Logistic Models for Classifying Online Grooming Conversation

Pranoto, Hady; Gunawan, Fergyanto E.; Soewito, Benfano

doi:10.1016/j.procs.2015.07.536

Cited by 24 publications

(31 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We used the logistic regression algorithm to construct a classifier ( Zhang et al, 2014 ; Pranoto et al, 2015 ). Logistic regression uses the sigmoid function to represent the probability of a sample being labeled as a certain category, and prediction of tissue origin can be explained as a one-to-many classification problem.…”

Section: Methodsmentioning

confidence: 99%

“…The International Cancer Genome Consortium (ICGC), together with machine learning methods could improve the predictive performance. Here, the random forest algorithm ( Sandri and Zuccolotto, 2006 ) was selected as a gene selection algorithm, and the logistic regression algorithm ( Zhang et al, 2014 ; Pranoto et al, 2015 ) was utilized to establish a classifier. Performance evaluation was judged by metrics, such as accuracy and specificity.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Predicting Cancer Tissue-of-Origin by a Machine Learning Method Using DNA Somatic Mutation Data

Liu

Peng

et al. 2020

Front. Genet.

View full text Add to dashboard Cite

Patients with carcinoma of unknown primary (CUP) account for 3–5% of all cancer cases. A large number of metastatic cancers require further diagnosis to determine their tissue of origin. However, diagnosis of CUP and identification of its primary site are challenging. Previous studies have suggested that molecular profiling of tissue-specific genes could be useful in inferring the primary tissue of a tumor. The purpose of this study was to evaluate the performance somatic mutations detected in a tumor to identify the cancer tissue of origin. We downloaded the somatic mutation datasets from the International Cancer Genome Consortium project. The random forest algorithm was used to extract features, and a classifier was established based on the logistic regression. Specifically, the somatic mutations of 300 genes were extracted, which are significantly enriched in functions, such as cell-to-cell adhesion. In addition, the prediction accuracy on tissue-of-origin inference for 3,374 cancer samples across 13 cancer types reached 81% in a 10-fold cross-validation. Our method could be useful in the identification of cancer tissue of origin, as well as the diagnosis and treatment of cancers.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Predicting Cancer Tissue-of-Origin by a Machine Learning Method Using DNA Somatic Mutation Data

Liu

Peng

et al. 2020

Front. Genet.

View full text Add to dashboard Cite

show abstract

“…In the scientific field, grooming has been conceptualized as a procedural technique, criminal activity, or operational concept used by cybernetic attackers, who in some cases have a disorder of sexual preference for children or adolescents. In the development of false friendship, the attacker applies strategies to determine affinities, tastes or activities of interest to the victim, thus developing a relationship of trust where the main objective is sexual desensitization, giving rise to the satisfaction of the needs of the attacker; as the sexual act [1], [2], [12]. As a computer attack technique, grooming can be applied for very long periods, in order to guarantee the cooperation of its victims and minimizing the risk of exposure.…”

Section: What Is Grooming?mentioning

confidence: 99%

“…Some authors, supported by previous research and psychological studies apply techniques of text mining and machine learning to determine the nature and different levels of danger of this attack [4], [7]- [9]. However, it has been shown that the results of the research related to the study of grooming, contemplate different lines of research, are not conclusive and support other relevant studies [6], [10]- [12].…”

Section: Introductionmentioning

confidence: 99%

Technical Mapping of the Grooming Anatomy Using Machine Learning Paradigms: An Information Security Approach

et al. 2019

View full text Add to dashboard Cite

“…The Support Vector Machine (SVM) was then adopted as the classifier to solve the text classification task, thus to raise an alarm when a grooming type activity in a conversation is detected [7]. A grooming detection system was proposed by establishing a logistic mathematical model based on some frequently appeared key characteristics to classify online conversation logs [8]. However, the uncertainty naturally included in the conversions may affect the efficiency of these approaches.…”

Section: Introductionmentioning

confidence: 99%

Grooming Detection using Fuzzy-Rough Feature Selection and Text Classification

Zuo

Anderson

et al. 2018

2018 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

View full text Add to dashboard Cite

Online child grooming detection has recently attracted intensive research interests from both the machine learning community and digital forensics community due to its great social impact. The existing data-driven approaches usually face the challenges of lack of training data and the uncertainty of classes in terms of the classification or decision boundary. This paper proposes a grooming detection approach in an effort to address such uncertainty based on a data set derived from a publicly available profiling data set. In particular, the approach firstly applies the conventional text feature extraction approach in identifying the most significant words in the data set. This is followed by the application of a fuzzy-rough feature selection approach in reducing the high dimensions of the selected words for fast processing, which at the same time addressing the uncertainty of class boundaries. The experimental results demonstrate the efficiency and efficacy of the proposed approach in detecting child grooming.

show abstract

Logistic Models for Classifying Online Grooming Conversation

Cited by 24 publications

References 3 publications

Predicting Cancer Tissue-of-Origin by a Machine Learning Method Using DNA Somatic Mutation Data

Predicting Cancer Tissue-of-Origin by a Machine Learning Method Using DNA Somatic Mutation Data

Technical Mapping of the Grooming Anatomy Using Machine Learning Paradigms: An Information Security Approach

Grooming Detection using Fuzzy-Rough Feature Selection and Text Classification

Contact Info

Product

Resources

About