Pub Date : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00280
Pouya Shiri, A. Baniasadi
Capsule Network (CapsNet) classifier has several advantages over CNNs, including better detection of images containing overlapping categories and higher accuracy on transformed images. Despite the advantages, CapsNet is slow due to its different structure. In addition, CapsNet is resource-hungry, includes many parameters and lags in accuracy compared to CNNs. In this work, we propose LE-CapsNet as a light, enhanced and more accurate variant of CapsNet. Using 3.8M weights, LECapsNet obtains 76.73% accuracy on the CIFAR-10 dataset while performing inference 4x faster than CapsNet. In addition, our proposed network is more robust at detecting images with affine transformations compared to CapsNet. We achieve 94.37% accuracy on the AffNIST dataset (compared to CapsNet’s 90.52%).
{"title":"LE-CapsNet: A Light and Enhanced Capsule Network","authors":"Pouya Shiri, A. Baniasadi","doi":"10.1109/ICMLA52953.2021.00280","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00280","url":null,"abstract":"Capsule Network (CapsNet) classifier has several advantages over CNNs, including better detection of images containing overlapping categories and higher accuracy on transformed images. Despite the advantages, CapsNet is slow due to its different structure. In addition, CapsNet is resource-hungry, includes many parameters and lags in accuracy compared to CNNs. In this work, we propose LE-CapsNet as a light, enhanced and more accurate variant of CapsNet. Using 3.8M weights, LECapsNet obtains 76.73% accuracy on the CIFAR-10 dataset while performing inference 4x faster than CapsNet. In addition, our proposed network is more robust at detecting images with affine transformations compared to CapsNet. We achieve 94.37% accuracy on the AffNIST dataset (compared to CapsNet’s 90.52%).","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"2 1","pages":"1767-1772"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73354851","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}
Pub Date : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00253
M. Fahim, S. Gokhale
Hateful and offensive speech on online social media platforms has seen a rise in the recent years. Often used to convey humor through sarcasm or to emphasize a point, offensive speech may also be employed to insult, deride and mock alternate points of view. In turbulent and chaotic circumstances, insults and mockery can lead to violence and unrest, and hence, such speech must be identified and tagged to limit its damage. This paper presents an application of machine learning to detect hateful and offensive content from Twitter feeds shared after the protests by Proud Boys, an extremist, ideological and violent hate group. A comprehensive coding guide, consolidating definitions of what constitutes offensive content based on the potential to trigger and incite people is developed and used to label the tweets. Linguistic, auxiliary and social features extracted from these labeled tweets were used to train machine learning classifiers, which detect offensive content with an accuracy of about 92%. An analysis of the importance scores reveals that offensiveness is pre-dominantly a function of words and their combinations, rather than meta features such as punctuations and quotes. This observation can form the foundation of pre-trained classifiers that can be deployed to automatically detect offensive speech in new and unforeseen circumstances.
{"title":"Detecting Offensive Content on Twitter During Proud Boys Riots","authors":"M. Fahim, S. Gokhale","doi":"10.1109/ICMLA52953.2021.00253","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00253","url":null,"abstract":"Hateful and offensive speech on online social media platforms has seen a rise in the recent years. Often used to convey humor through sarcasm or to emphasize a point, offensive speech may also be employed to insult, deride and mock alternate points of view. In turbulent and chaotic circumstances, insults and mockery can lead to violence and unrest, and hence, such speech must be identified and tagged to limit its damage. This paper presents an application of machine learning to detect hateful and offensive content from Twitter feeds shared after the protests by Proud Boys, an extremist, ideological and violent hate group. A comprehensive coding guide, consolidating definitions of what constitutes offensive content based on the potential to trigger and incite people is developed and used to label the tweets. Linguistic, auxiliary and social features extracted from these labeled tweets were used to train machine learning classifiers, which detect offensive content with an accuracy of about 92%. An analysis of the importance scores reveals that offensiveness is pre-dominantly a function of words and their combinations, rather than meta features such as punctuations and quotes. This observation can form the foundation of pre-trained classifiers that can be deployed to automatically detect offensive speech in new and unforeseen circumstances.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"44 3","pages":"1582-1587"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72631341","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}
Pub Date : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00100
Yuehan Yin, Yahya Alqahtani, Jinjuan Feng, J. Chakraborty, M. P. McGuire
Eye tracking data can help design effective user interfaces by showing how users visually process information. In this study, three neural network models were developed and employed to classify three types of information display methods by using eye gaze data that was collected in visual information processing behavior studies. Eye gaze data was first converted into a sequence and was fed into neural networks to predict the information display type. The results of the study show a comparison between three methods for the creation of eye tracking sequences and how they perform using three neural network models including CNN-LSTM, CNN-GRU, and 3D CNN. The results were positive with all models having an accuracy of higher than 88 percent.
{"title":"Deep Learning Methods for the Prediction of Information Display Type Using Eye Tracking Sequences","authors":"Yuehan Yin, Yahya Alqahtani, Jinjuan Feng, J. Chakraborty, M. P. McGuire","doi":"10.1109/ICMLA52953.2021.00100","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00100","url":null,"abstract":"Eye tracking data can help design effective user interfaces by showing how users visually process information. In this study, three neural network models were developed and employed to classify three types of information display methods by using eye gaze data that was collected in visual information processing behavior studies. Eye gaze data was first converted into a sequence and was fed into neural networks to predict the information display type. The results of the study show a comparison between three methods for the creation of eye tracking sequences and how they perform using three neural network models including CNN-LSTM, CNN-GRU, and 3D CNN. The results were positive with all models having an accuracy of higher than 88 percent.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"82 1","pages":"601-605"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72707683","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}
Pub Date : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00107
B. Paudel, Danushka Senarathna, Haibo Wang, S. Tragoudas, Yao Hu, Shengbing Jiang
Despite the immense performance improvement of deep learning-based object detection, the state-of-the-art object detection systems are still prone to misdetections. This work presents a method to predict such misdetections at run-time by using a small network, referred to as ConsensusNet, to learn the correlation patterns or consensus of neighboring detections before non-maximum suppression (NMS). Based on such correlations, ConsensusNet predicts if there are misdetection failures. The proposed method is experimentally evaluated considering single person class from COCO dataset and using YOLOv3 as the object detection system. It shows the proposed method can achieve accuracy of 84.6% and the performance measured in other metrics are also promising. To the best of our knowledge, ConsensusNet is the first network reported for predicting misdetections in object detection.
{"title":"Predicting YOLO Misdetection by Learning Grid Cell Consensus","authors":"B. Paudel, Danushka Senarathna, Haibo Wang, S. Tragoudas, Yao Hu, Shengbing Jiang","doi":"10.1109/ICMLA52953.2021.00107","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00107","url":null,"abstract":"Despite the immense performance improvement of deep learning-based object detection, the state-of-the-art object detection systems are still prone to misdetections. This work presents a method to predict such misdetections at run-time by using a small network, referred to as ConsensusNet, to learn the correlation patterns or consensus of neighboring detections before non-maximum suppression (NMS). Based on such correlations, ConsensusNet predicts if there are misdetection failures. The proposed method is experimentally evaluated considering single person class from COCO dataset and using YOLOv3 as the object detection system. It shows the proposed method can achieve accuracy of 84.6% and the performance measured in other metrics are also promising. To the best of our knowledge, ConsensusNet is the first network reported for predicting misdetections in object detection.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"134 1","pages":"643-648"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77894493","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}
Pub Date : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00273
Maya Kapoor, Joshua Melton, Michael Ridenhour, S. Krishnan, Thomas Moyer
Data provenance graphs, detailed traces of system behavior, are a popular construct to analyze and forecast malicious cyber activity like advanced persistent threats (APT). A critical limitation of existing analysis techniques is the lack of an automated analytic framework to predict APTs. In this work, we address that limitation by augmenting efficient capture and storage mechanisms to include automated analysis. Specifically, we propose PROV-GEM, a deep graph learning framework to identify malicious anomalous behavior from provenance data. Since data provenance graphs are complex datasets often expressed as heterogeneous attributed multiplex networks, we use a unified relation-aware embedding framework to capture the necessary contexts and associated interactions between the various entities manifest in the data. Furthermore, provenance graphs by nature are rich detailed structures that are heavily attributed compared to other complex systems that have been used traditionally in graph machine learning applications. Towards that end, our framework uniquely captures “multi-embeddings” that can represent varied contexts of nodes and their multi-faceted nature. We demonstrate the efficacy of our embeddings by applying PROV-GEM to two publicly available APT provenance graph datasets from StreamSpot and Unicorn. PROV-GEM achieves strong performance on both datasets with a 99% accuracy and 97% F1-score on the StreamSpot dataset, and a 97% accuracy and 89% F1-score on the Unicorn dataset, equaling or outperforming comparable state-of-the-art APT threat detection models. Unlike other frameworks, PROV-GEM utilizes an efficient graph convolutional approach coupled with relational self-attention to generate rich graph embeddings that capture the complex topology of data provenance graphs, providing an effective automated analytic framework for APT detection.
{"title":"PROV-GEM: Automated Provenance Analysis Framework using Graph Embeddings","authors":"Maya Kapoor, Joshua Melton, Michael Ridenhour, S. Krishnan, Thomas Moyer","doi":"10.1109/ICMLA52953.2021.00273","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00273","url":null,"abstract":"Data provenance graphs, detailed traces of system behavior, are a popular construct to analyze and forecast malicious cyber activity like advanced persistent threats (APT). A critical limitation of existing analysis techniques is the lack of an automated analytic framework to predict APTs. In this work, we address that limitation by augmenting efficient capture and storage mechanisms to include automated analysis. Specifically, we propose PROV-GEM, a deep graph learning framework to identify malicious anomalous behavior from provenance data. Since data provenance graphs are complex datasets often expressed as heterogeneous attributed multiplex networks, we use a unified relation-aware embedding framework to capture the necessary contexts and associated interactions between the various entities manifest in the data. Furthermore, provenance graphs by nature are rich detailed structures that are heavily attributed compared to other complex systems that have been used traditionally in graph machine learning applications. Towards that end, our framework uniquely captures “multi-embeddings” that can represent varied contexts of nodes and their multi-faceted nature. We demonstrate the efficacy of our embeddings by applying PROV-GEM to two publicly available APT provenance graph datasets from StreamSpot and Unicorn. PROV-GEM achieves strong performance on both datasets with a 99% accuracy and 97% F1-score on the StreamSpot dataset, and a 97% accuracy and 89% F1-score on the Unicorn dataset, equaling or outperforming comparable state-of-the-art APT threat detection models. Unlike other frameworks, PROV-GEM utilizes an efficient graph convolutional approach coupled with relational self-attention to generate rich graph embeddings that capture the complex topology of data provenance graphs, providing an effective automated analytic framework for APT detection.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"115 1","pages":"1720-1727"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77194918","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}
Pub Date : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00036
Yasutaka Furusho, Shuhei Nitta, Y. Sakata
Autoencoders (AEs) have been widely used for anomaly detection because models trained to reconstruct a normal data are expected to have a higher reconstruction error for anomalous data than that for normal data, and the higher error is adopted as a criterion for identifying anomalies. However, the high capacity of AEs is sometimes able to reconstruct anomalous data even when trained only on normal data, which leads to overlooked anomalies. To remedy this problem, we propose a kernel ridge reconstruction (KRR) approach for general, high-performance, and low computational anomaly detection. KRR replaces the non-linear decoder network of the AE with a linear regressor, which uses the weighted sum of training normal data for reconstruction, and thus prevents the reconstruction of anomalous data. We also reveal the desired property of the encoder for KRR to achieve high anomaly detection performance and propose an effective training algorithm to realize such property by instance discrimination and feature decorrelation. In addition, KRR reduces the computational cost because it replaces the non-linear decoder network with a linear regressor. Our experiments on MNIST, CIFAR10, and KDDCup99 datasets prove its applicability, high performance, and low computational cost. In particular, KRR achieved an area under the curve (AUC) of 0.670 with 12 millions multiply-accumulate operations (MACs) on the CIFAR10 dataset, outperforming a recent reconstruction-based anomaly detection method (MemAE) with a 1.1-fold higher AUC and 0.291 as many MACs.
{"title":"Kernel ridge reconstruction for anomaly detection: general and low computational reconstruction","authors":"Yasutaka Furusho, Shuhei Nitta, Y. Sakata","doi":"10.1109/ICMLA52953.2021.00036","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00036","url":null,"abstract":"Autoencoders (AEs) have been widely used for anomaly detection because models trained to reconstruct a normal data are expected to have a higher reconstruction error for anomalous data than that for normal data, and the higher error is adopted as a criterion for identifying anomalies. However, the high capacity of AEs is sometimes able to reconstruct anomalous data even when trained only on normal data, which leads to overlooked anomalies. To remedy this problem, we propose a kernel ridge reconstruction (KRR) approach for general, high-performance, and low computational anomaly detection. KRR replaces the non-linear decoder network of the AE with a linear regressor, which uses the weighted sum of training normal data for reconstruction, and thus prevents the reconstruction of anomalous data. We also reveal the desired property of the encoder for KRR to achieve high anomaly detection performance and propose an effective training algorithm to realize such property by instance discrimination and feature decorrelation. In addition, KRR reduces the computational cost because it replaces the non-linear decoder network with a linear regressor. Our experiments on MNIST, CIFAR10, and KDDCup99 datasets prove its applicability, high performance, and low computational cost. In particular, KRR achieved an area under the curve (AUC) of 0.670 with 12 millions multiply-accumulate operations (MACs) on the CIFAR10 dataset, outperforming a recent reconstruction-based anomaly detection method (MemAE) with a 1.1-fold higher AUC and 0.291 as many MACs.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"73 1","pages":"185-190"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76213444","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}
Pub Date : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00092
Marzieh Mousavian, Jianhua Chen, S. Greening
Automatic detection of Major Depression Disorder (MDD) from brain MRI images with machine learning has been an active area of study. In this paper several methods are explored for MDD detection by combining features from structural and functional brain MRI images, and combining Atlas-based and spatial cube-based features. Experiments demonstrate good classification performance on an imbalanced dataset. The paper also presents a visualization that captures the spatial overlapping between the top discriminating spatial cube pairs and the regions of interests in the Harvard Atlas.
{"title":"Depression Detection Using Combination of sMRI and fMRI Image Features","authors":"Marzieh Mousavian, Jianhua Chen, S. Greening","doi":"10.1109/ICMLA52953.2021.00092","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00092","url":null,"abstract":"Automatic detection of Major Depression Disorder (MDD) from brain MRI images with machine learning has been an active area of study. In this paper several methods are explored for MDD detection by combining features from structural and functional brain MRI images, and combining Atlas-based and spatial cube-based features. Experiments demonstrate good classification performance on an imbalanced dataset. The paper also presents a visualization that captures the spatial overlapping between the top discriminating spatial cube pairs and the regions of interests in the Harvard Atlas.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"125 5 1","pages":"552-557"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80502286","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}
Pub Date : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00126
John T. Hancock, T. Khoshgoftaar, Joffrey L. Leevy
We present a simple approach for detecting brute force attacks in the CSE-CIC-IDS2018 Big Data dataset. We show our approach is preferable to more complex approaches since it is simpler, and yields stronger classification performance. Our contribution is to show that it is possible to train and test simple Decision Tree models with two independent variables to classify CSE-CIC-IDS2018 data with better results than reported in previous research, where more complex Deep Learning models are employed. Moreover, we show that Decision Tree models trained on data with two independent variables perform similarly to Decision Tree models trained on a larger number independent variables. Our experiments reveal that simple models, with AUC and AUPRC scores greater than 0.99, are capable of detecting brute force attacks in CSE-CIC-IDS2018. To the best of our knowledge, these are the strongest performance metrics published for the machine learning task of detecting these types of attacks. Furthermore, the simplicity of our approach, combined with its strong performance, makes it an appealing technique.
{"title":"Detecting SSH and FTP Brute Force Attacks in Big Data","authors":"John T. Hancock, T. Khoshgoftaar, Joffrey L. Leevy","doi":"10.1109/ICMLA52953.2021.00126","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00126","url":null,"abstract":"We present a simple approach for detecting brute force attacks in the CSE-CIC-IDS2018 Big Data dataset. We show our approach is preferable to more complex approaches since it is simpler, and yields stronger classification performance. Our contribution is to show that it is possible to train and test simple Decision Tree models with two independent variables to classify CSE-CIC-IDS2018 data with better results than reported in previous research, where more complex Deep Learning models are employed. Moreover, we show that Decision Tree models trained on data with two independent variables perform similarly to Decision Tree models trained on a larger number independent variables. Our experiments reveal that simple models, with AUC and AUPRC scores greater than 0.99, are capable of detecting brute force attacks in CSE-CIC-IDS2018. To the best of our knowledge, these are the strongest performance metrics published for the machine learning task of detecting these types of attacks. Furthermore, the simplicity of our approach, combined with its strong performance, makes it an appealing technique.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"25 1","pages":"760-765"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81309974","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}
Pub Date : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00136
Aninditha Ramesh, Anusha S. Rao, Sanjana Moudgalya, K. S. Srinivas
Deep Learning models have been a tremendous breakthrough in the field of Drug discovery, greatly simplifying the pre-clinical phase of this intricate task. With an intention to ease this further, we introduce a novel method to generate target-specific molecules using a Generative Adversarial Network (GAN). The dataset consists of drugs whose target proteins belong to the class of Tyrosine kinase and are specifically active against some of the growth factor receptors present in the human body. An Autoencoder network is used to learn the embeddings of the drug which is represented in the SMILES format and the deep neural network GAN is used to generate structurally valid molecules using drug-target interaction as the validating criteria. The model has successfully produced 39 novel structures and 15 of them show satisfactory binding with at least one of the target receptors.
{"title":"GAN Based Approach for Drug Design","authors":"Aninditha Ramesh, Anusha S. Rao, Sanjana Moudgalya, K. S. Srinivas","doi":"10.1109/ICMLA52953.2021.00136","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00136","url":null,"abstract":"Deep Learning models have been a tremendous breakthrough in the field of Drug discovery, greatly simplifying the pre-clinical phase of this intricate task. With an intention to ease this further, we introduce a novel method to generate target-specific molecules using a Generative Adversarial Network (GAN). The dataset consists of drugs whose target proteins belong to the class of Tyrosine kinase and are specifically active against some of the growth factor receptors present in the human body. An Autoencoder network is used to learn the embeddings of the drug which is represented in the SMILES format and the deep neural network GAN is used to generate structurally valid molecules using drug-target interaction as the validating criteria. The model has successfully produced 39 novel structures and 15 of them show satisfactory binding with at least one of the target receptors.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"10 1","pages":"825-828"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81938131","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}
Pub Date : 2021-12-01DOI: 10.1109/ICMLA52953.2021.00053
Narges Manouchehri, N. Bouguila, Wentao Fan
In this paper, we propose hierarchical Pitman-Yor process mixtures of multivariate Beta distributions and learn this novel clustering method by online variational inference. The flexibility of this mixture model and its non-parametric hierarchical structure help in fitting our data. Also, the model complexity and model parameters are estimated simultaneously. We apply our proposed model to real medical applications. Our motivation is that labelling healthcare data is sensitive and expensive. Also, interpretability and evidence-based decision-making are some basic needs of medicine. These conditions led us to focus on clustering as it doesn’t need labelling. Another driving reason is that the amount of publicly available data in medicine is less compared to other fields due to the confidential regulations. To evaluate our proposed model, we compare its performance with other similar alternatives. The experimental results indicate the potential of our proposed model.
{"title":"Batch and Online Variational Learning of Hierarchical Pitman-Yor Mixtures of Multivariate Beta Distributions","authors":"Narges Manouchehri, N. Bouguila, Wentao Fan","doi":"10.1109/ICMLA52953.2021.00053","DOIUrl":"https://doi.org/10.1109/ICMLA52953.2021.00053","url":null,"abstract":"In this paper, we propose hierarchical Pitman-Yor process mixtures of multivariate Beta distributions and learn this novel clustering method by online variational inference. The flexibility of this mixture model and its non-parametric hierarchical structure help in fitting our data. Also, the model complexity and model parameters are estimated simultaneously. We apply our proposed model to real medical applications. Our motivation is that labelling healthcare data is sensitive and expensive. Also, interpretability and evidence-based decision-making are some basic needs of medicine. These conditions led us to focus on clustering as it doesn’t need labelling. Another driving reason is that the amount of publicly available data in medicine is less compared to other fields due to the confidential regulations. To evaluate our proposed model, we compare its performance with other similar alternatives. The experimental results indicate the potential of our proposed model.","PeriodicalId":6750,"journal":{"name":"2021 20th IEEE International Conference on Machine Learning and Applications (ICMLA)","volume":"6 1","pages":"298-303"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87435668","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：