The cluster validity index plays an important role in most clustering algorithm based natural computations. So far, four typical cluster validity indexes have been proposed for clustering data with ...different structures, including the Euclid distance based Pakhira–Bandyopadhyay–Maulik index, the kernel function induced Chou–Su measure, the point symmetry distance based index and the manifold distance (MD) induced index. However, there is no detailed comparison made among these indexes. This paper compares these four cluster validity indexes by using a simple clustering technique based on particle swarm optimization (PSO). Extensive experiments on a large number of artificial synthesized data sets and UC Irvine data sets, texture images and synthetic-aperture radar images are performed in order to make a comprehensive comparison. Experimental results show that the PSO-based clustering algorithm using the MD induced index has a good performance on most of the data sets.
With the rapid development of the Internet-of-Things (IoT) enabled healthcare, the coexistence of real-time applications (RTA) and non-RTA is urgently needed to be sup-ported as healthcare often ...involves various applications. Different techniques toward this goal have been developed in wired and cellular networks, while limited efforts are dedicated to Wi-Fi networks. To address this issue, we propose a hybrid channel access by admission and contention (HCAAC) scheme in this paper to achieve the coexistence of RTA and non-RTA while optimizing the delay performance of RTA in healthcare. With this scheme, the access point can schedule the transmission of RTA packets and temporarily interrupt the transmission procedure of non-RTA packets to guarantee a quick channel access for RTA packets. Moreover, we analyze the performance of RTA packets and illustrate how to tune the backoff parameters to minimize the delay performance of RTA. It is revealed that the optimal backoff parameters only depend on the number of stations and the packet input rate of RTA packets. Simulations show that with the proposed HCAAC scheme, the delay performance of RTA can achieve a dramatic improvement, while the performance of non-RTA does not deteriorate, which sheds significant light on the design of the IoT-Health infrastructure.
Cement was used in oil industry to fix well. After hydration of cement, a porous material with overbased pore solution will be formed. Passivation analysis will be conducted on the passivation of the ...outer wall of downhole P110 casing steel under overbased conditions. Due to the difficulty of obtaining cement pore solution, two kinds of simulated concrete pore solutions (SP solution, CF solution) were used to carry out experiments. The different properties of passive film in two different solutions were obtained, which provided reliable data to support for the research of passive film properties of casing steel. Therefore, the electrochemical properties were characterized by electrochemical impedance spectroscopy (EIS), polarization curves method and Mott-Schottky curves method during the formation of the passive film. Moreover, X-ray photoelectron spectroscopy (XPS) was measured to qualitatively analyze the composition of the passive film on the casing surface, and scanning electron microscope (SEM) was used to observe surface morphology of the P110 casing steel. The result showed that the passive film was enhanced with time increasing and the time for complete passivation of P110 steel in two simulated concrete pore solutions was different, requiring longer passivation in CF solution. The passive film in the CF solution had a larger film resistance and the film layer was more stable. The semiconductor characteristics of the passive film were n-type and the donor density of the passive film in CF solution was lower than that of the SP solution. The passive film formed in two simulated concrete pore solutions was all Fe oxides, but not completely the same. Also the steady-state passive film formed in the two solutions had a different microscopic morphology.
•Passivation characteristics of P110 casing in simulated concrete pore solution were studied. Two solutions were used.•A simulated pore solution was probably approaching the true concrete pore solution from pH and solution ion components.•The properties of passive film were obtained, which provided reliable data to support casing passivation properties research.
Humans can retain old knowledge while learning new information, but Large Language Models (LLMs) often suffer from catastrophic forgetting when post-pretrained or supervised fine-tuned (SFT) on ...domain-specific data. Moreover, for Multimodal Large Language Models (MLLMs) which are composed of the LLM base and visual projector (e.g. LLaVA), a significant decline in performance on language benchmarks was observed compared to their single-modality counterparts. To address these challenges, we introduce a novel model-agnostic self-decompression method, Tree Generation (TG), that decompresses knowledge within LLMs into the training corpus. This paper focuses on TG-SFT, which can synthetically generate SFT data for the instruction tuning steps. By incorporating the dumped corpus during SFT for MLLMs, we significantly reduce the forgetting problem.
Most of clustering algorithms based on natural computation aim to find the proper partition of data to be processed by optimizing certain criteria, so–called as cluster validity index, which must be ...effective and can reflect a similarity measure among objects properly. Up to now, four typical cluster validity indices such as Euclid distance-based PBM index, the kernel function induced CS measure, Point Symmetry (PS) distance-based index, Manifold Distance (MD) induced index have been proposed. But, there is not a detailed comparison among these indexes. In this paper, we design a particle swarm optimization based clustering algorithm, in which, four different cluster validity index above mentioned are used as the fitness of a particle respectively. By applying the proposed algorithm to a number of artificial synthesized data and UCI data, the performance of different validity indices are compared in terms of clustering accuracy and robustness at length.
Event extraction is an important work of medical text processing. According to the complex characteristics of medical text annotation, we use the end-to-end event extraction model to enhance the ...output formatting information of events. Through pre training and fine-tuning, we can extract the attributes of the four dimensions of medical text: anatomical position, subject word, description word and occurrence state. On the test set, the accuracy rate was 0.4511, the recall rate was 0.3928, and the F1 value was 0.42. The method of this model is simple, and it has won the second place in the task of mining clinical discovery events (task2) in the Chinese electronic medical record of the seventh China health information processing Conference (chip2021).
Trajectory planning and coordination for connected and automated vehicles (CAVs) have been studied at isolated ``signal-free'' intersections and in ``signal-free'' corridors under the fully CAV ...environment in the literature. Most of the existing studies are based on the definition of approaching and exit lanes. The route a vehicle takes to pass through an intersection is determined from its movement. That is, only the origin and destination arms are included. This study proposes a mixed-integer linear programming (MILP) model to optimize vehicle trajectories at an isolated ``signal-free'' intersection without lane allocation, which is denoted as ``lane-allocation-free'' (LAF) control. Each lane can be used as both approaching and exit lanes for all vehicle movements including left-turn, through, and right-turn. A vehicle can take a flexible route by way of multiple arms to pass through the intersection. In this way, the spatial-temporal resources are expected to be fully utilized. The interactions between vehicle trajectories are modeled explicitly at the microscopic level. Vehicle routes and trajectories (i.e., car-following and lane-changing behaviors) at the intersection are optimized in one unified framework for system optimality in terms of total vehicle delay. Considering varying traffic conditions, the planning horizon is adaptively adjusted in the implementation procedure of the proposed model to make a balance between solution feasibility and computational burden. Numerical studies validate the advantages of the proposed LAF control in terms of both vehicle delay and throughput with different demand structures and temporal safety gaps.
Relay protection systems in the power grid are individually modeling protection devices based on their respective operational requirements. However, this approach leads to issues such as redundant ...modeling, independent operation of protection systems, data silos, and challenges in interacting with other business systems. To enhance the level of integrated operation and management, as well as the informatization, automation, and interactivity of the power grid dispatching, there is an urgent need to research the construction method of a relay protection device model center. This research aims to integrate and share comprehensive models and data elements of protection devices distributed across different systems, address the problem of independent maintenance of models and parameters in various systems, improve workforce efficiency, and contribute to the development of modern power systems.
The powerful expression and learning ability of the machine learning model make it possible to become a surrogate model of a physical system. However, the embedding of physical prior into the machine ...learning model remains a challenging task. Recently, the physical informed neural network (PINN) emerged as an alternative that transfers the constraints of physical governing equations to a loss function of the neural networks, and then the surrogate model enabled the capability of expressing the physical law of the governing equations. In this study, PINN is introduced in the field of structural dynamics to construct a feedforward solution framework for the second-order ordinary differential equations. Leveraging the interpretability of the physical loss constructed with the governing equation, the proposed framework can enforce the predicted value of the neural network convergent to the real one of the governing equation, and thus enhance the generalization capability. The validity of the proposed framework is verified with the vibration analysis of a single-degree-of-freedom (SDOF) system.
Conventional heterogeneous-traffic scheduling schemes utilize zero-delay constraint for real-time services, which aims to minimize the average packet delay among real-time users. However, in light or ...moderate load networks this strategy is unnecessary and leads to low data throughput for non-real-time users. In this paper, we propose a heuristic scheduling scheme to solve this problem. The scheme measures and assigns scheduling priorities to both real-time and non-real-time users, and schedules the radio resources for the two user classes simultaneously. Simulation results show that the proposed scheme efficiently handles the heterogeneous-traffic scheduling with diverse QoS requirements and alleviates the unfairness between real-time and non-real-time services under various traffic loads.