Meksel Cengiz
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Meksel Cengiz has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Muhammet Can
Department of Forensic Medicine, Faculty of Medicine, Balıkesir University, 10145 Balıkesir, Türkiye
3 shared publications - Cihangir Işık
Department of Forensic Medicine, Balıkesir Atatürk City Hospital, 10100 Balıkesir, Türkiye
2 shared publications - Hasan Burkay Göksel
BALIKESİR ÜNİVERSİTESİ, TIP FAKÜLTESİ
1 shared publication - Hivdan Nacar
BALIKESİR ÜNİVERSİTESİ, TIP FAKÜLTESİ
1 shared publication - Hümeyra Yıldırım
Balıkesir University
1 shared publication - Mehmet Oğuz Dikilitaş
BALIKESİR ÜNİVERSİTESİ TIP FAKÜLTESİ ADLİ TIP ANABİLİM DALI
1 shared publication
Latest Publications
- Open Access
- 20 May 2026
- Published by MDPI AG in Forensic Sciences
- Vol. 6 (2) , 41
AI-Based Quantitative Handwriting and Signature Feature Analysis: Development and Validation of a Mobile Application for Forensic Document Examination—A Preliminary Study
Background/Objective: Forensic document examination (FDE) traditionally relies on subjective expert opinion. This preliminary study was designed to develop and validate a hybrid deep learning model (ResNet-50 + bidirectional long short-term memory [BiLSTM]) for quantitative handwriting and signature feature analysis, and to compare its performance, under standardized experimental conditions, with that of three certified forensic document examiners. Methods: Handwriting and signature samples were collected from 225 individuals in a standardized setting. Fifteen quantitative handwriting features were extracted, the dataset was split into training (70%, n = 158) and testing (30%, n = 67) subsets using stratified random sampling, and ground truth for analytic categories was defined by majority consensus among the three examiners (with adjudicated review for disagreements). A hybrid architecture combining a ResNet-50 backbone and a bidirectional LSTM encoder was used. Results: The model demonstrated 93.4% accuracy, an F1-score of 0.926, and an AUC-ROC of 0.968 on the held-out test set. Under our task-specific experimental conditions, the model performed better than examiners on slant analysis (96.8% vs. 93.2%, p = 0.002), pressure profiling (94.1% vs. 91.7%, p = 0.019), and age estimation (87.4% vs. 82.1%, p = 0.011); examiners performed better on forgery detection (95.8% vs. 91.2%, p = 0.008) and signature verification (96.1% vs. 92.3%, p < 0.012). Mean processing time was reduced by 99.6% (0.8 s vs. 197 s per case). Conclusions: Within the limits of this preliminary single-centre study, the system showed performance comparable to certified examiners on several quantitative tasks and complementary strengths overall, supporting its feasibility as an adjunctive tool in a hybrid human–AI workflow. Broader, multi-centre validation and explainability work are required before any forensic deployment can be considered.
- 20 May 2026
- Published by MDPI AG in Forensic Sciences
- Vol. 6 (2) , 41
Open AccessAI-Based Quantitative Handwriting and Signature Feature Analysis: Development and Validation of a Mobile Application for Forensic Document Examination—A Preliminary Study
Background/Objective: Forensic document examination (FDE) traditionally relies on subjective expert opinion. This preliminary study was designed to develop and validate a hybrid deep learning model (ResNet-50 + bidirectional long short-term memory [BiLSTM]) for quantitative handwriting and signature feature analysis, and to compare its performance, under standardized experimental conditions, with that of three certified forensic document examiners. Methods: Handwriting and signature samples were collected from 225 individuals in a standardized setting. Fifteen quantitative handwriting features were extracted, the dataset was split into training (70%, n = 158) and testing (30%, n = 67) subsets using stratified random sampling, and ground truth for analytic categories was defined by majority consensus among the three examiners (with adjudicated review for disagreements). A hybrid architecture combining a ResNet-50 backbone and a bidirectional LSTM encoder was used. Results: The model demonstrated 93.4% accuracy, an F1-score of 0.926, and an AUC-ROC of 0.968 on the held-out test set. Under our task-specific experimental conditions, the model performed better than examiners on slant analysis (96.8% vs. 93.2%, p = 0.002), pressure profiling (94.1% vs. 91.7%, p = 0.019), and age estimation (87.4% vs. 82.1%, p = 0.011); examiners performed better on forgery detection (95.8% vs. 91.2%, p = 0.008) and signature verification (96.1% vs. 92.3%, p < 0.012). Mean processing time was reduced by 99.6% (0.8 s vs. 197 s per case). Conclusions: Within the limits of this preliminary single-centre study, the system showed performance comparable to certified examiners on several quantitative tasks and complementary strengths overall, supporting its feasibility as an adjunctive tool in a hybrid human–AI workflow. Broader, multi-centre validation and explainability work are required before any forensic deployment can be considered.
- Open Access
- 30 April 2026
- Published by Balikesir Medical Journal in Balıkesir Medical Journal
- Vol. 10 (1) , 23-34
Balıkesir University Faculty of Medicine First Year Student Recognition Survey
Objective: Discussions on the quality and nature of medical education in our country have been ongoing for years. This study, conducted in 2022, aims to evaluate the socioeconomic and cultural characteristics of first-year students at Balıkesir University Faculty of Medicine, their level of satisfaction with the faculty, and their thoughts and suggestions regarding physical conditions, ease of communication with instructors, and transportation. Materials and Methods: A total of 146 students who completed their first year in the 2021–2022 academic term participated in the study, including 77 (52.7%) females and 69 (47.3%) males. The questionnaire consisted of 34 questions: 25 on sociodemographic characteristics, 5 on physical and social conditions of the faculty, and 4 on students’ opinions about education. Results: The mean age of the participants was 19.29 years. Among them, 46 students (%31.5) had placed Balıkesir University Faculty of Medicine among their top five choices during the university entrance exam. Accommodation preferences included 72 (49.3%) students in private dormitories, 39 (26.7%) in public dormitories, 19 (13%) with family, and 16 (11%) in rented apartments. Regarding their reasons for choosing medicine, 63 students (43.2%) identified it as their ideal profession, while 40 (27.4%) cited prestige, financial gain, and job security. Conclusion: The most common complaint among students was the inadequacy of transportation to the medical school, followed by a lack of social activities and insufficient educational materials. It is believed that evaluating students' concerns and expectations will help improve medical education and that conducting such surveys regularly would be a beneficial practice.
- 30 April 2026
- Published by Balikesir Medical Journal in Balıkesir Medical Journal
- Vol. 10 (1) , 23-34
Open AccessBalıkesir University Faculty of Medicine First Year Student Recognition Survey
Objective: Discussions on the quality and nature of medical education in our country have been ongoing for years. This study, conducted in 2022, aims to evaluate the socioeconomic and cultural characteristics of first-year students at Balıkesir University Faculty of Medicine, their level of satisfaction with the faculty, and their thoughts and suggestions regarding physical conditions, ease of communication with instructors, and transportation. Materials and Methods: A total of 146 students who completed their first year in the 2021–2022 academic term participated in the study, including 77 (52.7%) females and 69 (47.3%) males. The questionnaire consisted of 34 questions: 25 on sociodemographic characteristics, 5 on physical and social conditions of the faculty, and 4 on students’ opinions about education. Results: The mean age of the participants was 19.29 years. Among them, 46 students (%31.5) had placed Balıkesir University Faculty of Medicine among their top five choices during the university entrance exam. Accommodation preferences included 72 (49.3%) students in private dormitories, 39 (26.7%) in public dormitories, 19 (13%) with family, and 16 (11%) in rented apartments. Regarding their reasons for choosing medicine, 63 students (43.2%) identified it as their ideal profession, while 40 (27.4%) cited prestige, financial gain, and job security. Conclusion: The most common complaint among students was the inadequacy of transportation to the medical school, followed by a lack of social activities and insufficient educational materials. It is believed that evaluating students' concerns and expectations will help improve medical education and that conducting such surveys regularly would be a beneficial practice.
- Open Access
- 1 August 2023
- Published by Cetus Publishing in The Bulletin of Legal Medicine
- Vol. 28 (2) , 160-165
Göz Travmalarına Adli Tıp Bakış Açısı: Balıkesir İli Örneği
Objective: General forensic examination and reporting after trauma due to forensic events is important. It is aimed to evaluate the general forensic examination reports prepared for forensic eye injuries due to trauma in our region, taking into account penal law. Methods: In the study, the medical records of 8.651 cases who applied to the Forensic Medicine Department for the preparation of forensic reports in the 6-year period between January 2016 and February 2022 were retrospectively analyzed. Eye injury was detected in 146 of the cases. Results: According to years, 8 (5.5%) cases were 2016, 17 (11.6%) 2017, 23 (15.8%) 2018, 24 (16.4%) 2019, 18 (12.3%) 2020, 48 (32.9%) of 2021 and 8 (5.5%) of them belonged to January and February of 2022. Thirty seven (25.3%) of 146 cases about whom a report was made were female and 109 (74.7%) were male. The male/female ratio (109/37) was found to be 2.94. Considering age groups of the cases; 87 (59.6%) cases, 25 female and 62 male, aged 20-49, 2 female and 13 male, total 15 (10.3%) cases aged 10-19, and aged 0-9 years. A total of 3 (2.1%) cases were detected, 1 female and 2 male. There was no significant relationship between age groups and gender. Conclusion: In addition to general forensic examination reports, various difficulties are encountered in the evaluation of forensic eye injury cases. It was concluded that ophthalmologists and forensic medicine specialists should work together in forensic eye injuries, as in many branches, in the preparation of forensic reports.
- 1 August 2023
- Published by Cetus Publishing in The Bulletin of Legal Medicine
- Vol. 28 (2) , 160-165
Open AccessGöz Travmalarına Adli Tıp Bakış Açısı: Balıkesir İli Örneği
Objective: General forensic examination and reporting after trauma due to forensic events is important. It is aimed to evaluate the general forensic examination reports prepared for forensic eye injuries due to trauma in our region, taking into account penal law. Methods: In the study, the medical records of 8.651 cases who applied to the Forensic Medicine Department for the preparation of forensic reports in the 6-year period between January 2016 and February 2022 were retrospectively analyzed. Eye injury was detected in 146 of the cases. Results: According to years, 8 (5.5%) cases were 2016, 17 (11.6%) 2017, 23 (15.8%) 2018, 24 (16.4%) 2019, 18 (12.3%) 2020, 48 (32.9%) of 2021 and 8 (5.5%) of them belonged to January and February of 2022. Thirty seven (25.3%) of 146 cases about whom a report was made were female and 109 (74.7%) were male. The male/female ratio (109/37) was found to be 2.94. Considering age groups of the cases; 87 (59.6%) cases, 25 female and 62 male, aged 20-49, 2 female and 13 male, total 15 (10.3%) cases aged 10-19, and aged 0-9 years. A total of 3 (2.1%) cases were detected, 1 female and 2 male. There was no significant relationship between age groups and gender. Conclusion: In addition to general forensic examination reports, various difficulties are encountered in the evaluation of forensic eye injury cases. It was concluded that ophthalmologists and forensic medicine specialists should work together in forensic eye injuries, as in many branches, in the preparation of forensic reports.