Alzheimer’s and related diseases are significant health issues of this era. The interdisciplinary use of deep learning in this field has shown great promise and gathered considerable interest. This paper surveys deep learning literature related to Alzheimer’s disease, mild cognitive impairment, and related diseases from 2010 to early 2023. We identify the major types of unsupervised, supervised, and semi-supervised methods developed for various tasks in this field, including the most recent developments, such as the application of recurrent neural networks, graph-neural networks, and generative models. We also provide a summary of data sources, data processing, training protocols, and evaluation methods as a guide for future deep learning research into Alzheimer’s disease. Although deep learning has shown promising performance across various studies and tasks, it is limited by interpretation and generalization challenges. The survey also provides a brief insight into these challenges and the possible pathways for future studies.
{"title":"A Survey of Deep Learning for Alzheimer's Disease","authors":"Qinghua Zhou, Jiaji Wang, Xiang Yu, Shuihua Wang, Yudong Zhang","doi":"10.3390/make5020035","DOIUrl":"https://doi.org/10.3390/make5020035","url":null,"abstract":"Alzheimer’s and related diseases are significant health issues of this era. The interdisciplinary use of deep learning in this field has shown great promise and gathered considerable interest. This paper surveys deep learning literature related to Alzheimer’s disease, mild cognitive impairment, and related diseases from 2010 to early 2023. We identify the major types of unsupervised, supervised, and semi-supervised methods developed for various tasks in this field, including the most recent developments, such as the application of recurrent neural networks, graph-neural networks, and generative models. We also provide a summary of data sources, data processing, training protocols, and evaluation methods as a guide for future deep learning research into Alzheimer’s disease. Although deep learning has shown promising performance across various studies and tasks, it is limited by interpretation and generalization challenges. The survey also provides a brief insight into these challenges and the possible pathways for future studies.","PeriodicalId":93033,"journal":{"name":"Machine learning and knowledge extraction","volume":"21 1","pages":"611-668"},"PeriodicalIF":0.0,"publicationDate":"2023-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87281088","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}
This paper presents a conceptual mathematical framework for developing rich human–machine interactions in order to improve decision-making in a social organisation, S. The idea is to model how S can create a “multi-level artificial cognitive system”, called a data analyser (DA), to collaborate with humans in collecting and learning how to analyse data, to anticipate situations, and to develop new responses, thus improving decision-making. In this model, the DA is “processed” to not only gather data and extend existing knowledge, but also to learn how to act autonomously with its own specific procedures or even to create new ones. An application is given in cases where such rich human–machine interactions are expected to allow the DA+S partnership to acquire deep anticipation capabilities for possible future changes, e.g., to prevent risks or seize opportunities. The way the social organization S operates over time, including the construction of DA, is described using the conceptual framework comprising “memory evolutive systems” (MES), a mathematical theoretical approach introduced by Ehresmann and Vanbremeersch for evolutionary multi-scale, multi-agent and multi-temporality systems. This leads to the definition of a “data analyser–MES”.
{"title":"A Mathematical Framework for Enriching Human-Machine Interactions","authors":"A. Ehresmann, Mathias Béjean, J. Vanbremeersch","doi":"10.3390/make5020034","DOIUrl":"https://doi.org/10.3390/make5020034","url":null,"abstract":"This paper presents a conceptual mathematical framework for developing rich human–machine interactions in order to improve decision-making in a social organisation, S. The idea is to model how S can create a “multi-level artificial cognitive system”, called a data analyser (DA), to collaborate with humans in collecting and learning how to analyse data, to anticipate situations, and to develop new responses, thus improving decision-making. In this model, the DA is “processed” to not only gather data and extend existing knowledge, but also to learn how to act autonomously with its own specific procedures or even to create new ones. An application is given in cases where such rich human–machine interactions are expected to allow the DA+S partnership to acquire deep anticipation capabilities for possible future changes, e.g., to prevent risks or seize opportunities. The way the social organization S operates over time, including the construction of DA, is described using the conceptual framework comprising “memory evolutive systems” (MES), a mathematical theoretical approach introduced by Ehresmann and Vanbremeersch for evolutionary multi-scale, multi-agent and multi-temporality systems. This leads to the definition of a “data analyser–MES”.","PeriodicalId":93033,"journal":{"name":"Machine learning and knowledge extraction","volume":"613 1","pages":"597-610"},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86676769","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}
Course recommender systems play an increasingly pivotal role in the educational landscape, driving personalization and informed decision-making for students. However, these systems face significant challenges, including managing a large and dynamic decision space and addressing the cold start problem for new students. This article endeavors to provide a comprehensive review and background to fully understand recent research on course recommender systems and their impact on learning. We present a detailed summary of empirical data supporting the use of these systems in educational strategic planning. We examined case studies conducted over the previous six years (2017–2022), with a focus on 35 key studies selected from 1938 academic papers found using the CADIMA tool. This systematic literature review (SLR) assesses various recommender system methodologies used to suggest course selection tracks, aiming to determine the most effective evidence-based approach.
{"title":"Systematic Review of Recommendation Systems for Course Selection","authors":"Shrooq Algarni, Frederick T. Sheldon","doi":"10.3390/make5020033","DOIUrl":"https://doi.org/10.3390/make5020033","url":null,"abstract":"Course recommender systems play an increasingly pivotal role in the educational landscape, driving personalization and informed decision-making for students. However, these systems face significant challenges, including managing a large and dynamic decision space and addressing the cold start problem for new students. This article endeavors to provide a comprehensive review and background to fully understand recent research on course recommender systems and their impact on learning. We present a detailed summary of empirical data supporting the use of these systems in educational strategic planning. We examined case studies conducted over the previous six years (2017–2022), with a focus on 35 key studies selected from 1938 academic papers found using the CADIMA tool. This systematic literature review (SLR) assesses various recommender system methodologies used to suggest course selection tracks, aiming to determine the most effective evidence-based approach.","PeriodicalId":93033,"journal":{"name":"Machine learning and knowledge extraction","volume":"1 1","pages":"560-596"},"PeriodicalIF":0.0,"publicationDate":"2023-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83201618","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}
Saliency methods are designed to provide explainability for deep image processing models by assigning feature-wise importance scores and thus detecting informative regions in the input images. Recently, these methods have been widely adapted to the time series domain, aiming to identify important temporal regions in a time series. This paper extends our former work on identifying the systematic failure of such methods in the time series domain to produce relevant results when informative patterns are based on underlying latent information rather than temporal regions. First, we both visually and quantitatively assess the quality of explanations provided by multiple state-of-the-art saliency methods, including Integrated Gradients, Deep-Lift, Kernel SHAP, and Lime using univariate simulated time series data with temporal or latent patterns. In addition, to emphasize the severity of the latent feature saliency detection problem, we also run experiments on a real-world predictive maintenance dataset with known latent patterns. We identify Integrated Gradients, Deep-Lift, and the input-cell attention mechanism as potential candidates for refinement to yield latent saliency scores. Finally, we provide recommendations on using saliency methods for time series classification and suggest a guideline for developing latent saliency methods for time series.
{"title":"What about the Latent Space? The Need for Latent Feature Saliency Detection in Deep Time Series Classification","authors":"Maresa Schröder, Alireza Zamanian, N. Ahmidi","doi":"10.3390/make5020032","DOIUrl":"https://doi.org/10.3390/make5020032","url":null,"abstract":"Saliency methods are designed to provide explainability for deep image processing models by assigning feature-wise importance scores and thus detecting informative regions in the input images. Recently, these methods have been widely adapted to the time series domain, aiming to identify important temporal regions in a time series. This paper extends our former work on identifying the systematic failure of such methods in the time series domain to produce relevant results when informative patterns are based on underlying latent information rather than temporal regions. First, we both visually and quantitatively assess the quality of explanations provided by multiple state-of-the-art saliency methods, including Integrated Gradients, Deep-Lift, Kernel SHAP, and Lime using univariate simulated time series data with temporal or latent patterns. In addition, to emphasize the severity of the latent feature saliency detection problem, we also run experiments on a real-world predictive maintenance dataset with known latent patterns. We identify Integrated Gradients, Deep-Lift, and the input-cell attention mechanism as potential candidates for refinement to yield latent saliency scores. Finally, we provide recommendations on using saliency methods for time series classification and suggest a guideline for developing latent saliency methods for time series.","PeriodicalId":93033,"journal":{"name":"Machine learning and knowledge extraction","volume":"23 1","pages":"539-559"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90893026","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}
Alzheimer’s disease (AD) is an old-age disease that comes in different stages and directly affects the different regions of the brain. The research into the detection of AD and its stages has new advancements in terms of single-modality and multimodality approaches. However, sustainable techniques for the detection of AD and its stages still require a greater extent of research. In this study, a multimodal image-fusion method is initially proposed for the fusion of two different modalities, i.e., PET (Positron Emission Tomography) and MRI (Magnetic Resonance Imaging). Further, the features obtained from fused and non-fused biomarkers are passed to the ensemble classifier with a Random Forest-based feature selection strategy. Three classes of Alzheimer’s disease are used in this work, namely AD, MCI (Mild Cognitive Impairment) and CN (Cognitive Normal). In the resulting analysis, the Binary classifications, i.e., AD vs. CN and MCI vs. CN, attained an accuracy (Acc) of 99% in both cases. The class AD vs. MCI detection achieved an adequate accuracy (Acc) of 91%. Furthermore, the Multi Class classification, i.e., AD vs. MCI vs. CN, achieved 96% (Acc).
阿尔茨海默病(AD)是一种不同阶段的老年疾病，直接影响大脑的不同区域。从单模态和多模态两方面对阿尔茨海默病及其阶段的检测研究有了新的进展。然而，可持续的检测阿尔茨海默病及其阶段的技术仍然需要更大程度的研究。本研究首次提出了一种多模态图像融合方法，用于融合两种不同的模式，即PET(正电子发射断层扫描)和MRI(磁共振成像)。此外，通过基于随机森林的特征选择策略，将从融合和非融合生物标志物中获得的特征传递给集成分类器。在这项工作中使用了三类阿尔茨海默病，即AD, MCI(轻度认知障碍)和CN(认知正常)。在结果分析中，二元分类，即AD vs. CN和MCI vs. CN，在两种情况下都达到了99%的准确率(Acc)。AD类与MCI类检测达到了91%的足够准确度(Acc)。此外，Multi Class分类，即AD、MCI和CN，达到96% (Acc)。
{"title":"Alzheimer's Disease Detection from Fused PET and MRI Modalities Using an Ensemble Classifier","authors":"A. Shukla, Rajeev Tiwari, Shamik Tiwari","doi":"10.3390/make5020031","DOIUrl":"https://doi.org/10.3390/make5020031","url":null,"abstract":"Alzheimer’s disease (AD) is an old-age disease that comes in different stages and directly affects the different regions of the brain. The research into the detection of AD and its stages has new advancements in terms of single-modality and multimodality approaches. However, sustainable techniques for the detection of AD and its stages still require a greater extent of research. In this study, a multimodal image-fusion method is initially proposed for the fusion of two different modalities, i.e., PET (Positron Emission Tomography) and MRI (Magnetic Resonance Imaging). Further, the features obtained from fused and non-fused biomarkers are passed to the ensemble classifier with a Random Forest-based feature selection strategy. Three classes of Alzheimer’s disease are used in this work, namely AD, MCI (Mild Cognitive Impairment) and CN (Cognitive Normal). In the resulting analysis, the Binary classifications, i.e., AD vs. CN and MCI vs. CN, attained an accuracy (Acc) of 99% in both cases. The class AD vs. MCI detection achieved an adequate accuracy (Acc) of 91%. Furthermore, the Multi Class classification, i.e., AD vs. MCI vs. CN, achieved 96% (Acc).","PeriodicalId":93033,"journal":{"name":"Machine learning and knowledge extraction","volume":"8 1","pages":"512-538"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80634773","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}
The scores of distance-based outlier detection methods are difficult to interpret, and it is challenging to determine a suitable cut-off threshold between normal and outlier data points without additional context. We describe a generic transformation of distance-based outlier scores into interpretable, probabilistic estimates. The transformation is ranking-stable and increases the contrast between normal and outlier data points. Determining distance relationships between data points is necessary to identify the nearest-neighbor relationships in the data, yet most of the computed distances are typically discarded. We show that the distances to other data points can be used to model distance probability distributions and, subsequently, use the distributions to turn distance-based outlier scores into outlier probabilities. Over a variety of tabular and image benchmark datasets, we show that the probabilistic transformation does not impact outlier ranking (ROC AUC) or detection performance (AP, F1), and increases the contrast between normal and outlier score distributions (statistical distance). The experimental findings indicate that it is possible to transform distance-based outlier scores into interpretable probabilities with increased contrast between normal and outlier samples. Our work generalizes to a wide range of distance-based outlier detection methods, and, because existing distance computations are used, it adds no significant computational overhead.
{"title":"A Probabilistic Transformation of Distance-Based Outliers","authors":"David Muhr, M. Affenzeller, Josef Küng","doi":"10.3390/make5030042","DOIUrl":"https://doi.org/10.3390/make5030042","url":null,"abstract":"The scores of distance-based outlier detection methods are difficult to interpret, and it is challenging to determine a suitable cut-off threshold between normal and outlier data points without additional context. We describe a generic transformation of distance-based outlier scores into interpretable, probabilistic estimates. The transformation is ranking-stable and increases the contrast between normal and outlier data points. Determining distance relationships between data points is necessary to identify the nearest-neighbor relationships in the data, yet most of the computed distances are typically discarded. We show that the distances to other data points can be used to model distance probability distributions and, subsequently, use the distributions to turn distance-based outlier scores into outlier probabilities. Over a variety of tabular and image benchmark datasets, we show that the probabilistic transformation does not impact outlier ranking (ROC AUC) or detection performance (AP, F1), and increases the contrast between normal and outlier score distributions (statistical distance). The experimental findings indicate that it is possible to transform distance-based outlier scores into interpretable probabilities with increased contrast between normal and outlier samples. Our work generalizes to a wide range of distance-based outlier detection methods, and, because existing distance computations are used, it adds no significant computational overhead.","PeriodicalId":93033,"journal":{"name":"Machine learning and knowledge extraction","volume":"569 1","pages":"782-802"},"PeriodicalIF":0.0,"publicationDate":"2023-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83496234","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}
Karthik Santhanaraj, Dinakaran Devaraj, Ramya Mm, J. Dhanraj, K. Ramanathan
Recent technological advancements have fostered human–robot coexistence in work and residential environments. The assistive robot must exhibit humane behavior and consistent care to become an integral part of the human habitat. Furthermore, the robot requires an adaptive unsupervised learning model to explore unfamiliar conditions and collaborate seamlessly. This paper introduces variants of the growing hierarchical self-organizing map (GHSOM)-based computational models for assistive robots, which constructs knowledge from unsupervised exploration-based learning. Traditional self-organizing map (SOM) algorithms have shortcomings, including finite neuron structure, user-defined parameters, and non-hierarchical adaptive architecture. The proposed models overcome these limitations and dynamically grow to form problem-dependent hierarchical feature clusters, thereby allowing associative learning and symbol grounding. Infants can learn from their surroundings through exploration and experience, developing new neuronal connections as they learn. They can also apply their prior knowledge to solve unfamiliar problems. With infant-like emergent behavior, the presented models can operate on different problems without modifications, producing new patterns not present in the input vectors and allowing interactive result visualization. The proposed models are applied to the color, handwritten digits clustering, finger identification, and image classification problems to evaluate their adaptiveness and infant-like knowledge building. The results show that the proposed models are the preferred generalized models for assistive robots.
{"title":"Biologically Inspired Self-Organizing Computational Model to Mimic Infant Learning","authors":"Karthik Santhanaraj, Dinakaran Devaraj, Ramya Mm, J. Dhanraj, K. Ramanathan","doi":"10.3390/make5020030","DOIUrl":"https://doi.org/10.3390/make5020030","url":null,"abstract":"Recent technological advancements have fostered human–robot coexistence in work and residential environments. The assistive robot must exhibit humane behavior and consistent care to become an integral part of the human habitat. Furthermore, the robot requires an adaptive unsupervised learning model to explore unfamiliar conditions and collaborate seamlessly. This paper introduces variants of the growing hierarchical self-organizing map (GHSOM)-based computational models for assistive robots, which constructs knowledge from unsupervised exploration-based learning. Traditional self-organizing map (SOM) algorithms have shortcomings, including finite neuron structure, user-defined parameters, and non-hierarchical adaptive architecture. The proposed models overcome these limitations and dynamically grow to form problem-dependent hierarchical feature clusters, thereby allowing associative learning and symbol grounding. Infants can learn from their surroundings through exploration and experience, developing new neuronal connections as they learn. They can also apply their prior knowledge to solve unfamiliar problems. With infant-like emergent behavior, the presented models can operate on different problems without modifications, producing new patterns not present in the input vectors and allowing interactive result visualization. The proposed models are applied to the color, handwritten digits clustering, finger identification, and image classification problems to evaluate their adaptiveness and infant-like knowledge building. The results show that the proposed models are the preferred generalized models for assistive robots.","PeriodicalId":93033,"journal":{"name":"Machine learning and knowledge extraction","volume":"46 1","pages":"491-511"},"PeriodicalIF":0.0,"publicationDate":"2023-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76167857","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}
Gaurav Nanda, A. Jaiswal, Hugo Castellanos, Yuzhe Zhou, Alex Choi, Alejandra J. Magana
Fields in the social sciences, such as education research, have started to expand the use of computer-based research methods to supplement traditional research approaches. Natural language processing techniques, such as topic modeling, may support qualitative data analysis by providing early categories that researchers may interpret and refine. This study contributes to this body of research and answers the following research questions: (RQ1) What is the relative coverage of the latent Dirichlet allocation (LDA) topic model and human coding in terms of the breadth of the topics/themes extracted from the text collection? (RQ2) What is the relative depth or level of detail among identified topics using LDA topic models and human coding approaches? A dataset of student reflections was qualitatively analyzed using LDA topic modeling and human coding approaches, and the results were compared. The findings suggest that topic models can provide reliable coverage and depth of themes present in a textual collection comparable to human coding but require manual interpretation of topics. The breadth and depth of human coding output is heavily dependent on the expertise of coders and the size of the collection; these factors are better handled in the topic modeling approach.
{"title":"Evaluating the Coverage and Depth of Latent Dirichlet Allocation Topic Model in Comparison with Human Coding of Qualitative Data: The Case of Education Research","authors":"Gaurav Nanda, A. Jaiswal, Hugo Castellanos, Yuzhe Zhou, Alex Choi, Alejandra J. Magana","doi":"10.3390/make5020029","DOIUrl":"https://doi.org/10.3390/make5020029","url":null,"abstract":"Fields in the social sciences, such as education research, have started to expand the use of computer-based research methods to supplement traditional research approaches. Natural language processing techniques, such as topic modeling, may support qualitative data analysis by providing early categories that researchers may interpret and refine. This study contributes to this body of research and answers the following research questions: (RQ1) What is the relative coverage of the latent Dirichlet allocation (LDA) topic model and human coding in terms of the breadth of the topics/themes extracted from the text collection? (RQ2) What is the relative depth or level of detail among identified topics using LDA topic models and human coding approaches? A dataset of student reflections was qualitatively analyzed using LDA topic modeling and human coding approaches, and the results were compared. The findings suggest that topic models can provide reliable coverage and depth of themes present in a textual collection comparable to human coding but require manual interpretation of topics. The breadth and depth of human coding output is heavily dependent on the expertise of coders and the size of the collection; these factors are better handled in the topic modeling approach.","PeriodicalId":93033,"journal":{"name":"Machine learning and knowledge extraction","volume":"91 ","pages":"473-490"},"PeriodicalIF":0.0,"publicationDate":"2023-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72422652","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}
L. Summers, Alyssa N. Shallenberger, John Cruz, Lawrence V. Fulton
Sex trafficking victims are often advertised through online escort sites. These ads can be publicly accessed, but law enforcement lacks the resources to comb through hundreds of ads to identify those that may feature sex-trafficked individuals. The purpose of this study was to implement and test multi-input, deep learning (DL) binary classification models to predict the probability of an online escort ad being associated with sex trafficking (ST) activity and aid in the detection and investigation of ST. Data from 12,350 scraped and classified ads were split into training and test sets (80% and 20%, respectively). Multi-input models that included recurrent neural networks (RNN) for text classification, convolutional neural networks (CNN, specifically EfficientNetB6 or ENET) for image/emoji classification, and neural networks (NN) for feature classification were trained and used to classify the 20% test set. The best-performing DL model included text and imagery inputs, resulting in an accuracy of 0.82 and an F1 score of 0.70. More importantly, the best classifier (RNN + ENET) correctly identified 14 of 14 sites that had classification probability estimates of 0.845 or greater (1.0 precision); precision was 96% for the multi-input model (NN + RNN + ENET) when only the ads associated with the highest positive classification probabilities (>0.90) were considered (n = 202 ads). The models developed could be productionalized and piloted with criminal investigators, as they could potentially increase their efficiency in identifying potential ST victims.
{"title":"A Multi-Input Machine Learning Approach to Classifying Sex Trafficking from Online Escort Advertisements","authors":"L. Summers, Alyssa N. Shallenberger, John Cruz, Lawrence V. Fulton","doi":"10.3390/make5020028","DOIUrl":"https://doi.org/10.3390/make5020028","url":null,"abstract":"Sex trafficking victims are often advertised through online escort sites. These ads can be publicly accessed, but law enforcement lacks the resources to comb through hundreds of ads to identify those that may feature sex-trafficked individuals. The purpose of this study was to implement and test multi-input, deep learning (DL) binary classification models to predict the probability of an online escort ad being associated with sex trafficking (ST) activity and aid in the detection and investigation of ST. Data from 12,350 scraped and classified ads were split into training and test sets (80% and 20%, respectively). Multi-input models that included recurrent neural networks (RNN) for text classification, convolutional neural networks (CNN, specifically EfficientNetB6 or ENET) for image/emoji classification, and neural networks (NN) for feature classification were trained and used to classify the 20% test set. The best-performing DL model included text and imagery inputs, resulting in an accuracy of 0.82 and an F1 score of 0.70. More importantly, the best classifier (RNN + ENET) correctly identified 14 of 14 sites that had classification probability estimates of 0.845 or greater (1.0 precision); precision was 96% for the multi-input model (NN + RNN + ENET) when only the ads associated with the highest positive classification probabilities (>0.90) were considered (n = 202 ads). The models developed could be productionalized and piloted with criminal investigators, as they could potentially increase their efficiency in identifying potential ST victims.","PeriodicalId":93033,"journal":{"name":"Machine learning and knowledge extraction","volume":"101 1","pages":"460-472"},"PeriodicalIF":0.0,"publicationDate":"2023-05-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80783006","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}
In this article, we propose a tree-structured method for either complete or partial rank data that incorporates covariate information into the analysis. We use conditional independence tests based on hierarchical log-linear models for three-way contingency tables to select split variables and cut points, and apply a simple Bonferroni rule to declare whether a node worths splitting or not. Through simulations, we also demonstrate that the proposed method is unbiased and effective in selecting informative split variables. Our proposed method can be applied across various fields to provide a flexible and robust framework for analyzing rank data and understanding how various factors affect individual judgments on ranking. This can help improve the quality of products or services and assist with informed decision making.
{"title":"Tree-Structured Model with Unbiased Variable Selection and Interaction Detection for Ranking Data","authors":"Yu-Shan Shih, Yi-Hung Kung","doi":"10.3390/make5020027","DOIUrl":"https://doi.org/10.3390/make5020027","url":null,"abstract":"In this article, we propose a tree-structured method for either complete or partial rank data that incorporates covariate information into the analysis. We use conditional independence tests based on hierarchical log-linear models for three-way contingency tables to select split variables and cut points, and apply a simple Bonferroni rule to declare whether a node worths splitting or not. Through simulations, we also demonstrate that the proposed method is unbiased and effective in selecting informative split variables. Our proposed method can be applied across various fields to provide a flexible and robust framework for analyzing rank data and understanding how various factors affect individual judgments on ranking. This can help improve the quality of products or services and assist with informed decision making.","PeriodicalId":93033,"journal":{"name":"Machine learning and knowledge extraction","volume":"10 1","pages":"448-459"},"PeriodicalIF":0.0,"publicationDate":"2023-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72615773","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：