Ransomware is a significant cybersecurity risk that keeps increasing and threats like the WannaCry keep showing the need to be more intelligent and adaptive in detection methods. This paper presents DeepRansom, a powerful deep learning model that has been designed to detect WannaCry ransomware in complex malware environments with high precision and in a transparent manner. The architecture combines the feature selection of TabNet and the learning context of the FT-Transformer to create a dual-model architecture that can provide performance and interpretability. DeepRansom was trained and tested on a broad dataset of 21,752 samples of 26 malware families with 11 key ransomware variants. The proposed model reformulates WannaCry recognition as a binary classification task and delivers better results than the classical algorithms including Random Forest, SVM, and XGBoost among other deep learning baselines. The experiments have proven accuracy of 99.82%, precision of 97.89%, recall of 93.94% and AUC of 0.99% with strong generalization and low false positives. In addition, the SHAP-based analysis of interpretability shows that the predictions obtained by DeepRansom are based on the appropriate behavioral and structural predictors, which supports the idea of its implementation in the practice of network forensics and threat intelligence missions.
Advancements in smart surveillance and digital forensics have been significantly influenced by artificial intelligence (AI), machine learning (ML), and cloud computing, enabling real-time forensic analysis of CCTV footage to detect suspicious activities and reduce reliance on manual monitoring. While these technologies enhance public safety and policing efficiency, they also raise important concerns related to privacy, ethics, and regulation. This study proposes a deep learning-based forensic framework for real-time detection of suspicious human activity in CCTV videos, trained without relying on any external sensors. The model utilizes EfficientNet-B5 for spatial feature extraction and a Vision Transformer (ViT) that has been adapted to model both spatial and temporal dependencies between consecutive video frames. Specifically, the ViT processes frame sequences as token embeddings, enabling temporal context learning through self-attention. The EfficientNet-B5, a convolutional neural network (CNN), functions primarily as a high-level feature extractor, capturing geometric and spatial characteristics such as scale variations, aspect ratios, and motion-relevant visual patterns from individual frames. The Binary UCF-Crime dataset is used for training and validation, with class rebalancing achieved through data augmentation and weighted loss adjustment to mitigate class imbalance. Performance is evaluated using accuracy, precision, F1-score, and AUC metrics, each averaged across 5-fold cross-validation. The reported accuracy is obtained through this cross-validation protocol and benchmarked against baseline models, including standalone EfficientNet-B5 and traditional machine learning approaches. The ViT-enhanced model achieves an accuracy of 87.23%, outperforming the EfficientNet-B5 baseline by a significant margin. To address ethical concerns, the framework incorporates anonymization of personal identities and local edge-based processing to prevent raw data exposure.
Insects associated with vertebrate carrions play an important role in forensic investigations, especially in estimating post-mortem interval (PMI). Unfortunately, baseline data on local insect species associated with carrions in southern Nigeria is still limited. In this study, a checklist was compiled of insects associated with asphyxiated pig carrion was carried out in a grassland habitat. The study was conducted across both dry and rainy seasons of 2023, 2024, and 2025. Fresh pig carrions of 21kg were humanely euthanized by asphyxiation and exposed in wire-mesh cages to exclude vertebrate scavengers but allowed insects access. Insect sampling on the carrions was carried out throughout the decomposition stages. Adult and immature insects were collected, preserved, and identified to species using standard morphological keys. Four stages of carrion decomposition were observed for both seasons, but tissue depletion was faster during the rainy season than the dry season. Insect species collected on the carrions were 25 in 19 families, and 6 orders. The dipterans were the earliest and most dominant colonizers, starting from the fresh to wet stages. The coleopterans became prominent during dry stages throughout the skeletonized remains. Seasonal and interannual variations in species composition were also observed across the three-year study period. The findings provide a comprehensive checklist of carrion-associated insects in a grassland habitat in southern Nigeria and contribute baseline data for forensic entomology in the region. This study emphasizes the importance of localized entomological data for improving the accuracy of PMI estimation and forensic investigations in tropical environments.
Forensic document examination is a highly specialized branch of forensic science that focuses on determining the authenticity of disputed documents. Practitioners use a variety of scientific techniques to detect forgery, alterations, and other forms of document tampering, including ultraviolet (UV) and infrared (IR) imaging, electrostatic detection (ESDA), and high-resolution microscopy. Despite its evidentiary value, this discipline has received limited recognition in Pakistan's legal system. The study aimed to assess the role of forensic questioned documents in criminal investigation and its evidentiary limitations in the justice system of Khyber Pakhtunkhwa, Pakistan. The researcher conducted qualitative research by interviewing five forensic document examiners who work at the Peshawar Forensic Science Laboratory; along with fifteen public prosecutors, and five defense counsels. Since there are a limited number of forensic document examiners in the provincial laboratory, a census sample was used, while purposive sampling was employed for public prosecutors and defense counsels who had been involved in experiences with documents related cases. Thematic analysis of interview transcripts identified key themes, including chain of custody, process of forensic analysis, judicial perception, limited weightage of forensic reports, forensic capacity gaps. Findings revealed that the most frequent disputed documents received by the lab, were stamp papers, cheques, academic degrees, Nikah Namas (marriage certificates), burnt documents, mutation records, and even writings on walls, leaves, and human skin. Tasks such as ink differentiation, indented writing detection, and signature verification are currently performed using VSC 6000/HS and ESDA-2 apparatus however, they require more advanced instruments such as VSC 9000/HS and high-resolution microscopes for optimal results. Courts treat forensic reports as corroborative rather than primary evidence. Major challenges include delays in reports, poor stakeholder coordination, and limited qualifications and training of experts. The findings suggested that the role of forensic analysts need to be enhanced by providing them advance training. Further, policy reforms and mechanism of collaborative relationships between the relevant stakeholders for the pursuance of criminal investigation need to be developed for effective justice system administration
Incestuous paternity investigations are considered among the most analytically and ethically complex challenges in forensic genetics. Extensive allele sharing occurs among family members and close biological relatives. Mutations in short tandem repeat (STR) markers, together with the concealment or frequent absence of key family members, can interfere with reliable paternity interpretation and increase the risk of false inclusion or exclusion. This study describes a legally significant forensic DNA case, where the use of the national DNA database revealed unexpected paternal candidates, ultimately resolving a highly complex case. Initial autosomal STR profiling using AmpFlSTR™ Identifiler™ Plus and GlobalFiler™ multiplex systems indicated non-exclusion of an alleged father (AF1) accused of sibling incest, despite a single-locus mismatch consistent with mutation. Subsequent blind comparison within the DNA Database identified a second related individual who also could not be excluded as the biological father (AF2). Further investigation, including Y-chromosomal STR analysis and expanded testing of multiple maternal relatives, ultimately established a third individual (AF3), a maternal nephew, as the true biological father without mutational inconsistencies. These findings highlight the essential role of mutation-aware interpretation, comprehensive kinship analysis, and forensic DNA databases in accurately resolving complex incest-associated paternity disputes and preventing wrongful judicial outcomes.
Gender estimation from handwriting has long been of interest in forensic document examination. However, most prior studies rely on static handwriting features, with limited exploration of dynamic writing behaviour. The advent of advanced technologies in recording handwriting made it possible to study the dynamic nature of the handwriting. The present study investigates gender-related differences in dynamic handwriting features derived from digitally captured natural style-handwriting, integrating statistical analysis with machine learning classification. Handwriting samples were collected from 200 participants (100 males, 100 females) using a pen-enabled digital tablet across three trials. Five primary dynamic features: Time-stamped X and Y coordinate data, pressure, azimuth, altitude and time, were recorded and used to derive 21 kinematic, spatial, pressure-based, and temporal features. The statistical analysis using Mann-Whitney U test, indicated significant gender-related differences in several dynamic features, including temporal parameters (pen-up duration, pen-down duration, total duration), pressure-related measures, spatial (handwriting width and height) and kinematic parameters like velocity and acceleration. Features demonstrating statistical significance were subsequently employed as inputs to supervised machine learning models, including Random Forest, Support Vector Machine, and Gradient Boosting classifiers. The Random Forest achieved the highest classification accuracy (86.7%) followed by Support Vector Machine (82.7%) and Gradient Boosting (80%). The findings demonstrate the potential of dynamic handwriting features in forensic document examination for gender estimation and preliminary profiling of writers
The analysis of overlapping of different ink strokes has always been an important factor in forensic document examination, as seen in cases of fraud and tampering of documents. The objective of this study is to use microscopy to analyse the sequence of strokes of laser printer toner and stamp pad inks and evaluate its potential in identifying various characteristics that are found at the intersections. Samples prepared with different printer, ink brands and paper types, were examined by making two types of stroke intersections. At these intersections, features such as gloss variation, gaps in strokes, surface morphology and stroke narrowing were observed. This study contributes in establishing that despite variations in paper, ink and toner, microscopy can be a reliable technique for the determination of sequence of strokes in laser printer toner and stamp pad inks. With the existing studies mainly focusing on the use of more sophisticated analyses, this study shows the importance of the use of stereomicroscopy on its own as a non-destructive and easily available method for stroke sequence determination. It is an adaptable and dependable method that can be effectively applied across laboratory setups with varying levels of technical infrastructure
Questioned document examiners come across various documents to establish their originality, authorship and authenticity. With technological advancement, documents are printed using different printing devices, of which laser printers are highly commercialised. However, the misuse of such technological advancements has also increased, so laser printers can be used to create forged documents. One class of forged documents is built-up documents, which contain authentic signatures, but the contents of the document are added after appending the signatures. These documents might be printed using a laser printer, and stamp impressions may also be present, which do not intersect each other. Thus, to address such cases, the present study has been conducted to establish the sequence of production of a laser-printed document containing a stamp impression. A total of 720 samples were prepared, of which 360 samples were first printed and then stamped, and the rest of the samples were first stamped and then printed. For the analysis, a NIKON SMZ800N stereo microscope with a magnification of 2×10×8X was used. The technique was non-destructive, reliable and inexpensive. Variables such as the colour of the stamp, substrate (paper), and printouts from different laser printers were also studied to analyse their effect on the determination of the sequence of document production. Micro-conformation features of toner particles, fibre distribution, and ink distribution were analysed. The results obtained showed that the sequence of non-intersecting laser printing and stamping could be established using micro-conformation features of fibre distribution and ink distribution. However, the micro-conformation features of toner particles do not help in establishing the sequence. The study also highlights the precautions that must be taken while forming an opinion on the sequence of non-intersecting strokes.
ُعد الشعر أحد أكثر أنواع الأدلة الضئيلة (Trace Evidence) شيوعاً في التحقيقات الجنائية؛ حيث يساهم في إيجاد صلة ربط محتملة بين المشتبه به والضحية ومسرح الجريمة. ويمكن أن تكون الخصائص المورفولوجية (الشكلية) للشعر مفيدة في غالبية القضايا الجنائية. تعتمد الدراسة الحالية تقنيات المجهر الضوئي لفحص ومعايرة الاختلافات في الخصائص المورفولوجية بين شعر فروة الرأس للذكور والإناث. وقد استُخدم في فحص الشعر مجهر مقارنة مركب (Olympus BX-53) مزود بملحقات الاستقطاب والفلورة، بالإضافة إلى مجهر ستيريو (Olympus SZ-61). كان الهدف من هذه الدراسة هو فحص ومقارنة سمات فيزيائية ومجهرية مختارة لشعر فروة الرأس البشري لمتطوعين من الجنسين. وتم استقصاء مجموعة من الخصائص المورفولوجية عبر الجنسين، شملت: توزيع الصبغات، شكل الجذر، سمك القشرة (Cuticle)، ونمط حراشف القشرة، والأنماط النخاعية (Medullary patterns)، وقطر الساق، والملمس، وبعض السمات المجهرية الأخرى. كما لوحظ وجود وخصائص حواف الأجسام البيضاوية (Ovoid bodies) كسمات مجهرية مساعدة. وتشير الملاحظات التجريبية لهذه الدراسة، عند النظر إليها جنباً إلى جنب مع النتائج الواردة في الدراسات السابقة، إلى وجود اتجاهات معينة مرتبطة بالجنس في مورفولوجيا الشعر. وتلعب الوراثة دوراً هاماً في تحديد خصائص الشعر، على الرغم من وجود تداخل كبير في السمات المجهرية بين شعر فروة الرأس للذكور والإناث. وقد لوحظ وجود متوسط قطر أكبر لساق الشعرة في ذكور (98.2 ± 12.42 ميكرومتر) مقارنة بالإناث (73.88 ± 10.84 ميكرومتر). وبشكل عام، أظهرت عينات شعر الذكور مظهراً سطحياً أكثر نعومة وطبقات قشرية سميكة نسبياً تحت المجهر الضوئي. وبالمثل، لوحظت معايير أخرى مثل عدد الأطراف المتقصفة، ونطاق أوسع للألوان الطبيعية. كانت الملاحظة الرئيسية لهذه الدراسة هي وجود اتجاهات ملموسة مرتبطة بالجنس في سمات مجهرية مختارة لشعر فروة الرأس بين الذكور والإناث.
Ink has always been an important aspect of document examination, which while may appear optically similar to the naked eye, but can vary significantly in terms of their chemical constituents. Majority of studies has been focussed on distinguishing these visibly similar inks. However, disappearing inks, also known as magic inks presents a unique set of challenge to document security given its ability to fade entirely within approximately seconds to days, thus enabling undetectable forgery. The current study attempted a non-destructive chemical profiling and classification of blue disappearing inks available in Indian markets using Attenuated Total Reflectance – Fourier Transform Infrared (ATR-FTIR) spectroscopy in conjunction with chemometric methods In the present study, a total of ninety different blue magic pen (disappearing) inks, representing the 30 different brands were purchased from e-shopping websites and local markets of Jhansi district of Uttar Pradesh in India. The samples were prepared by drawing circles of 2 cm radius and filling it completely with ink in five subsequent strokes on 80 gsm white A4 copying paper for each pen which was then spectroscopically analyzed by ATR-FTIR within the range of 4000- 600 cm-1. The spectral data was further subjected to chemometric analysis viz. HCA and PC-DA. FTIR spectroscopy of magic pen inks demonstrated significant similarities in spectra with characteristic peaks for O-H (alcohol/water), C-H (aliphatic), C=C (aromatic) and C-O stretching peaks indicating the presence of thymolphthalein as fundamental constituent to most of the blue disappearing ink formulations available in the markets. Chemometric analysis using Hierarchical Cluster Analysis (HCA) revealed four major clusters within the samples. PC based Discriminant Analysis (DA) model was then used to assess the classification of samples in these respective groups which performed reasonably well achieving an accuracy of 100% in classification and cross-validation. Also, PC based DA model for classification of samples according to manufacturer successfully, linked samples to their respective manufacturer with an original and cross-validated accuracy of 97.8% and 82.2% respectively.
Postmortem pink teeth may occur in forensic cases being frequently associated with death by drowning, asphyxiation, trauma, or electrocution. Although it has been frequently described in forensic literature, its causative mechanisms, prevalence, and usefulness in diagnosis are still unclear. Hence, the goal of this scoping review is to map available data concerning the pink teeth phenomenon and analyse its potential interest in the identification of the cause of death. The addressed question is to find out if this phenomenon has diagnostic value in forensic medicine. One suggested hypothesis is that the pink colour results from haemoglobin infiltration into dentinal tubules, and it seems that this infiltration is influenced by the cause of death as well as by environmental factors such as humidity. However, due to the variability in presentation and the difficulty in differentiation from antemortem discolorations like tooth trauma and congenital disorders, the applicability of this phenomenon in determining the cause of death is complicated. Therefore, a deep analysis of published data is crucial to separate forensically significant patterns from coincidental findings. This review will be prepared following the Joanna Briggs Institute (JBI) methodology and PRISMA-ScR guidelines, and multiple databases will be used in the bibliographic search to identify studies discussing the occurrence, proposed mechanisms, and forensic interpretation of this phenomenon. The review will summarize the nature of existing re-search, observation, hypothesized pathophysiology, and forensic implications. Through the identification of knowledge deficiencies and future research goals, this work wants to support a clearer understanding of pink teeth and their significance in forensic investiga-tions.
This article addresses the new term Desert Forensics, an important need in dealing with deaths that occur in the desert environment. The review article expands on the challenges forensic scientists encounter in desert environments, including limited access, dry and extreme climate conditions, uncontrolled decay of forensic remains, and even scavenger activity. Specialized methods and techniques are needed to help address these issues; because while forensic science has broad appeal across disciplines, there is no research addressing specific forensic needs in a desert environment. The article discusses specific methods for the identification, collection, and analysis of forensic evidence because the review article focuses on: drone forensics, forensic imaging, and remote sensing. The article also discusses the importance of cultural sensitivity in forensic death scene investigations because of the diverse communities within the desert.
This study examined forensic insect diversity across three Gambian communities representing urbanization gradients: Brikama (urban), Gunjur (semi-urban), and Faraba (rural). Using RESCUE POP Fly Traps baited with rotten beef, dipterans were collected over 24-hour periods and identified morphologically. Seven species were documented, with Chrysomya albiceps dominating all sites. Brikama showed highest diversity (6 species; Simpson's D=0.622, Shannon H=1.162), Gunjur the lowest (D=0.213, H=0.369), and Faraba intermediate values (D=0.476, H=0.669). Similarity indices (Sørensen, Bray-Curtis) indicated moderate overlap between Brikama-Gunjur but lower Brikama-Faraba similarity. Calliphoridae was the predominant family. Results demonstrate that urbanization and habitat type significantly influence forensic insect communities, highlighting the necessity of location-specific data for accurate post-mortem interval estimation. This work provides foundational entomological data for The Gambia’s forensic investigations, though broader geographical sampling is recommended to fully characterize the country’s forensic insect biodiversity.
Electrical tapes are frequently used by deviants and criminals to perpetrate violent crimes. These trace materials can be an ideal tool in solving such crimes. Although tapes can consist of multiple layers, their characteristics and primary functions are largely determined by the adhesive and backing layers. In the present study, a total of 25 electrical tapes from different manufacturers were analyzed for both the backing and adhesive sides using a non-invasive, non-destructive analytical technique, ATR-FTIR. The spectral data revealed presence of rubber-based and acrylic-based adhesives with rubber-based adhesives being more common while PVC as the primary backing material. Further chemometric classification using Principal Components (PCs) based Discriminant Analysis (DA) attained an original and cross-validated accuracy of 100% in classification of adhesives and 100% original and 88% cross-validated accuracy in classification of backing. Alternatively, the SVM model demonstrated strong potential as a chemometric classifier, achieving up to 100% accuracy in distinguishing adhesives and backings of electrical tapes, with cross-validation accuracies of 100% for the adhesive side and 92% for the backing side, respectively. Study reveals ATR-FTIR as a valuable analytical tool for preliminary identification of chemical constituents of the electrical tapes and with chemometric models like DA and SVM, it could successfully link adhesives and backings to their respective groups. SVM models which haven’t been used much in previous studies, appeared to perform better than traditional chemometric models in the current study.
Forensic entomologists face several challenges in determining the post-mortem interval (PMI) while dealing with burnt remains. It is important to consider the succession and colonization patterns of insects on such remains while arriving at minimum post-mortem interval (PMImin). The purpose of the present study was to investigate the decomposition rate and insect succession pattern on burnt and unburnt pig carcasses during the spring season (March-May 2022) in a semi-arid region of Haryana with replication in the subsequent year. A total of eight pig carcasses were used during the study, out of which six pig carcasses were burnt at the Crow-Glassman Scale (CGS) level 1, 2, and 3, while two were left unburnt (Control) during both the years. The average ADD for control carcass was estimated 1232.1, while for burnt level 1, 2, and 3 carcasses it was 1392.5, 1524, and 1943.9 respectively. Chrysomya megacephala was the earliest visitor on the control carcasses, whereas Vespa orientalis was the first one to visit on all the burnt carcasses. As the only Indian study focused on burnt carcasses, this study reveals that more severe the burns, the longest is the dry stage and slowest is the decomposition rate. The abundance of coleopterans on burnt carcasses may hold potential value in exploring their effectiveness for estimating an approximate post-mortem interval (PMI).
This paper presents a retrospective analysis of reported cases and examinations conducted by the Document Division of a prominent forensic science laboratory covering six districts in Himachal Pradesh, India, over the five years (2018–2022), additionally, we provide updated data for 2023–2024 limited to case intake and disposal at RFSL Dharamshala to reflect recent forensic case handling trends. The data collection process involved reviewing case files and examination reports to identify commonalities and deviations in cases related to document alterations. The dataset includes information on the types of document alterations, techniques used, and legal provisions applicable to each case. The analysis aims to provide insights into evolving trends in white-collar crimes involving document alterations within the jurisdiction. The dataset's reuse potential lies in its ability to inform future forensic investigations, policy development, and educational initiatives aimed at combating document-related fraudulent activities. This study contributes to the forensic science community's understanding of regional trends in document-related white-collar crimes and underscores the importance of continuous monitoring and adaptation to emerging threats. By elucidating patterns and methods employed by perpetrators, the dataset facilitates the development of proactive strategies for prevention, investigation, and prosecution. The establishment of robust forensic databases is advocated to effectively combat the persistent threat of document-related fraudulent activities. The insights gained from this study are anticipated to guide future forensic investigations and support efforts to address the dynamic nature of document alterations in a rapidly evolving technological landscape.
Forensic botany is a scientific investigation methodology that deals with the analysis of plant based evidence for solving crimes. The correlation of plants as the basis of life is supplemented by their extensive ability to seek justice for the dead and wronged through this domain. The ubiquity of botanical matter results in its presence in virtually all outdoor crime scenes. In such a scenario, these evidences can provide valuable insights into the place and manner of occurrence of the crime, among others. This case report presents one such instance of homicide, demonstrating the prowess of botanical evidence in establishing the place of discovery of the body as the primary crime scene. This was achieved through the comparison of grass at the intended site with control samples to ascertain factors such as morphology, compression and traces of blood. The breakthrough came with the analysis of the victim’s hair strands entwined with grass fibres, severed through the application of sharp trauma rather than decomposition. Thus the study of botanical evidence was able to rule out possibilities of attack occurring elsewhere and attest to the site of discovery of the body as the scene of the fatality
Dental morphological variations, such as the entoconulid or cusp 6, hold significant value in forensic identification and anthropological studies. These traits often vary across populations and provide insights into genetic and evolutionary patterns. The entoconulid is an uncommon dental trait observed primarily in Mongoloid and African populations. It reflects complex genetic, epigenetic, and environmental interactions during tooth development. In forensic contexts, the presence of such morphological features can aid in population-specific identification and provide additional evidence in cases lacking ante-mortem data.The entoconulid, though rare, is a significant morphological characteristic with applications in forensic identification and anthropological research. Dentists should recognize and document such traits to support the identification of human remains, especially in the absence of other identifiers. This article will disscuss about a 21-year-old deceased male that was involved in a gang fight and was referred to Said Sukanto Bhayangkara Police Hospital in Jakarta for postmortem examination. Extraoral findings included multiple abrasions and fractures on the body, while intraoral examination revealed dental caries, unerupted teeth, and the presence of entoconulid on tooth 46.
Diffuse axonal injury (DAI) is a common type of traumatic brain injury, whose detection remains a significant clinical challenge. Recent studies suggest that traumatic cerebral microbleeds (TCMs) may serve as indirect indicators of axonal injury. Given the similar mechanisms underlying the formation of axonal injury and cerebral microbleeds, the aim of this study is to investigate the potential association between these two types of cerebral trauma. In the total sample of 36 brains, axonal injury was detected in 32 cases (88.9%), identical to the incidence of traumatic cerebral microbleeds. βAPP immunopositivity was relatively evenly distributed across the examined brain regions, with slightly stronger expression in the posterior brain regions and the highest frequency of intense immunopositivity in the pons, albeit without statistical significance. The χ2 test, along with the Spearman correlation test, indicates an association between traumatic microbleeds in the genu of the corpus callosum and βAPP immunopositivity in all four observed brain regions, with the strongest correlation observed in the genu of the corpus callosum (p=0.011).
The study employed Thin Layer Chromatography (TLC) and Attenuated Total Reflectance-Fourier Transform Infrared (ATR-FTIR) to analyze local brands of vermillion and lipstick samples. In TLC, vermillion and lipsticks exhibited notable separation patterns among various brands. The ATR-FTIR spectrum analysis of both vermillion and lipstick samples revealed distinct spectral patterns. After analyzing the FTIR library's cosmetics spectrum, notable similarities were found among compounds like Butyl Stearate, Nonane, and Linoleic Acid. Principal Component Analysis (PCA) categorized by cosmetic type and form revealed significant variance within the datasets. PCA based on cosmetic type explained approximately 83.57% of the total variance, while PCA based on form elucidated about 90% of the variance. Support Vector Machine (SVM) analysis demonstrated high precision and recall for classifying cosmetic types and forms. SVM results showed a precision of 1.00 for both lipstick and vermillion, indicating accurate predictions. Additionally, Hierarchical Cluster Analysis (HCA) identified six clusters of data points with shared characteristics. Overall, the study provides valuable insights into the composition and characteristics of vermillion and lipstick samples. The combination of TLC, ATR-FTIR spectrum analysis, PCA, SVM, and HCA offers a comprehensive approach for analyzing cosmetics
