An evaluation model for children's foot & ankle deformity severity using sparse multi-objective feature selection algorithm

A new insight into pilot-scale development of low-salinity polymer flood using an intelligent-based proxy model coupled with particle swarm optimization

To successfully implement low-salinity polymer flooding in heterogeneous heavy oil reservoirs, it is crucial to comprehend the interactions between salinity, polymer properties, and reservoir characteristics. Artificial intelligence-driven proxy models can assist in identifying critical parameters and predicting performance outcomes, thereby enabling optimizing field-scale applications of this technique in heterogeneous heavy oil reservoirs. This study focused on developing a proxy model by coupling neural network and particle swarm optimization algorithms to analyze low-salinity polymer flooding. The model, trained with data from a pilot-scale dynamic simulator, achieved high predictive accuracy, featuring a regression value of 0.996 and a mean square error of 0.0011. It effectively forecasts key performance indicators such as oil recovery, water cut, and well bottom-hole pressure. The model identified injection rate as the most influential factor and polymer concentration as the least significant. Through the optimization of input parameters, the study established optimized values for the injection rate, injected fluid salinity, and polymer concentration at 1450 (bbl/day), 4000 ppm, and 1500 ppm, respectively. The optimization considers economic viability by maximizing net present value and addresses practical challenges of maintaining injectivity over time, making it a valuable tool for enhancing water-based recovery methods in oil field development.

IRIME: Mitigating exploitation-exploration imbalance in RIME optimization for feature selection

Rime optimization algorithm (RIME) encounters issues such as an imbalance between exploitation and exploration, susceptibility to local optima, and low convergence accuracy when handling problems. This paper introduces a variant of RIME called IRIME to address these drawbacks. IRIME integrates the soft besiege (SB) and composite mutation strategy (CMS) and restart strategy (RS). To comprehensively validate IRIME's performance, IEEE CEC 2017 benchmark tests were conducted, comparing it against many advanced algorithms. The results indicate that the performance of IRIME is the best. In addition, applying IRIME in four engineering problems reflects the performance of IRIME in solving practical problems. Finally, the paper proposes a binary version, bIRIME, that can be applied to feature selection problems. bIRIMR performs well on 12 low-dimensional datasets and 24 high-dimensional datasets. It outperforms other advanced algorithms in terms of the number of feature subsets and classification accuracy. In conclusion, bIRIME has great potential in feature selection.

Environment random interaction of rime optimization with Nelder-Mead simplex for parameter estimation of photovoltaic models

As countries attach importance to environmental protection, clean energy has become a hot topic. Among them, solar energy, as one of the efficient and easily accessible clean energy sources, has received widespread attention. An essential component in converting solar energy into electricity are solar cells. However, a major optimization difficulty remains in precisely and effectively calculating the parameters of photovoltaic (PV) models. In this regard, this study introduces an improved rime optimization algorithm (RIME), namely ERINMRIME, which integrates the Nelder-Mead simplex (NMs) with the environment random interaction (ERI) strategy. In the later phases of ERINMRIME, the ERI strategy serves as a complementary mechanism for augmenting the solution space exploration ability of the agent. By facilitating external interactions, this method improves the algorithm's efficacy in conducting a global search by keeping it from becoming stuck in local optima. Moreover, by incorporating NMs, ERINMRIME enhances its ability to do local searches, leading to improved space exploration. To evaluate ERINMRIME's optimization performance on PV models, this study conducted experiments on four different models: the single diode model (SDM), the double diode model (DDM), the three-diode model (TDM), and the photovoltaic (PV) module model. The experimental results show that ERINMRIME reduces root mean square error for SDM, DDM, TDM, and PV module models by 46.23%, 59.32%, 61.49%, and 23.95%, respectively, compared with the original RIME. Furthermore, this study compared ERINMRIME with nine improved classical algorithms. The results show that ERINMRIME is a remarkable competitor. Ultimately, this study evaluated the performance of ERINMRIME across three distinct commercial PV models, while considering varying irradiation and temperature conditions. The performance of ERINMRIME is superior to existing similar algorithms in different irradiation and temperature conditions. Therefore, ERINMRIME is an algorithm with great potential in identifying and recognizing unknown parameters of PV models.

Bridging the gap: Geometry-centric discriminative manifold distribution alignment for enhanced classification in colorectal cancer imaging

The early detection of colorectal cancer (CRC) through medical image analysis is a pivotal concern in healthcare, with the potential to significantly reduce mortality rates. Current Domain Adaptation (DA) methods strive to mitigate the discrepancies between different imaging modalities that are critical in identifying CRC, yet they often fall short in addressing the complexity of cancer's presentation within these images. These conventional techniques typically overlook the intricate geometrical structures and the local variations within the data, leading to suboptimal diagnostic performance. This study introduces an innovative application of the Discriminative Manifold Distribution Alignment (DMDA) method, which is specifically engineered to enhance the medical image diagnosis of colorectal cancer. DMDA transcends traditional DA approaches by focusing on both local and global distribution alignments and by intricately learning the intrinsic geometrical characteristics present in manifold space. This is achieved without depending on the potentially misleading pseudo-labels, a common pitfall in existing methodologies. Our implementation of DMDA on three distinct datasets, involving several unique DA tasks, has consistently demonstrated superior classification accuracy and computational efficiency. The method adeptly captures the complex morphological and textural nuances of CRC lesions, leading to a significant leap in domain adaptation technology. DMDA's ability to reconcile global and local distributional disparities, coupled with its manifold-based geometrical structure learning, signals a paradigm shift in medical imaging analysis. The results obtained are not only promising in terms of advancing domain adaptation theory but also in their practical implications, offering the prospect of substantially improved diagnostic accuracy and faster clinical workflows. This heralds a transformative approach in personalized oncology care, aligning with the pressing need for early and accurate CRC detection.

A despeckling method for ultrasound images utilizing content-aware prior and attention-driven techniques

The despeckling of ultrasound images contributes to the enhancement of image quality and facilitates precise treatment of conditions such as tumor cancers. However, the use of existing methods for eliminating speckle noise can cause the loss of image texture features, impacting clinical judgment. Thus, maintaining clear lesion boundaries while eliminating speckle noise is a challenging task. This paper presents an innovative approach for denoising ultrasound images using a novel noise reduction network model called content-aware prior and attention-driven (CAPAD). The model employs a neural network to automatically capture the hidden prior features in ultrasound images to guide denoising and embeds the denoiser into the optimization module to simultaneously optimize parameters and noise. Moreover, this model incorporates a content-aware attention module and a loss function that preserves the structural characteristics of the image. These additions enhance the network's capacity to capture and retain valuable information. Extensive qualitative evaluation and quantitative analysis performed on a comprehensive dataset provide compelling evidence of the model's superior denoising capabilities. It excels in noise suppression while successfully preserving the underlying structures within the ultrasound images. Compared to other denoising algorithms, it demonstrates an improvement of approximately 5.88% in PSNR and approximately 3.61% in SSIM. Furthermore, using CAPAD as a preprocessing step for breast tumor segmentation in ultrasound images can greatly improve the accuracy of image segmentation. The experimental results indicate that the utilization of CAPAD leads to a notable enhancement of 10.43% in the AUPRC for breast cancer tumor segmentation.