Skip to Content

8,403 Results Found

  • Article
  • Open Access
7 Citations
4,441 Views
24 Pages

This paper presents Laor Initialization, an innovative weight initialization technique for deep neural networks that utilizes forward-pass error feedback in conjunction with k-means clustering to optimize the initial weights. In contrast to tradition...

  • Article
  • Open Access
1 Citations
1,144 Views
24 Pages

Revisiting Weight Initialization for Transfer Learning on Tabular Data: The Feature-Adaptive Variance Initialization (FAVI) Approach

  • Miroslav Nikolić,
  • Danilo Nikolić,
  • Miroslav Stefanović,
  • Tina Bigović and ,
  • Sara Koprivica and
  • Darko Stefanović
  • + 1 author+ 0 author

1 April 2026

Transfer learning has advanced significantly in domains like computer vision and natural language processing, yet its application to tabular data remains challenging, with traditional models like XGBoost often outperforming deep learning approaches d...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Article
  • Open Access
1 Citations
3,101 Views
17 Pages

23 July 2024

Addressing the issues of prolonged training times and low recognition rates in large model applications, this paper proposes a weight training method based on entropy gain for weight initialization and dynamic adjustment of the learning rate using th...

(This article belongs to the Section Signal and Data Analysis)
  • Article
  • Open Access
2 Citations
3,717 Views
26 Pages

13 July 2021

A repeatable and deterministic non-random weight initialization method in convolutional layers of neural networks examined with the Fast Gradient Sign Method (FSGM). Using the FSGM approach as a technique to measure the initialization effect with con...

(This article belongs to the Collection Robotics, Sensors and Industry 4.0)
  • Article
  • Open Access
263 Views
29 Pages

21 September 2026

The choice of activation functions and weight initialization strategies plays a critical role in the trainability and performance of deep neural networks. In deep architectures, improper weight initialization can lead to vanishing or exploding signal...

  • Article
  • Open Access
1 Citations
1,708 Views
27 Pages

2 September 2025

This study presents a gradient-informed proxy initialization framework designed to improve training efficiency and predictive performance in deep learning models for time-series forecasting. The method extends the Laor Initialization approach by intr...

  • Feature Paper
  • Article
  • Open Access
6 Citations
2,143 Views
18 Pages

11 October 2023

The focus of this study is to investigate the impact of different initialization strategies for the weight matrix of Successor Features (SF) on the learning efficiency and convergence in Reinforcement Learning (RL) agents. Using a grid-world paradigm...

(This article belongs to the Special Issue Medical Applications of Artificial Intelligence)
  • Article
  • Open Access
1 Citations
1,883 Views
29 Pages

Initial Body Weight as an Important Factor for Improving the Reliability and Translational Relevance of the Preclinical Monocrotaline-Induced Rat Pulmonary Hypertension Model

  • Patryk Remiszewski,
  • Piotr Ryszkiewicz,
  • Marta Baranowska-Kuczko,
  • Anna Pędzińska-Betiuk and ,
  • Krzysztof Mińczuk,
  • Monika Kloza,
  • Jolanta Weresa,
  • Tomasz Hutsch and
  • Barbara Malinowska
  • + 4 authors+ 0 author

12 September 2025

Animal preclinical experiments in pulmonary hypertension (PH) need to be conducted with detailed methodological rigor to improve their translational relevance. One of its crucial yet insufficiently studied aspects is animal body weight (BW). Thus, ou...

(This article belongs to the Special Issue Advances in Pulmonary Hypertension and Interstitial Lung Diseases: Mechanisms and Treatments)
  • Article
  • Open Access
20 Citations
3,494 Views
16 Pages

14 December 2023

The deep learning diagnosis of aircraft engine-bearing faults enables cost-effective predictive maintenance while playing an important role in increasing the safety, reliability, and efficiency of aircraft operations. Because of highly dynamic and ha...

(This article belongs to the Special Issue Advances in Fault Diagnosis and Anomaly Detection)
  • Article
  • Open Access
12 Citations
7,511 Views
14 Pages

Toward Efficient Image Recognition in Sensor-Based IoT: A Weight Initialization Optimizing Method for CNN Based on RGB Influence Proportion

  • Zile Deng,
  • Yuanlong Cao,
  • Xinyu Zhou,
  • Yugen Yi and ,
  • Yirui Jiang and
  • Ilsun You
  • + 1 author+ 0 author

18 May 2020

As the Internet of Things (IoT) is predicted to deal with different problems based on big data, its applications have become increasingly dependent on visual data and deep learning technology, and it is a big challenge to find a suitable method for I...

(This article belongs to the Special Issue Selected papers from WISA 2019)
  • Concept Paper
  • Open Access
2 Citations
2,916 Views
10 Pages

Heuristic Weight Initialization for Diagnosing Heart Diseases Using Feature Ranking

  • Musulmon Lolaev,
  • Shraddha M. Naik,
  • Anand Paul and
  • Abdellah Chehri

The advent of Artificial Intelligence (AI) has had a broad impact on life to solve various tasks. Building AI models and integrating them with modern technologies is a central challenge for researchers. These technologies include wearables and implan...

(This article belongs to the Section Assistive Technologies)
  • Review
  • Open Access
34 Citations
7,273 Views
11 Pages

18 September 2022

Heat stress during the preflowering panicle initiation stage seriously decreases rice grain weight in an invisible way and has not been given enough attention. The current review aims to (i) specify the heat effects on rice grain weight during the pa...

(This article belongs to the Special Issue Advanced Research in Plant Responses to Environmental Stresses 2.0)
  • Article
  • Open Access
5 Citations
5,887 Views
20 Pages

18 February 2023

One essential problem in aircraft conceptual design is initial sizing in which the aircraft primary parameters such as weight, size, and thrust are estimated for given design requirements. The airbreathing hypersonic aircraft is a type of novel aircr...

(This article belongs to the Special Issue Supersonic and Hypersonic Transportation Systems)
  • Article
  • Open Access
11 Citations
3,044 Views
10 Pages

25 December 2021

Drop-weight tests were conducted to investigate the impact-initiation sensitivity of high-temperature PTFE-Al-W reactive materials. The test results show that the impact-initiation sensitivity of the materials more than doubles with increasing the sa...

  • Article
  • Open Access
2 Citations
2,932 Views
23 Pages

29 July 2023

This paper proposes a wireless channel equalization method applied to the constant modulus blind equalization system, which addresses the slow convergence and strong randomness in the initialization of equalizer weights in the constant modulus blind...

(This article belongs to the Section E: Applied Mathematics)
  • Article
  • Open Access
417 Views
20 Pages

Mechanical Mechanism of Abnormally High Pumping Pressure During Hydraulic Fracturing of Deep-to-Ultra-Deep Fine Sandstone Reservoirs in the Junggar Basin

  • Liyan Pan,
  • Han Song,
  • Jian Zhou,
  • Beibei Chen and ,
  • Qi Chen,
  • Yiyu Bao,
  • Zerun Duan,
  • Zewei Liu,
  • Xiaohan Wang and
  • Yan Peng
  • + 5 authors+ 0 author

20 June 2026

To address the widespread issue of abnormally high pump pressure during hydraulic fracturing of deep-to-ultra-deep reservoirs (burial depth > 4500 m) in the Junggar Basin, this study systematically reveals the mechanical mechanism underlying this...

(This article belongs to the Special Issue Hydraulic Fracturing Experiment, Simulation, and Optimization)
  • Article
  • Open Access
29 Citations
5,850 Views
13 Pages

27 April 2023

Behavioral malware analysis is a powerful technique used against zero-day and obfuscated malware. Additionally referred to as dynamic malware analysis, this approach employs various methods to achieve enhanced detection. One such method involves usin...

(This article belongs to the Special Issue Machine Learning for Cybersecurity Threats, Challenges, and Opportunities III)
  • Article
  • Open Access
34 Citations
3,895 Views
24 Pages

20 January 2022

Particle Swarm Optimization is a metaheuristic optimization algorithm widely used across a broad range of applications. The algorithm has certain primary advantages such as its ease of implementation, high convergence accuracy, and fast convergence s...

(This article belongs to the Collection Software Engineering: Computer Science and System)
  • Article
  • Open Access
18 Citations
10,453 Views
13 Pages

16 April 2016

A polymerizable ionic liquid, N,N-diethyl-N-(2-methacryloylethyl)-N-methylammonium bis(trifluoromethylsulfonyl)imide (DEMM-TFSI), was polymerized via copper-mediated atom transfer radical polymerization (ATRP). The polymerization proceeded in a livin...

(This article belongs to the Collection Silicon-Containing Polymeric Materials)
  • Article
  • Open Access
4 Citations
2,287 Views
32 Pages

29 November 2024

The Belt and Road Initiative holds significant importance for achieving the United Nations’ Sustainable Development Goals, particularly Goals 9 and 17. Drawing on data from the Web of Science database, the BRI database, and the World Bank datab...

(This article belongs to the Section Development Goals towards Sustainability)
  • Article
  • Open Access
24 Citations
4,888 Views
16 Pages

The In Vitro Enzymatic Degradation of Cross-Linked Poly(trimethylene carbonate) Networks

  • Zhipeng Hou,
  • Jianshe Hu,
  • Jianxin Li,
  • Wei Zhang and ,
  • Miao Li,
  • Jing Guo,
  • Liqun Yang and
  • Zhangpei Chen
  • + 3 authors+ 0 author

13 November 2017

The in vitro enzymatic degradation of cross-linked poly(trimethylene carbonate) networks (PTMC-Ns) was performed in lipase solutions at 37 °C, and the effect of the initial molecular weight and cross-linker amount as well as the cross-linker type on...

  • Article
  • Open Access
2 Citations
1,827 Views
24 Pages

A Research on Multi-Index Intelligent Integrated Prediction Model of Catchment Pollutant Load under Data Scarcity

  • Donghao Miao,
  • Wenquan Gu,
  • Wenhui Li,
  • Jie Liu and ,
  • Wentong Hu,
  • Jinping Feng and
  • Dongguo Shao
  • + 2 authors+ 0 author

16 April 2024

Within a river catchment, the relationship between pollutant load migration and its related factors is nonlinear generally. When neural network models are used to identify the nonlinear relationship, data scarcity and random weight initialization mig...

  • Article
  • Open Access
2 Citations
1,629 Views
15 Pages

12 October 2024

The disposal and reutilization of the enormous amounts of slurry-like mud (MS) dredged from navigation channel construction, ecological dredging, and other construction activities have been receiving increasing attention. In this paper, a flocculatio...

  • Article
  • Open Access
10 Citations
2,018 Views
8 Pages

11 February 2022

This work deals with the design of the thickness of an AZ31 alloy blank, which is a superplastic magnesium material, to manufacture a hemisphere with a uniform final thickness. The finite element technique was used for the design process. The superpl...

(This article belongs to the Section Mechanical Engineering)
  • Article
  • Open Access
538 Views
22 Pages

20 April 2026

Full fine-tuning of pre-trained models sometimes requires inserting trainable layers into the middle of a pre-trained backbone, but such middle-layer insertion can severely degrade downstream performance. We hypothesize that this degradation arises b...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Article
  • Open Access
9 Citations
4,026 Views
10 Pages

Determinants of Delayed Initiation of Breastfeeding: A Cross-Sectional Multicenter Study in Abu Dhabi, the United Arab Emirates

  • Zainab Taha,
  • Aysha Ibrahim Al Dhaheri,
  • Ludmilla Wikkeling-Scott,
  • Ahmed Ali Hassan and
  • Dimitrios Papandreou

One of the best practices to reduce the risk of infant morbidity and mortality is the early initiation of breastfeeding, specifically within the first hour of birth, as the World Health Organization (WHO) recommends. Limited data exist on breastfeedi...

(This article belongs to the Special Issue 1000 Days to Get a Good Start in a Child's Life)
  • Feature Paper
  • Article
  • Open Access
7 Citations
6,001 Views
20 Pages

24 September 2019

With the increase in offshore wind farms, the demands for umbilicals and power cables have increased. The on-bottom stability of umbilicals and power cables under the combined wave and current loading is the most challenging design issue, due to thei...

(This article belongs to the Special Issue Recent Advances in Offshore Wind Technology)
  • Article
  • Open Access
14 Citations
2,877 Views
24 Pages

Empowering Foot Health: Harnessing the Adaptive Weighted Sub-Gradient Convolutional Neural Network for Diabetic Foot Ulcer Classification

  • Abdullah Alqahtani,
  • Shtwai Alsubai,
  • Mohamudha Parveen Rahamathulla,
  • Abdu Gumaei and ,
  • Mohemmed Sha,
  • Yu-Dong Zhang and
  • Muhammad Attique Khan
  • + 2 authors+ 0 author

1 September 2023

In recent times, DFU (diabetic foot ulcer) has become a universal health problem that affects many diabetes patients severely. DFU requires immediate proper treatment to avert amputation. Clinical examination of DFU is a tedious process and complex i...

(This article belongs to the Special Issue Explainable Artificial Intelligence for Trustworthy Machine Learning and Deep Learning Models in Healthcare)
  • Article
  • Open Access
65 Views
20 Pages

Heterogeneous Effects of Cesarean Delivery Across Maternal and Infant Outcomes Using Population-Based Causal Machine Learning

  • Emmanuel U. Azu,
  • Gulzar Shah,
  • Tobi Oloyede,
  • Jing X. Kersey and ,
  • Timothy Kizza and
  • Lili Yu
  • + 1 author+ 0 author

6 November 2026

Cesarean delivery is associated with maternal and infant outcomes, but population-average estimates may obscure variation across individuals. This study examined associations between delivery mode and four maternal and infant outcomes and explored he...

  • Article
  • Open Access
44 Citations
6,726 Views
28 Pages

4 April 2019

Agriculture is increasingly facing major challenges such as climate change, scarcity of natural resources, and changing societal demands. To tackle these challenges, there is a pressing need to evolve towards more sustainable agricultural practices....

(This article belongs to the Section Sustainable Agriculture)
  • Article
  • Open Access
299 Views
22 Pages

21 September 2026

To address the issue of long ambiguity resolution (AR) time for existing medium-to-long baseline reference stations, this paper proposes a rapid ambiguity fixing method with empirical ionospheric constraints. The method directly treats the L1 and wid...

(This article belongs to the Topic Theory and Methods for High-Trust and High-Security PNT Information)
  • Article
  • Open Access
14 Citations
2,374 Views
18 Pages

4 April 2022

In this paper, we deal with the existence of integrable solutions of Gripenberg-type equations with m-product of fractional operators on a half-line R+=[0,∞). We prove the existence of solutions in some weighted spaces of integrable functions,...

(This article belongs to the Special Issue Fractional Differential Equations: Theory and Application)
  • Article
  • Open Access
29 Citations
5,007 Views
21 Pages

Electric Power Investment Risk Assessment for Belt and Road Initiative Nations

  • Jiahai Yuan,
  • Yurong Zeng,
  • Xiaoxuan Guo,
  • Yu Ai and
  • Minpeng Xiong

31 August 2018

In recent years, Chinese companies’ investment in overseas electric power has grown rapidly. Chinese enterprises with matured technology and abundant talent in the field of electric power and electric power investment are becoming the focus of...

  • Article
  • Open Access
69 Citations
4,885 Views
18 Pages

25 March 2023

Overfitting may affect the accuracy of predicting future data because of weakened generalization. In this research, we used an electronic health records (EHR) dataset concerning breast cancer metastasis to study the overfitting of deep feedforward ne...

(This article belongs to the Collection Artificial Intelligence in Oncology)
  • Article
  • Open Access
3 Citations
3,108 Views
15 Pages

Dynamic Initial Weight Assignment for MaxSAT

  • Abdelraouf Ishtaiwi and
  • Qasem Abu Al-Haija

31 March 2021

The Maximum Satisfiability (Maximum Satisfiability (MaxSAT)) approach is the choice, and perhaps the only one, to deal with most real-world problems as most of them are unsatisfiable. Thus, the search for a complete and consistent solution to a real-...

(This article belongs to the Section Randomized, Online, and Approximation Algorithms)
  • Article
  • Open Access
3 Citations
1,159 Views
29 Pages

Under large azimuth misalignment conditions, the initial alignment of strapdown inertial navigation systems (SINS) is challenged by the nonlinear characteristics of the error model. Traditional particle filter (PF) algorithms suffer from the inapprop...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
10 Citations
4,977 Views
19 Pages

8 October 2020

With the implementation of China’s “Going Out” strategy and “Belt and Road Initiative” (BRI) as well as the shortage of domestic hydropower market, the scale of hydropower investment along BRI by Chinese companies has ex...

(This article belongs to the Section Energy Sustainability)
  • Article
  • Open Access
12 Citations
3,820 Views
18 Pages

Compression of Deep Convolutional Neural Network Using Additional Importance-Weight-Based Filter Pruning Approach

  • Shrutika S. Sawant,
  • Marco Wiedmann,
  • Stephan Göb,
  • Nina Holzer and ,
  • Elmar W. Lang and
  • Theresa Götz
  • + 1 author+ 0 author

4 November 2022

The success of the convolutional neural network (CNN) comes with a tremendous growth of diverse CNN structures, making it hard to deploy on limited-resource platforms. These over-sized models contain a large amount of filters in the convolutional lay...

  • Article
  • Open Access
1 Citations
2,143 Views
31 Pages

14 August 2025

Amid an increasingly complex and uncertain global landscape, geopolitical tensions and frequent trade frictions have emerged as critical external risks threatening the economic stability and sustainable development of Chinese cities. Enhancing cities...

  • Article
  • Open Access
18 Citations
4,609 Views
17 Pages

Effect of Initial Configuration of Weights on Training and Function of Artificial Neural Networks

  • Ricardo J. Jesus,
  • Mário L. Antunes,
  • Rui A. da Costa,
  • Sergey N. Dorogovtsev and ,
  • José F. F. Mendes and
  • Rui L. Aguiar
  • + 1 author+ 0 author

13 September 2021

The function and performance of neural networks are largely determined by the evolution of their weights and biases in the process of training, starting from the initial configuration of these parameters to one of the local minima of the loss functio...

(This article belongs to the Special Issue Computational Optimizations for Machine Learning)
  • Article
  • Open Access
6 Citations
2,286 Views
31 Pages

MISAO: Ultra-Short-Term Photovoltaic Power Forecasting with Multi-Strategy Improved Snow Ablation Optimizer

  • Xu Zhang,
  • Jun Ye,
  • Shenbing Ma,
  • Lintao Gao and ,
  • Hui Huang and
  • Qiman Xie
  • + 1 author+ 0 author

19 August 2024

The increase in installed PV capacity worldwide and the intermittent nature of solar resources highlight the importance of power prediction for grid integration of this technology. Therefore, there is an urgent need for an effective prediction model,...

  • Article
  • Open Access
48 Citations
34,738 Views
13 Pages

Long-Term Weight Change after Initiating Second-Generation Antidepressants

  • David Arterburn,
  • Tamar Sofer,
  • Denise M. Boudreau,
  • Andy Bogart and ,
  • Emily O. Westbrook,
  • Mary Kay Theis,
  • Greg Simon and
  • Sebastien Haneuse
  • + 3 authors+ 0 author

(1) Objective: To examine the relationship between the choice of second-generation antidepressant drug treatment and long-term weight change; (2) Methods: We conducted a retrospective cohort study to investigate the relationship between choice of ant...

  • Article
  • Open Access
1 Citations
2,814 Views
13 Pages

The Effects of Post-Surgical Pregnancy on Weight Loss Trajectories after Bariatric Surgery: Are Initial Weight and Age Prognostic Factors?

  • Juan S. Barajas-Gamboa,
  • Mohammed Sakib Ihsan Khan,
  • Jerry T. Dang,
  • Gustavo Romero-Velez and ,
  • Gabriel Diaz Del Gobbo,
  • Mohammed Abdallah,
  • Juan Pablo Pantoja,
  • Carlos Abril,
  • Alfredo D. Guerron and
  • M. Jean Uy-Kroh
  • + 9 authors+ 4 authors

23 February 2024

Introduction: A substantial percentage of patients undergoing bariatric surgery are of childbearing age. Pregnancy outcomes after bariatric surgery are known. However, there are limited data on the impact of pregnancy on weight loss after surgery. Ob...

(This article belongs to the Section General Surgery)
  • Article
  • Open Access
10 Citations
3,528 Views
14 Pages

A Dynamic Clause Specific Initial Weight Assignment for Solving Satisfiability Problems Using Local Search

  • Abdelraouf Ishtaiwi,
  • Feda Alshahwan,
  • Naser Jamal,
  • Wael Hadi and
  • Muhammad AbuArqoub

5 January 2021

For decades, the use of weights has proven its superior ability to improve dynamic local search weighting algorithms’ overall performance. This paper proposes a new mechanism where the initial clause’s weights are dynamically allocated ba...

(This article belongs to the Section Randomized, Online, and Approximation Algorithms)
  • Article
  • Open Access
5 Citations
3,772 Views
17 Pages

Evaluation of Gel Coating Performance in Extending the Shelf Life of Egg: The Role of Surface Area and Initial Weight

  • Thanh Tung Pham,
  • Lien Le Phuong Nguyen,
  • László Baranyai,
  • Mai Sao Dam and ,
  • Nga Thi Thanh Ha,
  • Adrienn Varga-Tóth,
  • István Dalmadi,
  • Csaba Németh and
  • László Ferenc Friedrich
  • + 4 authors+ 0 author

23 July 2024

This work investigated the impact of chicken egg size, including surface area and initial weight, on the effectiveness of cassava starch-based gel coating during storage at room temperature. The quality of a total of 540 fresh eggs in four different...

(This article belongs to the Special Issue Bioactive Gel Films and Coatings Applied in Active Food Packaging (2nd Edition))
  • Article
  • Open Access
976 Views
11 Pages

Feasibility of T2-Weighted MRI Radiomics for Initial Risk Stratification in Pediatric Neuroblastoma

  • Annalisa Tondo,
  • Irene Ferri,
  • Mattia Biavati,
  • Federica Carra and ,
  • Irene Trambusti,
  • Andrea Di Cataldo,
  • Maurizio Aricò,
  • Lorenzo Lasagni,
  • Ubaldo Bongini and
  • Anna Perrone
  • + 7 authors+ 2 authors

26 March 2026

Purpose: The purpose of this study was to evaluate the feasibility of magnetic resonance imaging (MRI)-based radiomics derived from routine T2-weighted imaging for initial risk stratification in pediatric neuroblastoma (NB) and to explore its potenti...

(This article belongs to the Section Pediatric Hematology & Oncology)
  • Article
  • Open Access
27 Citations
6,637 Views
25 Pages

20 February 2024

Soil-water characteristic curve (SWCC) is an essential parameter in unsaturated soil mechanics, and it plays a significant role in geotechnical engineering to enhance theoretical analysis and numerical calculations. This study investigated the effect...

(This article belongs to the Section Soil and Water)
  • Article
  • Open Access
3 Citations
2,268 Views
16 Pages

Synthesis of Ultrahigh Molecular Weight Poly (Trifluoroethyl Methacrylate) Initiated by the Combination of Palladium Nanoparticles with Organic Halides

  • Jian Guan,
  • Xiaodi Yu,
  • Minghui He,
  • Wenfeng Han and ,
  • Ying Li,
  • Zongjian Liu,
  • Panpan Zhang and
  • Haodong Tang
  • + 3 authors+ 0 author

30 September 2024

Ultrahigh molecular weight polymers display outstanding properties and have great application potential. However, the traditional polymerization methods have inevitable disadvantages that challenge the green synthesis of ultrahigh molecular weight po...

(This article belongs to the Special Issue Nanopolymers and Nanocomposites)
  • Article
  • Open Access
1 Citations
1,865 Views
16 Pages

28 November 2024

Using the quenching process to create a specific residual stress distribution in steel parts is a key method for improving their strength. Although finite element simulation can overcome the time-consuming and labor-intensive limitations of experimen...

  • Article
  • Open Access
1 Citations
3,372 Views
19 Pages

Initial Weight Loss, Anthropometric Parameters, and Proinflammatory Transcript Levels in Patients with Class I Obesity

  • Beata Jabłonowska-Lietz,
  • Grażyna Nowicka,
  • Marta Włodarczyk,
  • Sławomir Rejowski and ,
  • Maria Stasiowska and
  • Małgorzata Wrzosek
  • + 1 author+ 0 author

Research into early predictors of effective weight loss could help determine more effective therapeutic interventions. In this study, 106 subjects with class I obesity, genotyped with the fat mass and obesity-associated (FTO) rs9930506 gene variant,...

(This article belongs to the Special Issue State-of-the-Art Molecular and Translational Medicine in Poland)

of 169