion is a promising technique for raw data reconstruction, especially in data-free quantization of Vision Transformers (ViTs). Previous inversion methods for ViTs have focused on extracting necessary foreground information while discarding irrelevant noise. However, these mode inversion methods for ViTs are inefficient in terms of data synthesis speed. In this paper, we propose a novel method to accelerate model inversion for efficient data-free quantization of ViTs(Eff-DFQT). Our method has the following features. 1) Token fusion strategy tailored for model inversion. We propose a token fusion strategy tailored for model inversion to lower the computations for image inversion. 2) Label compensation function. We propose a label compensation function to model the label uncertainty of the inverted image and accurately capture the real labels, which improves the quality of the inverted data by compensating for the negative effects of token reduction. Extensive experimental results demonstrate that Eff-DFQT, significantly accelerates the inversion process through token fusion strategy tailored for model inversion and label compensation function, while maintaining or even improving model performance in data-free quantization of ViTs.

Implicit Neural Representations (INRs), as a versatile representation paradigm, have achieved success in various computer vision tasks. Due to the spectral bias of the vanilla multi-layer perceptrons (MLPs), existing methods focus on designing MLPs with sophisticated architectures or repurposing training techniques for highly accurate INRs. In this paper, we delve into the linear dynamics model of MLPs and theoretically identify the empirical Neural Tangent Kernel (eNTK) matrix as a reliable link between spectral bias and training dynamics. Based on this insight, we propose a practical **I**nductive **G**radient **A**djustment (**IGA**) method, which could purposefully improve the spectral bias via inductive generalization of eNTK-based gradient transformation matrix. Theoretical and empirical analyses validate impacts of IGA on spectral bias. Further, we evaluate our method on different INRs tasks with various INR architectures and compare to existing training techniques. The superior and consistent improvements clearly validate the advantage of our IGA. Armed with our gradient adjustment method, better INRs with more enhanced texture details and sharpened edges can be learned from data by tailored impacts on spectral bias. The codes are available at: [https://github.com/LabShuHangGU/IGA-INR](https://github.com/LabShuHangGU/IGA-INR).

ABSTRACT 3D object detection is one of the current popular hotspots by perceiving the surrounding environment through LiDAR and camera sensors to recognise the category and location of objects in the scene. Deep neural networks (DNNs) have been found to be vulnerable to adversarial examples. Although some approaches have begun to investigate the robustness of 3D object detection models, they are currently generating adversarial examples in a white‐box setting and there is a lack of research into generating transferable adversarial examples in a black‐box setting. In this paper, a non‐end‐to‐end attack algorithm was proposed for LiDAR pipelines that crafts transferable adversarial examples against 3D object detection. Specifically, the method generates adversarial examples by restraining features with high contribution to downstream tasks and amplifying features with low contribution to downstream tasks in the feature space. Extensive experiments validate that the method produces more transferable adversarial point clouds, for example, the method generates adversarial point clouds in the nuScenes dataset that are about 10 and 7 better than the state‐of‐the‐art method on mAP and NDS, respectively.

ABSTRACT Recent studies have shown that deep neural networks are vulnerable to adversarial attacks. In the field of 3D point cloud classification, transfer‐based black‐box attack strategies have been explored to address the challenge of limited knowledge about the model in practical scenarios. However, existing approaches typically rely excessively on network structure, resulting in poor transferability of the generated adversarial examples. To address the above problem, the authors propose AEattack , an adversarial attack method capable of generating highly transferable adversarial examples. Specifically, AEattack employs an autoencoder (AE) to extract features from the point cloud data and reconstruct the adversarial point cloud based on these features. Notably, the AE does not require pre‐training, and its parameters are jointly optimised using a loss function during the process of generating adversarial point clouds. The method makes the generated adversarial point cloud not overly dependent on the network structure, but more concerned with the data distribution. Moreover, this design endows AEattack with a broader potential for application. Extensive experiments on the ModelNet40 dataset show that AEattack is capable of generating highly transferable adversarial point clouds, with up to 61.8% improvement in transferability compared to state‐of‐the‐art adversarial attacks.

ABSTRACT Traditional codebooks used for tracing information leakage in text documents often suffer from limitations in embedding capacity, robustness, and efficiency due to their manual generation process. This paper proposes a robust text watermarking method based on the stroke components of Chinese characters. By designing an innovative approach, Chinese character strokes are divided into several distinct components, with only specific ones being selectively modified to generate new glyphs, thus forming a unique codebook. The watermark signals are embedded by substituting the carrier glyph with the newly generated one, and the signals are extracted using a template matching method. Experimental results demonstrate that, compared to traditional manually designed codebooks, the proposed method significantly reduces human labor and computational overhead while maintaining high visual quality. Moreover, it exhibits superior robustness and adaptability across various challenging scenarios, including digital noise attacks, print‐scanning attacks, and print‐camera capture, making it a highly effective solution for protecting textual information.

One of the most popular methods for analyzing the robustness of 3D Deep Neural Networks (DNNs) is the transfer-based adversarial attack method, as it allows to analyze the robustness of an unknown model by generating an adversarial point cloud on an alternative model. However, the adversarial point clouds generated by current methods may overfit the surrogate models that generated them, thus limiting their performance in transfer attacks against different target 3D classifiers. To enhance the transferability of the adversarial point cloud, we propose in this letter an adversarial attack method by Initializing the Transferable Adversarial Noise, which named asITAN. Specifically, we pre-train on the training set a generator capable of generating the adversarial noise with transferability and diversity, and then the noise generated by the generator serves as the initial adversarial noise to be integrated into the iterations of the attack. Extensive experiments on well-recognized benchmark datasets demonstrate that the adversarial point clouds generated by the proposed ITAN could be effectively transferred across unknown 3D classifiers.

Transfer-based adversarial attacks involve generating adversarial point clouds in surrogate models and transferring them to other models to assess 3D model robustness. However, current methods rely too much on surrogate model parameters, limiting transferability. In this work, we use Shapley value to identify positive and negative features, guiding optimization of adversarial noise in feature space. To effectively mislead the 3D classifier, we factorize the adversarial noise into positive and negative noise, with the former keeping the features of the adversarial point cloud close to the negative features, and the latter and the adversarial noise moving it away from the positive features. Finally, a novel adversarial point cloud attack method with Adversarial Noise Factorization is proposed, which is abbreviated asANF. ANF simultaneously optimizes the adversarial noise and its positive and negative noise in the feature space, only relying on partial network parameters, which significantly reduces the reliance on the surrogate model and improves the transferability of the adversarial point cloud. Experiments on well-recognized benchmark datasets show that the transferability of adversarial point clouds generated by ANF could be improved by more than 26.7$\%$on average over state-of-the-art transfer-based adversarial attack methods.

Deploying state-of-the-art object detectors on resource-limited devices presents significant challenges. Knowledge distillation is an efficient and streamlined lightweight technique to improve the accuracy of compact detectors. However, its effectiveness is limited by the redundancy of different types of semantics on the feature map and the closure of same level’s feature distillation. To alleviate this problem, we propose Decoupled and Interactive Distillation, an effective and versatile method to improve knowledge distillation in some complex object detection tasks. The method has two key components. A knowledge decoupled module captures category awareness and localization awareness features. A multi-level feature interaction distillation can aggregate feature distillations from shallow to deep levels, facilitating the collaboration between feature transfers at different levels. The relevant experiments in traffic-related, 3D, rotated object detection have verified the effectiveness of the proposed method, particularly in challenging scenes.

It has been shown that deep recommendation models are susceptible to adversarial attacks, with this vulnerability potentially leading to significant economic losses in the e-commerce field. However, the robustness of deep recommendation models in response to adversarial attacks has not been systematically investigated. In this article, therefore, we comprehensively evaluate the adversarial robustness of various representative deep models in different settings, aiming to analyze their performance impact under adversarial attacks and compare it with traditional collaborative filtering models. Notably, we examine poisoning attacks under different proportions of fake users and various popularity conditions to understand why certain deep recommendation models perform exceptionally or sub-optimally. On this basis, we further proposed practical robustness improvement strategy for the problems found in the evaluation and fully verified it through rigorous experiments. Key findings include: (1) the sparser the training dataset, the weaker the robustness of a recommendation model’s performance under adversarial attacks; (2) deep recommendation models exhibit greater robustness in recommending popular items under adversarial attacks, while they are more vulnerable when attacked with non-popular items; (3) the robustness of deep recommendation models is not consistently weaker than that of traditional collaborative filtering models across all attack settings. These findings highlight the security concerns in deep recommendation systems and contribute to developing more reliable models.

3D point cloud classifiers exhibit vulnerability to imperceptible perturbations, which poses a serious threat to the security and reliability of deep learning models in practical applications, making the robustness evaluation of deep 3D point cloud models increasingly important. Due to the difficulty in obtaining model parameters, black-box attacks have become a mainstream means of assessing the adversarial robustness of 3D classification models. The core of improving the transferability of adversarial examples generated by black-box attacks is to generate better generalized adversarial examples, where data augmentation has become one of the popular approaches. In this article, we employ five mainstream attack methods and combine six data augmentation strategies, namely point dropping, flipping, rotating, scaling, shearing, and translating, in order to comprehensively explore the impact of these strategies on the transferability of adversarial examples. Our research reveals that data augmentation methods generally improve the transferability of the adversarial examples, and the effect is better when the methods are stacked. The interaction between data augmentation methods, model characteristics, attack, and defense strategies collectively determines the transferability of adversarial examples. In order to comprehensively understand and improve the effectiveness of adversarial examples, it is necessary to comprehensively consider these complex interrelationships.

In this paper, we employ an unmanned aerial vehicle (UAV) to ensurethe freshness of sensing data, as measured by the age of information (AoI), in Internet of Things (IoT) networks. Specifically, the UAV switches between flying and hovering modes to collect data from widely distributed IoT devices. UAV trajectory planning, which determines the times and moments of data collection, is vital for optimizing the system AoI. Considering the limited UAV onboard energy and mission duration, AoI-optimal trajectory planning is formulated as a mixed-integer nonlinear programming (MINLP) problem. We first decompose the MINLP problem into two subproblems: a UAV time scheduling subproblem and a UAV path planning subproblem. Then, we propose a learning-based iterative (LBI) algorithm that consists of two modules: a successive convex approximation (SCA)-based module for solving the time scheduling subproblem, and a hierarchical asynchronous advantage actor-critic (A3C) module for addressing the path planning subproblem. The numerical results verify that the proposed LBI algorithm outperforms typical baselines in terms of the AoI performance.

LoRa is considered one of the most promising low-power wide-area techniques. Given that end devices (EDs) are typically battery-powered, energy efficiency (EE) is a critical factor to consider. In this paper, we aim to improve the system EE of the LoRa network by jointly allocating transmission parameters such as the channel (CH), transmission power (TP) and spreading factor (SF) for each ED. Owing to the low duty cycle and sporadic traffic of LoRa networks, evaluating the system EE under various parameter settings proves to be time-consuming. Consequently, we propose an analytical model aimed at calculating the system EE while fully considering the impact of multiple gateways, quasi-orthogonal SFs and capture effects. On this basis, we investigate a joint CH, SF and TP allocation problem to optimize the system EE for uplink transmissions. Given the NP-hard complexity of the problem, the original problem is decomposed into two subproblems: CH assignment and SF/TP assignment. First, a matching-based algorithm is introduced to tackle the CH assignment subproblem. Then, an attention-based multiagent reinforcement learning technique is employed to address the SF/TP assignment subproblem for EDs allocated to the same CH. The simulation outcomes indicate that the proposed approach converges quickly and obtains significantly better system EE than baseline algorithms.

Recent research has demonstrated that recommendation systems exhibit vulnerability under data poisoning attacks. The primary process of data poisoning attacks involves generating malicious data (i.e., fake users) through surrogate models and injecting the malicious data into the target models’ datasets, thereby manipulating the output results of the target models. However, current methods generating fake users based on gradient descent may cause them to fall into undesired local minimum in the loss landscape and overfitting to the surrogate model, thus limiting the performance of attacking other recommendation models. To address this problem, we propose the reverse optimization algorithm (ReOP), which utilizes the reverse direction of optimization to update fake users, enabling them to steer clear of sharp local minimum in loss landscape and navigate towards the flat local minimum. ReOP makes fake users less sensitive to model changes, alleviates their overfitting to the surrogate model, and thus significantly improves the transferability of fake users. Experimental results demonstrate that ReOP surpasses the state-of-the-art baseline methods, effectively generating fake users with significant attack effects on various target models.

The reliability and robustness of 3D object detection play an instrumental role in the practical deployment of autonomous driving systems. Despite previous research indicating that adversarial examples can negatively affect 3D object detection models, leading to misinterpretations of the environment, these models still maintain the capability to detect the majority of objects within adversarially manipulated point clouds. To further probe into the adversarial robustness of these models, we propose an effective adversarial attack method named IoU-S attack in this paper. We meticulously formulate the adversarial loss to adversely affect the decision-making behavior (such as localization, etc.) of 3D object detection, thereby compromising its ability to accurately interpret the environment. Owing to the significant relevance of this adversarial loss to 3D object detection tasks, we have integrated the IoU-S attack into three attack paradigms: point cloud perturbation, detachment, and attachment. Comprehensive experiments on the widely accepted nuScenes dataset illustrate that the IoU-S attack outperforms existing attack methods in both white-box and black-box scenarios (https://github.com/haichen-ber/IoU-S-Attack). It reinforces its potential to serve as a valuable method in understanding and enhancing the robustness of 3D object detection models against adversarial attacks.

The recommendation performance of deep collaborative filtering models drops sharply under imperceptible adversarial perturbations. Some methods promote the robustness of recommendation systems by adversarial training. However, these methods only study shallow models and lack the exploration of deep models. Furthermore, the way these methods add adversarial noise to the weight parameters of users and items is not fully applicable to deep collaborative filtering models, because the adversarial noise is not sufficient to fully affect its network structure with multiple hidden layers. In this article, we propose a novel adversarial training framework, Random Layer-wise Adversarial Training (RAT), which trains a robust deep collaborative filtering model via adversarial noise propagation. Specifically, we inject adversarial noise into the output of the hidden layer in a random layer-wise manner. The adversarial noise propagates forward from the injected position to obtain more flexible model parameters during the adversarial training process. We validate the effectiveness of RAT on multilayer perceptron (MLP) and implement RAT on MLP-based and convolutional neural networks-based deep collaborative filtering models. Experiments on three publicly available datasets show that the deep collaborative filtering model trained by RAT not only defends against adversarial noise but also guarantees recommendation performance.

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird's-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations; 2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features; 3) Camera-LiDARfusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models.

The attacker's malicious behavior of injecting well-designed adversarial examples (i.e., fake users) into recommender systems will severely affect the security of systems. It's difficult to fully obtain details of victim recommendation models (i.e., black-box model) in practical recommendation scenarios, using the transferability of adversarial examples to achieve black-box attacks is still an effective way. At present, adversarial examples generated by existing gradient-based methods are prone to drop into local minima, making it impossible to achieve the expected attack effect and reducing the transferability. In this article, we propose an attack algorithm that enhances the transferability of adversarial examples based on the Nesterov Momentum for Recommendation Systems (ETANRS). With white-box recommendation surrogate models, we utilize Nesterov momentum to generate better adversarial examples, then inject them into black-box victim models to attack. We utilize the accumulated gradients and pre-determine the update direction of the gradients to keep the optimal value from being lost, thus enhancing the transferability of the adversarial examples. Experimental results demonstrate that our method is better than state-of-the-art gradient-based attack algorithms, which affect recommendation performance.

This paper presents an adaptive anchor-point selection method for single image super-resolution (SR), which is based upon internal example-based SR model via locality constrained anchored neighborhood regression. The anchor points are fixed in anchored SR methods and are not flexible and customized for different input low-resolution (LR) images. To overcome this defect, we adaptively select anchor points via constructing customized training set for different input LR images, which can be realized by an internal example-based SR method. We introduce a locality-constrained anchored neighborhood regression to learn the relationship between LR space and high-resolution (HR) space. Extensive experimental results demonstrate that the performance of proposed method is competitive with several state-of-the-art SR methods.

The mystery of the asteroid (4179) Toutatis was revealed by Chang'e-2 spacecraft during a close flyby on December 13, 2012. Optical imaging and navigation of the probe during the flyby were performed entirely under ground-based radio tracking and default sequence built on ground. This paper establishes a set of estimation algorithms of the relative trajectory between Chang'e-2 and Toutatis based on dynamics, optical, and radio constraints that are determined by the unique flyby mode. This study is the first time to precisely reproduce the core process of Chang'e-2's encounter with Toutatis based on several optical images. In addition to constructing a strict photogrammetric model, the shadowing effects caused by the illumination and the deviation of the center-of-mass (COM) from the center-of-figure (COF) in optical images are also considered. The spacecraft trajectory with regard to the COF of the body is estimated using images taken from 120 km or less. The formal one sigma uncertainty is (67, 20, and 11 m) in the principal axes frame of the position error ellipse, and the closest approaching distance between Chang'e-2 and Toutatis's COF is calculated as 1557 ± 11 m, which is more precise than previous results with an uncertainty of hundreds of meters. The spacecraft trajectory with regard to the COM of the body is estimated with an uncertainty of (211, 34, and 17 m), and the corresponding closest distance is estimated as 1451 ± 18 m based on the previously developed shape model of Toutatis. The algorithms and results in this study are important for evaluating the performance of this flyby mission and are also valuable for any similar optical navigation during a close approach. In addition, our results can help in precisely determining the axis of Toutatis and sizes of impact craters, which are critical for understanding the formation and evolution of Toutatis.

In this paper, we present a unified frame based on collaborative representation (CR) for single-image super-resolution (SR), which learns low-resolution (LR) and high-resolution (HR) dictionaries independently in the training stage and adopts a consistent coding scheme (CCS) to guarantee the prediction accuracy of HR coding coefficients during SR reconstruction. The independent LR and HR dictionaries are learned based on CR with l2-norm regularization, which can well describe the corresponding LR and HR patch space, respectively. Furthermore, a mapping function is learned to map LR coding coefficients onto the corresponding HR coding coefficients. Propagation filtering can achieve smoothing over an image while preserving image context like edges or textural regions. Moreover, to preserve the edge structures of a super-resolved image and suppress artifacts, a propagation filtering-based constraint and image nonlocal self-similarity regularization are introduced into the SR reconstruction framework. Experimental comparison with state-of-the-art single image SR algorithms validates the effectiveness of proposed approach.

Wireless sensor nodes require longevity, zero maintenance, and self-sufficiency. However, constraints on power, system volume, and cost are prohibitive to satisfy these requirements. In this paper, a reconfigurable energy management unit (EMU) is introduced that works within the constraints to meet the requirements. With multi-directional energy flow control, the EMU achieves the unification of photovoltaic (PV) energy harvesting with maximum power point tracking (MPPT), energy storage, voltage regulation, and energy recycling for dynamic voltage scaling (DVS). Supercapacitors are employed for energy storage to enhance operation lifetime. A reconfigurable DC-DC converter architecture is implemented to accommodate flexible voltage conversion and multi-directional energy flows. Functionality is implemented and verified using a CMOS 0.35-μm process. The PV cell voltage is well controlled from 1 V to 5 V to achieve MPPT under varying illumination conditions. Meanwhile, the output voltage is regulated from 1.2 V to 3.3 V with no additional regulator. Energy recycling improves DVS down-tracking by over 15 times.

Current accuracy of an LED is vital to its brightness control. Existing hysteretic current control method provides accurate average current, but requires high power dissipation. Peak current control (PCC) method mitigates the power issue, but does not supply accurate average current. A quasi-hysteretic control with adaptive off-time technique is thus proposed in this paper to solve both problems, where low power loss is obtained with discontinuous low-side current sensing, and accurate average current is achieved, regardless of input, output, temperature, and process variations. The design was implemented with 0.35-μm CMOS process. Its average current achieves less than 1% variation, whereas the traditional PCC method with constant off-time control suffers 33.6% current variation with equivalent load conditions.

Due to innovative computer technologies of Internet, hypermedia and virtual reality, Intelligent Tutoring System not only can support tutoring for a single learner, but also can manage groups of learners to interact for collaborative learning environment. As collaborative learning becomes more and more popular, the grouping according to learners are also become an important topic. The paper analyzes the characteristic of collaborative learning in Intelligent Tutoring System, and researches grouping strategy in the collaborative learning environment to provide learners to discuss with peers, present and defend ideas, exchange diverse beliefs, and be actively engaged in the learning process. A collaborative learning grouping strategy was proposed to enhance the students' learning efficiency by the combination of genetic algorithm with k-means clustering. According to the experimental analysis, it can be concluded that the proposed grouping strategy can efficiently improve the learning achievement.

Aiming at the disadvantages of the word segmentation method based on string matching, the word segmentation method based on comprehension and the word segmentation method based on statistic, a novel field word segmentation model based on ontology was studied. With ontology technology introduced into Chinese word segmentation, the novel model eliminates ambiguities to a great extent and avoids semantic losing problem which is result from ignoring the context information in traditional Chinese word segmentation method. The experimental results show that the novel method can improve the segmentation precision greatly. And this study is valuable for next semantic retrieval in the future work.

Efficiency and fidelity is of key importance to audio power amplifiers. A new configuration of power amplifier was proposed to improve both of them. By combining a linear amplifier with a nonlinear one in parallel, it features high efficiency and low distortion. Simulation shows that at the output power of 8.5W its efficiency could be up to 83%, while its THD (total harmonic distortion) is as low as 0.14%.

To support the rapid growth of the web and e-commerce, W3C developed DOM as an application programming interface that provides the abstract, logical tree structure of an XML document. In this paper, we propose ordered-set-at-a-time extensions for DOM while maintaining its tightly managed navigational nature. In particular, we define the NodeSequence interface with functions that filter, navigate, and transform sequences of nodes simultaneously. The extended DOM greatly simplifies writing some application code, and it can reduce the communications overhead and response time between a client application and the DOM server to provide applications with more efficient processing. As validation of our proposals, we present application examples that compare the convenience and efficiency of DOM with and without extensions.

We consider maximum-likelihood sequence estimation (MLSE) algorithms for unknown, time-varying intersymbol interference communication channels. We assume a statistical channel model, and marginalize over model parameters to derive expectation-maximization (EM) algorithms for both time-independent Gaussian and Gauss-Markov models, and we contrast these with direct MLSE and computationally efficient per-survivor processing implementations. We identify a general concern associated with the convergence of EM-based discrete parameter (e.g., symbol) estimators.

We address sequence estimation when the intersymbol interference (ISI) communication channel is unknown and time varying. We employ a maximum a posteriori (MAP) approach, in which the unknown channel parameters are assigned a distribution and integrated out. For several channel models of interest we describe both the exact MAP estimator and Viterbi algorithm based implementations. We also present EM algorithms for solving these MAP sequence estimation problems, and we contrast these EM solutions with direct MAP algorithms.

OBJECTIVES: The authors discuss the usability of an automated tool that supports entry, by clinical experts, of the knowledge necessary for forming high-level concepts and patterns from raw time-oriented clinical data. DESIGN: Based on their previous work on the RESUME system for forming high-level concepts from raw time-oriented clinical data, the authors designed a graphical knowledge acquisition (KA) tool that acquires the knowledge required by RESUME. This tool was designed using Protégé, a general framework and set of tools for the construction of knowledge-based systems. The usability of the KA tool was evaluated by three expert physicians and three knowledge engineers in three domains-the monitoring of children's growth, the care of patients with diabetes, and protocol-based care in oncology and in experimental therapy for AIDS. The study evaluated the usability of the KA tool for the entry of previously elicited knowledge. MEASUREMENTS: The authors recorded the time required to understand the methodology and the KA tool and to enter the knowledge; they examined the subjects' qualitative comments; and they compared the output abstractions with benchmark abstractions computed from the same data and a version of the same knowledge entered manually by RESUME experts. RESULTS: Understanding RESUME required 6 to 20 hours (median, 15 to 20 hours); learning to use the KA tool required 2 to 6 hours (median, 3 to 4 hours). Entry times for physicians varied by domain-2 to 20 hours for growth monitoring (median, 3 hours), 6 and 12 hours for diabetes care, and 5 to 60 hours for protocol-based care (median, 10 hours). An increase in speed of up to 25 times (median, 3 times) was demonstrated for all participants when the KA process was repeated. On their first attempt at using the tool to enter the knowledge, the knowledge engineers recorded entry times similar to those of the expert physicians' second attempt at entering the same knowledge. In all cases RESUME, using knowledge entered by means of the KA tool, generated abstractions that were almost identical to those generated using the same knowledge entered manually. CONCLUSION: The authors demonstrate that the KA tool is usable and effective for expert physicians and knowledge engineers to enter clinical temporal-abstraction knowledge and that the resulting knowledge bases are as valid as those produced by manual entry.