Breast cancer, marked by uncontrolled cell growth in breast tissue, is the most common cancer among women and a second-leading cause of cancer-related deaths. Among its types, ductal and lobular carcinomas are the mos...
详细信息
Breast cancer, marked by uncontrolled cell growth in breast tissue, is the most common cancer among women and a second-leading cause of cancer-related deaths. Among its types, ductal and lobular carcinomas are the most prevalent, with invasive ductal carcinoma accounting for about 70–80% of cases and invasive lobular carcinoma for about 10–15%. Accurate identification is crucial for effective treatment but can be time-consuming and prone to interobserver variability. AI can rapidly analyze pathological images, providing precise, cost-effective identification, thus reducing the pathologists’ workload. This study utilizes a deep learning framework for advanced, automatic breast cancer detection and subtype identification. The framework comprises three key components: detecting cancerous patches, identifying cancer subtypes (ductal and lobular carcinoma), and predicting patient-level outcomes from whole slide images (WSI). The validation process includes visualization using Score-CAM to highlight cancer-affected areas prominently. Datasets include 111 WSIs (85 malignant from the Warwick HER2 dataset and 26 benign from pathologists). For subtype detection, there are 57 ductal and 8 lobular carcinoma cases. A total of 28,428 annotated patches were reviewed by two expert pathologists. Four pre-trained models—DenseNet-201, MobileNetV2, an ensemble of these two, and a Vision Transformer-based model—were fine-tuned and tested on the patches. Patient-level results were predicted using a majority voting technique based on the percentage of each patch type in the WSI. The Vision Transformer-based model outperformed other models in patch classification, achieving an accuracy of 96.74% for cancerous patch detection and 89.78% for cancer subtype classification. For WSI-based cancer classification, the majority voting method attained an F1-score of 99.06 and 96.13% for WSI-based cancer subtype classification. The proposed deep learning-based framework for advanced breast cancer det
Price based demand response schemes may significantly improve power system efficiency. Additionally, it is desired that such schemes yield improved power operation, by reducing the peak consumption. This paper propose...
详细信息
This paper presents an improved tuning fork gyroscope (TFG) structure utilizing two gyroscope drive resonator frames and a diamond-shaped coupling spring mechanism. It explores a two-degree-of-freedom system for the d...
详细信息
Conventional fuzzy systems(type-1 and type 2)are universal *** goal of this paper is to design and implement a new chaotic fuzzy system(NCFS)based on the Lee oscil-lator for function approximation and chaotic *** inco...
详细信息
Conventional fuzzy systems(type-1 and type 2)are universal *** goal of this paper is to design and implement a new chaotic fuzzy system(NCFS)based on the Lee oscil-lator for function approximation and chaotic *** incorporates fuzzy reasoning of the fuzzy systems,self-adaptation of the neural networks,and chaotic signal generation in a unique *** features enable the structure to handle uncertainties by generating new information or by chaotic search among prior *** fusion of chaotic structure into the neurons of the membership layer of a conventional fuzzy system makes the NCFS more capable of confronting nonlinear *** on the GFA and Stone-Weierstrass theorems,we show that the proposed model has the function approximation *** NCFS perfor-mance is investigated by applying it to the problem of chaotic *** results are demonstrated to ilustrate the concept of function approximation.
In 2023,pivotal advancements in artificial intelligence(AI)have significantly *** that in mind,traditional methodologies,notably the p-y approach,have struggled to accurately model the complex,nonlinear soil-structure...
详细信息
In 2023,pivotal advancements in artificial intelligence(AI)have significantly *** that in mind,traditional methodologies,notably the p-y approach,have struggled to accurately model the complex,nonlinear soil-structure interactions of laterally loaded large-diameter drilled *** study undertakes a rigorous evaluation of machine learning(ML)and deep learning(DL)techniques,offering a comprehensive review of their application in addressing this geotechnical challenge.A thorough review and comparative analysis have been carried out to investigate various AI models such as artificial neural networks(ANNs),relevance vector machines(RVMs),and least squares support vector machines(LSSVMs).It was found that despite ML approaches outperforming classic methods in predicting the lateral behavior of piles,their‘black box'nature and reliance only on a data-driven approach made their results showcase statistical robustness rather than clear geotechnical insights,a fact underscored by the mathematical equations derived from these ***,the research identified a gap in the availability of drilled shaft datasets,limiting the extendibility of current findings to large-diameter *** extensive dataset,compiled from a series of lateral loading tests on free-head drilled shaft with varying properties and geometries,was introduced to bridge this *** paper concluded with a direction for future research,proposes the integration of physics-informed neural networks(PINNs),combining data-driven models with fundamental geotechnical principles to improve both the interpretability and predictive accuracy of AI applications in geotechnical engineering,marking a novel contribution to the field.
In recent years, unmanned aerial vehicles (UAVs) have proven their effectiveness in surveillance due to their superior mobility. By utilizing multiple UAVs with collaborated learning, surveillance of a huge area while...
详细信息
This paper addresses the problem of switching event-triggered self-adjusting prescribed performance force control of electro-hydraulic load simulator (EHLS). A reduced-order fuzzy speed state observer for speed estima...
详细信息
Exploration strategy design is a challenging problem in reinforcement learning(RL),especially when the environment contains a large state space or sparse *** exploration,the agent tries to discover unexplored(novel)ar...
详细信息
Exploration strategy design is a challenging problem in reinforcement learning(RL),especially when the environment contains a large state space or sparse *** exploration,the agent tries to discover unexplored(novel)areas or high reward(quality)*** existing methods perform exploration by only utilizing the novelty of *** novelty and quality in the neighboring area of the current state have not been well utilized to simultaneously guide the agent’s *** address this problem,this paper proposes a novel RL framework,called clustered reinforcement learning(CRL),for efficient exploration in *** adopts clustering to divide the collected states into several clusters,based on which a bonus reward reflecting both novelty and quality in the neighboring area(cluster)of the current state is given to the *** leverages these bonus rewards to guide the agent to perform efficient ***,CRL can be combined with existing exploration strategies to improve their performance,as the bonus rewards employed by these existing exploration strategies solely capture the novelty of *** on four continuous control tasks and six hard-exploration Atari-2600 games show that our method can outperform other state-of-the-art methods to achieve the best performance.
We have realized efficient photopatterning and high-quality ZrO_(2)films through combustion synthesis and manufactured resistive random access memory(RRAM)devices with excellent switching stability at low temperatures...
详细信息
We have realized efficient photopatterning and high-quality ZrO_(2)films through combustion synthesis and manufactured resistive random access memory(RRAM)devices with excellent switching stability at low temperatures(250℃)using these *** synthesis reduces the energy required for oxide conversion,thus accelerating the decomposition of organic ligands in the UV-exposed area,and promoting the formation of metal-oxygen networks,contributing to *** analysis confirmed a reduction in the conversion temperature of combustion precursors,and the prepared combustion ZrO_(2)films exhibited a high proportion of metal-oxygen bonding that constitutes the oxide lattice,along with an amorphous ***,the synergistic effect of combustion synthesis and UV/O_(3)-assisted photochemical activation resulted in patterned ZrO_(2)films forming even more complete metal-oxygen *** devices fabricated with patterned ZrO_(2)films using combustion synthesis exhibited excellent switching characteristics,including a narrow resistance distribution,endurance of 103 cycles,and retention for 105 s at 85℃,despite low-temperature *** synthesis not only enables the formation of high-quality metal oxide films with low external energy but also facilitates improved photopatterning.
Adopting high penetration levels of electric vehicles(EVs) necessitates the implementation of appropriate charging management systems to mitigate their negative impacts on power distribution networks. Currently, most ...
详细信息
Adopting high penetration levels of electric vehicles(EVs) necessitates the implementation of appropriate charging management systems to mitigate their negative impacts on power distribution networks. Currently, most of the proposed EV charging management techniques rely on the availability of high-bandwidth communication links. Such techniques are far from realization due to(1) the lack of utility-grade communication systems in many cases such as secondary(low-voltage) power distribution systems to which EVs are connected, rural areas, remote communities, and islands, and(2) existing fears and concerns about the data privacy of EV users and cyber-physical security. For these cases, appropriate local control schemes are needed to ensure the adequate management of EV charging without violating the grid operation requirements. Accordingly, this paper introduces a new communication-less management strategy for EV charging in droop-controlled islanded microgrids. The proposed strategy is autonomous, as it is based on the measurement of system frequency and local bus voltages. The proposed strategy implements a social charging fairness policy during periods when the microgrid distributed generators(DGs) are in short supply by allocating more system capacity to the EVs with less charging in the past. Furthermore, a novel communication-less EV load shedding scheme is incorporated into the management strategy to provide relief to the microgrid during events of severe undervoltage or underfrequency occurrences due to factors such as high loading or DG outages. Numerical simulations demonstrate the superiority of the proposed strategy over the state-of-the-art controllers in modulating the EV charging demand to counteract microgrid instability.
暂无评论