The potential of SMOTHE to enhance the precision of gender prediction: an investigation of artificial neural networks with cephalometry determination



Cite item

Full Text

Open Access Open Access
Restricted Access Access granted
Restricted Access Subscription or Fee Access

Abstract

Background: When creating models utilizing artificial neural networks (ANN), it is crucial to consider the quantity of training data and the distribution of data, particularly when making gender predictions. 

Objectives: This study seeks to determine the potential impact of using Synthetic Minority Oversampling Technique (SMOTE) on gender prediction using ANN model.

Material and Method: The current study utilized a dataset consisting of 297 Indonesian cephalometric measurements, comprising 229 samples from females and 68 samples from males. Web ceph is using for measures parameters SNA angle, mandibular length, mandibular angle, and SGA angle and diagnosis. Data processing and model ANN creation were carried out using Python.

Result: The gender identification accuracy of the artificial neural network (ANN) model is 87% for females and 0% for males, resulting in an overall average accuracy of 78%. When using SMOTE, the accuracy is 22%, with 0% accuracy for females and 37% accuracy for males. However, when using SMOTE and normalization, the accuracy increases to 71%, with 82% accuracy for females and 30% accuracy for males. The accuracy of normalization without SMOTE is 76%, with 86% accuracy for females and 14% accuracy for males.

Conclusion: Research has proven the efficacy of SMOTE in improving the classification of malematrices. Nevertheless, the study reveals that the overall accuracy results of SMOTE are suboptimal in comparison to the absence of SMOTE and normalization. The application of data balancing strategies is necessary in order to achieve optimal accuracy in gender prediction when ANN, and other parameters must be applied.

Full Text

I.    Introduction

Radiography is an essential component of forensic odontology since it is a straightforward, cost-effective, and non-invasive method of identification, particularly for identifying corpses by comparing pre- and post-mortem radiographs (1). Dental radiographs can provide reliable information as comparison data through the anatomical shape of teeth, periapical anomalies, fillings, cavities, outlines, and the position of impacted teeth, among others (1). Broadbents created lateral cephalometry in 1931, which offers the benefit of gaining a comprehensive visual representation of the cranial structure and soft tissue contour (2). In addition, it permits the evaluation of several anatomical components, such as the nasal bones, frontal sinuses, sphenoideus sinuses, and other images that assist in the gender identification process (3–5).

Patil et.al. (2020), using Artificial Neural Networks (ANN) in order to predict gender using mandibular radiography (6). ANN is a type of computing system that utilizes Machine Learning (ML) to generate intricate information (7). An Artificial Neural Network (ANN) is a computational model that draws inspiration from the biological nervous system of the brain (7).   They possess the capacity to obtain and retain knowledge (information-based) and can be characterized as a collection of processing units, represented by artificial neurons, interconnected by numerous interconnections (artificial synapses), implemented by vectors and matrices of synaptic weights (8,9). The main advantage of Artificial Neural Networks (ANN) is their capacity to acquire knowledge and maintain stability even when confronted with minor errors by generate its own information through the learning process (7,8,10).

Previous studies by Handayani et.al (2024) have demonstrated how well both of these models predict adult Indonesian gender utilizing 297 lateral cephalometry ANN models with 80 samples for training, 10 percent for testing, and 10 percent for validating. However, although we get 80% accuracy overall, the data imbalance reduces the accuracy of predicting the male gender. The imbalance in data happens when the number of people in each class is not equal. In other words, one class is not well represented (minority class), while the other class has a lot more cases (majority class). In many real-life situations, the class mismatch problem comes up (11). The most well-known way to deal with uneven data is the synthetic minority over-sampling technique (SMOTE) method. The SMOTE method creates new fake data patterns by combining samples from the minority class with their K closest neighbors in a straight line (11). This study uses an ANN model to predict gender and examines the possible effects of applying the SMOTE.

II.    Materials and Method

297 cephalometry image was taken from the patients' medical records at the Airlangga University Dental and Mouth Hospital (RSGMP Unair) in Surabaya, part of this data is the taken from previous study (12). Subsequently, the sample will be partitioned into three subsets: 70% of the cephalometry images will be allocated for training purposes, 15% will be reserved for validation tests, and the remaining 15% will be utilized for testing. Training, development and data analysis of cephalometric algorithms using ANN in Phyton.

Regarding the inclusion criteria that will be employed, they are as follows:
(1) Cephalometric images were obtained from pre-existing cephalometric photographs at the RSGMP FKG Airlangga University in Surabaya.
(2) Cephalometric pictures were acquired from individuals of Indonesian descent.
(3) Cephalometric photographs are captured using standardized instruments and identical equipment.
(4) The cephalometric photograph is in a satisfactory state, with no evidence of superimposition.
(5) The cephalometric photograph exhibits a satisfactory state of preservation, devoid of any discernible distortions.
(6) Cephalometric photographs are captured by operators possessing a minimum of D3 radiology education, together with a minimum of 1 year of practical experience operating cephalometric equipment.
(7) Cephalometric images of individuals between the ages of 18 and 40 years. The cephalometric photograph exhibits comprehensive dentition in both the mandibular and maxillary regions, with the exception of the third molar.
(8) Cephalometric photographs are taken of individuals who either lack orthodontic intervention or possess a prior record of orthodontic intervention.
(9) Cephalometric photographs were obtained from individuals lacking a prior record of orthognathic surgery.
(10) Cephalometric photographs are taken of individuals who do not possess any documented instances of jaw injuries.
This study employs the following instruments:
(1) The cephalometric photographs were captured using equipment that adheres to defined protocols.
(2) The cephalometric device employed in this study is the ZULASSUNG THA/HV-GEN Type THA100.
(3) Operators of cephalometric equipment possess standardized skills.
(4) A computer system equipped with a minimum of two 8-gigabyte random access memory (RAM) modules and a solid-state drive (SSD) with a storage capacity of 1 terabyte.
(5) The computer is equipped with the NVIDIA GeForce RTX 3060 graphics processing unit.
(6)    The utilization of Python in web development and Google Collaboration
(7)    The utilization of Pandas
(8)    The utilization of SHAP
(9)    The utilization of Web chep application

III.    Variables and definition

Variables studied are:
1. Dependent variables: the precision of cephalometric analysis utilizing the ANN techniques, taking into account various variables, which can be seen in Table 1.
2. Independent Variable: gender-based variations in cephalometric data employing the AI computational analysis method, namely Artificial Neural Networks (ANN).
3. Control variables: Age, Cephalometric Instrument, Operator Skill, Indonesian people form 

IV.    Research Result


Cephalometry radiographs were obtained from patients who sought treatment at Airlangga University Dental Hospital in Surabaya, Indonesia, as part of this research endeavor. This study has passed ethics with ethical number 316/HRECC.FODM/III/2023 by Airlangga University Faculty of Dental Medicine Health research Ethical Clearance Commission. We choose a suitable shape for people between the ages of 18 and 40. The collection comprises 297 cephalometry photographs, including 229 images in the female category and 68 images in the male category. The observed disparity in data between males and females can be attributed to the predominant representation of female patients seeking orthodontic therapy, as indicated by the majority of cephalometry data collected. The Python programming language is utilized to partition the photos into three distinct segments: 80% for training, 15% for validation, and 15% for testing, as depicted in Table 2.   

A. Measurement of variables

We employed the backpropagation method in this investigation. In this methodology, two computational processes are executed, namely sophisticated computations to ascertain the disparity between the output of the artificial neural network (ANN) and the intended goal. The next step entails doing a reverse calculation that utilizes the obtained errors to modify the weights of all the neurons in the system.

The ANN cephalometry parameters were measured using the Web Front program, which is a medical record application for orthodontic care. This application is utilized due to its cost-free nature and its ability to reduce errors associated with manual procedures. The visual representation of the measurement obtained from the web front is depicted in Figure 1.

 

After obtaining the value of the parameters searched using the frontal web, the results of the four parameters were analyzed using the Pandas found in Phyton, and the ANN was trained based on the diagnosis of malocclusion of the patient as obtained in table 3 below. And it was found that the sample ratio is in Class I malocclusion Angle with normal occlusion.

 

The average values of the four parameters were determined by analyzing them using Pandas in Python.   The parameters obtained from the cephalometry photo were used as a gender reference in the ANN algorithm. The results are displayed in the table labeled as "Table 4" below:

B. Network training and validation

The purpose of employing Python is to develop the artificial neural network (ANN) architecture. The first step involves training and validating the model prior to conducting testing. This study employs four distinct scenarios. The first scenario involves the absence of SMOTE and normalization. The second scenario entails the presence of SMOTE without normalization. The third scenario involves the combination of SMOTE and normalization. Lastly, the fourth scenario involves the presence of normalization without SMOTE. The training method and validation of photocephalometry are exemplified by Figures 2 and 3. The observation of a decreasing loss graph in both the training and validation stages provides additional support for this claim. 

 

C. Artificial neural network model analysis

The results of accuracy, precision, recall, f1, and support for the artificial neural network (ANN) model under four different scenarios are presented in Table 6. The first scenario involves developing the model without incorporating SMOTE and normalizing techniques. The accuracy outcome for the first scenario is 0.78, or 78%, with a male F1 score of 0.00 and a female score of 0.87. The second scenario of the artificial neural network (ANN) model involves the use of SMOTE without normalization. The accuracy score obtained is 0.22, which corresponds to 22%. The f1 score for males is 0.00, while for females it is 0.37. The third ANN model scenario involves the use of SMOTE and normalization. The accuracy result is 0.71, which corresponds to a 71% accuracy rate. The male f1 score is 0.30, while the female f1 score is 0.82. In the final scenario, the absence of SMOTE with normalization leads to an accuracy result of 0.76, or 76%. The f1 score for males is 0.14, while for females it is 0.86.

 

 

A matrix Classification provides a concise representation of the classification accuracy of a classifier in relation to a given set of test data. A two-dimensional matrix is created, with one dimension containing the true class of an object and the other dimension containing the class assigned by the classifier. This study employed a two-class design, with one class representing females and the other class representing males, which were classified as the positive class and the negative class. Within this framework, the four cells of the matrix are classified as true positives (TP), false positives (FP), true negatives (TN), and false negatives (FN), as specified in table 6 below. 

 

This ANN model utilizes four cephalometric factors as the foundation for gender prediction. However, certain parameters may undermine the accuracy of the prediction. The SHAP model (Shapley Additive exPlanation) was employed in this work to determine the most relevant parameters in predicting gender. Figure 5 illustrates that the mandibula angle had the strongest positive impact on gender prediction, while the SGA angle had the most negative impact with.

V. DISCUSSION

The creation of a machine or autonomous mechanism with intelligence has long been a cherished aspiration of researchers across several scientific and technical disciplines, which ANN have the capability to be utilized in various technical and scientific difficulties (7). Although established more than 50 years ago, Artificial Neural Networks (ANN) garnered substantial interest and research in the early 90s, and still have great promise for further exploration (9).  The applications of intelligent systems cover a wide range of areas, including the field of forensic odontology (9). This study utilizes a combined approach of parameters measuring using deep learning; Web ceph, and machine learning: artificial neural networks (ANN) to investigate gender determination.

It is crucial to accurately interpret the results of an ANN prediction model. This interpretation provides dependable user confidence, valuable insights for model enhancement, and an improved understanding of the modelled process (14). However, the effectiveness of this artificial neural network technique is dependent on a significant volume of acquired data, as demonstrated in previous research conducted by Vathsala Patil, et. al., Tanvi et al., Deeepthi Bharadwaj et al., Naveen et al., and Usha Jambunath et al. The investigations conducted had a sample size of over 500 radiographs (6,15–17). By assessing the precision rate, it becomes evident that artificial neural networks (ANN) have demonstrated effectiveness in accurately detecting gender, regardless of the specific diagnosis of the sample used. These systems can forecast future values of a certain process by considering several past samples within its domain (9). As a result, ANN show promise in the field of forensic odontology, particularly in the prediction of gender identification (18).

 Lateral cephalometry has long been an essential tool for diagnosing orthodontic issues and creating treatment programs and it is now also applicable in the field of forensic odontology (18,19). In a prior investigation conducted by Bao (2023), it was discovered that automatic analysis software is capable of gathering cephalometric measures with a level of effectiveness that is nearly sufficient for clinical application (19).

A sizable data set is required in order to create a machine learning model (20). Handayani et al. (2024) found that collecting data on cephalometry presents a greater challenge compared to panoramic radiography, as RSGMP Unair exclusively uses cephalometry radiography for patients undergoing orthodontic therapy (13). In addition, there is a significant discrepancy in the statistics between males and females, which may be due to the fact that women are more aware of dental aesthetics than men. Additionally, the study discovered data imbalances that prevent accuracy results from exceeding 90%. The ANN model's composition is 80% for training, 10% for validating, and 80% for training, with precision values for males and females being 25% and 88%, respectively, in that study (13). 

Table 5 demonstrates four scenarios of ANN model. The first scenario is making the model without SMOTE and normalization that the ANN model achieves a precision rate of 78 percent in predicting gender. The second ANN model scenario is we used SMOTE without normalization an the accuracy decrease into 22%. The third scenario is with SMOTE and normalization it give better accuracy result which is 71%. For the fourth scenario, with normalization without SMOTE, it gives better result, which is 76%. The discrepancy in these precision values may be attributed to variations in the distribution of the number of samples for male and female cephalometry. In cases where the sample numbers are imbalanced, the accuracy value tends to favour larger sample sizes (21). This is corroborated by the metrics of Accuracy, Precision, and Recall obtained from Artificial Neural Networks (ANN) (22).

SMOTE is a resampling strategy that seeks to augment the number of samples in the minority class by generating synthetic samples in that class. It is utilized to stabilize datasets with a significantly imbalanced ratio. Upon analyzing the results of this study, it is clear from the matrix classification in Table 6 that SMOTE can enhance the accuracy of male predictions but fall short in predicting females. Overall, the absence of normalization in SMOTE does not contribute to the improvement of accuracy. In fact, it actually reduces the accuracy of the model. Based on the findings of Elreedy and Atiya (2019) and Duan et al. (2022), it has been demonstrated that the implementation of SMOTE can enhance the accuracy of minority samples (23,24). However, when normalization is applied, SMOTE demonstrates improved performance. This can be attributed to its ability to mitigate the problem of overfitting. Additionally, the procedure for generating fresh synthetic samples differs from that of the multiplication method.

Cephalometry radiographs are examined in order to assess the SNA angles, SGA angles, and mandibular length parameters. We utilize the SHAP (Shapley Additive Explanations) method, which is a Python-based metric, to measure the level of integration of the cephalometric components used in the artificial neural network (ANN) and determine their importance. The SHAP approach is utilized to aid artificial neural network (ANN) models in acquiring precise parameters for the purpose of identifying a novel category of parameter measurements (25). Additionally, it aids in determining whether there exists a singular answer inside this category that possesses a collection of desirable attributes. Hence, using the SHAP methodology in our research, we have ascertained that the mandibular angle derived from cephalometric radiographs emerges as the most dependable parameter for assessing gender prediction in the Indonesian population. This research pertains to the studies conducted by Sikka et al. (2016) and Patil et al. (2020), which showed significant variations in the mandible between males and girls. This research demonstrates that the selected characteristics, particularly the SGA angle, pose a problem in accurately predicting gender (6,26).

Artificial neural networks (ANNs) possess a notable advantage in that they do not require any prior familiarity with system models (27). This attribute is highly advantageous when used for the processing of files that exhibit missing or corrupted data. However, due to the exclusive operation of artificial neural networks (ANNs) on the tasks for which they have been trained, it is crucial to use a substantial amount of data. To accomplish any objective, it is important to retrain the data, and the augmentation of the image count within the cephalometry picture collection has the potential to yield improved performance (27,28). This study is hampered by the shortage of male sample data in comparison to females, as well as the limited parameters employed, which may have a negative impact on the accuracy of gender prediction and do not measures the density of the cranium.

VI. Conclusion

This study suggests the use of SMOTE as a solution to address the issue of imbalanced data in an artificial neural network (ANN) model used for gender identification. The efficacy of SMOTE in augmenting male data samples has been demonstrated, although this study did not observe any improvement in accuracy. Among the four selected characteristics, it is the mandibula angle factor that exerts an influence on gender prediction. To enhance performance, future research could involve expanding the dataset and conducting a thorough analysis of gender sample distribution. Additionally, researchers could evaluate additional characteristics and parameters, such as skull density, that can be utilized in the study of unidentified cranium and mass disasters.  

  

 

 

 

×

About the authors

Vitria Wuri Handayani

Airlangga University and Pontianak Polytechnic Health of Health Ministry

Email: vitriawuri@gmail.com
ORCID iD: 0000-0002-5076-0118
Indonesia

Ahmad Yudianto

Forensic Department, Medical Faculty, Airlangga University, Surabaya

Author for correspondence.
Email: ahmad-yudianto@fk.unair.ac.id
ORCID iD: 0000-0003-4754-768X
Scopus Author ID: 57202040365

Ahmad Yudianto is a Ph,D and Professor in Forensic Medicine at Airlangga University, Surabaya, Indonesia. his concern with the DNA profiler. Ahmad Yudianto is a Head Department of Forensic Department in Medical Faculty of Airlangga University. 

Indonesia

Mieke Sylvia M.A.R.

Forensic Odontology Department, Dental Medical Faculty, Airlangga University, Surabaya, Indonesia

Email: mieke-s-m-a-r@fkg.unair.ac.id
ORCID iD: 0000-0001-8821-0157
Scopus Author ID: 57221727472

Mieke Sylvia MAR is a Professor in Odontology Forensic Medicine at Airlangga University, Surabaya, Indonesia.

Indonesia

Riries Rulaningtyas

Physics Departement, Sains and Tecnology Faculty, Airlangga University, Surabaya, Indonesia

Email: riries-r@fst.unair.ac.id
ORCID iD: 0000-0001-7058-1566
Scopus Author ID: 35796063000

Riries Rulaningtayas is Doctor and a lecturer in Sains and Technology Faculty at Airlangga University, Surabaya, Indonesia

Indonesia

Muhammad Rasyad Caesarardhi

Department of Information Systems, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia

Email: mrasyadc@gmail.com
ORCID iD: 0000-0002-1235-8849
Indonesia, Department of Information Systems, Institut Teknologi Sepuluh Nopember, Surabaya, Indonesia

Ramadhan Hardani Putra

Department of Dentomaxillofacial Radiology, Faculty of Dental Medicine, Universitas Airlangga

Email: ramadhan.hardani@fkg.unair.ac.id
ORCID iD: 0000-0002-0622-3892
Indonesia, Prof. Dr. Mayjen Moestopo Street. No. 47, Surabaya 60132, East Java, Indonesia Tel) 62-31-503-0255

References

  1. Tanjung, R; Farizka I. Book of abstracts: The 4th Indonesia international symposium of forensic odontology “Incorporating Recent Advances and New Technologies for Delivering Good Evidence in Forensic Odontology.” In Makassar; 2023. p. 45.
  2. Subramanian AK, Chen Y, Almalki A, Sivamurthy G, Kafle D. Cephalometric Analysis in Orthodontics Using Artificial Intelligence - A Comprehensive Review. Biomed Res Int. 2022;2022.
  3. Ruth MSM. Sefalometri radiografi dasar. Surabaya: Sagung Seto; 2013.
  4. Indra Sukmana B, Rijaldi F. Buku Ajar Kedokteran Gigi Forensik [Internet]. Vol. vi. 2022. 1–79 p. Available from: https://idndentist.com/article/93
  5. Taner L, Metin Gursoy G, Deniz Uzuner F. Does Gender Have an Effect on Craniofacial Measurements? Turkish J Orthod [Internet]. 2019 Jun 27;32(02):59–64. Available from: http://cms.galenos.com.tr/Uploads/Article_53427/Turk J Orthod-32-59-En.pdf
  6. Patil V, Vineetha R, Vatsa S, Shetty DK, Raju A, Naik N, et al. Artificial neural network for gender determination using mandibular morphometric parameters: A comparative retrospective study. Cogent Eng [Internet]. 2020;7(1). Available from: https://doi.org/10.1080/23311916.2020.1723783
  7. Chen, M; Chalita, U; Saad, W; Yin, C; Chakraborty P. Artificial neural networks-based machine learning for wireless networks: a tutorial. IEEE Commun Surv Tutorials 21. 2019;3039(4).
  8. Dastres R, Soori M. Artificial neural network systems. Int J Imaging Robot [Internet]. 2021;2021(2):13–25. Available from: www.ceserp.com/cp-jour
  9. Ivan Nunes da Silva; Spatti, Danilo Hernane; Faluzino Rogerio Andrade; Liboni, Luisa Helena bartocci; Alves SF dos RA. Artificial neural networks: A practical course. Springer Nature. Switzerland; 2017.
  10. Wu Y, Feng J. Development and application of artificial neural network. Wirel Pers Commun [Internet]. 2018;102(2):1645–56. Available from: https://doi.org/10.1007/s11277-017-5224-x
  11. Elreedy D, Atiya AF, Kamalov F. A theoretical distribution analysis of synthetic minority oversampling technique (SMOTE) for imbalanced learning. Mach Learn [Internet]. 2023 Jan 5; Available from: https://link.springer.com/10.1007/s10994-022-06296-4
  12. Handayani, Vitria Wuri; Yudianto, Ahmad; Sylvia M.A.R, Mieke; Rulaningtyas R. Classification of Indonesian adult forensic gender using cephalometric radiography with VGG16 and VGG19: A Preliminary research. 2023;16.
  13. Handayani VW. Cephalometry radiology based on rrtificial intelligence model for predict gender determination in unidentified cranium. Universitas Airlangga; 2024.
  14. Hapsari RK, Miswanto M, Rulaningtyas R, Suprajitno H, Seng GH. Modified Gray-Level Haralick Texture Features for Early Detection of Diabetes Mellitus and High Cholesterol with Iris Image. 2022;2022.
  15. Satish, B. N. V. S., Moolrajani, C., Basnaker, M., & Kumar P. Dental sex dimorphism : Using odontometrics and digital jaw radiography. J Forensic Dent Sci. 2017;9(1):43.
  16. Arab MA, Khankeh HR, Mosadeghrad AM, Farrokhi M. Developing a hospital disaster risk management evaluation model. Risk Manag Healthc Policy. 2019;12:287–96.
  17. Vahanwala S. Assessment of the effect of dimensions of the mandibular ramus and mental foramen on age and gender using digital panoramic radiographs : A retrospective study. Contemp Clin Dent. 2019;9:343–348.
  18. Handayani, Vitria Wuri; Yudianto, Ahmad; Sylvia MAR, Mieke; Rulaningtyas R. Book of abstracts: The 4th Indonesia international symposium of forensic odontology “Incorporating Recent Advances and New Technologies for Delivering Good Evidence in Forensic Odontology.” In Makassar; 2023. p. 36–7.
  19. Bao H, Zhang K, Yu C, Li H, Cao D, Shu H, et al. Evaluating the accuracy of automated cephalometric analysis based on artificial intelligence. BMC Oral Health [Internet]. 2023 Apr 1;23(1):191. Available from: https://bmcoralhealth.biomedcentral.com/articles/10.1186/s12903-023-02881-8
  20. Ramezanzade S, Laurentiu T, Bakhshandah A, Ibragimov B, Kvist T, Bjørndal L. The efficiency of artificial intelligence methods for finding radiographic features in different endodontic treatments - a systematic review. Acta Odontol Scand [Internet]. 2022;81(6):422–35. Available from: https://doi.org/10.1080/00016357.2022.2158929
  21. Shung KP. Accuracy, Precision, Recall or F1? [Internet]. Towards Data Science. 2018 [cited 2023 Sep 2]. Available from: https://towardsdatascience.com/accuracy-precision-recall-or-f1-331fb37c5cb9
  22. Jeong SH, Yun JP, Yeom H-G, Lim HJ, Lee J, Kim BC. Deep learning based discrimination of soft tissue profiles requiring orthognathic surgery by facial photographs. Sci Rep [Internet]. 2020 Oct 1;10(1):16235. Available from: https://www.nature.com/articles/s41598-020-73287-7
  23. Elreedy D, Atiya AF. A Comprehensive Analysis of Synthetic Minority Oversampling Technique (SMOTE) for handling class imbalance. Inf Sci (Ny) [Internet]. 2019 Dec;505:32–64. Available from: https://linkinghub.elsevier.com/retrieve/pii/S0020025519306838
  24. Duan F, Zhang S, Yan Y, Cai Z. An Oversampling Method of Unbalanced Data for Mechanical Fault Diagnosis Based on MeanRadius-SMOTE. Sensors [Internet]. 2022 Jul 10;22(14):5166. Available from: https://www.mdpi.com/1424-8220/22/14/5166
  25. Zhang K, Zhang Y, Wang M. A Unified Approach to Interpreting Model Predictions Scott. Nips. 2012;16(3):426–30.
  26. Sikka, A., & Jain A. Sex determination of mandible : A Morphological and morphometric analysis. Int J Contemp Med Res. 2016;3(7):1869–1872.
  27. Pavithra V, Jayalakshmi V. Smart energy and electric power system: current trends and new intelligent perspectives and introduction to AI and power system. In: Smart Energy and Electric Power Systems [Internet]. Elsevier; 2023. p. 19–36. Available from: https://linkinghub.elsevier.com/retrieve/pii/B9780323916646000012
  28. Fan D-P, Zhang J, Xu G, Cheng M-M, Shao L. Salient Objects in Clutter. IEEE Trans Pattern Anal Mach Intell [Internet]. 2023 Feb 1;45(2):2344–66. Available from: https://ieeexplore.ieee.org/document/9755062/

Supplementary files

Supplementary Files
Action
1. JATS XML
Download

Copyright (c) Eco-Vector


СМИ зарегистрировано Федеральной службой по надзору в сфере связи, информационных технологий и массовых коммуникаций (Роскомнадзор).
Регистрационный номер и дата принятия решения о регистрации СМИ: серия ПИ № ФС 77 - 60835 выдано 09.09.2021 г. 
СМИ зарегистрировано Федеральной службой по надзору в сфере связи, информационных технологий и массовых коммуникаций (Роскомнадзор).
Регистрационный номер и дата принятия решения о регистрации СМИ: серия ЭЛ № ФС 77 – 59181 выдано 03.09.2014 г.


This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies