Search

Gastrointestinal stromal tumor (GIST) is the most common malignant tumor originating from interstitial cells in the gastrointestinal tract. Different grades require various surgical interventions and adjuvant treatments, which are closely linked to the patient’s prognosis. The current clinical risk stratification method relies heavily on the identification and counting of mitotic figures, which serve as important criteria. However, manual evaluation of pathological slides in clinical practice is often limited by the shortage of experienced clinicians and the subjectivity in interpreting results. Therefore, in this paper, we propose an enhanced YOLOv8 network framework for the automatic detection of mitotic cells in GIST. We substituted the backbone network with VanillaNet, known for its simplified model complexity in feature extraction. This change facilitated the identification of specific targets and improved network performance. Additionally, we introduced the Advanced Feature Pyramid Network (AFPN) to further enhance the model’s accuracy. Experimental results show that the proposed model achieved an accuracy of 0.816, a recall rate of 0.858, and an F1-score of 0.837 on the test dataset. It demonstrates superior efficacy in identifying mitotic cells, outperforming the original YOLOv8 model in overall performance. This augmented model has the potential to significantly reduce reading time while ensuring consistent diagnostic results, thereby greatly improving diagnostic efficiency. Future large-scale validation is necessary for the clinical adoption of this model.

In this paper, the consensus problem of heterogeneous multi-agent systems under directed topology is investigated. Specifically, this system is composed of three classes of agents respectively described by first-order, second-order and third-order integrator dynamics. By the aid of linear filter, graph theory and matrix theory, the consensus problem is realized based on the two proposed consensus protocols. Moreover, group consensus can also be solved by adjusting parameters. Finally, some examples were presented to illustrate the theoretical results. Our study is expected to establish a more realistic model and provide a method to solve the consensus problem of heterogeneous multi-agent systems in more complex situations.

Landslide risk assessment is an important component of the landslide research field. For the problem of landslide assessment indicators, we utilize the TOPSIS-Entropy method to assess the risk situation of landslide occurrences, which is easy to obtain directly from sensor data. By using the TOPSIS-Entropy method in landslide datasets, the instability margins of landslide risk are obtained, reflecting the current instability probability of the landslide body. For the landslide prediction issue, deep neural networks are used to predict the corresponding landslide instability margins (LIMs). Attention mechanism-based (Attn) temporal convolutional networks (TCN) connected with recurrent neural network (RNN) models for landslide risk prediction are proposed, including TCN-Attn-RNN and RNN-Attn-TCN, which both use an encoder–decoder architecture. The encoder in the first model uses the temporal convolutional network (TCN), and the decoder uses a neural network with an RNN architecture, including long short-term memory (LSTM) networks, gated recurrent units (GRUs), and their derivative algorithms. In the second model, the encoder uses a neural network with an RNN architecture, and the decoder uses a TCN. Combining the TOPSIS-Entropy method with TCN-Attn-RNN and RNN-Attn-TCN, reliable prediction models of landslide risk are proposed. By building a landslide simulation platform, we obtained landslide data. Compared to their counterparts, the proposed prediction models of landslide risk instability margins have better predictive effects.

To overcome the problems of wind power forecast for the current deterministic wind power turbine output model cannot accurately describe the statistical characterization of wind turbine output, this article proposes a novel wind power stochastic cloud model. There are three steps to build this model. Firstly, it is necessary to analyze the power data and to filter out the disturbed data by utilizing the improved Bin method and data fitting. Secondly, it is available to obtain respectively two groups of the expectation, entropy and hyper entropy of the waist and upper data of stochastic cloud model by the known and unknown membership of backward cloud generators. Finally, the wind-speed data can be transformed into a stochastic cloud model, which is composed of X condition cloud generator and the positive cloud generator component. In short, the comparative data of the wind power cloud droplets and the measured data of wind power show that the line correlation coefficient of the wind power frequency of the proposed model reaches to 0.8868, which could simulate the statistical characterization of wind turbine output effectively.

In air cushion furnace, the floating height is a key process parameter which greatly affects the quality and production efficiency of high quality metal strips. However, the floating height is hard to be collected in the complex and abominable industry environment. Furthermore, due to the flow field characteristics, some important process variables are difficult to accurately calculate by traditional mechanism modeling methods. In order to accurately predict the floating height, firstly, a low discrepancy heuristic evolution ELM and ground effect theory based serial hybrid soft sensor model is proposed, which constituted by a mechanism model and two data driven models. Secondly, based on the force equilibrium equation and ground effect theory, the mechanism model is constructed, which describes the relationship between the floating height and the process variables including the jet impact angle. Thirdly, a low discrepancy heuristic evolution ELM is proposed as the data driven model to predict the jet impinging angle. In the data driven model, the novel dual mutation strategies collaboration differential evolution is proposed to guarantee the low discrepancy and physical applicability of data driven model. The effectiveness of the proposed method was validated on the self-developed air cushion experiment platform and got desirable experimental results. The research lays an important foundation for the successful implementation of monitoring and control of the strip floating process.

Functionally graded materials (FGMs) used in electrical insulation have spatially inhomogeneous dielectric properties (i.e., permittivity or conductivity), which can be applied to relieve localized electric field (E-field) intensification and improve insulation performance. However, previous research shows some limitations in inadequate considerations on the material feasibility, and insufficient universality on material grading type and voltage form. In this study, a material study of silicone rubber (SiR) nanocomposites containing carbon nanotubes (CNTs) is conducted to determine the practical variation range of dielectric properties (both permittivity and conductivity) in joint insulation materials. Then, the optimal design of both multilayer and pointwise FGM joint insulation is investigated under both AC and DC voltage, in which the lower and upper limits of permittivity and conductivity were derived from the experimental results. Experimental results on SiR/CNT nanocomposites indicate that low-amount doping of the CNTs (0-0.5% wt%) can effectively increase the permittivity and conductivity of joint insulation materials. The successive simulation study indicates that compared to uniform joints, cable joints employing optimally designed FGM insulation show a considerable increase in the E-field utilization factor (from 0.08-0.17 to 0.23-0.56), indicating elevated E-field uniformity. Finally, the optimal range of CNT doping ratios is determined to be 0-0.3 wt% from both experimental and simulation results. This study systematically verifies the applicability of FGMs in enhancing the performance of power cable accessories, which can show some guidance to the design and fabrication of advanced power cable systems.

To address the problems of edge blur and weak detail resolution when fusing infrared and visible images with traditional methods, a novel image fusion approach based on fast super-resolution convolutional neural network and anisotropic diffusion is proposed. The proposed method first employs super-resolution reconstruction based on fast convolutional neural networks to get high-resolution infrared images. Second, the visible and high-resolution infrared images are anisotropically diffused to obtain the corresponding base layers and detail layers. Next, the fusion of the detail layer is performed through Karhunen-Loeve transform, and an adaptive saliency module is constructed to fuse the base layer. Finally, the fusion result is obtained by applying linear reconstruction on the fused detail layer and base layer. Compared with other algorithms, the experimental results show that the proposed algorithm not only has better objective evaluation indexes but also can better retain the details of the original image.

It is of great significance to promote energy revolution in China due to the serious carbon emission problem. The IES (Integrated Energy System), based on an optimized scheduling of multi-energy, such as electricity and gas, heat and cold, could break through the limitations of technical, market and management constraints in traditional energy system. But, how to operate an integrated energy system in a cleaner way and take the economic issues into consideration is always a hot research topic at home and abroad. This paper presents a new optimization scheduling method, which takes the environment and economy into consideration, and the operation results under different scenarios are compared and analyzed based on Min-Max Scaling method. The optimization algorithm is developed in MATLAB and the solver is MILP (Mixed Integer Linear Programming). A case analysis based on the real-data in this paper shows that the joint optimization method can achieve a balanced decision-making results by taking environmental protection and economic objectives into account. Besides, it makes the operation strategy of each equipment unit in IES more scientific and reasonable.

In the RFID system, the tag collision problem seriously affects the efficiency of tag identification. Among the anti-collision algorithms, tree-based anti-collision algorithms are popular for the reason that they can ensure that the tags can theoretically 100% be identified by readers. As multi-reader scenarios are more and more widely used in complex internet of things environments, there are more collision slots and idle slots in traditional anti-collision algorithms, which affects the efficiency of the algorithm. We propose a tree-based multi-reader interactive anti-collision algorithm (TMIA) for multi-reader tag identification scenarios to solve the problems above. Readers optimize the broadcast prefix sequence by sharing the broadcast results. The proposed algorithm works in two phases: In the first phase, the reader selects a suitable broadcast prefix by the multi-reader inverse probability function (MIPF) to reduce the initial redundant collision in tag identification. In the second phase, the priority of the broadcast prefix is adjusted through the information exchange between readers, the readers thus avoid broadcasting a large number of invalid prefixes. Theoretical analysis and simulation results show that TMIA has a lower total number of slots and better system efficiency than existing tree-based algorithms. TMIA also greatly reduce the number of collision slots.

The strip floating height is a key factor affecting production efficiency and quality of the air cushion furnace. At present, the air cushion furnace with hybrid nozzles is the most typical heating and drying equipment. In order to predict the floating height of the strip in this equipment, a hard-division and multi-model based floating height prediction method is proposed. In hard division method, the process is divided into several stable and vibration stages. On the one hand, time interval based novel density clustering algorithm is proposed so as to avoid the wrong division caused by noise at hard division stage. On the other hand, covariance matrices based local density is presented to better capture dynamic characteristics of the process. In the multi-model stage, a hybrid prediction model under stable state and XGBoost-based model under vibration state are established to predict the strip floating height. The hybrid prediction model is composed of mechanism model and data driven model. The mechanism model is proposed by combining the force balance equation and inviscid theory which can predict the major information of the floating height and the data driven model compensates the error of the mechanism model. A mount of experiments have been carried out on the existing air cushion experimental platform and show desirable prediction effect.

For electrified transportation (eTransportation) systems, multi-phase motors can provide higher performance and reliability than three-phase ones, but also bring more challenges in their optimal design and control. In this article, a set of high reliable electric drive system based on dual three-phase permanent magnet synchronous motor (DTP PMSM) is developed for auxiliary systems in eTransportation field. A digital collaborative develop process is proposed with the support of multiple software tools. Design, manufacture, and bench testing stages of the DTP PMSM, the two-level six-phase inverter, and the control algorithm are efficiently incorporated. A prototype of the multi-phase electric drive system is fabricated and tested. Comparison of the simulation analysis and experimental results confirms the effectiveness of the collaborative develop progress. Control algorithms based on dual d-q model and vector space decomposition model are both verified and compared via the bench test. Operation mode switching from six-phase mode to three-phase mode is also realized with the prototype system, verifying its capability in fault-tolerant and potential in efficiency optimizing.

Hydraulic systems have been frequently used in deep-sea equipment because of their renowned long service life, stable and reliable performance. However, impurities contained in hydraulic oil, such as solid particles, gas and water, would jeopardize work efficiency of deep-sea hydraulic systems, and in some extreme cases even cause failure of the whole system, resulting in breakdown of crucial deep-sea equipment. Therefore, this paper aims to present a device, multifunctional oil-injection equipment (MOIE), expected to be able to purify hydraulic oil in deep-sea hydraulic systems. Its major functions are to absorb oil, remove impurities and fill oil, among which the removal of water and gas, i.e. dewatering and degassing, is of significance. Theoretical analysis shows that the paper oil filter is able to remove the solid particles in hydraulic oil, and degassing and dewatering of hydraulic oil could be achieved through vacuum filtration and vacuum heating in high-temperature and low-pressure environment. The prototype of the MOIE is designed and manufactured. The results from laboratory experiments indicate that this equipment can effectively remove solid particles, gas and water from hydraulic oil. This study ensures the stability, safety and reliability of the deep-sea hydraulic system by improving the quality of hydraulic oil.

To reduce the secrecy loss due to the correlation between main and wiretap channels, this paper introduces a cooperative jamming relay to degrade the reception at the eavesdropper. We consider slow-fading multiple-input-single-output wiretap channels with a passive single-antenna eavesdropper, where full information for the channels to the legitimate receiver and statistical information for the channels to the eavesdropper is available. By deploying the cooperative jamming relay reasonably, the correlation between the channels from the introduced relay to the legitimate receiver and the eavesdropper can be much below than that between the main and wiretap channels. Thus, the relay can interfere with the eavesdropper more effectively than the traditional scheme of artificial noise-aided beamforming at the transmitter. The simulation results demonstrate that the secrecy outage probability under the transmit power and target secrecy rate constraints is reduced substantially.

In Time Domain Duplex (TDD) massive MIMO systems, multi-group multi-casting becomes a promising technology since it supports services of mass content distribution. Based on the nature of transmitting common message to groups of users simultaneously, there exists a rich literature discussing the resource allocation under various constraints. However, the practical acquisition of CSI has not been fully explored when the number of multi-groups is large and the band is narrow. The insufficient sounding reference signal resources lead to the limited Channel Estimation Capacity (CEC). Under this case, even with Multi-User (MU) channel estimation techniques, some users still cannot be estimated in-timely, which introduces degradation. Aiming at this problem, in this paper we provide a preliminary exploration on CEC enhancement. Based on Denoising Convolutional Neuron Network (DnCNN), which is recently proposed and has succeeded in image denoising, we propose MU-DnCNN Channel Estimation (M-DnCNN CE). M-DnCNN CE includes three parts. First, we modify the utilization of SRS sequences. Then we establish the feature maps and propose M-DnCNN to denoise the signals. Finally, a matched channel restoration method is provided. The practical 3-D MIMO channel model is utilized to evaluate the performance. Compared with DFT-based and conjugated separation methods, results show that the performance of M-DnCNN CE is robust and superior, and the CEC is remarkably improved on the premise of satisfying latency constraint.

With the popularity of location-based services in the field of mobile network applications, users enjoy the convenience on one side, they may face the risk of privacy disclosure on the other side. Attackers can easily dig out the user's home address, occupation, and other personal privacy from the data of location-based services. For the problem of user location privacy disclosure based on semantic query of point of interest (POI) in the road network environment, the previous research seldom paid attention to the temporal association relationship between the query semantic and the user's location, as well, seldom considered whether the constructed anonymity sets of fake-locations can fulfill the property of reciprocity. Therefore, in this paper, we propose a location privacy protection algorithm T-SR based on POI query. The algorithm can be divided into three steps. First, the whole road network is divided into multiple areas based on the Voronoi structure, so that the areas are independent and non-overlapping, and the road grid that contains user's real location will be located according to the level of privacy protection H. Second, the temporal association between the POI semantics are mined from the real check-in data based on Gaussian distribution σ rule, and the POIs which have weak association with the POI of user's location will be filtered to resist the temporal association attack. Third, the POI semantics within the grid will be split into several buckets according to query times record, anonymity degree k, and semantic degree l, then the dummy locations will be selected from various kinds of POIs of the bucket where the user's location is. The resulted anonymity set can defend against replay attack, inference attack, and temporal association attack. The theoretical analysis and experimental evaluation prove that the proposed solution can protect user's location privacy efficiently and effectively.

Researches on computer games for Go, Chess, and Japanese Chess stand out as one of the notable landmarks in the progress of artificial intelligence. AlphaGo, AlphaGo Zero, and AlphaZero algorithms, which are called AlphaZero style (AZ-style) algorithms in some literature [1], have achieved superhuman performance by using deep reinforcement learning (DRL). However, the unavailability of training details, expensive equipment used for model training, and the low evaluation accuracy resulted by slow self-play training without expensive computing equipment in practical applications have been the defects of AZ-style algorithms. To solve the problems to a certain extent, the paper proposes an improved online sequential extreme learning machine (IOS-ELM), a new evaluation method, to evaluate chess board positions for AZ-style algortihm. Firstly, the theoretical principles of IOS-ELM is given. Secondly, the study considers Gomoku as the application object and uses IOS-ELM as the evaluation method for AZ-style's board positions to discuss the loss in the training process and hyperparameters affecting performance in detail. Under the same experimental conditions, the proposed method reduces the training parameters by 14 times, training time to 15%, and error of evaluation by 13% compared with the board evaluation network used in original AZ-style algorithms.

Accurate short-term prediction of the natural gas load is of great significance to the operation and allocation of the pipeline network. Because the short-term natural gas load has obvious nonlinearity and randomness, the traditional regression model is difficult to predict accurately. Therefore, this paper proposes a hybrid prediction model that integrates an improved whale swarm algorithm (IWOA) and relevance vector machine (RVM). In addition, empirical mode decomposition (EMD), approximate entropy (ApEn), and C-C method are introduced to aid the calculation. In this paper, the IWOA is used to test the four functions and compared with the other five algorithms. The results show that the convergence accuracy and convergence speed of the new algorithm are higher than other algorithms, indicating that it has better global optimization ability. Second, the IWOA-RVM model is used to predict the supply data of two natural gas stations in Anhui Province, China. The prediction results are compared with the five algorithms including RBFNN, GRNN, ELMANNN, LSSVM, and SMOSVM. The results show that: 1) through the test of four functions, IWOA has better ability to jump out of local optimum, has higher optimization performance, and the calculation speed is at a medium level and 2) compared with other models, the IOWA-RVM model has higher prediction accuracy when the amount of data is larger or smaller, but the calculation time is relatively long, but the calculation time is acceptable in engineering.

The prediction method plays crucial roles in the accurate prediction of rockfall runout range which could improve the protection of endangered residential areas and infrastructure. Recently, the Knearest neighbor (KNN) algorithm, one of many machine learning techniques, showed good performance in pattern classification. Therefore, the aim of this study was to use the K-nearest neighbor (KNN) algorithm to predict the rockfall runout range which is classified into different subintervals according to the distance from the slope toe. First, we proposed the prediction model of the rockfall runout range based on our improved KNN algorithm which could better offer robustness against different choices of the neighborhood size k, and it is the first work of applying our improved KNN algorithm to rockfall runout range prediction. Second, the shaking table tests of rockfall runout models were conducted for simulating the rockfall process, and the influence laws of factors-including types of an earthquake, peak ground acceleration, vibration frequency, slope angle, slope height, and block mass and block shape-on rockfall distance are investigated. Finally, there is a discussion of the performance of our proposed prediction model based on our improved KNN algorithm in the prediction of rockfall runout range. The extensive experimental results for rockfall runout range prediction demonstrate the effectiveness of our proposed prediction model.

Increasing consumers' environmental awareness has drawn more firms' attention to low-carbon production. CO2 emission management control is a critical factor in the process of low-carbon production in a supply chain. Such kind of inter-organizational control includes two different strategies: the emission control and emission reduction. Those two strategies have different influences on the performance of the supply chain. This paper uses the differential method to study the Stackelberg game between a manufacturer and a supplier in four situations: (1) the non-cooperative situation where no coordination is considered; (2) the weak incentive situation where the emission control incentive is considered; (3) the strong incentive situation where both the emission control incentive and the emission reduction incentive are considered; (4) the cooperative situation where the cooperation is considered. Optimal inter-organizational control of the emission control efforts, emission reduction efforts and cost subsidy are solved and discussed. The results show that although the emission control cost lower, its positive effect on the supply chain performance is still limited. Both the supplier and the manufacturer have the Pareto improvements from the non-cooperative situation to the cooperative situation in sequence. Finally, the simulations and sensitivity analyses are conducted to support the models. Our study provides theoretical insights to the optimal control of low-carbon production in an inter-organizational setting.

In recent years, unmanned aerial vehicles (UAVs) have received considerable attention from regulators, industry and research community, due to rapid growth in a broad range of applications. Particularly, UAVs are being used to provide a promising solution to reliable and cost-effective wireless communications from the sky. The deployment of UAVs has been regarded as an alternative complement of existing cellular systems, to achieve higher transmission efficiency with enhanced coverage and capacity. However, heavily utilized microwave spectrum bands below 6 GHz utilized by legacy wireless systems are insufficient to attain remarkable data rate enhancement for numerous emerging applications. To resolve the spectrum crunch crisis and satisfy the requirements of 5G and beyond mobile communications, one potential solution is to use the abundance of unoccupied bandwidth available at millimeter wave (mmWave) frequencies. Inspired by the technique potentials, mmWave communications have also paved the way into the widespread use of UAVs to assist wireless networks for future 5G and beyond wireless applications. In this paper, we provide a comprehensive survey on current achievements in the integration of 5G mmWave communications into UAV-assisted wireless networks. More precisely, a taxonomy to classify the existing research issues is presented, by considering seven cutting-edge solutions. Subsequently, we provide a brief overview of 5G mmWave communications for UAV-assisted wireless networks from two aspects, i.e., key technical advantages and challenges as well as potential applications. Based on the proposed taxonomy, we further discuss in detail the state-of-the-art issues, solutions, and open challenges for this newly emerging area. Lastly, we complete this survey by pointing out open issues and shedding new light on future directions for further research on this area.

Energy efficiency in data center networks (DCNs) is critical to the operations of modern large-scale data centers. One effective way is to make the size of DCNs elastic along with flow demands by centralized routing and scheduling, i.e., turning off idle network components to reduce the power consumption. As such, software-defined networking (SDN) is widely used for achieving such elasticity conveniently. Meanwhile, the scale and structure of modern DCNs get much larger and more complex. Central control and global computing become impractical due to the heavy time and space complexity. Therefore, distributed power control is necessary for large-scale SDN-DCNs, and yet there are few research achievements in this area. In this paper, we present an extensible energy-efficient mechanism, which: 1) leverages distributed flow routing for both intraand inter-domain elephant flows and 2) extendedly considers distributed energy efficiency for control plane. A local power-saving function is operated within each domain of control plane, and a distributed energy-efficient routing algorithm is computed to optimize the effectiveness for the inter-domain flows. The simulation results demonstrate that this distributed mechanism applies to large-scale DCNs and achieves an effective power saving.

Spoofing attacks are one of the most dangerous threats for the application of the global navigation satellite system (GNSS), especially for autonomous driving and unmanned aerial vehicles. In this paper, we present a more robust spoofing mitigation algorithm based on subspace projection that is independent of the number of antennas and that can be utilized in single-antenna GNSS receivers. During a spoofing attack, authentic signals are contaminated by spoofing signals. We demonstrate that all spoofing signals can be eliminated by projecting the received signal onto the orthogonal null space of the spoofing signals. Moreover, two types of receiver structures are designed: a centralized structure that has the ability to suppress cross-correlation interference and a distributed structure with lower computational complexity and lower projection power losses. The proposed algorithm is verified by the Beidou B1I signals for improving the security of the receiver.

Energy consumed by network constitutes a significant portion of the total power budget in modern data centers. Thus, it is critical to understand the energy consumption and improve the power efficiency of data center networks (DCNs). In doing so, one straightforward and effective way is to make the size of DCNs elastic along with traffic demands, i.e., turning off unnecessary network components to reduce the energy consumption. Today, software defined networking (SDN), as one of the most promising solutions for data center management, provides a paradigm to elastically control the resources of DCNs. However, to the best of our knowledge, the features of SDN have not been fully leveraged to improve the power saving, especially for large-scale multi-controller DCNs. To address this problem, we propose E3MC, a mechanism to improve DCN's energy efficiency via the elastic multi-controller SDN. In E3MC, the energy optimizations for both forwarding and control plane are considered by utilizing SDN's fine-grained routing and dynamic control mapping. In particular, the flow network theory and the bin-packing heuristic are used to deal with the forwarding plane and control plane, respectively. Our simulation results show that E3MC can achieve more efficient power management, especially in highly structured topologies such as Fat-Tree and BCube, by saving up to 50% of network energy, at an acceptable level of computation cost.