Abdelhamid ZAIDI

Abdelhamid ZAIDI

Qassim University

H-index: 5

Asia-Saudi Arabia

Abdelhamid ZAIDI Information

University

Qassim University

Position

Assistant professor

Citations(all)

759

Citations(since 2020)

236

Cited By

86

hIndex(all)

5

hIndex(since 2020)

4

i10Index(all)

3

i10Index(since 2020)

2

Email

University Profile Page

Qassim University

Abdelhamid ZAIDI Skills & Research Interests

Statistics

applied mathematics

optimization

machine learning

artificial intelligence

Top articles of Abdelhamid ZAIDI

A bibliometric analysis of machine learning techniques in photovoltaic cells and solar energy (2014–2022)

Solar energy presents a promising solution to replace fossil-based energy sources, mitigating global warming and climate change. However, solar energy faces socio-economic, environmental, and technical challenges. Computational tools like machine learning offer solutions to these technical challenges. Despite numerous studies, there's a lack of comprehensive research on ML applications in Photovoltaics and Solar Energy. This study conducts a critical analysis of ML applications in Photovoltaics and Solar Energy research using publication trends and bibliometric analysis, employing the PRISMA approach on Scopus database. Results reveal a high publication output, citations, and international collaboration. Notable researchers include G. E. Georghiou and Haibo Ma, with the Ministry of Education (China) being a prolific affiliation. China emerges as the most active nation due to funding programs like the …

Authors

Abdelhamid Zaidi

Published Date

2024/6/1

Utilisation of Deep Learning (DL) and Neural Networks (NN) Algorithms for Energy Power Generation: A Social Network and Bibliometric Analysis (2004-2022)

The research landscape on the applications of advanced computational tools (ACTs) such as machine/deep learning and neural network algorithms for energy and power generation (EPG) was critically examined through publication trends and bibliometrics data analysis. The Elsevier Scopus database and the PRISMA methodology were employed to identify and screen the published documents, whereas the bibliometric analysis software VOSviewer was used to analyse the co-authorships, citations, and keyword occurrences. The results showed that 152 documents have been published on the topic comprising conference proceedings (58.6%) and articles (41.4%) between 2004 and 2022. Publication trends analysis revealed the number of publications increased from 1 to 31 or by 3,000% over the same period, which was ascribed to the growing scientific interest and research impact of the topic. Stakeholder analysis revealed the top authors/researchers are Anvari M, Ghaderi SF and Saberi M, whereas the most prolific affiliation and nations actively engaged in the topic are the North China Electric Power University, and China, respectively. Conversely, the top funding agency actively backing research on the topic is the National Natural Science Foundation of China (NSFC). Co-authorship analysis revealed high levels of collaboration between researching nations compared to authors and affiliations. Hotspot analysis revealed three major thematic focus areas namely, Energy Grid Forecasting, Power Generation Control, and Intelligent Energy Optimization. In conclusion, the study showed that the application of ACTs in EPG is an active …

Authors

Abdelhamid ZAIDI

Journal

International Journal of Energy Economics and Policy

Published Date

2024/1/15

New Insights into the Emerging Trends Research of Machine and Deep Learning Applications in Energy Storage: A Bibliometric Analysis and Publication Trends

The publication trends and bibliometric analysis of the research landscape on the applications of machine and deep learning in energy storage (MDLES) research were examined in this study based on published documents in the Elsevier Scopus database between 2012 and 2022. The PRISMA technique employed to identify, screen, and filter related publications on MDLES research recovered 969 documents comprising articles, conference papers, and reviews published in English. The results showed that the publications count on the topic increased from 3 to 385 (or a 12,733.3% increase) along with citations between 2012 and 2022. The high publications and citations rate was ascribed to the MDLES research impact, co-authorships/collaborations, as well as the source title/journals’ reputation, multidisciplinary nature, and research funding. The top/most prolific researcher, institution, country, and funding body on MDLES research are; is Yan Xu, Tsinghua University, China, and the National Natural Science Foundation of China, respectively.

Authors

Samuel Ajibade,Abdelhamid Zaidi,Asamh Saleh M. Al Luhayb

Journal

International Journal of Energy Economics and Policy

Published Date

2023/9/16

Policy conflict detection approach for decision-making in intelligent industrial Internet of Things

Improving Industrial Internet of Things (IIOT), device flexibility and lowering maintenance costs are significant problems. However, as the scale of the Intelligent Industrial Internet of Things (IIIOTs) system expands, the interactions between the rules get more sophisticated, potentially leading to rule discrepancies. The algorithm for Formal Rule Conflict Detection (FRCD) is created, and a thorough explanation of the procedure is given in this paper. Two IIIOT systems were used in experiments and the results were compared with three existing standard IIIOT rule conflict detection techniques. They include policy conflict detection systems based on Web semantics (Semantic Web-Based Policy Interaction Detection with Rules, (SPIDER)), conflict detection methods based on Users, Triggers, Environment entities, and Actuators (UTEA), and semiformal conflict detection methods (Identifying Requirements Interactions using …

Authors

Pradyumna Tripathy,Mohammad Shabaz,Abdelhamid Zaidi

Journal

Computers and Electrical Engineering

Published Date

2023

Two statistical approaches to justify the use of the logistic function in binary logistic regression

Logistic regression is a commonly used classification algorithm in machine learning. It allows categorizing data into discrete classes by learning the relationship from a given set of labeled data. It learns a linear relationship from the given dataset and then introduces nonlinearity through an activation function to determine a hyperplane that separates the learning points into two subclasses. In the case of logistic regression, the logistic function is the most used activation function to perform binary classification. The choice of logistic function for binary classifications is justified by its ability to transform any real number into a probability between 0 and 1. This study provides, through two different approaches, a rigorous statistical answer to the crucial question that torments us, namely where does this logistic function on which most neural network algorithms are based come from? Moreover, it determines the computational cost of logistic regression, using theoretical and experimental approaches.

Authors

Abdelhamid Zaidi,Asamh Al Luhayb

Journal

Mathematical Problems in Engineering

Published Date

2023/4/20

Smart Implementation of Industrial Internet of Things using Embedded Mechatronic System

In Industry 4.0, integrating IIoT and smart manufacturing is crucial for high-quality, efficient, and cost-effective production. However, the performance of IIoT systems can be hindered by unevenly distributed ESPs. To tackle this challenge, we propose an optimized embedded system for edge intelligence and smart manufacturing, leveraging digital twin technology. Our approach employs a digital twin-assisted alliance game resource optimization strategy to jointly optimize multi-dimensional resource allocation, including bandwidth, computing, and caching resources, while considering constraints like maximum delay. The optimization problem maximizes edge terminal utility and ESP utility, transformed into a convex optimization problem with linear constraints. An approximate optimal solution is obtained through an alternating iterative method. Simulation results demonstrate significant enhancements in resource …

Authors

Abdelhamid Zaidi,Ismail Keshta

Journal

IEEE Embedded Systems Letters

Published Date

2023/9/1

Statistical Analysis of a Linear Multi-Step Numerical Treatment

The aim of this paper is to compare the relative accuracies between predictor-corrector methods, Adams-Bashforth method and Adams-Moulton method for solving initial value Differential Equations numerically to observe which methods tend to function well in which step-size brackets as well as which ones provide the minimum amount of error when compared to the true value. The statistical analysis shows that there is always a small amount of error present using Heun’s method; however, the error is rarely large enough unless the function is rapidly rising.

Authors

Abdelhamid ZAIDI,Ohood ALHARBI

Journal

Journal of Statistics Applications & Probability

Published Date

2023/1

Effects of Dietary Supplementation of Banana Peel on Performance Traits, Carcass Characteristics and Serological Parameters in Broiler

The purpose of this research was to investigate the safe amounts of banana peel inclusion in chicken diets and to examine the impact on broiler performance, carcass features, and serological markers. A total of 400 Cobb500TM day-old broiler chicks were split among four treatments, each with 100 birds. Each group was then subdivided into five duplicates, each with 20 birds. T8 was given a normal control diet with antibiotics (Enramycine 0.3 grammes/Kg), T9 was given a baseline diet without antibiotics, T10 was given a basal diet with maize 2% replaced by banana peels, and T11 was given a basal diet with maize 4% replaced by banana peels. Data will be analyzed under a complete randomized design through one-way ANOVA using SPSS. The body weight, feed intake and FCR manifested significant improvement in the T11 group in comparison with the control. Moreover, serum HDL, dressed weight and giblet weight results were found significant in treatment groups as compared to the control. The serum LDL concentration and cholesterol were significantly lowered in T10 and T11 as compared to the control group. Hence, banana peel supplementation as a replacement for corn in a broiler diet can support normal broiler growth and performance and can also lower the cost of feed efficiently.

Authors

Prakashbhai Doshi,Biswaranjan Senapati,AbdulMajid Soomro,Abdelhamid Zaidi,Awad Naeem

Journal

Journal of Computing & Biomedical Informatics

Published Date

2023/3/29

Predicting wildfires in Algerian forests using machine learning models

Algeria is one of the Maghreb countries most affected by wildfires. The economic, environmental, and societal consequences of these fires can last several years after the wildfire. Often, it is possible to avoid such disasters if the detection of the outbreak of fire is fast enough, reliable, and early. The lack of datasets has limited the methods used to predict wildfires in Algeria to the mapping risk areas, which is updated annually. This study is the result of the availability of a recent dataset relating the history of forest fires in the cities of Bejaia and Sidi Bel-Abbes during the year 2012. The dataset being small size, we used principal component analysis to reduce the number of variables to 6, while retaining 96.65% of the total variance. Moreover, we developed an artificial neural network (ANN) with two hidden layers to predict wildfires in these cities. Next, we trained and compared the performance of our classifier with those …

Authors

Abdelhamid Zaidi

Journal

Heliyon

Published Date

2023/7/1

Early Gender Identification of Date Palm Using Machine Learning

Date palm is a tree grown for its sweet edible fruit by the palm family. Palm's long-life cycle and heterozygous nature, date palm breeding is challenging. So, sex identification at seedlings is essential to overcome the cost and tidy effort of the growers. Our study proposes an efficient technique for the sex identification of Date palms at the seedling stage. We aim to use supervised Machine Learning Techniques (KNN, SVM, Naive Byes, and AdaBoost) for the sex identification of date palms. We use the feature extraction technique before classification to represent the exciting part of the image. Results indicated that the SVM algorithm is the most accurate for sex identification, with 97% accuracy. When given information about the shape of a Date palm's leaves, machine learning models can be used to figure out what the palm is. This study gives us a fast and accurate way to test for DNA markers, and it has the potential to significantly improve the selection efficiencies of date growers. Because male and female date palm genotypes can be identified before maturation, breeders' costs and time commitment are reduced. Deep learning and other methods should be evaluated for their utility in answering additional date palm sex questions. A more comprehensive database of Date palm genotype biodiversity could be created and used to support the findings presented.

Authors

Awad Naeem,Faiza Khalid,AbdulMajid Soomro,Abdelhamid Zaidi

Journal

Journal of Computing & Biomedical Informatics

Published Date

2023/3/29

New Insights into the Research Landscape on the Application of Artificial Intelligence in Sustainable Smart Cities: A Bibliometric Mapping and Network Analysis Approach

Humanity’s quest for safe, resilient, and liveable cities has prompted research into the application of computational tools in the design and development of sustainable smart cities. Thus, the application of artificial intelligence in sustainable smart cities (AISC) has become an important research field with numerous publications, citations, and collaborations. However, scholarly works on publication trends and the research landscape on AISC remain lacking. Therefore, this paper examines the current status and future directions of AISC research. The PRISMA approach was selected to identify, screen, and analyse 1,982 publications on AISC from Scopus between 2011 and 2022. Results showed that the number of publications and citations rose from 2 to 470 and 157 to 1,540, respectively. Stakeholder productivity analysis showed that the most prolific author and affiliation are Tan Yigitcanlar (10 publications and 518 citations) and King Abdulaziz University (23 publications and 793 citations), respectively. Productivity was attributed to national interests, research priorities, and national or international funding. The largest funder of AISC research is the National Natural Science Foundation of China (126 publications or 6.357% of the total publications). Keyword co-occurrence and cluster analyses revealed 6 research hotspots on AISC: Digital innovation and technologies; digital infrastructure and intelligent data systems; cognitive computing; smart sustainability; smart energy efficiency; nexus among artificial intelligence, Internet of Things, data analytics and smart cities. Future research would likely focus on the socio-economic, ethical, policy, and …

Authors

Abdelhamid Zaidi ZAidi,Samuel-Soma M Ajibade,Majd Musa,Festus Victor Bekun

Journal

International Journal of Energy Economics and Policy

Published Date

2023/6/20

A Quantitative Based Research on the Production of Image Captioning

It is widely recognized that modern systems can discern the context of an image and enrich it with relevant captions through the fusion of computer vision and natural language processing, a technique referred to as' image caption production.'This article aims to shed light on and analyze various image captioning techniques that have evolved over the past few decades, including the Attention Model, Region-Level Caption Detection, Semantic Content-Based Models, Multimodal Models, and more. The evaluation of these techniques employs diverse criteria such as Precision Rate, Recall Rate, F1 Score, Accuracy Rate, among others, while employing various datasets for comparison. This article offers a comprehensive structural examination of contemporary image captioning methods. Researchers can leverage the insights from this analysis to develop innovative, improved approaches that sidestep the shortcomings of older methods while retaining their beneficial aspects.

Authors

Samuel-Soma M Ajibade,Abdelhamid Zaidi,Siti Sarah Maidin,Wan Hussain Wan Ishak,Adedotun Adetunla

Journal

International Journal of Intelligent Systems and Applications in Engineering

Published Date

2023/9/21

Technological Acceptance Model for Social Media Networking in E-Learning in Higher Educational Institutes

Twitter and Facebook are popular among college educators. The use of social media in schools of higher learning has also been the subject of study. The use of social media has opened up new avenues of contact, collaboration, and participation between students and teachers. Accepting students and educators who make use of technological tools to do so requires insight into the factors that shape their propensity to do so. Using the Technology Acceptance Model (TAM) framework, which highlights perceived ease of use, perceived usefulness, and behavioral intention to use new technologies, this paper investigates the extent to which Nigerians are adopting social networking media for e-learning. Quantitative studies made use of surveys. Teachers and students from four different Nigerian schools participated in this survey. The suggested model factors were predicted using structural equation modeling (SEM). Intentions to utilize social media for e-learning by students and faculty at Nigerian institutions were shown to be impacted by these factors: perceived ease of use and perceived utility. The research is limited in that it does not offer any insight into interactive factors such interaction with research group members and peers, interaction with supervisors or lecturers, engagement, or active collaborative learning.

Authors

Abdelhamid ZAIDI,Samuel Ajibade

Journal

International Journal of Information and Education Technology

Published Date

2023/2/2

Identification of Coronary Artery Disease using Extra Tree Classification

Caused by a shortage of oxygen-rich blood, cardiac artery disease occurs when coronary arteries get blocked. Arterial occlusion decreases the heart's blood flow and hence its oxygen supply. Plaque buildup is the leading cause of arterial obstruction. Both cholesterol and calcium can be found in plaque. Atherosclerosis refers to the development of plaque within the arteries. It is possible to have total ischemia due to an arterial clot. As arterial plaque ruptures, blood clots form. A diet rich in cholesterol can contribute to the development of plaque in a person's arteries. Cholesterol is transported in the bloodstream via lipoproteins, which are protein complexes. Lipoproteins come in two main types, high-density (HDL) and low-density (LDL). Plaque builds up in the arteries when levels of LDL are too high. The term “bad cholesterol” (LDL) is also commonly used. HDL is responsible for transporting cholesterol from the …

Authors

Nazia Wahid,Abdelhamid Zaidi,Gaurav Dhiman

Published Date

2023/6/1

A research landscape bibliometric analysis on climate change for last decades: Evidence from applications of machine learning

Climate change (CC) is one of the greatest threats to human health, safety, and the environment. Given its current and future impacts, numerous studies have employed computational tools (e.g., machine learning, ML) to understand, mitigate, and adapt to CC. Therefore, this paper seeks to comprehensively analyze the research/publications landscape on the MLCC research based on published documents from Scopus. The high productivity and research impact of MLCC has produced highly cited works categorized as science, technology, and engineering to the arts, humanities, and social sciences. The most prolific author is Shamsuddin Shahid (based at Universiti Teknologi Malaysia), whereas the Chinese Academy of Sciences is the most productive affiliation on MLCC research. The most influential countries are the United States and China, which is attributed to the funding activities of the National Science …

Authors

Samuel-Soma M Ajibade,Abdelhamid Zaidi,Festus Victor Bekun,Anthonia Oluwatosin Adediran,Mbiatke Anthony Bassey

Journal

Heliyon

Published Date

2023/9/19

Research Article Two Statistical Approaches to Justify the Use of the Logistic Function in Binary Logistic Regression

Logistic regression is a commonly used classification algorithm in machine learning. It allows categorizing data into discrete classes by learning the relationship from a given set of labeled data. It learns a linear relationship from the given dataset and then introduces nonlinearity through an activation function to determine a hyperplane that separates the learning points into two subclasses. In the case of logistic regression, the logistic function is the most used activation function to perform binary classification. Te choice of logistic function for binary classifications is justified by its ability to transform any real number into a probability between 0 and 1. Tis study provides, through two different approaches, a rigorous statistical answer to the crucial question that torments us, namely where does this logistic function on which most neural network algorithms are based come from? Moreover, it determines the computational cost of logistic regression, using theoretical and experimental approaches.

Authors

Abdelhamid Zaidi,Asamh Saleh M Al Luhayb

Published Date

2023

A remark on Dynamical behavior of a fractional three-species food chain model [Nonlinear Dynamics, 95, February 2019]

In the current manuscript, we comment on (Alidousti J and Mostafavi 2019 in Nonlinear Dyn 95: 1841), where a three-species fractional differential equation food chain model is considered. It is shown in Alidousti J and Mostafavi (2019) that under certain parametric restrictions the model has bounded solutions for all positive initial conditions. We show that this is not true. Solutions to the model can blow up in finite time, for sufficiently large initial data, even under the restrictions derived in Alidousti J and Mostafavi (2019). We validate all of our results via numerical simulations.

Authors

Parshad Rana,Zaidi Abdelhamid,Said Kouachi

Journal

Nonlinear Dynamics

Published Date

2023/5/13

Memory Type Estimator Of Population Mean Using Exponentially Weighted Moving Averages In Two-Phase Sampling

To propose a new memory type estimator of Population Mean in two phase simple random sampling with one auxiliary using EWMA for time scaled surveys and to compare the proposed estimator with related previous estimator. Using Two-Phase Sampling technique, a generalized difference-cum-ratio type estimator has been proposed for estimating the population mean. The expressions for bias and mean square error of proposed estimator have been obtained. The conditions under which proposed estimator is better than the regression estimator and mean per unit estimator have also been obtained. Simulation study has also been done to support the results by generating data. Exponentially weighted moving average (EWMA) statistic is a memory type statistic that used present and past information to estimate the population parameter. This study utilizes EWMA statistic to propose a ratio and product estimator for the surveys based on time scale. The usual ratio and product estimators consist of only current sample information, whereas the proposed estimators contains of current as well as past sample information. The mean square error expressions of the proposed estimators are derived and mathematical conditions are established to prove the efficiency of proposed estimators. It is revealed from the results of simulation study that utilization of the past samples information excels the performance of estimator in terms of efficiency.

Authors

Naeem Shahzad,Abdelhamid ZAIDI

Journal

Journal of Positive School Psychology

Published Date

2022/10/23

Mathematical methods for iot-based annotating object datasets with bounding boxes

Object datasets used in the construction of object detectors are typically annotated with horizontal or oriented bounding rectangles for IoT-based. The optimality of an annotation is obtained by fulfilling two conditions: (i) the rectangle covers the whole object and (ii) the area of the rectangle is minimal. Building a large-scale object dataset requires annotators with equal manual dexterity to carry out this tedious work. When an object is horizontal for IoT-based, it is easy for the annotator to reach the optimal bounding box within a reasonable time. However, if the object is oriented, the annotator needs additional time to decide whether the object will be annotated with a horizontal rectangle or an oriented rectangle for IoT-based. Moreover, in both cases, the final decision is not based on any objective argument, and the annotation is generally not optimal. In this study, we propose a new method of annotation by rectangles for IoT-based, called robust semi-automatic annotation, which combines speed and robustness. Our method has two phases. The first phase consists in inviting the annotator to click on the most relevant points located on the contour of the object. The outputs of the first phase are used by an algorithm to determine a rectangle enclosing these points. To carry out the second phase, we develop an algorithm called RANGE-MBR, which determines, from the selected points on the contour of the object, a rectangle enclosing these points in a linear time. The rectangle returned by RANGE-MBR always satisfies optimality condition (i). We prove that the optimality condition (ii) is always satisfied for objects with isotropic shapes. For objects with …

Authors

Abdelhamid Zaidi

Journal

Mathematical Problems in Engineering

Published Date

2022/8/23

Numerical integration of locally peaked bivariate functions

The aim of this paper is to compare the relative accuracies between deterministic and stochastic methods for solving bounded integrals numerically to observe which methods tend to function well and converge to a small amount of error based on computational resources. For the deterministic method, the Gauss-Legendre quadrature method has been selected and for the stochastic method, the Monte Carlo integration has been selected. For each case, the number of variables will be adjusted to observe the effect on error.

Authors

Abdelhamid Zaidi,Mishael Mohammed S Alharbi

Published Date

2022

Data Mining Analysis of Online Drug Reviews

Data mining methods like sentiment analysis provide useful information. This paper examines drug online user reviews. This research predicts user satisfaction with sentiments and applied drugs on effectiveness and side effects using sentiment analysis based on classification and analyzes model transfer across data sources like Emzor and May & Baker data. Online medication review data. Web crawlers was used to collect the ratings and comments of forum members. Emzor Pharmaceutical Company had 463 reviews and May & Baker Pharmaceutical Company had 421 reviews. Data was split 70% for training and 30% for testing. We used sentiment analysis to predict user ratings on overall satisfaction, side effects, and drug efficacy. Emzor data performs better 89.1% in-domain sentiment analysis, while May & Baker data accuracy is 86.90% overall. In cross-data sentiment analysis, the Emzor and May & Baker …

Authors

Samuel-Soma M Ajibade,Abdelhamid Zaidi,Catherine P Tapales,Dai-Long Ngo-Hoang,Muhammad Ayaz,Johnry P Dayupay,Yakubu Aminu Dodo,Sushovan Chaudhury,Anthonia Oluwatosin Adediran

Published Date

2022/12/17

Mathematical justification on the origin of the sigmoid in logistic regression

Logistic regression is a commonly used classification algorithm in machine learning. It allows categorizing data into discrete classes by learning the relationship from a given set of labeled data. It learns a linear relationship from the given data set and then introduces nonlinearity through an activation function to determine a hyperplane that separates the learning points into two subclasses. In the case of logistic regression, the sigmoid is the most used activation function to perform binary classification. The choice of sigmoid for binary classifications is justified by its ability to transform any real number into a probability between 0 and 1. This study provides, through two different approaches, a rigorous mathematical answer to the crucial question that torments us, namely where does this logistic function on which most neural network algorithms are based come from?

Authors

Abdelhamid ZAIDI

Journal

Central European Management Journal

Published Date

2022/11/21

Qualitative Comparison Between Performance Of Quadrature Rules For Triangles And Squares

Numerical integration on an arbitrary compact set D⊂ ℝ 2 generally goes through two phases. The first consists in discretizing D into simple finite elements. The second phase consists in calculating an approximation of the integral on each finite element, to deduce from it an approximation of the integral on D. The triangle and the square are the finite elements most used in affine discretization. Constructing an effective quadrature rule is a laborious and time-consuming task. The quadrature rules discovered so far owe much to the power of supercomputers. This research topic, more than a century old, is still relevant thanks to the continuous growth of supercomputers. We describe in this study the different approaches that allowed the development of positive interior symmetric (PIS) quadrature rules for the triangle and the square. Next, we determine the strength and relative error associated with each rule. Additionally, we use Genz test functions to assess the accuracy of different quadrature rules. Finally, we propose two techniques to reduce the integration error inherent in non-regular integrands.

Authors

Abdelhamid Zaidi,Mishael AlHarbi

Journal

Journal of Positive School Psychology

Published Date

2022/11/7

Accurate IoU computation for rotated bounding boxes in and

In object detection, the Intersection over Union () is the most popular criterion used to validate the performance of an object detector on the testing object dataset, or to compare the performances of various object detectors on a common object dataset. The calculation of this criterion requires the determination of the overlapping area between two bounding boxes. If these latter are axis-aligned (or horizontal), then the exact calculation of their overlapping area is simple. But if these bounding boxes are rotated (or oriented), then the exact calculation of their overlapping area is laborious. Many rotated objects detectors have been developed using heuristics to approximate between two rotated bounding boxes. We have shown, through counterexamples, that these heuristics are not efficient in the sense that they can lead to false positive or false negative detection, which can bias the performance of comparative studies between object detectors. In this paper, we …

Authors

Abdelhamid Zaïdi

Journal

Machine Vision and Applications

Published Date

2021/11

Robust Semi-Automatic Annotation of object Data Sets with Bounding Rectangles.

Object datasets used in the construction of object detectors are typically manually annotated with horizontal or rotated bounding rectangles. The optimality of an annotation is obtained by fulfilling two conditions (i) the rectangle covers the whole object (ii) the area of​​ the rectangle is minimal. Building a large-scale object dataset requires annotators with equal manual dexterity to carry out this tedious work. When an object is horizontal, it is easy for the annotator to reach the optimal bounding box within a reasonable time. However, if the object is rotated, the annotator needs additional time to decide whether the object will be annotated with a horizontal rectangle or a rotated rectangle. Moreover, in both cases, the final decision is not based on any objective argument, and the annotation is generally not optimal. In this study, we propose a new method of annotation by rectangles, called Robust Semi-Automatic Annotation, which combines speed and robustness. Our method has two phases. The first phase consists in inviting the annotator to click on the most relevant points located on the contour of the object. The outputs of the first phase are used by an algorithm to determine a rectangle enclosing these points. To carry out the second phase, we develop an algorithm called RANGE-MBR, which determines, from the selected points on the contour of the object, a rectangle enclosing these points in a linear time. The rectangle returned by RANGE-MBR always satisfies optimality condition (i). We prove that the optimality condition (ii) is always satisfied for objects with isotropic shapes. For objects with anisotropic shapes, we study the optimality …

Authors

Abdelhamid ZAIDI

Published Date

2021/9/7

Abdelhamid ZAIDI FAQs

What is Abdelhamid ZAIDI's h-index at Qassim University?

The h-index of Abdelhamid ZAIDI has been 4 since 2020 and 5 in total.

What are Abdelhamid ZAIDI's top articles?

The articles with the titles of

A bibliometric analysis of machine learning techniques in photovoltaic cells and solar energy (2014–2022)

Utilisation of Deep Learning (DL) and Neural Networks (NN) Algorithms for Energy Power Generation: A Social Network and Bibliometric Analysis (2004-2022)

New Insights into the Emerging Trends Research of Machine and Deep Learning Applications in Energy Storage: A Bibliometric Analysis and Publication Trends

Policy conflict detection approach for decision-making in intelligent industrial Internet of Things

Two statistical approaches to justify the use of the logistic function in binary logistic regression

Smart Implementation of Industrial Internet of Things using Embedded Mechatronic System

Statistical Analysis of a Linear Multi-Step Numerical Treatment

Effects of Dietary Supplementation of Banana Peel on Performance Traits, Carcass Characteristics and Serological Parameters in Broiler

...

are the top articles of Abdelhamid ZAIDI at Qassim University.

What are Abdelhamid ZAIDI's research interests?

The research interests of Abdelhamid ZAIDI are: Statistics, applied mathematics, optimization, machine learning, artificial intelligence

What is Abdelhamid ZAIDI's total number of citations?

Abdelhamid ZAIDI has 759 citations in total.

What are the co-authors of Abdelhamid ZAIDI?

The co-authors of Abdelhamid ZAIDI are Rana Parshad, Samuel-Soma M. Ajibade, Majd Musa, Dr. Anurag Vijay Agrawal, Senior Member IEEE.

    Co-Authors

    H-index: 21
    Rana Parshad

    Rana Parshad

    Iowa State University

    H-index: 11
    Samuel-Soma M. Ajibade

    Samuel-Soma M. Ajibade

    Universiti Teknologi Malaysia

    H-index: 5
    Majd Musa

    Majd Musa

    University of Sharjah

    H-index: 4
    Dr. Anurag Vijay Agrawal, Senior Member IEEE

    Dr. Anurag Vijay Agrawal, Senior Member IEEE

    Indian Institute of Technology Roorkee

    academic-engine

    Useful Links