Processing, Please wait...

  • Publisher Home
  • Home
  • ๐Ÿ”™ Back
  • ๐Ÿ“š Journals
    • โš™๏ธ IJIEC - Industrial Engineering Computations
    • ๐ŸŒ IJDNS - Data and Network Science
    • ๐Ÿงช CCL - Current Chemistry Letters
    • ๐Ÿ’น AC - Accounting
    • ๐ŸŽฏ DSL - Decision Science Letters
    • ๐Ÿš› USCM - Uncertain Supply Chain Management
    • ๐Ÿ—๏ธ JPM - Journal of Project Management
    • ๐Ÿฅ HE - Healthcare Engineering
    • ๐Ÿ“ˆ SCI - Scientometrica
    • ๐Ÿ”ฉ ESM - Engineering Solid Mechanics
    • ๐ŸŒฟ JFS - Journal of Future Sustainability
    • ๐Ÿ’ผ MSL - Management Science Letters
  • ๐Ÿ“ Submit Article
  • ๐Ÿ“Š Statistics
  • ๐Ÿ“‹ About
    • ๐Ÿ“„ About Us
    • ๐Ÿ“ฐ Blog
    • ๐Ÿ“ข News
    • ๐Ÿ“ง Contact
  • ๐Ÿ“บ Tutorial
  • Search:
  • Advanced Search

Growing Science » Tags cloud » Convolutional neural network

โญ Highly Cited Articles

  • Jaya Algorithm
  • Rao Algorithm
  • TLBO Algorithm
  • ChatGPT and Blended Learning

Journals

  • IJIEC (840)
  • IJDS (1032)
  • DSL (759)
  • ESM (434)
  • CCL (563)
  • JPM (350)
  • AC (572)
  • JFS (106)
  • MSL (2658)
  • USCM (1104)
  • HE (56)
  • SCI (53)

๐Ÿ”‘ Keywords

Jordan(175)
Supply chain management(172)
Vietnam(154)
Customer satisfaction(124)
Performance(117)
Supply chain(115)
Artificial intelligence(108)
Service quality(101)
Competitive advantage(100)
SMEs(95)
Tehran Stock Exchange(94)
Sustainability(94)
optimization(88)
Financial performance(86)
TOPSIS(85)
Trust(85)
Organizational performance(81)
Job satisfaction(81)
Genetic Algorithm(81)
Social media(80)


» Show all keywords

โœ๏ธ Authors

Naser Azad(82)
Zeplin Jiwa Husada Tarigan(70)
Mohammad Reza Iravani(65)
Endri Endri(45)
Hotlan Siagian(43)
Muhammad Alshurideh(42)
Dmaithan Almajali(39)
Jumadil Saputra(37)
Muhammad Turki Alshurideh(35)
Ahmad Makui(33)
Sautma Ronni Basana(33)
Barween Al Kurdi(32)
Basrowi Basrowi(31)
Mohammad Khodaei Valahzaghard(30)
Haitham M. Alzoubi(30)
Ni Nyoman Kerti Yasa(30)
Hassan Ghodrati(30)
Shankar Chakraborty(29)
Sulieman Ibraheem Shelash Al-Hawary(28)
Mahmoud Allahham(28)


» Show all authors

๐ŸŒ Countries

1. Algeria (52)
2. Angola (2)
3. Argentina (22)
4. Armenia (2)
5. Australia (52)
6. Austria (2)
7. Bahrain (26)
8. Bangladesh (58)
9. Belarus (4)
10. Belgium (3)
11. Benin (2)
12. Benin Republic (1)
13. Bhutan (1)
14. Bosnia and Herzegovina (1)
15. Botswana (9)
16. Brazil (40)
17. Brunei (1)
18. Bulgaria (1)
19. Burkina Faso (1)
20. Cameroon (1)
Total: 121 countries

Show all countries
Sort articles by: ๐Ÿ“– Volume | ๐Ÿ“… Date | โญ Most Rates | ๐Ÿ‘๏ธ Most Views | ๐Ÿš€ Rising Stars | ๐Ÿ”— Citations (Scopus) | ๐Ÿ”ฅ Hot Papers
1.

A convolutional deep reinforcement learning architecture for an emerging stock market analysis Pages 313-326 PDF Download PDF

Authors: Anita Hadizadeh, Mohammad Jafar Tarokh, Majid Mirzaee Ghazani

doi 10.5267/j.dsl.2025.1.006

๐Ÿ”‘ Keywords: Deep reinforcement learning, DDQN, Convolutional neural network, Stock Market Prediction, Q-learning, Overfitting Prevention

Abstract:
In the complex and dynamic stock market landscape, investors seek to optimize returns while minimizing risks associated with price volatility. Various innovative approaches have been proposed to achieve high profits by considering historical trends and social factors. Despite advancements, accurately predicting market dynamics remains a persistent challenge. This study introduces a novel deep reinforcement learning (DRL) architecture to forecast stock market returns effectively. Unlike traditional approaches requiring manual feature engineering, the proposed model leverages convolutional neural networks (CNNs) to directly process daily stock prices and financial indicators. The model addresses overfitting and data scarcity issues during training by replacing conventional Q-tables with convolutional layers. The optimization process minimizes the sum of squared errors, enhancing prediction accuracy. Experimental evaluations demonstrate the model's robustness, achieving a 67% improvement in directional accuracy over the buy-and-hold strategy across short-term and long-term horizons. These findings underscore the modelโ€™s adaptability and effectiveness in navigating complex market environments, offering a significant advancement in financial forecasting.
Details
  • 0
  • 1
  • 2
  • 3
  • 4
  • 5

Journal: DSL | Year: 2025 | Volume: 14 | Issue: 2 | Views: 3521

 
2.

A convolutional neural network for the resource-constrained project scheduling problem (RCPSP): A new approach Pages 225-238 PDF Download PDF

Authors: Amir Golab, Ehsan Sedgh Gooya, Ayman Al Falou, Mikael Cabon

doi 10.5267/j.dsl.2023.2.002

๐Ÿ”‘ Keywords: Project scheduling, Scheduling, Project management, Artificial neural network, Convolutional neural network, RCPSP, Resource constraint

Abstract:
All projects require a structure to meet project requirements and achieve established goals. This framework is called project management. Therefore, project management plays an important role in national development and economic growth. Project management includes various knowledge areas such as project integration management, project scope management, project schedule management, etc. The article focuses on the resource-constrained project scheduling known as problem so- called the resource-constrained project scheduling problem (RCPSP). The RCPSP is a part of schedule management. The standard RCPSP has two important constraints, resource constraints and precedence relationships of activities during project scheduling. The objective of the problem is to optimize and minimize the project duration, subject to the above constraints. In this paper, we develop a convolutional neural network approach to solve the standard single mode RCPSP. The advantage of this algorithm over conventional methods such as metaheuristics is that it does not need to generate many solutions or populations. In this paper, the serial schedule generation scheme (SSGS) is used to schedule the project activities using an evolved convolutional neural network (CNN) as a tool to select an appropriate priority rule to filter out a candidate activity. The evolved CNN learns according to the eight project parameters, namely network complexity, resource factor, resource strength, average work per activity, etc. The above parameters are the inputs of the network and are recalculated at each step of the project planning. Moreover, the developed network has priority rules which are the outputs of the developed neural network. Therefore, after the learning process, the network can automatically select an appropriate priority rule to filter an activity from the eligible activities. In this way, the algorithm is able to schedule all project activities according to the given project constraints. Finally, the performance of the Convolutional Neural Network (CNN) approach is investigated using standard benchmark problems from PSPLIB in comparison to the MLFNN approach and standard metaheuristics.
Details
  • 0
  • 1
  • 2
  • 3
  • 4
  • 5

Journal: DSL | Year: 2023 | Volume: 12 | Issue: 2 | Views: 2085

 
3.

Neural technology and human augmentation: A bibliometric analysis of research evolution, emerging paradigms, and future trajectories based on 200 highly cited publications (2009โ€“2025) Pages 281-302 PDF Download PDF

Authors: Kouroush Jenab

doi 10.5267/j.sci.2026.5.010

๐Ÿ”‘ Keywords: Brain-Computer Interface, Neural Technology, Human Augmentation, Deep Learning, Convolutional Neural Network, Data Augmentation, Bibliometric Analysis, Generative Adversarial Network, Transfer Learning, Neurorehabilitation, Medical Image Analysis, Assisti

Abstract:
This bibliometric survey examines 200 highly cited publications spanning from 2009 to 2025, retrieved from the Scopus database using the search strategy targeting neural technology and human augmentation. The analysis reveals a transformative evolution from foundational neuroscience discoveries to sophisticated artificial intelligence-driven augmentation systems. Key findings indicate that deep learning architectures, particularly convolutional neural networks (CNNs), generative adversarial networks (GANs), and transfer learning approaches have become dominant methodological frameworks across 78% of analyzed publications. Data augmentation emerges as a critical enabling technology, appearing in over 35% of publications, addressing the persistent challenge of limited labeled data in biomedical applications. The United States, China, Germany, India, and South Korea represent the most productive nations, with intensifying international collaboration networks from 2015 onward. Thematic clustering identifies five major research domains: (1) brain-computer interfaces and neural signal decoding, (2) deep learning for medical image analysis, (3) sensory augmentation and assistive technologies, (4) data augmentation and synthetic data generation, and (5) ethical and regulatory frameworks for human enhancement. Emerging trends include transformer-based architectures, self-supervised learning, federated learning for privacy-preserving applications, and the convergence of neurotechnology with IoT-enabled wearable systems. This survey provides a comprehensive mapping of the intellectual landscape, identifies persistent research gaps including clinical translation barriers and dataset standardization, and proposes future directions for responsible neural augmentation technology development.
Details
  • 68
  • 1
  • 2
  • 3
  • 4
  • 5

Journal: SCI | Year: 2026 | Volume: 2 | Issue: 4 | Views: 193

 

® 2010-2026 GrowingScience.Com