IETE journal of research Acceptance Rate - ResearchHelpDesk - IETE Journal of Research is a bimonthly journal published by the Institution of Electronics and Telecommunication Engineers (IETE), India. It publishes scientific and technical papers describing original research work or novel product/process development. Occasionally special issues are brought out on new and emerging research areas. This journal is useful to researchers, engineers, scientists, teachers, managers, and students who are interested in keeping track of original research and development work being carried out in the broad area of electronics, telecommunications, computer science, and engineering and information technology. Subjects covered by this journal are: Communications: Digital and analog communication, Digital signal processing, Image processing, Satellite communication, Secure communication, Speech and audio processing, Space communication, Vehicular communications, Wireless communication. Computers and Computing: Algorithms, Artificial intelligence, Computer graphics, Compiler programming and languages, Computer vision, Data mining, High-performance computing, Information technology, Internet computing, Multimedia, Networks, Network Security, Operating systems, Quantum learning systems, Pattern Recognition, Sensor networks, Soft computing. Control Engineering: Control theory and practice- Conventional control, Non-linear control, Adaptive control, Robust Control, Reinforcement learning control, Soft computing tools in control application- Fuzzy logic systems, Neural Networks, Support vector machines, Intelligent control. Electromagnetics: Antennas and arrays, Bio-electromagnetics, Computational electromagnetics, Electromagnetic interference, Electromagnetic compatibility, Metamaterials, Millimeter-wave and Terahertz circuits and systems, Microwave measurements, Microwave Photonics, Passive, active and tunable microwave circuits, Propagation studies, Radar and remote sensing, Radio wave propagation and scattering, RFID, RF MEMS, Solid-state microwave devices and tubes, UWB circuits and systems. Electronic Circuits, Devices, and Components: Analog and Digital circuits, Display Technology, Embedded Systems VLSI Design, Microelectronics technology and device characterization, MEMS, Nano-electronics, Nanotechnology, Physics and technology of CMOS devices, Sensors, Semiconductor device modeling, Space electronics, Solid state devices, and modeling. Instrumentation and Measurements: Automated instruments and measurement techniques, Industrial Electronics, Non-destructive characterization and testing, Sensors. Medical Electronics: Bio-informatics, Biomedical electronics, Bio-MEMS, Medical Instrumentation. Opto-Electronics: Fibre optics, Holography and optical data storage, Optical sensors Quantum Electronics, Quantum optics. Power Electronics: AC-DC/DC-DC/DC-AC/AC-AC converters, Battery chargers, Custom power devices, Distributed power generation, Electric vehicles, Electrochemical processes, Electronic blast, Flexible AC transmission systems, Heating/welding, Hybrid vehicles, HVDC transmission, Power quality, Renewal energy generation, Switched-mode power supply, Solid-state control of motor drives. The IETE Journal of Research is indexed in: British Library CLOCKSS CrossRef EBSCO - Applied Science & Technology Source EBSCO - Academic Search Complete EBSCO - STM Source EI Compendex/ Engineering Village (Elsevier) Google Scholar Microsoft Academic Portico ProQuest - ProQuest Central ProQuest - Research Library ProQuest - SciTech Premium Collection ProQuest - Technology Collection Science Citation Index Expanded (Thomson Reuters) SCImago (Elsevier) Scopus (Elsevier) Ulrich's Periodicals Directory Web of Science (Thomson Reuters) WorldCat Local (OCLC) Zetoc RG Journal Impact: 0.59 * *This value is calculated using ResearchGate data and is based on average citation counts from work published in this journal. The data used in the calculation may not be exhaustive. RG Journal impact history 2020 Available summer 2021 2018 / 2019 0.59 2017 0.39 2016 0.33 2015 0.49 2014 0.49 2013 0.41 2012 0.61 2011 0.90 2010 0.43 2009 0.22 2008 0.19 2007 0.23 2006 0.09 2005 0.11 2004 0.23 2003 0.38 IETE Journal of Research more details H Index - 20 Subject Area and Category: Computer Science, Computer Science Applications, Engineering, Electrical, and Electronic Engineering, Mathematics, Theoretical Computer Science Publisher: Taylor & Francis Publication Type: Journals Coverage : 1979-1989, 1993-ongoing

Relevant Papers: Nadine Hajj, Yara Rizk, and Mariette Awad, "A Subjectivity Classification Framework for Sports Articles using Cortical Algorithms for Feature Selection," Springer Neural Computing and Applications, 2018 (accepted for publication). Yara Rizk, and Mariette Awad, "Syntactic Genetic Algorithm for a Subjectivity Analysis of Sports Articles," International Conference on Cybernetic Intelligent Systems, Limerick, Ireland, 2012.

Features: Quotes Frequency of quotation pairs in the entire article questionmarks Frequency of questions marks in the entire article exclamationmarks Frequency of exclamation marks in the entire article fullstops Frequency of full stops commas Frequency of commas semicolon Frequency of semicolons colon Frequency of colons ellipsis Frequency of ellipsis pronouns1st Frequency of first person pronouns (personal and possessive) pronouns2nd Frequency of second person pronouns (personal and possessive) pronouns3rd Frequency of third person pronouns (personal and possessive) compsupadjadv Frequency of comparative and superlative adjectives and adverbs past Frequency of past tense verbs with 1st and 2nd person pronouns imperative Frequency of imperative verbs present3rd Frequency of present tense verbs with 3rd person pronouns present1st2nd Frequency of present tense verbs with 1st and 2nd person pronouns sentence1st First sentence class sentencelast Last sentence class txtcomplexity Text complexity score

The human brain can be considered as a complex dynamic and recurrent neural network. There are several models for neural networks of the human brain, that cover sensory to cortical information processing. Large majority models include feedback mechanisms that are hard to formalise to realistic applications. Recurrent neural networks and Long short-term memory (LSTM) inspire from the neuronal feedback networks. Long short-term memory (LSTM) prevent vanishing and exploding gradients problems faced by simple recurrent neural networks and has the ability to process order-dependent data. Such recurrent neural units can be replicated in hardware and interfaced with analog sensors for efficient and miniaturised implementation of intelligent processing. Implementation of analog memristive LSTM hardware is an open research problem and can offer the advantages of continuous domain analog computing with relatively low on-chip area compared with a digital-only implementation. Designed for solving time-series prediction problems, overall architectures and circuits were tested with TSMC 0.18 μm CMOS technology and hafnium-oxide (HfO2) based memristor crossbars. Extensive circuit based SPICE simulations with over 3,500 (inference only) and 300 system-level simulations (training and inference) were performed for benchmarking the system performance of the proposed implementations. The analysis includes Monte Carlo simulations for the variability of memristors' conductance, and crossbar parasitic, where non-idealities of hybrid CMOS-memristor circuits are taken into the account.

Big data images for conduction heat transfer The related paper has been published here: Edalatifar, Mohammad, Mohammad Bagher Tavakoli, Mohammad Ghalambaz, and Farbod Setoudeh. "Using deep learning to learn physics of conduction heat transfer." Journal of Thermal Analysis and Calorimetry 146, no. 3 (2021): 1435-1452. Links: https://doi.org/10.1007/s10973-020-09875-6 https://link.springer.com/article/10.1007/s10973-020-09875-6

Mohammad Edalatifar, Mohammad Ghalambaz, Mohammad Bagher Tavakoli, Farbod Setoudeh, New loss functions to improve deep learning estimation of heat transfer, Neural Computing and Applications Link: https://doi.org/10.1007/s00521-022-07233-1

Keywords: Deep convolutional neural networks - Loss function - Heat transfer images - Physical images - Artificial intelligence - CFD - Computational fluids dynamics - Finite volume method - Laplace equation - Dirichlet boundary condition

This dataset is being shared for the first time for public research after extensive research performed. See the following publications for more information.

• Jafari-Marandi, R., Denton, J., Idris, A., Smith, B. K., & Keramati, A. Optimum profit-driven churn decision making: innovative artificial neural networks in telecom industry. Neural Computing and Applications, 1-34.
• Keramati, A., Jafari-Marandi, R., Aliannejadi, M., Ahmadian, I., Mozaffari, M., & Abbasi, U. (2014). Improved churn prediction in the telecommunication industry using data mining techniques. Applied Soft Computing, 24, 994-1012.
• Keramati, A., & Ardabili, S. M. (2011). Churn analysis for an Iranian mobile operator. Telecommunications Policy, 35(4), 344-356.

This dataset is perfect for practicing prescriptive analysis such as predictive prescription or predictive decision making. The reason is that the dataset has the attribute of customer value which allows for creating False Positive (FP) and False Negative(FN) costs in case of misclassification. In standard classification tasks, it is assumed that FPs and FNs are the same, which is not the case for many cases. Furthermore, even if it is recognized that FPs and FNs are indeed different, their different balances per each data object are not understood or taken into consideration. This dataset gives you the opportunity to create a model that recognizes these complexities. For further information about the balance of FPs and FNs see the first mentioned publication. Also, you can find more information about each attribute on one of the publications.

Houssein, E. H., Emam, M. M., & Ali, A. A. (2021). Improved manta ray foraging optimization for multi-level thresholding using COVID-19 CT images. Neural Computing and Applications, 1-21.

A self-collected dataset named Handwritten Urdu Character dataset (HUCD) containing a total of 106, 120 samples of Handwritten Urdu is used in the proposed CNN algorithm. In the Urdu language, there are a total of 38 basic characters, 10 numerals and two field characters and many special characters in Urdu language, out of 38 basic characters, 27 characters are joiners, 10 characters are non-joiners and 1 character has no joining property at all. Among two field characters, one character is a non-joiner and the other has no joining property. Similarly, 10 numerals do not have any joining property. Thus, making a total of 142 unique forms With regard to this, the dataset was collected on an A4-sized paper, printed with rectangular boxes in landscape mode where each box corresponds to the unique Urdu character. Each page contained a total of 142 rectangular boxes to be used for writing 132

Citations: 1. Mushtaq, F., Misgar, M. M., Kumar, M., & Khurana, S. S. (2021). UrduDeepNet: offline handwritten Urdu character recognition using deep neural network. Neural Computing and Applications, 1-24.

1. Misgar, M.M., Mushtaq, F., Khurana, S.S. et al. Recognition of offline handwritten Urdu characters using RNN and LSTM models. Multimed Tools Appl 82, 2053–2076 (2023). https://doi.org/10.1007/s11042-022-13320-1

Contributors: Er. Surinder Singh Khurana Assistant Professor, Department of Computer Science & Technology, Central University of Punjab, Bathinda, India

Dr. Munish Kumar, Assistant Professor, Department of Computational Sciences, Maharaja Ranjit Singh Punjab Technical University, Bathinda, India

Er. Faisel Mushtaq Student, Department of Computer Science & Technology, Central University of Punjab, Bathinda, India

Er. Muzafar Mehraj Misgar Student, Department of Computer Science & Technology, Central University of Punjab, Bathinda, India

Houssein, Essam H., Mahmoud Dirar, Kashif Hussain, and Waleed M. Mohamed. "Assess deep learning models for Egyptian exchange prediction using nonlinear artificial neural networks." Neural Computing and Applications 33, no. 11 (2021): 5965-5987.

Author: Rami Mustafa A Mohammad ( University of Huddersfield","rami.mohammad '@' hud.ac.uk","rami.mustafa.a '@' gmail.com) Lee McCluskey (University of Huddersfield","t.l.mccluskey '@' hud.ac.uk ) Fadi Thabtah (Canadian University of Dubai","fadi '@' cud.ac.ae)
Source: UCI
Please cite: Please refer to the Machine Learning Repository's citation policy

Source:

Rami Mustafa A Mohammad ( University of Huddersfield, rami.mohammad '@' hud.ac.uk, rami.mustafa.a '@' gmail.com) Lee McCluskey (University of Huddersfield,t.l.mccluskey '@' hud.ac.uk ) Fadi Thabtah (Canadian University of Dubai,fadi '@' cud.ac.ae)

Data Set Information:

One of the challenges faced by our research was the unavailability of reliable training datasets. In fact this challenge faces any researcher in the field. However, although plenty of articles about predicting phishing websites have been disseminated these days, no reliable training dataset has been published publically, may be because there is no agreement in literature on the definitive features that characterize phishing webpages, hence it is difficult to shape a dataset that covers all possible features. In this dataset, we shed light on the important features that have proved to be sound and effective in predicting phishing websites. In addition, we propose some new features.

Attribute Information:

For Further information about the features see the features file in the data folder of UCI.

Relevant Papers:

Mohammad, Rami, McCluskey, T.L. and Thabtah, Fadi (2012) An Assessment of Features Related to Phishing Websites using an Automated Technique. In: International Conferece For Internet Technology And Secured Transactions. ICITST 2012 . IEEE, London, UK, pp. 492-497. ISBN 978-1-4673-5325-0

Mohammad, Rami, Thabtah, Fadi Abdeljaber and McCluskey, T.L. (2014) Predicting phishing websites based on self-structuring neural network. Neural Computing and Applications, 25 (2). pp. 443-458. ISSN 0941-0643

Mohammad, Rami, McCluskey, T.L. and Thabtah, Fadi Abdeljaber (2014) Intelligent Rule based Phishing Websites Classification. IET Information Security, 8 (3). pp. 153-160. ISSN 1751-8709

Citation Request:

Please refer to the Machine Learning Repository's citation policy

The Neural Network Accelerator (NNA) market is experiencing robust growth, driven by the increasing demand for artificial intelligence (AI) and machine learning (ML) applications across various sectors. The market, estimated at $15 billion in 2025, is projected to exhibit a Compound Annual Growth Rate (CAGR) of 25% from 2025 to 2033. This significant expansion is fueled by several key factors. The proliferation of data-intensive applications in areas like autonomous vehicles, healthcare, and finance necessitates high-performance computing solutions, driving the adoption of NNAs. Advancements in deep learning algorithms and the rising need for edge AI processing, where data is processed locally rather than in the cloud, further contribute to market growth. Major players like IBM, Intel, Qualcomm, and NVIDIA are heavily investing in research and development, leading to innovative NNA architectures and improved performance. The market segmentation includes various types of NNAs based on architecture (e.g., convolutional neural networks, recurrent neural networks), deployment (edge, cloud), and application (e.g., image recognition, natural language processing). While challenges like high development costs and power consumption remain, ongoing technological advancements are expected to mitigate these limitations and propel market growth. The competitive landscape is characterized by a mix of established semiconductor companies and specialized AI startups. Established players leverage their expertise in chip design and manufacturing to develop high-performance NNAs, while startups bring innovative architectures and software solutions. Strategic partnerships and acquisitions are further shaping the market dynamics. The regional distribution of the market is expected to be dominated by North America and Asia, reflecting the high concentration of technology companies and the rapid adoption of AI technologies in these regions. However, growth is anticipated across all regions as AI applications become increasingly prevalent. The continued advancements in AI and the expanding adoption of edge computing will continue to shape the future of this dynamic and rapidly growing market.

The data was analyzed in this article. Please cite it or cite the data article: Kaddoura, S., Alex, S. A., Itani, M., Henno, S., AlNashash, A., & Hemanth, D. J. (2023). Arabic spam tweets classification using deep learning. Neural Computing and Applications, 1-14.

The data are collected from Twitter using Twitter API between January 27, 2021, and March 10, 2021. The download tweet information is Tweet ID, DateTime, URL, Tweet Text, User Name, Location, Replied Tweet ID, Replied Tweet User ID, Replied Tweet Username, Retweet Count, Favorite Count, and Favorited.

The dataset contains 13241 records. Each record represents a tweet. The tweets are labeled either Ham or Spam. Ham means non-spam tweet. There are 1924 Spam tweets and 11299 Ham tweets. The tweets are unique i.e. there are no repeated tweets records.

This directory contains the supplementary material for the following journal paper:Harnack, D., Pivin-Bachler, J., & Navarro-Guerrero, N. (2022). Quantifying the Effect of Feedback Frequency in Interactive Reinforcement Learning for Robotic Tasks. Neural Computing and Applications. Special Issue on Human-aligned Reinforcement Learning for Autonomous Agents and Robots. https://doi.org/10.1007/s00521-022-07949-0Contact:For information please see the paper. For specific questions regarding the paper please contact: Nicolás Navarro-Guerrero.

The Neural Network Accelerator (NNA) market is experiencing robust growth, driven by the increasing demand for artificial intelligence (AI) and machine learning (ML) applications across diverse sectors. The market's expansion is fueled by the need for faster and more energy-efficient processing of complex neural networks, particularly in applications like autonomous vehicles, image recognition, natural language processing, and high-performance computing. The integration of NNAs into edge devices, enabling real-time AI processing at the point of data generation, is a key trend. While the precise market size for 2025 is unavailable, considering a plausible CAGR of 25% from a hypothetical 2024 market size of $5 billion (a reasonable estimate based on market reports from similar technologies), the 2025 market size would be approximately $6.25 billion. Companies like IBM, Intel, Qualcomm, and NVIDIA are leading the innovation, investing heavily in research and development to improve NNA performance and efficiency. Competition is fierce, prompting continuous advancements in architecture, memory bandwidth, and power consumption. This competitive landscape accelerates the overall market growth. However, the market faces certain restraints. The high cost of developing and implementing NNAs can be a barrier for entry for smaller companies. Furthermore, standardization challenges and the need for specialized skills to design and deploy NNA systems represent obstacles to wider adoption. Despite these challenges, the long-term outlook for the NNA market remains extremely positive. The continued proliferation of AI and ML across various industries, along with ongoing technological advancements in NNA technology, will fuel significant growth throughout the forecast period (2025-2033). The ongoing development of specialized NNAs optimized for specific workloads will further drive market expansion. Regional variations in adoption rates will exist, with North America and Asia-Pacific expected to lead the market due to strong technology infrastructure and significant investments in AI research.

This repository is also available in GitHub: https://github.com/leandroensina/FADbF The FADbF dataset companions the paper entitled "Fault Distance Estimation for Transmission Lines with Dynamic Regressor Selection", published in Neural Computing and Applications, doi: 10.1007/s00521-023-09155-y. More information about the dataset can be found in this reference. Associated Tasks: classification and regression Instances: 168,000 Attributes: 128, including the two possible targets Additional Information: this database comprises several attributes extracted from time series of fault simulations of a transmission line with 500 kV, 414 km, and 60 Hz. In total, we extracted 21 features separately for each of the three phases for both voltage and current waveforms along two post-fault cycles from a single terminal, resulting in 126 attributes (21 * 3 * 2 = 126) in addition to the two possible targets, i.e., fault type (classification task) and fault location (regression task). If desired, the fault type can also be used as a feature for the fault location task.

The neural network market is experiencing robust growth, driven by the increasing adoption of artificial intelligence (AI) across diverse sectors. The market's expansion is fueled by several key factors, including the exponential rise in data generation, advancements in computing power (particularly GPUs), and the development of more sophisticated neural network architectures like convolutional neural networks (CNNs) and recurrent neural networks (RNNs). These advancements enable the creation of more accurate and efficient AI systems for applications ranging from image recognition and natural language processing to predictive analytics and robotics. The market is segmented by application (e.g., computer vision, natural language processing, predictive analytics), deployment (cloud, on-premise), and industry (healthcare, finance, automotive). While challenges remain, such as the need for skilled professionals and concerns about data privacy and bias, the overall market outlook remains highly positive. We estimate the market size to be approximately $15 billion in 2025, growing at a Compound Annual Growth Rate (CAGR) of 25% from 2025 to 2033. This is based on observable market trends and growth in related AI sectors. This substantial growth is further supported by continuous innovation in hardware and software. Companies like NVIDIA, Intel, and AWS are investing heavily in developing specialized hardware and cloud infrastructure optimized for neural network processing. Meanwhile, software companies such as Microsoft, IBM, and Google are creating user-friendly platforms and tools, making neural network development more accessible to a wider range of users. The ongoing research and development in areas like transfer learning and federated learning is also poised to further accelerate market adoption. The competitive landscape is highly dynamic, with established tech giants and specialized AI startups vying for market share. The focus on developing more energy-efficient and explainable AI systems is crucial for broader acceptance and wider application across various industries.

Optical Neural Network Chip Market Outlook

According to our latest research, the global Optical Neural Network Chip market size reached USD 1.2 billion in 2024, driven by rapid advancements in artificial intelligence hardware and increasing demand for high-speed data processing. The market is exhibiting a robust CAGR of 34.7% and is expected to reach a forecasted value of USD 16.5 billion by 2033. This extraordinary growth is primarily attributed to the surge in AI workloads, the proliferation of edge computing, and the ongoing shift toward photonic-based data transmission and computation, which offer significant speed and energy efficiency advantages over traditional electronic counterparts.

The primary growth factor fueling the Optical Neural Network Chip market is the exponential increase in data generation and the corresponding need for faster, more efficient data processing. As industries like healthcare, finance, and telecommunications increasingly rely on AI-driven analytics, the limitations of conventional electronic chips have become apparent. Optical neural network chips, leveraging the principles of photonics, enable parallel data processing at the speed of light, drastically reducing latency and power consumption. This makes them especially suitable for applications such as real-time image recognition, natural language processing, and large-scale machine learning tasks. The ability to handle massive datasets with minimal heat generation and energy loss is a compelling advantage that is accelerating the adoption of optical neural network chips across various sectors.

Another significant driver is the evolution of data center architectures. With the rise of cloud computing and the Internet of Things (IoT), data centers are under immense pressure to deliver higher performance while minimizing energy costs. Optical neural network chips are emerging as a transformative solution, enabling data centers to achieve unprecedented processing speeds and scalability. The integration of photonic components, such as silicon photonics and photonic integrated circuits, allows for seamless interconnectivity and efficient data transmission within and between servers. This not only enhances computational throughput but also supports the growing trend of distributed AI processing, paving the way for more sophisticated and responsive AI services.

Furthermore, the push toward edge computing is reshaping the landscape of AI hardware deployment. As devices at the edge—ranging from autonomous vehicles to smart medical devices—require real-time decision-making capabilities, the limitations of traditional chips become a bottleneck. Optical neural network chips, with their compact form factors and ultra-low latency, are ideally positioned to meet these demands. Their integration into edge devices enables faster inference, reduced dependence on centralized cloud resources, and improved user experiences. The convergence of optical technologies with AI at the edge is expected to unlock new business models and applications, further propelling market growth.

Regionally, North America currently dominates the Optical Neural Network Chip market, accounting for the largest share of global revenue in 2024. This leadership is underpinned by significant investments in AI research, a robust ecosystem of semiconductor and photonics companies, and strong demand from sectors such as IT & telecommunications and healthcare. Meanwhile, the Asia Pacific region is witnessing the fastest growth, driven by rapid digital transformation, government initiatives supporting AI and photonics research, and the expansion of data center infrastructure in countries like China, Japan, and South Korea. Europe is also making notable strides, particularly in automotive and industrial automation applications, supported by a strong focus on innovation and sustainability. As the market matures, collaboration across regions and industries will be crucial in shaping the future trajectory of optical neural network chip adoption.

In the realm of AI hardware, the development of the Photonic Neural Network Accelerator Card is a significant milestone. This technology is designed to harness the power of light for data processing, offering unprecedented speed and efficiency. By integrating photonic components, these accelerator cards can handle

This data provides the detailed test results of the benchmarking for the binary-classification performance metrics. The benchmark comprising three stages was applied on 13 metrics namely True Positive Rate, True Negative Rate, Positive Predictive Value, Negative Predictive Value, Accuracy, Informedness, Markedness, Balanced Accuracy, G, Normalized Mutual Information, F1, Cohen’s Kappa, and Mathew’s Correlation Coefficient (MCC).

The new benchmarking method is described in Gürol Canbek, Tugba Taskaya Temizel, and Seref Sagiroglu, "BenchMetrics: A Systematic Benchmarking Method for Binary-Classification Performance Metrics", Neural Computing and Applications, 2020 (Submitted).

The related benchmarking API and an interactive ready-to-run experimentation platform is available online (see the references)

HMBD Dataset v1

HMBD v1 is an Arabic Handwritten Characters Dataset.

(1) Introduction:

The HMBD dataset captures the different positions of the Arabic handwritten characters; isolated, beginning, middle, and end; besides, the numbers.

(2) Published Paper:

The HMBD dataset is published in "A new Arabic handwritten character recognition deep learning system (AHCR-DLS)" where the construction, pre-processing, and compilation phases are discussed. Link: https://link.springer.com/article/10.1007/s00521-020-05397-2 DOI: https://doi.org/10.1007/s00521-020-05397-2

(3) Dataset Specifications:

• Version: 1.0.
• The number of classes (categories) is 115.
• The number of unique images is 54,115.
• The number of volunteers is 125.
• Each image dimension is 300 x 300 (i.e. width = 300 and height = 300).
• Background color: White.
• Character color: Black.

(4) Dataset Template:

The seven-page dataset template file used in collecting the dataset is stored in "Dataset Template v1.pdf".

(5) Directory Hierarchy:

The hierarchy of the folder is stored in "tree.txt" and "folders.txt". The first contains the folders' and files' names while the latter one contains only the folders' names.

(6) Citation:

Balaha, H.M., Ali, H.A., Saraya, M. et al. A new Arabic handwritten character recognition deep learning system (AHCR-DLS). Neural Comput & Applic (2020). https://doi.org/10.1007/s00521-020-05397-2

@article{balaha2020new,
 title={A new Arabic handwritten character recognition deep learning system (AHCR-DLS)},
 author={Balaha, Hossam Magdy and Ali, Hesham Arafat and Saraya, Mohamed and Badawy, Mahmoud},
 journal={Neural Computing and Applications},
 pages={1--43},
 year={2020},
 publisher={Springer}
}

(7) Licence:

The HMBD dataset is licensed by "CC BY-NC-SA 4.0".

The "CC BY-NC-SA 4.0" is one of the Creative Commons (CC) licenses and allows the different users to share the dataset only if they (1) give the credits to the copyright holders, (2) do not use the dataset for any commercial purposes, and (3) distribute any additions, transformations or changes to the dataset under this same license.

Full Description: https://creativecommons.org/licenses/by-nc-sa/4.0/

International Journal of Artificial Intelligence Acceptance Rate - ResearchHelpDesk - The main aim of the International Journal of Artificial Intelligence™ (ISSN 0974-0635) is to publish refereed, well-written original research articles, and studies that describe the latest research and developments in the area of Artificial Intelligence. This is a broad-based journal covering all branches of Artificial Intelligence and its application in the following topics: Technology & Computing; Fuzzy Logic; Neural Networks; Reasoning and Evolution; Automatic Control; Mechatronics; Robotics; Parallel Processing; Programming Languages; Software & Hardware Architectures; CAD Design & Testing; Web Intelligence Applications; Computer Vision and Speech Understanding; Multimedia & Cognitive Informatics, Data Mining and Machine Learning Tools, Heuristic and AI Planning Strategies and Tools, Computational Theories of Learning; Signal, Image & Speech Processing; Intelligent System Architectures; Knowledge Representation; Bioinformatics; Natural Language Processing; Mathematics & Physics. The International Journal of Artificial Intelligence (IJAI) is a peer-reviewed online journal and is published in Spring and Autumn i.e. two times in a year. The International Journal of Artificial Intelligence (ISSN 0974-0635) was reviewed, abstracted and indexed in the past by the INSPEC The IET, SCOPUS (Elsevier Bibliographic Databases), Zentralblatt MATH (io-port.net) of European Mathematical Society, Indian Science Abstracts, getCITED, SCImago Journal & Country Rank, Newjour, JournalSeek, Math-jobs.com’s Journal Index, Academic keys, Ulrich's Periodicals Directory, IndexCopernicus, and International Statistical Institute (ISI, Netherlands)Journal Index. The IJAI is already in request process to get reviewed, abstracted and indexed by the Clarivate Analytics Web of Science (Also known as Thomson ISI Web of Knowledge SCI), Mathematical Reviews and MathSciNet of American Mathematical Society, and by other agencies.