Accurate medical image segmentation is critical for disease quantification and treatment evaluation. While traditional U-Net architectures their transformer-integrated variants excel in automated tasks. Existing models also struggle with parameter efficiency computational complexity, often due to the extensive use of Transformers. However, they lack ability harness image’s intrinsic position channel features. Research employing Dual Attention mechanisms have not been specifically optimized...

Advances in deep learning have revolutionized medical image segmentation, facilitating the precise delineation of complex anatomical structures. The scarcity annotated training samples remains a significant bottleneck. To tackle data limitation, federated (FL) offers promise pooling from multiple healthcare institutions. However, as models grow larger, increase communication costs restricts FL to fewer nodes, which constrains volume data. This situation necessitates simultaneous achievement...

The COVID-19 pandemic and influenza outbreaks have underscored the critical need for predictive models that can effectively integrate spatial temporal dynamics to enable accurate epidemic forecasting. Traditional time-series analysis approaches fallen short in capturing intricate interplay between these factors. Recent advancements witnessed incorporation of graph neural networks machine learning techniques bridge this gap, enhancing accuracy providing novel insights into disease spread...

UHV (ultra-high voltage) by instant AC transmission system is accompanied huge reactive power transmission. When the load drops sharply, it easy to produce serious frequency overvoltage, which also defined as rejection overvoltage. This paper makes an in-depth analysis from perspective of voltage increase caused instantaneous unloading, and obtains causes key influencing factors Taking line a practical project example, suppression effect strategy represented installation opening resistance...

Introduction Accurate image segmentation is crucial in medical imaging for quantifying diseases, assessing prognosis, and evaluating treatment outcomes. However, existing methods often fall short integrating global local features a meaningful way, failing to give sufficient attention abnormal regions boundary details images. These limitations hinder the effectiveness of techniques clinical settings. To address these issues, we propose novel deep learning-based approach, MIPC-Net, designed...

With the further development of knowledge graphs, many weighted graphs (WKGs) have been published and greatly promote various applications. However, current deterministic graph embedding algorithms cannot encode well. This paper gives a promising framework WeExt that can extend models to enable them learn embeddings. In addtion, we introduce link prediction evaluate models' performance on completing WKGs. Finally, give concrete implementation based two translational distance semantic...

The penetration of new energy sources such as wind power is increasing, which consequently increases the occurrence rate subsynchronous oscillation events. However, existing source-identification methods primarily analyze fixed-mode oscillations and rarely consider time-varying features, frequency drift, caused by random volatility farms when occur. This paper proposes a source-localization method that involves an enhanced short-time Fourier transform convolutional neural network (CNN)....

This article proposes a proportional-integral-resonant (PIR) current control strategy for wind-driven brushless doubly fed generator (WDBDFG) during network unbalance. Firstly, four objectives of WDBDFG, including eliminating unbalanced currents power winding (PW), pulsations (CW) currents, torque, and PW power, are discussed different from controls in which the references to were computed; CW derived here. Then, an improved controller using PIR is proposed achieve objectives. In contrast...

Accurate medical image segmentation is critical for disease quantification and treatment evaluation. While traditional Unet architectures their transformer-integrated variants excel in automated tasks. However, they lack the ability to harness intrinsic position channel features of image. Existing models also struggle with parameter efficiency computational complexity, often due extensive use Transformers. To address these issues, this study proposes a novel deep framework, called...

In high voltage direct current transmission system, AC fluctuations in the converter station threaten safe and stable operation of converter, which requires dynamic reactive power support system to stabilize prevent from blocking due commutation failure. Conversion existing thermal generating units synchronous condenser is an economical convenient solution. Takeing Wuhan substation as a prototype example, this paper analyzes its affect on transient stability through digital simulation,...

In medical imaging, accurate image segmentation is crucial for quantifying diseases, assessing prognosis, and evaluating treatment outcomes. However, existing methods lack an in-depth integration of global local features, failing to pay special attention abnormal regions boundary details in images. To this end, we present a novel deep learning-based approach, MIPC-Net, precise Our inspired by radiologists' working patterns, features two distinct modules: (i) \textbf{Mutual Inclusion Position...

Abstract Liquid biopsies based on peripheral blood offer a minimally invasive alternative to solid tissue for the detection of diseases, primarily cancers. However, such tests currently consider only serum component blood, overlooking potentially rich source biomarkers: adaptive immune receptors (AIRs) expressed circulating B and T cells. Machine learning–based classifiers trained AIRs have been reported accurately identify not cancers but also autoimmune infectious diseases as well. when...

In the article, firstly it introduces characteristic as well its working principle of chips MC33035 and MC33039 which MOTORALA Corporation specially designs.The design uses PWM to control rotational speed, Hall is set in motor exams rotor position,and position signal obtained received by MC33035,and same time carries on decoding it,in order determine pole commutates.In internal differential amplifier way follower, speed command directly compares with saw-tooth wave, obtains signal. guarantee...

The impact of the large-scale new energy power station on near-zone DC receiving end grid was studied in this paper. Firstly, basic situation and introduced, structure installed supplies near-area were analyzed. Secondly, model analysis thermal units near area carried out. Finally, a simulation fault recovery capability base connected to based PSASP conducted, it concluded that commissioning Multi-energy complementary megawatt has no noticeable voltage grid.