Conventional Model Research Articles

Influence of the gut microbiome on appetite-regulating neuropeptides in the hypothalamus: Insight from conventional, antibiotic-treated, and germ-free mouse models of anorexia nervosa

Recent research highlights the profound impact of the gut microbiome on neuropsychiatric disorders, shedding light on its potential role in shaping human behavior. In this study, we investigate the role of the gut microbiome in appetite regulation using activity-based anorexia (ABA) mouse model of anorexia nervosa (AN) — a severe eating disorder with significant health consequences. ABA was induced in conventional, antibiotic-treated, and germ-free mice. Our results show the clear influence of the gut microbiome on the expression of four orexigenic (neuropeptide Y, agouti-related peptide, melanin-concentrating hormone, and orexin) and four anorexigenic peptides (cocaine- and amphetamine-regulated transcript, corticotropin-releasing hormone, thyrotropin-releasing hormone, and pro-opiomelanocortin) in the hypothalamus. Additionally, we assessed alterations in gut barrier permeability. While variations were noted in germ-free mice based on feeding and activity, they were not directly attributable to the gut microbiome. This research emphasizes that the gut microbiome is a pivotal factor in AN's appetite regulation beyond just dietary habits or physical activity.

DeepCG: A cell graph model for predicting prognosis in lung adenocarcinoma.

Lung cancer is the first leading cause of cancer-related death in the United States, with lung adenocarcinoma as the major subtype accounting for 40% of all cases. To improve patient survival, image-based prognostic models were developed due to the ready availability of pathological images at diagnosis. However, the application of these models is hampered by two main challenges: the lack of publicly available image datasets with high-quality survival information and the poor interpretability of conventional convolutional neural network models. Here, we integrated matched transcriptomic and H&E staining data from TCGA (The Cancer Genome Atlas) to develop an image-based prognostic model, termed Deep-learning based Cell Graph (DeepCG) model. Instead of survival data, we used a gene signature to predict patient prognostic risks, which was then used as labels for training DeepCG. Importantly, by employing graph structures to capture cell patterns, DeepCG can provide cell-level interpretation, which was more biologically relevant than previous region-level insights. We validated the prognostic values of DeepCG in independent datasets and demonstrated its ability to identify prognostically informative cells in images.

Stability Improvement of Adaptive Full-Order Observer for Sensorless Induction Motor Drives in Low-Speed Regenerating Mode

In the applications of high power induction motor railway traction systems, the switching frequency of power devices is relatively low. This restriction will severely reduce the accuracy and stability of conventional discrete model for adaptive full-order observer (AFO) in extremely high-speed region. What’s worse, due to the neglect of flux error during speed estimation derivation, the conventional AFO cannot maintain stability under low-speed regenerating mode. The above two reasons limit the application of AFO in rail traction systems for full speed range. To address this problem, this paper utilizes a high-accuracy discretization which is achieved in combined reference frames and feedback gains are designed in z-domain to ensure stability and dynamic performance of AFO. Moreover, a modified speed estimation mechanism with the error of d-axis current is developed to guarantee stability in extremely low-speed regenerating mode. Rigorous simulations and experiments are performed to verify that the proposed AFO model achieves excellent sensorless control performance in full speed range.

Biomimetic Deep Learning Networks With Applications to Epileptic Spasms and Seizure Prediction.

In this study, we present a novel biomimetic deep learning network for epileptic spasms and seizure prediction and compare its performance with state-of-the-art conventional machine learning models. Our proposed model incorporates modular Volterra kernel convolutional networks and bidirectional recurrent networks in combination with the phase amplitude cross-frequency coupling features derived from scalp EEG. They are applied to the standard CHB-MIT dataset containing focal epilepsy episodes as well as two other datasets from the Montefiore Medical Center and the University of California Los Angeles that provide data of patients experiencing infantile spasm (IS) syndrome. Overall, in this study, the networks can produce accurate predictions (100%) and significant detection latencies (10 min). Furthermore, the biomimetic network outperforms conventional ones by producing no false positives. Biomimetic neural networks utilize extensive knowledge about processing and learning in the electrical networks of the brain. Predicting seizures in adults can improve their quality of life. Epileptic spasms in infants are part of a particular seizure type that needs identifying when suspicious behaviors are noticed in babies. Predicting epileptic spasms within a given time frame (the prediction horizon) suggests their existence and allows an epileptologist to flag an EEG trace for future review.

Multi‐Platform Observations of Severe Typhoon Koinu

AbstractSevere Typhoon Koinu passed south of Hong Kong on 8 and 9 October 2023, triggering the issuance of the Increasing Gale or Storm Signal No. 9, the second highest tropical cyclone (TC) warning signal in Hong Kong. Koinu was a difficult case for TC warning service due to its compact size and rather erratic movement over the coastal waters of Guangdong. To monitor Koinu's movement and wind structure, the Hong Kong Observatory utilized various observational platforms, including meteorological aircraft, ocean radar, and synthetic aperture radar on polar orbiting satellites. The paper presents major observations derived from these measurements. The aircraft probe and dropsonde data suggested boundary layer inflow, warm core structure, eyewall updraft, and high turbulence in the eyewall of the typhoon. The weather radar observations indicated the occurrence of a waterspout in the vicinity of the typhoon. Additionally, the study highlights the forecasting performance of the AI‐based Pangu‐Weather model, which could outperform the conventional global numerical weather prediction models in forecasting TC track in the region. The documentation of these observations aims to provide valuable references for weather forecasters and stimulate further research on forecasting this type of tropical cyclone.

A novel ensemble model for detecting fake news

<div>Due the growing proliferation of fake news over the past couple of years, our</div><div>objective in this paper is to propose an ensemble model for the automatic classification of article news as being either real or fake. For this purpose, we opt</div><div>for a blending technique that combines three models, namely bidirectional long</div><div>short-term memory (Bi-LSTM), stochastic gradient descent classifier and ridge</div><div>classifier. The implementation of the proposed model (i.e. BI-LSR) on real</div><div>world datasets, has shown outstanding results. In fact, it achieved an accuracy</div><div>score of 99.16%. Accordingly, this ensemble learning has proven to do perform</div><div>better than individual conventional machine learning and deep learning models</div><div>as well as many ensemble learning approaches cited in the literature.</div>

Integrated algorithm evaluation of a scalable digital power management innovation model

Maintaining contemporary society’s steady progress depends on the reliable functioning of the electrical grid. The complexity and nonlinearity of today’s power networks make it difficult to manage them using conventional mathematical modeling approaches. To get around these problems, researchers have started using machine learning methods, such transient stability evaluation that is based on machine learning. This research suggests a way to evaluate the transient stability of power systems by making use of the complex feature extraction capabilities of multi-layer perceptron (MLP) networks. Another approach is to suggest an ensemble learning model that uses the easy-ensemble undersampling technique to deal with power system transient stability data that is unbalanced. This method preserves unstable power system samples, performs multiple undersampling on stable samples and combines unstable and undersampling samples into multiple new balanced training sets for MLP model training. The final ensemble model is obtained through voting integration strategy. Through conducting a comparative evaluation of individual models and ensemble models, this paper discovers that the ensemble learning models exhibit superior sensitivity and accuracy in effectively addressing system instability.

Validation of the Emotional Skills and Competence Questionnaire in Croatian and Portuguese samples using exploratory graph analysis

This study aimed to validate the Emotional Skills and Competence Questionnaire (ESCQ-42, Takšić et al., 2009) in Croatian and Portuguese samples using exploratory graph analysis (EGA). The ESCQ, rooted in the Mayer and Salovey emotional intelligence model (Mayer & Salovey, 1997), was administered to 627 Portuguese students (Mage = 15.5; SD = 0.76) and 562 Croatian students (Mage = 16.3; SD = 1.07). This questionnaire, featuring three subscales for perceiving, expressing, and managing emotions, has shown strong psychometric reliability across various studies and countries. Despite its widespread use and validation, item-level inconsistencies in cross-cultural research motivated the use of EGA.The EGA revealed that the Croatian sample exhibited a five-dimensional structure, while the Portuguese sample presented a four-dimensional structure, thus challenging the conventional three-factor model. Additional analyses of item stability, replicability, and network loadings provided deeper insights into item placements and contributions. Model fit comparisons between EGA-identified structures and the theoretical three-factor model were conducted using confirmatory factor analysis (CFA). Furthermore, EGA confirmed the three-factor structure on an abbreviated scale, achieving both configural and partial metric invariance across cultures. These findings underscore the necessity for ongoing refinement of the ESCQ-42 to enhance its cross-cultural applicability and reliability.

QoE-Aware Network Pricing, Power Allocation, and Admission Control

In wireless communications, focusing on end-user satisfaction and maximizing network operators' revenue are emerging business challenges. In this paper, we investigate the price-based power allocation problem where, first, base stations (BSs) set prices by maximizing users' utility modeled by their mean opinion score (MOS). Then, each user's optimal power is set by maximizing operator revenue while ensuring the minimum data rate for each user. We propose a hybrid MOS-based pricing method to model users' utility instead of the conventional achievable rate approach. Our hybrid approach applies a machine learning algorithm to model the MOS of the call service in terms of the received signal strength indicator (RSSI). In terms of MOS and outage probability, our proposed method outperforms the rate-based pricing method and the conventional objective MOS models. In addition, we consider a joint admission control and price-based power allocation problem. When a new user requests to connect, a central controller determines whether or not to accept the new connection based on the system's MOS and average outage probability. The results demonstrate a trade-off between the number of users admitted and their level of satisfaction, providing operators with crucial knowledge about how to use their network resources more effectively.

Semantics-Guided Contrastive Network for Zero-Shot Object Detection.

Zero-shot object detection (ZSD), the task that extends conventional detection models to detecting objects from unseen categories, has emerged as a new challenge in computer vision. Most existing approaches tackle the ZSD task with a strict mapping-transfer strategy that may lead to suboptimal ZSD results: 1) the learning process of these models neglects the available semantic information on unseen classes, which can easily bias towards the seen categories; 2) the original visual feature space is not well-structured for the ZSD task due to the lack of discriminative information. To address these issues, we develop a novel Semantics-Guided Contrastive Network for ZSD, named ContrastZSD, a detection framework that first brings contrastive learning mechanism into the realm of zero-shot detection. Particularly, ContrastZSD incorporates two semantics-guided contrastive learning subnets that contrast between region-category and region-region pairs respectively. The pairwise contrastive tasks take advantage of supervision signals derived from both the ground truth label and class similarity information. By performing supervised contrastive learning over those explicit semantic supervision, the model can learn more knowledge about unseen categories to avoid the bias problem to seen concepts, while optimizing the visual data structure to be more discriminative for better visual-semantic alignment. Extensive experiments are conducted on two popular benchmarks for ZSD, i.e., PASCAL VOC and MS COCO. Results show that our method outperforms the previous state-of-the-art on both ZSD and generalized ZSD tasks.

Robust and Sparse Principal Component Analysis With Adaptive Loss Minimization for Feature Selection.

Principal component analysis (PCA) is one of the most successful unsupervised subspace learning methods and has been used in many practical applications. To deal with the outliers in real-world data, robust principal analysis models based on various measure are proposed. However, conventional PCA models can only transform features to unknown subspace for dimensionality reduction and cannot perform features' selection task. In this article, we propose a novel robust PCA (RPCA) model to mitigate the impact of outliers and conduct feature selection, simultaneously. First, we adopt σ -norm as reconstruction error (RE), which plays an important role in robust reconstruction. Second, to conduct feature selection task, we apply l2,0 -norm constraint to subspace projection. Furthermore, an efficient iterative optimization algorithm is proposed to solve the objective function with nonconvex and nonsmooth constraint. Extensive experiments conducted on several real-world datasets demonstrate the effectiveness and superiority of the proposed feature selection model.

FCSN: Global Context Aware Segmentation by Learning the Fourier Coefficients of Objects in Medical Images.

The encoder-decoder model is a commonly used Deep learning (DL) model for medical image segmentation. Encoder-decoder models make pixel-wise predictions that focus heavily on local patterns. As a result, the predicted mask often fails to preserve the object's shape and topology, which requires an understanding of the image's global context. In this work, we propose a Fourier Coefficient Segmentation Network (FCSN)---a novel global context-aware DL model that segments an object by learning the complex Fourier Coefficients of the object's masks. The Fourier coefficients are calculated by integrating over the mask's contour. Hence, FCSN is naturally motivated to incorporate a broader image context when estimating the coefficients. The global context awareness of FCSN helps produce more accurate segmentation and is more robust to local perturbations, such as additive noise or motion blur. We compare FCSN on other state-of-the-art global context-aware models (UNet++, DeepLabV3+, UNETR) on 5 medical image segmentation tasks (ISIC_2018, RIM_CUP, RIM_DISC, PROSTATE, FETAL). When compared with UNETR, FCSN attains significantly lower Hausdorff scores with 19.14 (6%), 17.42 (6%), 9.16 (14%), 11.18 (22%), and 5.98 (6%) for ISIC_2018, RIM_CUP, RIM_DISC, PROSTATE, and FETAL tasks respectively. Moreover, FCSN is lightweight by discarding the decoder module. FCSN only requires 29.7 M parameters which are 75.6 M and 9.9 M fewer than UNETR and DeepLabV3+, respectively. FCSN attains inference/training speeds of 1.6 ms/img and 6.3 ms/img, which is 8 and 3 faster than UNet and UNETR. Our work is available at https://github.com/nus-morninlab/FCSN.

A comprehensive examination of the linear and numerical stability aspects of the bubble collision model in the TRACE-1D two-fluid model applied to vertical disperse flow in a PWR core channel under loss of coolant accident conditions

The one-dimensional Two-Fluid concept uses an area-average approach to simplify the time and phase-averaged Two-Fluid conservation equations, making it more suitable for addressing difficulties at an industrial scale. Nevertheless, the mathematical framework has inherent weaknesses due to the loss of details throughout the averaging procedures. This limitation makes the conventional model inappropriate for some flow regimes, where short-wavelength perturbations experience uncontrolled amplification, leading to solutions that need to be physically accurate. The critical factor in resolving this problem is the integration of closure relations. These relationships play a crucial function in reintroducing essential physical characteristics, thus correcting the loss that occurs during averaging and guaranteeing the stability of the model. To improve the accuracy of predictions, it is essential to assess the stability and grid dependence of one-dimensional formulations, which are particularly affected by closure relations and numerical schemes. The current research presented in the text focuses on improving the well-posedness of the TFM, specifically within the TRACE code, which is widely utilized for nuclear reactor safety assessments. Incorporating a bubble collision model in the momentum equations is demonstrated to enhance the TFM's resilience, especially in scenarios with high void fractions where conventional TFMs may face challenges. The analysis presents a linear stability analysis performed for the transient one-dimensional Two-Fluid Model of system code TRACE within the framework of vertically dispersed flows. The main emphasis is on evaluating the stability characteristics of the model while also acknowledging its susceptibility to closure relations and numerical techniques.

Study the thermal response of a solar flat-plate collector under transient solar radiation experimentally and numerically

The target of the current study is to investigate and comparing the thermal response of solar flat plate collector (SFPC) for traditional and new model numerically and experimentally. The new model consists of elliptical-shaped riser pipes and a flat plate with longitudinal channels and wavy fins. The idea behind the new model is to increase the surface area exposed to solar radiation. All numerical models were created and simulated using ANSYS Fluid 19. R3. While, all of the experimental tests were conducted during the winter season in Baghdad, Iraq. The study showed that there are agree well between experimental and numerical results, and both models have the same behavior. The results showed that the new model outperformed the traditional one in terms of thermal response. The new one performed 23.6% better to compare the conventional model in terms of liquid temperature in the container. Additionally, the mass flow rate of liquid flowing within the closed loop of the new model is 7.9% higher than the traditional model. Moreover, in terms of overall thermal efficiency, the new model outperformed the traditional model by 22.4%.

An Angle-Based Virtual Vector Model Predictive Current Control for IPMSM Considering Overmodulation

The conventional model predictive control method suffers from large current and torque harmonics due to the limited voltage vectors. To increase the control performance, in many papers, the methods of extending the predictive control set by adding virtual vectors are proposed. However, constructing virtual vectors will bring extra computational burden for vector optimization. To solve this problem, this paper proposes an angle-based virtual vector model predictive current control (ABVV-MPCC) method for interior permanent magnet synchronous motor (IPMSM). In this method, a hexagonal coordinate system is introduced to define the virtual vectors. After obtaining the composite relationship between the reference voltage vector and the adjacent basic vector, the vector optimization range is reduced from six voltage sectors to one voltage sector. And the optimal voltage vector is directly obtained by searching for the closest candidate voltage vector. After adopting the proposed method, the exhaustive optimization is avoided and the calculation burden is independent from the virtual voltage vectors number. Therefore, virtual voltage vectors number can be set arbitrarily, which greatly reduces current harmonics. Besides, a simple overmodulation dealing method by finding the optimal reachable voltage vector is proposed. And the dynamic performance under overmodulation is increased without adding additional control module.

A comparative study of CNN-capsule-net, CNN-transformer encoder, and Traditional machine learning algorithms to classify epileptic seizure

IntroductionEpilepsy is a disease characterized by an excessive discharge in neurons generally provoked without any external stimulus, known as convulsions. About 2 million people are diagnosed each year in the world. This process is carried out by a neurological doctor using an electroencephalogram (EEG), which is lengthy.MethodTo optimize these processes and make them more efficient, we have resorted to innovative artificial intelligence methods essential in classifying EEG signals. For this, comparing traditional models, such as machine learning or deep learning, with cutting-edge models, in this case, using Capsule-Net architectures and Transformer Encoder, has a crucial role in finding the most accurate model and helping the doctor to have a faster diagnosis.ResultIn this paper, a comparison was made between different models for binary and multiclass classification of the epileptic seizure detection database, achieving a binary accuracy of 99.92% with the Capsule-Net model and a multiclass accuracy with the Transformer Encoder model of 87.30%.ConclusionArtificial intelligence is essential in diagnosing pathology. The comparison between models is helpful as it helps to discard those that are not efficient. State-of-the-art models overshadow conventional models, but data processing also plays an essential role in evaluating the higher accuracy of the models.

A materials informatics framework based on reduced‐order models for extracting structure–property linkages of additively manufactured continuous fiber‐reinforced polymer composites

AbstractThe innovative combination of additive manufacturing (AM) and continuous fiber‐reinforced polymer composites (CFRPCs) confers products with the dual advantages of integrated manufacturing and designability of properties, but lack an efficient and reliable method for property prediction. This study presents a materials informatics framework using reduced‐order models and machine learning (ML) to extract the structure–property (SP) linkages between microstructures and macroscopic elastic properties of AM‐CFRPCs. The initial step involves generating microstructural 2D cross‐sections and representative volume elements (RVEs) with random fiber and pore distributions based on the minimum potential method. Then, finite element (FE) calculations are performed on RVEs to obtain nine macroscopic elastic properties. Following that, the quantification and dimensionality reduction of the 2D cross‐sectional dataset are conducted separately using two‐point spatial correlations and principal component analysis (PCA). Finally, a Bayesian optimized composite kernel support vector regression (CK‐SVR) algorithm is used to effectively establish complex mapping relationships between the reduced‐order representations of the microstructures and the mechanical properties. Despite the reduced‐order dataset containing only 3–6 variables, the framework generates an interpretable model exhibiting excellent accuracy with all predicted R2 values surpassing 0.91. Therefore, this framework presents a prospective solution for expediting the design and optimization of AM‐CFRPCs.Highlights A materials informatics scheme is proposed to predict the 9 elastic properties of AM‐CFRPCs. Microstructures are quantified and dimensionally reduced by two‐point statistics and PCA. SP linkages are established between 2D cross‐sections and 3D macromechanical properties. Modified CK‐SVR exhibits higher prediction accuracy compared to conventional models.

EXPLORING INDIA’S ECONOMIC SCENARIO THROUGH THE LENS OF FELDSTEIN HORIOKA PUZZLE

The Feldstein Horioka Puzzle has been a subject of extensive research, with various studies offering conflicting perspectives on its validity. The puzzle focuses on the relationship between saving and investment and whether the relationship holds true at the national level. The puzzle pertains to the persistent correlation between savings and investment, implying that countries with higher savings rates should also exhibit higher investment rates, in opposition to what conventional economic models predict. In the case of India, the Feldstein Horioka Puzzle has yielded diverse conclusions. Annual data from 1970 to 2021 has been used in the study to examine the validity of the Feldstein Horioka Puzzle in India. To confirm the long-term association between saving and investment, it is crucial to consider the cointegration test results. The results of the study KEYWORDS: Feldstein-Horioka Puzzle, saving, investment, fixed exchange rate, cointegration

Foray movements are common and vary with natal habitat for a highly mobile bird.

Understanding dispersal is central to interpreting the effects of climate change, habitat loss and habitat fragmentation, and species invasions. Prior to dispersal, animals may gather information about the surrounding landscape via forays, or systematic, short-duration looping movements away from and back to the original location. Despite theory emphasizing that forays can be beneficial for dispersing organisms and that such behaviors are predicted to be common, relatively little is known about forays in wild populations. Theory predicts that individuals that use forays may delay dispersal and such behaviors should increase survival, yet empirical tests of these predictions remain scarce. We tested these predictions in a natural system using the critically endangered snail kite (Rostrhaumus sociabilis), a wetland-dependent raptor. We GPS tracked 104 snail kites from fledging through emigration from the natal site across their breeding range to understand the demographic consequences of movement. We found that forays were common (82.7% of individuals tracked), and natal habitat played an important role in the initiation, execution, and outcome of foray behavior. The effect of foraying on survival was indirect, where forayers emigrated later than non-forayers, and individuals that emigrated later had the highest survival. Poor hydrological conditions in the natal environment were especially important for eliciting forays. Finally, females responded more strongly to natal hydrology than males, making more forays and significantly longer, more distant trips. These results emphasize the fundamental role of natal habitat for determining behavioral patterns, strengthen links between individual movement decisions and their demographic consequences, and provide an important behavioral focal point for interpreting movement tracks that would not otherwise be captured by conventional movement models.

Classification of Mobile-Based Oral Cancer Images Using the Vision Transformer and the Swin Transformer.

Oral cancer, a pervasive and rapidly growing malignant disease, poses a significant global health concern. Early and accurate diagnosis is pivotal for improving patient outcomes. Automatic diagnosis methods based on artificial intelligence have shown promising results in the oral cancer field, but the accuracy still needs to be improved for realistic diagnostic scenarios. Vision Transformers (ViT) have outperformed learning CNN models recently in many computer vision benchmark tasks. This study explores the effectiveness of the Vision Transformer and the Swin Transformer, two cutting-edge variants of the transformer architecture, for the mobile-based oral cancer image classification application. The pre-trained Swin transformer model achieved 88.7% accuracy in the binary classification task, outperforming the ViT model by 2.3%, while the conventional convolutional network model VGG19 and ResNet50 achieved 85.2% and 84.5% accuracy. Our experiments demonstrate that these transformer-based architectures outperform traditional convolutional neural networks in terms of oral cancer image classification, and underscore the potential of the ViT and the Swin Transformer in advancing the state of the art in oral cancer image analysis.