Journal of forensic sciences最新文献

AI as a decision support tool in forensic image analysis: A pilot study on integrating large language models into crime scene investigation workflows.

Journal of forensic sciences Pub Date : 2025-04-04 DOI: 10.1111/1556-4029.70035

Shai Farber

{"title":"AI as a decision support tool in forensic image analysis: A pilot study on integrating large language models into crime scene investigation workflows.","authors":"Shai Farber","doi":"10.1111/1556-4029.70035","DOIUrl":"https://doi.org/10.1111/1556-4029.70035","url":null,"abstract":"This study evaluates the effectiveness of artificial intelligence (AI) tools (ChatGPT-4, Claude, and Gemini) in forensic image analysis of crime scenes, marking a significant step toward developing bespoke AI models for forensic applications. The research involved independent analysis of 30 crime scene images by the AI tools, with the resulting reports rigorously assessed by 10 forensic experts. Findings reveal promising potential for AI as a decision support tool in forensic science, serving as a rapid initial screening mechanism to assist human experts in their comprehensive analysis. The results emphasize that current AI tools function optimally as assistive technologies, enhancing rather than replacing expert forensic analysis, particularly in scenarios involving multiple evidence points or high-volume caseloads. The AI tools demonstrated high accuracy in observations but faced challenges in evidence identification, with performance varying across different crime scene types-excelling in homicide scenarios (average score of 7.8) but encountering difficulties in arson scenes (average score of 7.1). This study's findings could significantly impact investigative procedures, forensic training, and the development of AI tools in law enforcement, while emphasizing the importance of establishing robust ethical guidelines for the integration of AI in criminal justice systems.","PeriodicalId":94080,"journal":{"name":"Journal of forensic sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143789478","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Correction to: Forensic investigation of a shawl linked to the "Jack the Ripper" murders.

Journal of forensic sciences Pub Date : 2025-04-04 DOI: 10.1111/1556-4029.70041

引用次数: 0

Effect of mounting a sound suppressor on distribution and total amount of inorganic gunshot residue on targets.

Journal of forensic sciences Pub Date : 2025-04-03 DOI: 10.1111/1556-4029.70025

Matteo Donghi, Alessandro Girella, Debora Pellegrino, Federica Maraschi, Antonella Profumo, Chiara Milanese, Daniele Merli

{"title":"Effect of mounting a sound suppressor on distribution and total amount of inorganic gunshot residue on targets.","authors":"Matteo Donghi, Alessandro Girella, Debora Pellegrino, Federica Maraschi, Antonella Profumo, Chiara Milanese, Daniele Merli","doi":"10.1111/1556-4029.70025","DOIUrl":"https://doi.org/10.1111/1556-4029.70025","url":null,"abstract":"Sound suppressors critically modify barrel overall length and ballistic performances of hosting guns and are therefore expected to influence the patterns of the plumes of gunshot residues (GSR) reaching the targets. Despite the forensic interest, in recent years, a single paper was published on the variations induced by the use of a suppressor in the spatial distribution of visible soot clouds on close targets and in the number of a few selected classes of GSR particles detected by scanning electron microscopy. A different approach, based on x-ray fluorescence (XRF) and inductively coupled plasma-optical emission (ICP-OES) spectroscopies, that points to most of the metallic elements ejected from the barrel, is suggested here. The confirmed effect of a sound suppressor up to a distance of 20 cm is to gather the cone of particles reaching the target. Despite this pattern modification, the global concentrations of the ammunition-related elements of interest (Pb, Ba, Sb, Cu) on targets cannot be considered significant (i.e., with 95% confidence) reduced by the use of a suppressor, due to the high intra-specimen and inter-specimen ICP-OES data dispersions. Differently, the hypothesis of a role of homemade suppressors in enriching GSR populations in Fe is supported by our results. The presence of iron is indeed the only indication of the actual use of a suppressor, a piece of information that is useful for the correct interpretation of the lead patterns visualized on targets for muzzle-to-target determination.","PeriodicalId":94080,"journal":{"name":"Journal of forensic sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143775276","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CMV2U-Net: A U-shaped network with edge-weighted features for detecting and localizing image splicing. CMV2U-Net：带有边缘加权特征的 U 型网络，用于检测和定位图像拼接。

Journal of forensic sciences Pub Date : 2025-04-03 DOI: 10.1111/1556-4029.70033

Arslan Akram, Muhammad Arfan Jaffar, Javed Rashid, Salah Mahmoud Boulaaras, Muhammad Faheem

{"title":"CMV2U-Net: A U-shaped network with edge-weighted features for detecting and localizing image splicing.","authors":"Arslan Akram, Muhammad Arfan Jaffar, Javed Rashid, Salah Mahmoud Boulaaras, Muhammad Faheem","doi":"10.1111/1556-4029.70033","DOIUrl":"https://doi.org/10.1111/1556-4029.70033","url":null,"abstract":"The practice of cutting and pasting portions of one image into another, known as \"image splicing,\" is commonplace in the field of image manipulation. Image splicing detection using deep learning has been a hot research topic for the past few years. However, there are two problems with the way deep learning is currently implemented: first, it is not good enough for feature fusion, and second, it uses only simple models for feature extraction and encoding, which makes the models vulnerable to overfitting. To tackle these problems, this research proposes CMV2U-Net, an edge-weighted U-shaped network-based image splicing forgery localization approach. An initial step is the development of a feature extraction module that can process two streams of input images simultaneously, allowing for the simultaneous extraction of semantically connected and semantically agnostic features. One characteristic is that a hierarchical fusion approach has been devised to prevent data loss in shallow features that are either semantically related or semantically irrelevant. This approach implements a channel attention mechanism to monitor manipulation trajectories involving multiple levels. Extensive trials on numerous public datasets prove that CMV2U-Net provides high AUC and F1 in localizing tampered regions, outperforming state-of-the-art techniques. Noise, Gaussian blur, and JPEG compression are post-processing threats that CMV2U-Net has successfully resisted.","PeriodicalId":94080,"journal":{"name":"Journal of forensic sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143775274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Assessment of handheld Raman spectroscopy for forensic analysis of dark-colored bulk explosive fuel-oxidizer mixtures. 评估手持式拉曼光谱对深色散装爆炸物燃料-氧化剂混合物的法证分析。

Journal of forensic sciences Pub Date : 2025-04-03 DOI: 10.1111/1556-4029.70038

Lúcio Paulo Lima Logrado, Bruna Miguel Ferreira da Silva, Breno Amaro da Silveira Neto

{"title":"Assessment of handheld Raman spectroscopy for forensic analysis of dark-colored bulk explosive fuel-oxidizer mixtures.","authors":"Lúcio Paulo Lima Logrado, Bruna Miguel Ferreira da Silva, Breno Amaro da Silveira Neto","doi":"10.1111/1556-4029.70038","DOIUrl":"https://doi.org/10.1111/1556-4029.70038","url":null,"abstract":"The field identification of explosives is critical for crime response, requiring specialized protocols and often the support of Explosive Ordnance Disposal (EOD) teams to ensure safety. Handheld Raman spectrometers are widely used for this purpose due to their portability, nondestructive analysis, and ability to detect both organic and inorganic compounds with minimal sample preparation. However, their effectiveness is limited for dark-colored explosives-such as black powder, flash powder, and sulfur-chlorate explosives-commonly encountered in criminal activities. These mixtures pose unique challenges, including poor spectral quality caused by light absorption and the risk of ignition during direct analysis. This study addresses these challenges by introducing a simple and effective methodology for the safe identification of oxidizing salts in dark-colored fuel-oxidizer mixtures using handheld Raman spectrometers. The approach involves aqueous extraction followed by Raman analysis of the extract, improving safety and yielding reliable results by circumventing the limitations of direct solid analysis. Results confirmed that direct analysis of these mixtures is unsafe and ineffective, with three mixtures igniting during testing and others providing insufficient spectral data. In contrast, the aqueous extraction method enabled the successful identification of oxidizing salts in all tested samples using basic materials commonly found in crime scene kits. This technique supports field investigations, such as the seizure of suspected explosive materials, helping in decision-making during on-site investigations.","PeriodicalId":94080,"journal":{"name":"Journal of forensic sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143775273","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Negative histopathology of Lichtenberg figures in lightning deaths supports physiologic phenomena as the cause.

Journal of forensic sciences Pub Date : 2025-04-01 DOI: 10.1111/1556-4029.70036

Siva Sai Kumar Pulagura, Sathish Ayyappan, Vikas P Meshram, Raghvendra Singh Shekhawat, Tanuj Kanchan

引用次数: 0

Research on adversarial identification methods for AI-generated image software Craiyon V3. 人工智能生成图像软件 Craiyon V3 的对抗识别方法研究。

Journal of forensic sciences Pub Date : 2025-03-29 DOI: 10.1111/1556-4029.70034

Weizheng Jin, Hao Luo, Yunqi Tang

{"title":"Research on adversarial identification methods for AI-generated image software Craiyon V3.","authors":"Weizheng Jin, Hao Luo, Yunqi Tang","doi":"10.1111/1556-4029.70034","DOIUrl":"https://doi.org/10.1111/1556-4029.70034","url":null,"abstract":"With the rapid development of diffusion models, AI generation technology can now generate very realistic images. If such AI-generated images are used as evidence, they may threaten judicial fairness. Taking the adversarial identification of images generated by Craiyon V3 software as an example, this paper studies the adversarial identification methods for AI-generated image software. First, an AI-generated image set containing 18,000 images is constructed using Craiyon V3; then, an AI-generated image detection model based on deep learning is selected, and a score-based likelihood ratio method is introduced to evaluate the strength of evidence. Experimental results show that the proposed method achieves an accuracy of over 99% on multiple threshold classifiers including Swin-Transformer, ResNet-18, and so on, and the fitted likelihood ratio model also passes a series of validation criteria including Tippett plots. The research results of this paper are expected to be applied to judicial practice in the future, providing judges with a reliable and powerful decision-making basis, and laying a foundation for further exploration of AI-generated image identification methods.","PeriodicalId":94080,"journal":{"name":"Journal of forensic sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143744662","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Decision trees for estimating osteological sex from the skull using an expanded suite of morphological traits.

Journal of forensic sciences Pub Date : 2025-03-28 DOI: 10.1111/1556-4029.70017

Morgan J Ferrell, John J Schultz, Donovan M Adams

{"title":"Decision trees for estimating osteological sex from the skull using an expanded suite of morphological traits.","authors":"Morgan J Ferrell, John J Schultz, Donovan M Adams","doi":"10.1111/1556-4029.70017","DOIUrl":"https://doi.org/10.1111/1556-4029.70017","url":null,"abstract":"Osteological sex estimation utilizing morphological traits of the skull primarily focuses on a set of five traits. Developing new models with an expanded suite of traits has the potential to increase sex classification accuracies and improve the classification of partial and fragmentary remains. Thus, this study seeks to improve classification accuracies for osteological sex estimation from the skull by assessing an expanded suite of traits and generating multiple decision tree classification models. Twenty-one traits were evaluated for a sample of 403 adult males and females. Krippendorff's alpha was used to assess intraobserver error, and aligned rank transformation was used to examine the effects of sex, age, population, and secular change on the traits. Prior to generating the decision trees, the data were randomly split into 80% model training samples and 20% holdout validation testing samples to test the predictive accuracy of each tree. The trees were generated for traits from the skull, cranium, and mandible. Separate trees were also generated for African Americans and European Americans, as well as for the pooled population sample. Overall, the recommended decision trees for the skull and cranium achieved higher accuracies (91.0%-100%) than models generated for the mandible (75.8%-85.0%). Additionally, the recommended pooled population (81.3%-97.3%) decision trees achieved similar accuracies compared with the African American (75.8%-94.0%) and European American (85.0%-100%) trees. Further, the trees generated in this study achieved improved classification accuracies for the skull compared with the current five-trait method by incorporating an expanded suite of traits.","PeriodicalId":94080,"journal":{"name":"Journal of forensic sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143733769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Human tissue oxygen and strontium isotope values in North America: A data compilation and assessment for forensic geolocation. 北美人体组织氧和锶同位素值：用于法医地理定位的数据汇编和评估。

Journal of forensic sciences Pub Date : 2025-03-26 DOI: 10.1111/1556-4029.70030

Kirsten A Verostick, Alejandro Serna, Chris Stantis, Gabriel J Bowen

{"title":"Human tissue oxygen and strontium isotope values in North America: A data compilation and assessment for forensic geolocation.","authors":"Kirsten A Verostick, Alejandro Serna, Chris Stantis, Gabriel J Bowen","doi":"10.1111/1556-4029.70030","DOIUrl":"https://doi.org/10.1111/1556-4029.70030","url":null,"abstract":"The use of isotopic analysis for human mobility, geolocation, and forensic identification has become common over the past two decades, yet its effectiveness depends on the availability of well-documented reference data. Many reference data exist in the literature, but the suitability of these data for forensic applications has not been critically assessed. Here, we compile oxygen and strontium isotope data for North American human tissues (hair, nails, bone, and tooth enamel). We review the geographic distribution of these data, evaluate their relationship with the predicted geographic variation, and assess potential sources of bias that may limit the comparability of different datasets in the compilation. A substantial number of data are available for some of these substrates and isotope systems, but in most cases, their geographic distribution is patchy with many areas under sampled. Except for hair Sr isotopes, a robust relationship occurs between human tissue values and modeled local environmental values, suggesting theoretically expected relationships between human tissues and local sources of O and Sr are expressed. These relationships are noisy; we identify several methodological differences that produce systematic biases across the compiled data. Based on these findings, we suggest interpreting forensic isotope data using currently published reference data is problematic. We propose the adoption of consistent metadata reporting and standardized laboratory protocols to enhance the utility of data gathered in future research as these practices could lead to measurable improvements in the strength of forensic interpretations derived from human tissue isotope data.","PeriodicalId":94080,"journal":{"name":"Journal of forensic sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143733772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The application of decision trees for estimating osteological sex from common measurements of the skull.

Journal of forensic sciences Pub Date : 2025-03-26 DOI: 10.1111/1556-4029.70031

Morgan J Ferrell, John J Schultz, Donovan M Adams

{"title":"The application of decision trees for estimating osteological sex from common measurements of the skull.","authors":"Morgan J Ferrell, John J Schultz, Donovan M Adams","doi":"10.1111/1556-4029.70031","DOIUrl":"https://doi.org/10.1111/1556-4029.70031","url":null,"abstract":"Skull measurements are commonly evaluated for osteological sex estimation in forensic anthropology, and decision tree-based classification models for the skull may improve accuracy compared to current metric methods. Additionally, decision trees can provide accurate sex classification with a limited number of measurements, which is valuable when analyzing fragmentary remains. Thus, the present study seeks to test the utility of decision trees for generating sex classification models from metric variables of the skull. Twenty-one skull measurements were evaluated for 403 adult males and females. Relative technical error of measurement was used to assess intraobserver error, and two-way ANOVAs and aligned rank transformation were used to examine the effects of sex, population, age, and temporal period on the measurements. The data set was split into 80% training and 20% holdout testing samples to assess the predictive accuracy of each tree. Trees were generated for the skull and cranium, with models for European Americans, African Americans, and the pooled population sample. Overall, the recommended trees for the cranium achieved higher accuracies (85.3-95.0%) compared to the skull trees (84.0-92.5%). Accuracies for the population-inclusive trees ranged from 84.0% to 85.3%, whereas the European American (92.5-95.0%) and African American (90.9%) trees achieved slightly higher accuracies. Improved accuracies were achieved compared to previous decision tree research as well as compared to current metric methods for the skull. These trees provide an additional option for estimating osteological sex, particularly when morphological methods do not yield adequate classification accuracies or cannot be assessed due to damage.","PeriodicalId":94080,"journal":{"name":"Journal of forensic sciences","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143712417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0