SCNet: Few-shot image classification via self-correlational and cross spatial-correlation attention by Congqing He, Ding Xu, Ke Gong, Fusen Guo, Dapeng Wei

“…Furthermore, we introduce a novel loss function that combines label-based classification loss and metric-based loss, which mitigates overfitting during meta-testing and enhances alignment of query embeddings with category prototypes. …”
Get full text

A Flexible Interconnected Distribution Network Power Supply Restoration Method Based on E-SOP by Lin Jiang, Canbin Wang, Wei Qiu, Hui Xiao, Wenshan Hu

“…The methodology begins with a comprehensive analysis of the E-SOP’s fundamental architecture and loss model. Subsequently, a dual-objective optimization function is formulated to maximize the sum of nodal active load restoration while minimizing network losses. …”
Get full text

Air quality prediction using stacked bi- long short-term memory and convolutional neural network in India by S Karkuzhali, Thendral Puyalnithi, R Nirmalan

“…During the training phase, the Adam optimizer is used to fine-tune the model’s hyperparameters, with Mean Squared Error (MSE) serving as the loss function. …”
Get full text

Peptides actively transported across the tympanic membrane: Functional and structural properties. by Arwa Kurabi, Kerry A Beasley, Lisa Chang, James McCann, Kwang Pak, Allen F Ryan

“…Comparable, reversible hearing loss was observed for saline controls, WT phage and trans-TM peptide phage, suggesting a mild conductive hearing loss due to ME fluid. …”
Get full text

Multi-Scenario Remote Sensing Image Forgery Detection Based on Transformer and Model Fusion by Jinmiao Zhao, Zelin Shi, Chuang Yu, Yunpeng Liu

“…Finally, to promote network optimization, on the one hand, we explore multiple loss functions and select label smooth loss, which can reduce the model’s excessive dependence on training data. …”
Get full text

A Simple Narrative Review of Progress on the Processing and Utilization of Functional Rice by Ziying Yi, Dagang Chen, Xinqiao Zhou, Jie Guo, Ke Chen, Chanjuan Ye, Chuanguang Liu, Juan Liu

“…Future efforts should focus on further optimizing processing techniques and utilizing genetic engineering and molecular breeding technologies to enhance the nutritional value and agronomic traits of functional rice, thus meeting market demands and health objectives.…”
Get full text

Restoring vestibular function during natural self-motion: Progress and challenges by Kantapon Pum Wiboonsaksakul, Olivia ME Leavitt Brown, Kathleen E Cullen

“…The vestibular system is integral to behavior; the loss of peripheral vestibular function leads to disabling consequences, such as blurred vision, dizziness, and unstable posture, severely limiting activities of daily living. …”
Get full text

Achieving chronic hepatitis B functional cure: Factors and potential mechanisms by Jiarui Zheng, Zilong Wang, Linxiang Huang, Zixuan Qiu, Yandi Xie, Suzhen Jiang, Bo Feng

“…Chronic hepatitis B (CHB) is a significant global health issue affecting approximately 254 million individuals worldwide. Achieving the loss of hepatitis B surface antigen (HBsAg), either with or without seroconversion to hepatitis B surface antibody (HBsAb), is regarded as a functional cure and the optimal goal for addressing CHB, and can be achieved through various approaches, including induction with nucleos(t)ide analogues (NAs), induction with pegylated interferon alpha (PegIFNα), and spontaneous clearance of HBsAg. …”
Get full text

Efficacy of Omega-3 supplementation in olfactory dysfunction: a systematic review of randomized controlled trials by Raghad S. Alzahrani, Taif F. Alkhatabi, Abdulaziz F. Bokhari, Wed M. Ismail, Abdullah S. Alyamani, Ali S. Alsudais, Bassam AlRajhi, Dakheelallah M. Almutairi

“…Two studies reported omega-3’s protective effect against olfactory loss over three months. However, a trial on COVID-19 patients found no significant improvement in olfactory function. …”
Get full text

The Impact of Churg–Strauss Syndrome on Nasal Function and Quality of Life: An Underexplored Dimension by Luca Galassi, Federica Facchinetti

Get full text

Robust power management capabilities of integrated energy systems in the smart distribution network including linear and non-linear loads by Kai Jin, Hamed Banizaman, Sina Samadi Gharehveran, Mohammad Reza Jokar, Alireza Mohammadi Amidi, Jianyong Yu, Hayder Oleiwi Shami

“…A deterministic model that optimizes for three distinct goals serves as the foundation for the proposed system. …”
Get full text

Convolutional neural network model over encrypted data based on functional encryption by Chen WANG, Jiarun LI, Jian XU

“…Currently, homomorphic encryption, secure multi-party computation, and other encryption schemes are used to protect the privacy of sensitive data in outsourced convolutional neural network (CNN) models.However, the computational and communication overhead caused by the above schemes would reduce system efficiency.Based on the low cost of functional encryption, a new convolutional neural network model over encrypted data was constructed using functional encryption.Firstly, two algorithms based on functional encryption were designed, including inner product functional encryption and basic operation functional encryption algorithms to implement basic operations such as inner product, multiplication, and subtraction over encrypted data, reducing computational and communication costs.Secondly, a secure convolutional computation protocol and a secure loss optimization protocol were designed for each of these basic operations, which achieved ciphertext forward propagation in the convolutional layer and ciphertext backward propagation in the output layer.Finally, a secure training and classification method for the model was provided by the above secure protocols in a module-composable way, which could simultaneously protect the confidentiality of user data as well as data labels.Theoretical analysis and experimental results indicate that the proposed model can achieve CNN training and classification over encrypted data while ensuring accuracy and security.…”
Get full text

Developmental riboflavin deficiency results in structural and functional changes in the neural retina and RPE by Xue Zhao, Mustafa S. Makia, Muna I. Naash, Muayyad R. Al-Ubaidi

“…The retina, a metabolically active tissue, relies on adequate flavin levels for optimal function. Our previous research demonstrated that ablation of RTBDN, a retina-specific riboflavin binding protein, plays a pivotal role in maintaining flavin levels, leading to progressive retinal degeneration. …”
Get full text

Decoding the Function of <i>FGFBP1</i> in Sheep Adipocyte Proliferation and Differentiation by Liming Tian, Zhaohua He, Guan Wang, Shuhong Zhang, Tenggang Di, Menghan Chang, Wei Han, Jingyi Gao, Meng Li, Ziyi Wang, Huan Zhang, Shaobin Li, Guangli Yang

“…Overexpression and knockdown methods were used to establish gain- and loss-of-function models, and the biological effects of <i>FGFBP1</i> on adipocyte dynamics were systematically assessed. …”
Get full text

NeuAFG: Neural Network-Based Analog Function Generator for Inference in CIM by Pengcheng Feng, Yihao Chen, Jinke Yu, Zhelong Jiang, Junjia Su, Qian Zhou, Hao Yue, Zhigang Li, Haifang Jian, Huaxiang Lu, Wan'Ang Xiao, Gang Chen

“…NeuAFG utilizes a one-hidden-layer ReLU neural network (ReLUNet) to approximate a variety of activation functions, incorporating two novel optimization algorithms: Low-Discrepancy Search (LDSearch) for efficient parameter initialization and KDE-FocusSampler for focused sampling of regions that are difficult to approximate. …”
Get full text

FOOD WASTE MANAGEMENT USING STATISTICAL ANALYSIS TO OBTAIN NEW FUNCTIONAL PRODUCTS by Gjore NAKOV, Zlatin ZLATEV, Nastia IVANOVA, Ivan DIMOV

“…It has been found that the amount of apple residues in cookies is APP=23,6±1,3%, which can be considered as optimal. The proposed methods and tools have the potential to reduce food and waste losses. …”
Get full text

Exposed conductor detection of 10 kV distribution line based on improved YOLOv8 by Qiwen JING, Sipeng HAO, Siyuan LI

Get full text

Enhancing Stock Price Forecasting With a Hybrid SES-DA-BiLSTM-BO Model: Superior Accuracy in High-Frequency Financial Data Analysis by Talabathula Jayanth, A. Manimaran, G. Siva

“…By outperforming baseline model on various error metrics, the proposed SES-DA-BiLSTM-BO hybrid model exhibits improved predictive capabilities and lower loss functions, making its highly reliable for forecasting stock prices under diverse market conditions. …”
Get full text

Activity cliff-aware reinforcement learning for de novo drug design by Xiuyuan Hu, Guoqing Liu, Yang Zhao, Hao Zhang

“…ACARL’s primary technical contributions include the formulation of an activity cliff index to detect these critical points, and a contrastive RL loss function that dynamically enhances the generation of activity cliff compounds, optimizing the model for high-impact SAR regions. …”
Get full text

Sentiment Analysis Algorithm Based on Deep Transfer Learning for Multi-Source Data Fusion by Long Qin

“…The experiment outcomes indicate that the artificial bee colony-improved particle swarm optimization algorithm designed in the study has the minimum convergence value under single-peak and multi-peak test functions, with a standard deviation of less than 0.25 and a success rate of 100% in optimization. …”
Get full text