Diffusion probabilistic models have effectively addressed the ill-posed nature of cardiac magnetic resonance imaging (CMRI) super-resolution (SR) by learning high-resolution image distributions from low-resolution inputs. However, the iterative sampling process in these models often suffers from slow inference speeds, as well as limitations in the quality and structural consistency of the generated images. To address these challenges, we propose a continuous-time conditional diffusion model (CCDM) for blind CMRI SR. Specifically, we propose a continuous-time conditional diffusion module that reduces the time consumption of the diffusion probability model by maintaining the mean and variance of the data in the forward process. Meanwhile, we design a cascaded residual attention network as a feature extractor to enhance the model’s discriminative power and feature representation capabilities. To further elevate image fidelity, we propose an image quality loss module that integrates a score matching loss, significantly improving detail reconstruction and overall perceptual quality. Furthermore, we develop a hybrid score predictor that approximates the conditional score function via a hybrid parameterized denoising network, facilitating efficient CMRI generation through probability flow sampling. Extensive experimental results demonstrate that compared to existing diffusion model-based SR methods, our CCDM achieves significant improvements in SR quality while substantially reducing time consumption.

Consistency learning combined with pseudo label training is a mainstream paradigm in semi-supervised medical image segmentation (SSMIS), yet it faces two challenges: 1)The one-sided search and handling of uncertainty regions make it difficult to address complex uncertainty situations caused by multiple networks. 2)The premature reaching of consensus in traditional SSMIS frameworks hinders the information complementarity between sub-networks. To address these, we propose a multi-view interactive interference training framework based on cross-network uncertainty (MIICU). Specifically, we design a cross-network uncertainty region searching (CUS) module, which combines the predictions from two networks to provide more reasonable uncertainty regions. Then, we design a dual-decision complementary displacement (DCD) strategy that performs displacement operations on cross-network uncertainty regions in different scenarios, so as to facilitate the learning of these regions. We further propose a multi-view interactive interference training strategy by expanding the training environment with three different concatenation forms, encouraging information complementarity between sub-networks. Evaluation on the TN3K and ACDC datasets shows that our approach outperforms existing SSMIS methods and is comparable to fully supervised methods. Code has been released at GitHub

This article investigates the event-triggered multiasynchronous dissipative sliding mode control problem for the gird-connected systems, where the coupled Inductance-Capacitance (LC) oscillators in electrical networks are subject to actuator attacks and external disturbances. To reduce the communication burden, the dynamic event-triggered mechanisms (DETMs) are introduced along with the switching mechanism for multiple topologies. Specifically, the topology switching process is further viewed as a general uncertain semi-Markov (GUSM) jumping process. This jumping process along with the DETM is thus represented by hidden Markov model (HMM). Then the distributed integral-type sliding mode controller is constructed on the top of the HMM. Sufficient conditions for the desired performance of the closed-loop synchronization error system are derived by constructing the mode-dependent Lyapunov-Krasovskii functional (LKF) with extended dissipativity analysis. The numerical simulation of LC oscillators in the single-phase photovoltagic grid interconnection process is conducted to validate the proposed method.

Contrast-enhanced ultrasound (CEUS) has been extensively employed as an imaging modality in thyroid nodule diagnosis due to its capacity to visualise the distribution and circulation of micro-vessels in organs and lesions in a non-invasive manner. However, current CEUS-based thyroid nodule diagnosis methods suffered from: 1) the blurred spatial boundaries between nodules and other anatomies in CEUS videos, and 2) the insufficient representations of the local structural information of nodule tissues by the features extracted only from CEUS videos. In this paper, we propose a novel dual-branch network with a cross-modality-attention mechanism for thyroid nodule diagnosis by integrating the information from tow related modalities, i.e., CEUS videos and ultrasound image. The mechanism has two parts: US-attention-from-CEUS transformer (UAC-T) and CEUS-attention-from-US transformer (CAU-T). As such, this network imitates the manner of human radiologists by decomposing the diagnosis into two correlated tasks: 1) the spatio-temporal features extracted from CEUS are hierarchically embedded into the spatial features extracted from US with UAC-T for the nodule segmentation; 2) the US spatial features are used to guide the extraction of the CEUS spatio-temporal features with CAU-T for the nodule classification. The two tasks are intertwined in the dual-branch end-to-end network and optimized with the multi-task learning (MTL) strategy. The proposed method is evaluated on our collected thyroid US-CEUS dataset. Experimental results show that our method achieves the classification accuracy of 86.92%, specificity of 66.41%, and sensitivity of 97.01%, outperforming the state-of-the-art methods. As a general contribution in the field of multi-modality diagnosis of diseases, the proposed method has provided an effective way to combine static information with its related dynamic information, improving the quality of deep learning based diagnosis with an additional benefit of explainability.

Weakly-supervised learning methods have become increasingly attractive for medical image segmentation, but suffered from a high dependence on quantifying the pixel-wise affinities of low-level features, which are easily corrupted in thyroid ultrasound images, resulting in segmentation over-fitting to weakly annotated regions without precise delineation of target boundaries. We propose a dual-branch weakly-supervised learning framework to optimize the backbone segmentation network by calibrating semantic features into rational spatial distribution under the indirect, coarse guidance of the bounding box mask. Specifically, in the spatial arrangement consistency branch, the maximum activations sampled from the preliminary segmentation prediction and the bounding box mask along the horizontal and vertical dimensions are compared to measure the rationality of the approximate target localization. In the hierarchical prediction consistency branch, the target and background prototypes are encapsulated from the semantic features under the combined guidance of the preliminary segmentation prediction and the bounding box mask. The secondary segmentation prediction induced from the prototypes is compared with the preliminary prediction to quantify the rationality of the elaborated target and background semantic feature perception. Experiments on three thyroid datasets illustrate that our model outperforms existing weakly-supervised methods for thyroid gland and nodule segmentation and is comparable to the performance of fully-supervised methods with reduced annotation time. The proposed method has provided a weakly-supervised segmentation strategy by simultaneously considering the target's location and the rationality of target and background semantic features distribution. It can improve the applicability of deep learning based segmentation in the clinical practice.

Banding artifact, as known as staircase-like contour, is a common quality annoyance that happens in compression, transmission, etc. scenarios, which largely affects the user’s quality of experience (QoE). The banding distortion typically appears as relatively small pixel-wise variations in smooth backgrounds, which is difficult to analyze in the spatial domain but easily reflected in the frequency domain. In this paper, we thereby study the banding artifact from the frequency aspect and propose a no-reference banding detection model to capture and evaluate banding artifacts, called the Frequency-Sensitive BANding Detector (FS-BAND). The proposed detector is able to generate a pixel-wise banding map with a perception correlated quality score. Experimental results show that the proposed FS-BAND method outperforms state-of-the-art image quality assessment (IQA) approaches with higher accuracy in banding classification task.

Assessing action quality is both imperative and challenging due to its significant impact on the quality of AI-generated videos, further complicated by the inherently ambiguous nature of actions within AI-generated video (AIGV). Current action quality assessment (AQA) algorithms predominantly focus on actions from real specific scenarios and are pre-trained with normative action features, thus rendering them inapplicable in AIGVs. To address these problems, we construct GAIA, a Generic AI-generated Action dataset, by conducting a large-scale subjective evaluation from a novel causal reasoning-based perspective, resulting in 971,244 ratings among 9,180 video-action pairs. Based on GAIA, we evaluate a suite of popular text-to-video (T2V) models on their ability to generate visually rational actions, revealing their pros and cons on different categories of actions. We also extend GAIA as a testbed to benchmark the AQA capacity of existing automatic evaluation methods. Results show that traditional AQA methods, action-related metrics in recent T2V benchmarks, and mainstream video quality methods perform poorly with an average SRCC of 0.454, 0.191, and 0.519, respectively, indicating a sizable gap between current models and human action perception patterns in AIGVs. Our findings underscore the significance of action quality as a unique perspective for studying AIGVs and can catalyze progress towards methods with enhanced capacities for AQA in AIGVs.

The advent of the Internet of Things (IoT) has brought forth an era of unprecedented connectivity, with an estimated 80 billion smart devices expected to be in operation by the end of 2025. These devices facilitate a multitude of smart applications, enhancing the quality of life and efficiency across various domains. Machine Learning (ML) serves as a crucial technology, not only for analyzing IoT-generated data but also for diverse applications within the IoT ecosystem. For instance, ML finds utility in IoT device recognition, anomaly detection, and even in uncovering malicious activities. This paper embarks on a comprehensive exploration of the security threats arising from ML’s integration into various facets of IoT, spanning various attack types including membership inference, adversarial evasion, reconstruction, property inference, model extraction, and poisoning attacks. Unlike previous studies, our work offers a holistic perspective, categorizing threats based on criteria such as adversary models, attack targets, and key security attributes (confidentiality, availability, and integrity). We delve into the underlying techniques of ML attacks in IoT environment, providing a critical evaluation of their mechanisms and impacts. Furthermore, our research thoroughly assesses 65 libraries, both author-contributed and third-party, evaluating their role in safeguarding model and data privacy. We emphasize the availability and usability of these libraries, aiming to arm the community with the necessary tools to bolster their defenses against the evolving threat landscape. Through our comprehensive review and analysis, this paper seeks to contribute to the ongoing discourse on ML-based IoT security, offering valuable insights and practical solutions to secure ML models and data in the rapidly expanding field of artificial intelligence in IoT.

Deep learning-based methods for super-resolution (SR) reconstruction of cardiac magnetic resonance imaging (CMRI) have achieved commendable reconstruction performance owing to the potent learning capability of neural networks. Nonetheless, these methods suffer from performance degradation when handling real-world CMRI images, failing to reconstruct high-fidelity CMRI high-resolution images. This degradation stems from the fact that real-world CMRI images are afflicted with blur and noise, whereas mainstream deep learning-based CMRI SR algorithms are typically trained on images degraded using bicubic methods. To address this problem, we propose a progressive alternate refinement for blind CMRI SR, which implements blind SR reconstruction through progressive alternate refinement optimization of the CMRI image feature extraction process and blur kernel feature extraction process. Moreover, we propose a novel progressive blind SR reconstruction subnetwork, which utilizes the alternate residual attention block (ARAB) to perform deep feature extraction. Meanwhile, we propose an ARAB, which uses channel and pixel attention mechanisms to extract high-frequency features from the extracted CMRI and blur kernel features. Extensive experimental results demonstrate that our proposed alternate refinement for blind CMRI super-resolution outperforms the state-of-the-art SR methods, exhibiting superior reconstruction performance and the ability to reconstruct high-fidelity CMRI images.

Cardiac magnetic resonance imaging (CMRI) can help experts quickly diagnose cardiovascular diseases. Due to the patient's breathing and slight movement during the magnetic resonance imaging scan, the obtained CMRI may be severely blurred, affecting the accuracy of clinical diagnosis. To address this issue, we propose the quadratic conditional diffusion model for blind CMRI super-resolution (DBSR). Specifically, we propose a conditional blur kernel noise predictor, which predicts the blur kernel from low-resolution images by the diffusion model, transforming the unknown blur kernel in low-resolution CMRI into a known one. Meanwhile, we design a novel conditional CMRI noise predictor, which uses the predicted blur kernel as prior knowledge to guide the diffusion model in reconstructing high-resolution CMRI. Furthermore, we propose a cascaded residual attention network feature extractor, which extracts feature information from CMRI low-resolution images for blur kernel prediction and SR reconstruction of CMRI images. Extensive experimental results indicate that our proposed DBSR achieves better blind super-resolution reconstruction results than several state-of-the-art baselines.

Opinion dynamics (OD) studies the members’ opinion formation process to a specific issue in a group interacting environment. The existing literature seldom considers the implicit information of their opinions and neighboring members’ influence during iterations. This article first proposes a method to describe the members’ mental processes of changing opinions based on the support information that consists of the trust relationship among the neighboring members and the difference among the neighboring members’ opinions, and this method is named the support-based method. Then, a convergence condition based on the network structure is given, and an analysis of the convergence of the model is also provided. Further, inspired by the idea of the proportional-integral-derivative (PID) controller, we propose a new method to capture the opinion changes in three areas: 1) the past cumulative performance; 2) the current performance; and 3) the future trend of the performance, and this method is named PID-inspired method. Numerical experiments are provided to validate the effectiveness of the support-based method and the PID-inspired method; specifically, the PID-inspired method has a higher-convergence rate than the support-based method.

This study proposes a novel control scheme for simultaneously tracking and stabilizing nonholonomic wheeled mobile robots (NWMRs) subject to actuator and sensor faults, measurement errors, uncertain dynamics, and time-varying slippage/skid disturbances. To this end, a nonlinear model based on a type-3 (T3) fuzzy logic system (FLS) is developed for NWMR tracking and stabilization. Furthermore, a nonlinear model predictive controller (NMPC) is designed analytically without employing iterative computations, thus achieving fast performance. A new approach of type-3 nonsingleton fuzzification is introduced to handle measurement errors. Additionally, faults in the actuators and sensors are detected by a supervisory scheme and eliminated by a devised compensator. Finally, extensive simulations and experimental validations are conducted to further verify the effectiveness of the proposed scheme, along with a comparative analysis of several benchmarking methods.

Fall detection is of increasing significance in terms of the health monitoring of the elderly and disabled people, as falls may lead to physical injuries or even mental trauma. The existing fall detection methods have achieved impressive performance, but limitations present in operability, interface with public healthcare systems, and other technical issues such as high-power consumption, cost, and reliability. In this article, we present a wearable fall detection system, which is based on a novel multilevel threshold algorithm. The algorithm combines micro-electro-mechanical-systems (MEMS) with narrow band Internet of Things (NB-IoT). The system also includes a user interface for healthcare professionals, developed based on the cloud technology and server-client architecture. For the verification of the algorithm, we recruited 20 volunteers to perform the activities of daily living and falls. The experimental result showed that the proposed algorithm can achieve an accuracy of 94.88%, a sensitivity of 95.25%, and a specificity of 94.5%, suggesting the effectiveness of our system.

Numerous tracking approaches attempt to improve target representation through target-aware or distractor-aware. However, the unbalanced considerations of target or distractor information make it diffcult for these methods to benefit from the two aspects at the same time. In this paper, we propose a target-distractor aware model with discriminative enhancement learning loss to learn target representation, which can better distinguish the target in complex scenes. Firstly, to enlarge the gap between the target and distractor, we design a discriminative enhancement learning loss. By highlighting the hard negatives that are similar to the target and shrinking the easy negatives that are pure background, the features sensitive to the target or distractor representation can be more conveniently mined. On this basis, we further propose a target-distractor aware model. Unlike existing methods of preference target or distractor, we construct the target-specific feature space by activating the target-sensitive and the distractor-silence feature. Therefore, the appearance model can not only represent the target well but also suppress the background distractor. Finally, the target-distractor aware target representation model is integrated with a Siamese matching network for visual tracking for achieving robust and realtime visual tracking. Extensive experiments are performed on eight tracking benchmarks show that the proposed algorithm achieves favorable performance.

In this paper we propose a new induced ordered weighted averaging (IOWA) operator for expert opinions aggregation, namely, the average-induced OWA (AIOWA) operator. The AIOWA operator defines the order-induced variable as the similarity of each individual expert's opinion with respect to the average opinion of the group, as the average opinion is notably an important piece of information of the group opinion and often used as an approximate estimate of the group opinion with equal weights. The new operator facilitates to capture the distribution characteristics of the opinion data with respect to the consensus and constructs a nonlinear aggregation of individual opinions. Further, we extend the new operator to the situation where the experts' opinions are represented by probability density functions (PDFs). Last, we incorporate the entropy-orness optimization model into the proposed aggregation operator. The new operator makes the aggregation process more flexible in terms of application problems. Two case studies are conducted to show the effectiveness of the proposed operators. The result is promising.

Colonoscopy is widely used in the diagnosis and treatment of colorectal diseases due to its minimal invasiveness, convenience and efficiency. However, it has two problems: bowel perforation and looping. In order to overcome these problems, it is necessary to get the information of the force and posture of the distal end of the colonoscope in the colonoscopy procedure. Elsewhere, we have reported an approach to have a sensor on the hose of colonoscope, which is outside the human body, to infer the force information at the distal end which is inside the human body, via a kinetic model. This paper presents a work on developing such a sensor. The goal of this work is to improve the accuracy of the senor while maintaining its low cost.

This paper presents a new under-actuated resilient robot that has the three recovery processes available, as we proposed elsewhere. The new feature with the proposed resilient robot is such that all the recovery strategies can be accomplished in a 2D plane instead of a 3D space, thus reducing the complexity of the recovery process. The robot also has the ability of switching between a fully-actuated robot and an under-actuated robot with the help of an electromagnetic clutch.

In group decision making, it is inevitable that the individual decision maker’s subjectivity is involved, which causes difficulty in reaching a group decision. One of the difficulties is to aggregate a small set of expert opinions with the individual subjectivity or uncertainty modeled with probability theory. This difficult problem is called probability distribution function aggregation (DFA). This paper presents a simple and efficient approach to the DFA problem. The main idea of the proposed approach is that the DFA problem is modeled as a nonlinear function of a set of probability distribution functions, and then a linear feedback iteration scheme is proposed to solve the nonlinear function, leading to a group judgment or decision. Illustration of this new approach is given by a well-known DFA example which was solved with the Delphi method. The DFA problem is a part of the group decision problem. Therefore, the proposed algorithm is also useful to the decision making problem in general. Another contribution of the this paper is the proposed notation of systematically representing the imprecise group decision problem with the classification of imprecise information into three classes, namely incomplete information, vague information, and uncertain information. The particular DFA problem dealt with in this paper is then characterized with this general notation.

In decision making, a group of experts give opinion on an event say X. There is a need to get a group consensus on X. It is usually not possible to have all experts with the same opinion. Therefore, one needs to fuse different opinions into one opinion (i.e., group opinion). The challenge for this task is the situation that the number of experts is too small, as this situation does not justify the use of the average statistics to come up with a group opinion. This paper addresses this challenge. The main idea of the approach to solve this group decision problem is to consider that the group consensus or opinion is a non-linear function of individual opinions and the non-linear function is further represented by a series of iterations to update the weights in a linear function (i.e., the weighted average of individual opinions). An example is given to illustrate the effectiveness of the approach.

The Likert scale is often used in subjective knowledge management (e.g., assessment and decision making) in enterprise systems. The scales typically have 5, 7, or 9 number of rating bars. A controversial issue is: what would be an optimal number of rating bars (5, 7, or 9) for a particular application problem or for all problems? The study reported in this paper addressed this issue. The study particularly restricted to the number of rating bars being 5, 7, and 9 (denoted as S5, S7, S9), as they are commonly used in practice. A cell phone interface design was taken as a test-bed, and twenty participants were involved in the experiment. A new criterion to evaluate a subjective rating scale was developed first and then the experiment was carried out. The study concluded that S7 is the best among the three scales. The contribution of this paper includes: (1) confirming that different numbers of rating bars in a subjective rating scale can have significant effects on the subjective measurement or assessment and (2) providing a new criterion to evaluate a subjective rating scale.

Contemporary information modeling of enterprise systems only focuses on the technical aspect of the systems, though it is known that they are social-technical (socio-tech) systems in essence. In fact, there are many lessons that can be learned from failures in the management of enterprise systems, which range from a small one (e.g., failure to install a printer driver) to a large one (e.g., nuclear power plant post-accident management). This paper, therefore, proposes that the enterprise system should be viewed as a socio-tech system. The paper presents a novel integrated approach to information modeling of socio-tech enterprise systems. In particular, the approach integrates object-orientation, systems-dynamics (as a means to represent high-level dynamics), and aspect-programming. The paper discusses an example to illustrate how the proposed approach works.

Multiple time-course microarray datasets with the same underlying gene network are collected from different experiments. The inference of gene regulatory networks (GRNs) can be improved by integrating these datasets. Microarray data may be contaminated with large errors or outliers, which may affect the inference results. A novel method, Huber group LASSO, is proposed to reconstruct the GRNs from multiple datasets as well as taking the robustness into account. To solve the optimization problem involved in the proposed method, an efficient algorithm which combines the ideas of auxiliary function minimization and block coordinate descent is developed. Simulations and real data applications demonstrate the effectiveness of our method. Results show that the proposed method outperforms the group LASSO method and is able to reconstruct reasonably good GRNs from multiple datasets even the number of genes exceeds the number of observations.

The endoscope system consists of a control hand unit with valves and manoeuvrable bend section at the distal end by turning two knobs from a control hand unit. An accurate kinematic model for the relationships between motion of the distal end and the control unit is essential for endoscopist to control a motion of the tip navigating in the human organ effectively. In this paper we introduce a new method for modeling of kinematics for the distal end of the colonoscope in the use of D-H (Denavit - Hartenberg) parameters when the distal end of the colonoscope is taken as continuum robot, and analyze the kinematic relationship between the motion of the tip of the enodoscope and angular control from the control hand unit. Our kinematical model plays an important role in controlling the motion of the distal end accurately.

Evacuation planning with the contraflow technique is a complex planning problem. The problem is further complicated when more realistic situations such as evacuation priorities and the setup time for the contraflow operation are considered. Such a complex problem has yet to be discussed in the present literature. In this paper, we present a multiple-objective optimization model for this problem and a two-layer algorithm to solve this model. Experiments on three transportation networks with different network scales are presented to show the excellent performance of the proposed model and algorithm.

In this paper, we present a driver-automation system for providing brake assistance to the driver using the concepts of various levels of intervention. The system offers potential for further development and integration into main stream cars using by-wire technology, both from passenger safety and system usability perspectives. The criticality of the situation of a potential crash is estimated using a Bayesian framework from literature which considers not only the vehicle's situational need for braking but also the driver's intent to apply brakes. The novel idea of our work is a well-defined dictionary for critical zone segmentation is incorporated into the system to decide the appropriate intervention level by the automation system for each situation, and appropriate assistance is provided to the driver, in terms of not only communicating auditory messages to the driver but also applying automatic brakes if need be to shift the criticality from a high/very high to a low zone. The second idea of our work is the feedback control of the amount of automatic braking necessary to be applied by the system. Results from sample runs of simulated testing of the system have been reported and future scope of work towards improvement is discussed.

In a companion paper published elsewhere [1], we proposed a design approach based on the general redundancy concept to improve the dynamic performance of a mechanism, especially shaking moment and driving torque, while fulfilling the required task. The approach was based on a partial redundancy function of the servomotor, so the approach is called partial redundancy servomotor (PRSM). In this paper, we apply the PRSM to the path generator problem in robot design, in particular closed-loop multi-degrees of freedom robots or mechanisms. We demonstrate how the path generator design problem is solved and dynamic performance is improved in an integrated manner with the PRSM approach and how mechanism design and robot design are combined to design a better path generator. The contribution of this paper is the proposed PRSM design procedure. The other contribution is an integrated mechanism design and robot design approach that has implication to other general design problems such as function generator and posture generator.

Reconstruction of a biological system from its experimental time series data is a challenging task in systems biology. The S-system which consists of a group of nonlinear ordinary differential equations (ODEs) is an effective model to characterize molecular biological systems and analyze the system dynamics. However, inference of S-systems without the knowledge of system structure is not a trivial task due to its nonlinearity and complexity. In this paper, a pruning separable parameter estimation algorithm (PSPEA) is proposed for inferring S-systems. This novel algorithm combines the separable parameter estimation method (SPEM) and a pruning strategy, which includes adding an l₁ regularization term to the objective function and pruning the solution with a threshold value. Then, this algorithm is combined with the continuous genetic algorithm (CGA) to form a hybrid algorithm that owns the properties of these two combined algorithms. The performance of the pruning strategy in the proposed algorithm is evaluated from two aspects: the parameter estimation error and structure identification accuracy. The results show that the proposed algorithm with the pruning strategy has much lower estimation error and much higher identification accuracy than the existing method.

The trajectory tracking problem of a closed-chain five-bar robot is studied in this paper. Based on an error transformation function and the backstepping technique, an approximation-based tracking algorithm is proposed, which can guarantee the control performance of the robotic system in both the stable and transient phases. In particular, the overshoot, settling time, and final tracking error of the robotic system can be all adjusted by properly setting the parameters in the error transformation function. The radial basis function neural network (RBFNN) is used to compensate the complicated nonlinear terms in the closed-loop dynamics of the robotic system. The approximation error of the RBFNN is only required to be bounded, which simplifies the initial "trail-and-error" configuration of the neural network. Illustrative examples are given to verify the theoretical analysis and illustrate the effectiveness of the proposed algorithm. Finally, it is also shown that the proposed approximation-based controller can be simplified by a smart mechanical design of the closed-chain robot, which demonstrates the promise of the integrated design and control philosophy.

A recurrent neural network is proposed for solving the non-smooth convex optimization problem with the convex inequality and linear equality constraints. Since the objective function and inequality constraints may not be smooth, the Clarke's generalized gradients of the objective function and inequality constraints are employed to describe the dynamics of the proposed neural network. It is proved that the equilibrium point set of the proposed neural network is equivalent to the optimal solution of the original optimization problem by using the Lagrangian saddle-point theorem. Under weak conditions, the proposed neural network is proved to be stable, and the state of the neural network is convergent to one of its equilibrium points. Compared with the existing neural network models for non-smooth optimization problems, the proposed neural network can deal with a larger class of constraints and is not based on the penalty method. Finally, the proposed neural network is used to solve the identification problem of genetic regulatory networks, which can be transformed into a non-smooth convex optimization problem. The simulation results show the satisfactory identification accuracy, which demonstrates the effectiveness and efficiency of the proposed approach.

Reconstruction of a biological system from its experimental time series data is a challenging task in systems biology. The S-system which consists of a group of nonlinear ordinary differential equations is an effective model to characterize molecular biological systems and analyze the system dynamics. However, inference of S-systems without the knowledge of system structure is not a trivial task due to its nonlinearity and complexity. In this paper, a pruning separable parameter estimation algorithm is proposed for inferring S-systems. This novel algorithm combines the separable parameter estimation method and a pruning strategy, which includes adding an ℓ1regularization term to the objective function and pruning the solution with a threshold value. The performance of the pruning strategy in the proposed algorithm is evaluated from two aspects: the parameter estimation error and structure identification accuracy. The proposed algorithm is applied to two S-systems with simulated data. The results show that the proposed algorithm has much lower estimation error and much higher identification accuracy than the existing method.

This paper proposes a dynamic-model-based method for selecting significantly expressed (SE) genes from their time-course expression profiles. A gene is considered to be SE if its time-course expression profile is more likely time-dependent than random. The proposed method describes a time-dependent gene expression profile by a nonzero-order autoregressive (AR) model, and a time-independent gene expression profile by a zero-order AR model. Akaike information criterion (AIC) is used to compare the models and subsequently determine whether a time-course gene expression profile is time-independent or time-dependent. The performance of the proposed method is investigated on both a synthetic dataset and a real-life biological dataset in terms of the false discovery rate (FDR) and the false nondiscovery rate (FNR). The results show that the proposed method is valid for selecting SE genes from their time-course expression profiles.

This paper presents our study on the emergency resource-planning problem, particularly on the development of a new approach to resource planning through contraflow techniques with consideration of the repair of damaged infrastructures. The contraflow technique is aimed at reversing traffic flows in one or more inbound lanes of a divided highway for the outbound direction. As opposed to the current literature, our approach has the following salient points: (1) simultaneous consideration of contraflow and repair of repair of roads; (2) classification of victims in terms of their problems and urgency in sending them to a safe place or place to be treated; and (3) consideration of multiple destinations for victims. A simulated experiment is also described by comparing our approach with some variations of our approach. The experimental results show that our approach can lead to a reduction in evacuation time by more than 50%, as opposed to the original resource operation on the damaged transportation network, and by about 20%, as opposed to the approach with resource replanning (only) on the damaged network. In addition, the multiobjective optimization algorithm to solve our model can be generalized to other network resource-planning problems under infrastructure damage.

A neural-network-based adaptive approach is proposed for the leader-following control of multiagent systems. The neural network is used to approximate the agent's uncertain dynamics, and the approximation error and external disturbances are counteracted by employing the robust signal. When there is no control input constraint, it can be proved that all the following agents can track the leader's time-varying state with the tracking error as small as desired. Compared with the related work in the literature, the uncertainty in the agent's dynamics is taken into account; the leader's state could be time-varying; and the proposed algorithm for each following agent is only dependent on the information of its neighbor agents. Finally, the satisfactory performance of the proposed method is illustrated by simulation examples.

BACKGROUND: One type of DNA microarray experiment is discovery of gene expression patterns for a cell line undergoing a biological process over a series of time points. Two important issues with such an experiment are the number of time points, and the interval between them. In the absence of biological knowledge regarding appropriate values, it is natural to question whether the behaviour of progressively generated data may by itself determine a threshold beyond which further microarray experiments do not contribute to pattern discovery. Additionally, such a threshold implies a minimum number of microarray experiments, which is important given the cost of these experiments. RESULTS: We have developed a method for determining the minimum number of microarray experiments (i.e. time points) for temporal gene expression, assuming that the span between time points is given and the hierarchical clustering technique is used for gene expression pattern discovery. The key idea is a similarity measure for two clusterings which is expressed as a function of the data for progressive time points. While the experiments are underway, this function is evaluated. When the function reaches its maximum, it indicates the set of experiments reach a saturated state. Therefore, further experiments do not contribute to the discrimination of patterns. CONCLUSION: The method has been verified with two previously published gene expression datasets. For both experiments, the number of time points determined with our method is less than in the published experiments. It is noted that the overall approach is applicable to other clustering techniques.

Journal Article On integration of interface design methods: Can debates be resolved? Get access Y. Lin, Y. Lin * a Department of Mechanical and Industrial Engineering, Northeastern University, 360 Huntington Avenue, Boston, MA 02115, USA * Corresponding author. Tel.: +1 617 3738610; fax: +1 617 3732921. E-mail address: [email protected] (Y. Lin). Search for other works by this author on: Oxford Academic Google Scholar W.J. Zhang, W.J. Zhang * b Advanced Engineering Design Laboratory, Department of Mechanical Engineering, The University of Saskatchewan, Saskatoon, Sask., Canada S7N 5A9 * Corresponding author. Tel.: +1 617 3738610; fax: +1 617 3732921. E-mail address: [email protected] (Y. Lin). Search for other works by this author on: Oxford Academic Google Scholar R.J. Koubek, R.J. Koubek c The Harold and Inge Marcus Department of Industrial and Manufacturing Engineering, The Pennsylvania State University, 310 Leonhard Building, University Park, PA 16802, USA Search for other works by this author on: Oxford Academic Google Scholar Ronald R. Mourant Ronald R. Mourant a Department of Mechanical and Industrial Engineering, Northeastern University, 360 Huntington Avenue, Boston, MA 02115, USA Search for other works by this author on: Oxford Academic Google Scholar Interacting with Computers, Volume 18, Issue 4, July 2006, Pages 709–722, https://doi.org/10.1016/j.intcom.2005.11.008 Published: 20 December 2005 Article history Received: 03 November 2004 Revision received: 01 November 2005 Accepted: 01 November 2005 Published: 20 December 2005

Human attention can only be inferred from certain causal clues. Such an inference process is of high uncertainty. Bayesian network (BN) is often used for modeling such a process; specifically different features that represent human attention can be fused to reach a consistent conclusion. Previous studies on BN have little consideration of so-called contextual features. In this paper, we propose a few contextual features related to human attention. A novel BN model is then formulated which combines both the contextual features and their corresponding observable behavioral features. At the end, an example is used to illustrate the potential use of the new BN model for human-machine interface design.

Microarray technologies are emerging as a promising tool for genomic studies. A huge body of time-course gene expression data has been and will continuously be produced by microarray experiments. Such gene expression data contains important information and has been proven useful in medical diagnosis, treatment, and drug design. The challenge now is how to analyze such data to obtain the inherent information. Cluster analysis has played an important role in analyzing time-course gene expression data. However, most clustering techniques do not take into consideration the inherent time dependence (dynamics) of time-course gene expression patterns. Accounting for the inherent dynamics of such data in cluster analysis should lead to higher quality clustering. This paper presents a model-based clustering method for time-course gene expression data. The presented method uses Markov chain models (MCMs) to account for the inherent dynamics of time-course gene expression patterns and assumes that expression patterns in the same cluster were generated by the same MCM. For the given number of clusters, the presented method computes cluster models using an EM algorithm and an assignment of genes to these models that maximizes their posterior probabilities. Further, this study employs the average adjusted Rand index (AARI) to evaluate the quality of clustering. The improved performance of the presented method is demonstrated by comparing to the k-means method on a publicly available dataset.

In general, evaluation of human–machine interface design remains a challenging task. Specifically, there remains a lack of method for tracking effective human operator's attention. This paper presents a study aimed at devising such a method. This method is based on a combination of operators' eye movement and hand movement behaviors. The eye movement reflects the operators' cognitive process and attention allocation, while the hand movement reflects the operators' physical action, which is the result of a cognitive process. Effectiveness of that piece of cognition (eye movement) can therefore be evaluated based on the result of an action (hand movement). The said measure, which may be called the hand–eye measure, is examined for its sensitivity to a good or poor operation behavior and patterns that are further correlated to the operator's behavior and performance. At present, the patterns across the whole operation period are explored. A reference system is employed to validate the hand–eye measure.

In order to sequence a target DNA, it is first cleaved into many shorter overlapping fragments by chemical or physical techniques. The nucleotide sequence of each fragment is then determined (read) by established methods. The set of all read fragments which cover the target DNA sequence is called its spectrum. It is believed that the shortest superstring of a spectrum is the best candidate for the target DNA sequence. The general problem of finding the shortest superstring for any given set of strings s is NP-hard. Fortunately, the biological instance of this problem is easier. It is not likely that two read fragments, each consisting of several hundred letters, which come from consecutive locations on the target DNA sequence have an overlap of only a few letters; typically, the overlap will be longer. Thus one may reasonably assume that two strings in the spectrum have significant overlap (connectivity) if they come from consecutive locations on the target DNA sequence. A class of important instances satisfying this assumption are those whose spectra are from DNA microarrays. This assumption allows us to claim and show the following: if the spectrum S of a target DNA sequence is substring-free and connected at level t, and the target DNA sequence has no repeats of size t or larger, then there exists an algorithm to reconstruct the target DNA sequence in the linear time O(|S|) after an overlap graph of the spectrum is built.

Gene expression profiles obtained from time-series microarray experiments can reveal important information about biological processes. However, conducting such experiments is costly and time consuming. The cost and time required are linearly proportional to sample size. Therefore, it is worthwhile to provide a way to determine the minimal number of samples or trials required in a microarray experiment. One of the uses of microarray hybridization experiments is to group together genes with similar patterns of the expression using clustering techniques. In this paper, the k-means clustering technique is used. The basic idea of our approach is an incremental process in which testing, analysis and evaluation are integrated and iterated. The process is terminated when the evaluation of the results of two consecutive experiments shows they are sufficiently close. Two measures of "closeness" are proposed and two real microarray datasets are used to validate our approach. The results show that the sample size required to cluster genes in these two datasets can be reduced; i.e. the same results can be achieved with less cost. The approach can be used with other clustering techniques as well.

This research treats a design for reconfigurable robotic systems with large variations in configurations. To evaluate system adaptability, we define the configuration space to be the set of all feasible configuration variations of the robotic system. We define the volume of the configuration space expressed in terms of physical structures to be a measure of system reconfigurability and the volume of the configuration space expressed in terms of Denevit-Hartenberg notation to be a measure of system adaptability. We develop an evaluation method to determine the architecture of reconfigurable robotic systems with high adaptability. A case study is presented to demonstrate that a reconfigurable robotic system with high reconfigurability may not have high adaptability. Finally, we describe how to achieve task-oriented configuration design of reconfigurable robotic systems.

Evaluation of human-machine interface design remains a challenging task. This paper presents a study on a more objective evaluation technique based on the combination of operators' eye movement and hand movement behaviors. The eye movement reflects the operators' cognitive process and attention allocation, and the hand movement reflects the operators' physical hand action. Combination of these two kinds of behaviors may provide an important measuring technique to evaluate different human-machine interfaces and may further give more detailed information about the uses of the information displayed. The experiment was conducted to develop this new technique. The result of the study is promising.

In comparison with dedicated robot systems, the main goal of modular robot systems is to achieve system adaptability by providing various modular configuration variations to meet possible task requirements. System architecture determines the system configuration variations, as the architecture specifies primary building blocks and the types of ways they are connected. In order to make systems more adaptive, configuration variations are expected to be as many as possible subject to the constraints of machining manufacturing applications. This paper reported briefly our recent research progresses on modular robot system architecture, including: (1) a proposed strategy to achieve high system adaptability; (2) a systematic method to develop modular system architecture; (3) the general representation of modular robot configurations.

The control of a dynamic system with multiple degrees-of-freedom (DOF) is far simpler if the system is uncoupled. The property of an uncoupled system can be achieved with careful design of mechanical structures in the case of conventional mechanisms. The study reported in this paper will show via experiment the uncoupling property in a compliant mechanism, which is driven by three PZT actuators. This observation has the significance to motivate study on a new methodology for designing uncoupled multi DOF compliant mechanisms.

In this paper, a novel evolutionary PD (EPD) control to improve the tracking performance is proposed and applied to the trajectory tracking of a closed-loop robot manipulator. The EPD control can incorporate the dynamic information of manipulator in a very plain way without requiring the knowledge of the robot dynamics, and it is simple and effective for the trajectory tracking. Comparison of the EPD control with some other PD-based controls for several different structures of manipulators is made. Simulation study demonstrates that the EPD control is promising in robot manipulator applications for trajectory tracking compared with the PD/NPD controls.

Visual servo control is needed for realizing automatic bio-micromanipulation and increasing the accuracy of micromanipulator. A dual-hand micromanipulation system with micro-visual-servo was developed for automating cell manipulation in biotechnology. This paper presents a complete solution for micro-visual-servo of the system, involving micro-visual-servo architecture, control law, modeling of image Jacobian and recognition algorithms of micro objects. The experimental results of micro-circle trajectory tracking and automatic transgenic operation verify the effectiveness of the micro-visual-servo solution.

This paper presents a study of examining nonlinear PD (NPD) control of multi-degree-of-freedom parallel manipulator systems for a generic task, i.e., trajectory tracking. The motivation of this study is the well-known observation that NPD control method can offer a means to improve the performance of plant systems. This study is also to examine how the mechanical structure of the manipulator affects dynamic performance. The design of mechanical structure follows the design-for-control (DFC) principle, and in particular it renders to a full force balanced mechanism. Simulation studies confirm that the concurrent consideration of mechanical structure design and NPD control can obtain good trajectory tracking performance for the parallel manipulators.

In this article, we focus on the issues of fuzzy data dependencies. After introducing the notion of semantic equivalence degree, fuzzy functional and multivalued dependencies are defined. A set of sound and complete inference rules, similar to Armstrong's axioms for classic cases, for fuzzy functional dependencies (FFDs) and fuzzy multivalued dependencies (FMVDs) are proposed. The strategies and approaches for compressing fuzzy values by FFDs and FMVDs are investigated. By such processing, the unnecessary elements are eliminated from a fuzzy value and its range is compressed. © 2002 Wiley Periodicals, Inc.

Based on the semantic equivalence degree the formal definitions of fuzzy functional dependencies (FFDs) and fuzzy multivalued dependencies (FMVDs) are first introduced to the fuzzy relational databases, where fuzziness of data appears in attribute values in the form of possibility attributions, as well as resemblance relations in attribute domain elements, called extended possibility-based fuzzy relational databases. A set of inference rules for FFDs and FMVDs is then proposed. It is shown that FFDs and FMVDs are consistent and the inference rules are sound and complete, just as Armstrong's axioms for classic cases. © 2002 Wiley Periodicals, Inc.

Entity-relationship–extended entity-relationship models play a crucial role in the conceptual design of relational databases as well as object-oriented databases. Recently, several approaches have been proposed to enhance object-oriented databases (OODBs) using fuzzy set theory. In this paper, we introduce a fuzzy extended entity-relationship model to cope with imperfect as well as complex objects in the real world at a conceptual level. In particular, we provide the formal approach to mapping a fuzzy extended entity-relationship model to a fuzzy object-oriented database schema. © 2001 John Wiley & Sons, Inc.

Fuzzy conceptual data modeling is concentrated on in this paper. Based on possibility theory, A conceptual data model IFO is extended. Different levels of fuzziness are introduced and the corresponding graphical representations are given. IFO data model is this extended to fuzzy IFO data model, denoted IF/sub 2/O in the paper. Attention is paid to the fuzzification of objects and relationships, specially on that of ISA relationships.

In this paper, we propose notions of equivalence and inclusion of fuzzy data in relational databases for measuring their semantic relationship. The fuzziness of data appears in attribute values in forms of possibility distribution as well as resemblance relations in attribute domain elements. An approach for evaluating semantic measures is presented. With the proposal, one can remove fuzzy data redundancy and define fuzzy functional dependency. © 2000 John Wiley & Sons, Inc.