2019 Grace Hopper Celebration India (GHCI)最新文献

{"title":"Multimodal Web Application to Infer Emotional Intelligence of Adolescent Counsellor","authors":"Prerna Agarwal, Anupama Ray, A. Shah, Akshay Gugnani, Priyanka Halli, Shubham Atreja, Gargi Dasgupta","doi":"10.1109/GHCI47972.2019.9071881","DOIUrl":"https://doi.org/10.1109/GHCI47972.2019.9071881","url":null,"abstract":"There are only 0.3 psychiatrists and 0.047 psychologists per 100,000 people in India, compared to a country like the US, which has 29 psychologists per 100,000 people (according to WHO), thereby leading to lack of counselling services and mental health-care. Fortunately, researchers in India have found mental health interventions delivered by lay counsellors rather than specialists to be effective in treating and preventing mental health problems. However, choosing a lay counsellor from a pool of candidates becomes a very important but time-consuming and tedious task because of our deficits in evaluating emotional capabilities, implicit biases and facilitation skills in a resume and standard interview. In this paper, we present a highly scalable web application that can help in hiring emotionally intelligent lay-counselors. The backend framework measures several vital emotional intelligence features that are crucial in a prospective lay counsellor. The framework uses multi-modal data and provides a ranking of potential counsellors. The results and inferencing help establish the importance of each modality and gives insights on features that are key to identify the emotional skills. We compare the predicted rankings to those given by the interviewers (a clinical psychologist and a psychiatrist) and recognize the benefits of automation of the process as well as a need for a deeper analysis of interview questions, discriminative features and importance of multi-modality assessments.","PeriodicalId":153240,"journal":{"name":"2019 Grace Hopper Celebration India (GHCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131301400","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}

{"title":"A Question Answering and Quiz Generation Chatbot for Education","authors":"A. S. Sreelakshmi, S. B. Abhinaya, Aishwarya Nair, S. Jaya Nirmala","doi":"10.1109/GHCI47972.2019.9071832","DOIUrl":"https://doi.org/10.1109/GHCI47972.2019.9071832","url":null,"abstract":"In recent years, there have been a number of chatbots developed in the field of education. While many of them are designed to answer queries based on publicly available information such as in community answering platforms, or from a predefined knowledge base, there is no possibility of customizing the information to be queried. Moreover, there are no existing chatbots capable of generating self assessment quizzes based on any given document. This paper proposes a Question Answering and Quiz Generation Chatbot that allows a user to upload relevant documents and perform two main functions on them, namely answer extraction and question generation. The uploaded document is converted into a knowledge base through a number of data cleaning and preprocessing steps. The Question Answering module uses ranking functions and neural networks to extract the most appropriate answer from the knowledge base and the Quiz Generation module identifies key sentences and generates question-answer pairs, which can be used to generate a quiz for the user.","PeriodicalId":153240,"journal":{"name":"2019 Grace Hopper Celebration India (GHCI)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123243683","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}

{"title":"Fair Transfer of Multiple Style Attributes in Text","authors":"Karan Dabas, Nishtha Madaan, Vijay Arya, S. Mehta, Gautam Singh, Tanmoy Chakraborty","doi":"10.1109/GHCI47972.2019.9071799","DOIUrl":"https://doi.org/10.1109/GHCI47972.2019.9071799","url":null,"abstract":"To preserve anonymity and obfuscate their identity on online platforms users may morph their text and portray themselves as a different gender or demographic. Similarly, a chatbot may need to customize its communication style to improve engagement with its audience. This manner of changing the style of written text has gained significant attention in recent years. Yet these past research works largely cater to the transfer of single style attributes. The disadvantage of focusing on a single style alone is that this often results in target text where other existing style attributes behave unpredictably or are unfairly dominated by the new style. To counteract this behavior, it would be nice to have a style transfer mechanism that can transfer or control multiple styles simultaneously and fairly. Through such an approach, one could obtain obfuscated or written text incorporated with a desired degree of multiple soft styles such as female-quality, politeness, or formalness. To the best of our knowledge this work is the first that shows and attempt to solve the issues related to multiple style transfer. We also demonstrate that the transfer of multiple styles cannot be achieved by sequentially performing multiple single-style transfers. This is because each single style-transfer step often reverses or dominates over the style incorporated by a previous transfer step. We then propose a neural network architecture for fairly transferring multiple style attributes in a given text. We test our architecture on the Yelp dataset to demonstrate our superior performance as compared to existing one-style transfer steps performed in a sequence.","PeriodicalId":153240,"journal":{"name":"2019 Grace Hopper Celebration India (GHCI)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133567083","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}

{"title":"Seed Segregation using Deep Learning","authors":"Swathi K Hiremath, Suhas Suresh, S. Kale, R. Ranjana, K. Suma, N. Nethra","doi":"10.1109/GHCI47972.2019.9071810","DOIUrl":"https://doi.org/10.1109/GHCI47972.2019.9071810","url":null,"abstract":"A superior crop yield is a vital part of the agricultural industry. The principal component for a good yield is good quality seeds. Generally, seeds are sown without prior quality checks and inspections as these processes are tedious and labor intensive. This tends to diminish the crop yield as well as crop quality. This paper proposes a novel method to automatically sort seeds as good or bad based on the visual characteristics of the seed using a Convolutional Neural Network. The data set used to train the model comprised of images of the top and bottom profiles of the seeds. The Convolutional Neural Network provided a classification accuracy of 96.875%. This study uses a hardware solution which classifies seeds using the CNN model. The device performs significantly better as it scans both profiles of a seed rather than one profile. A classification accuracy of 93.00% was obtained using our hardware setup.","PeriodicalId":153240,"journal":{"name":"2019 Grace Hopper Celebration India (GHCI)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134491729","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}

{"title":"Network Intrusion Detection Using Sequence Models","authors":"Archana Prabhu, H. Champa, Deepti Kalasapura","doi":"10.1109/GHCI47972.2019.9071806","DOIUrl":"https://doi.org/10.1109/GHCI47972.2019.9071806","url":null,"abstract":"The increase in network users has diversified the nature of attacks and increased their frequency. Existing intrusion detection systems rely on inefficient signature based approaches which can easily be evaded by attackers. Many shallow learning approaches have been explored but they require expert knowledge and longer training times. In this paper we utilize architectures such as RNN, LSTM and GRU to provide a solution to this problem. We also analyze and build upon an existing NDAE model and provide a comparative analysis. We have implemented our models using Keras with a TensorFlow backend. The benchmark NSL-KDD dataset is used for training and validation. The results obtained are promising and our models have potential to detect attacks in real-time backbone network traffic.","PeriodicalId":153240,"journal":{"name":"2019 Grace Hopper Celebration India (GHCI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115536465","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}

{"title":"Handling Gender Biases in E-Commerce Product Specifications","authors":"Ashima Suvarna, K. Dey, Seema Nagar, Nishtha Madaan, S. Mehta","doi":"10.1109/GHCI47972.2019.9071916","DOIUrl":"https://doi.org/10.1109/GHCI47972.2019.9071916","url":null,"abstract":"Fair computing has emerged as a key area of artificial intelligence (AI), and especially machine learning (ML). Identification and mitigation of several types of biases, spanning over data and machine learning models, has attracted both research and regulatory attention. In this work, we explore the presence and degree of gender bias in product descriptions featured on e-commerce websites. Using the knowledge obtained in analysis, we recommend methods to debias the product description, using a product feature level text selection scheme, sourced by customer reviews. Our work is the first of its kind, that establishes a baseline for enhancing the cross-gender acceptability of product descriptions, and proposes a framework for e-retailers to provide such gender-neutral product descriptions.","PeriodicalId":153240,"journal":{"name":"2019 Grace Hopper Celebration India (GHCI)","volume":"224 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124649186","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}

{"title":"Unified framework of Explainable AI to enhance classifier performance","authors":"R. Manjunath, B.N Chandrashekar, B. Vinutha, Rahul Arya, Arindam Chatterjee","doi":"10.1109/GHCI47972.2019.9071811","DOIUrl":"https://doi.org/10.1109/GHCI47972.2019.9071811","url":null,"abstract":"Deep learning image classifiers are extensively used in document processing, activity monitoring, object recognition and separations etc. However, even the best classifiers are not free from errors. It would be very helpful if the errors that are pumped in to the system due to the classifier decisions are reduced. The framework comprises of heat map generation, attribute generation, text explanation generation and activation.","PeriodicalId":153240,"journal":{"name":"2019 Grace Hopper Celebration India (GHCI)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116418307","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}

{"title":"Auto-scaling Resources for Cloud Applications using Reinforcement learning","authors":"I. John, Aiswarya Sreekantan, S. Bhatnagar","doi":"10.1109/GHCI47972.2019.9071835","DOIUrl":"https://doi.org/10.1109/GHCI47972.2019.9071835","url":null,"abstract":"Elasticity is an attractive feature of cloud computing, that enables increasing or decreasing the resources allocated to an application in order to adapt to changes in the workload. To efficiently utilize elasticity of clouds, the decisions on resource allocation need to be made algorithmically, adaptively and in real-time. The resource provisioning algorithm must also consider the performance requirements of the application as specified in the Service Level Agreement between the cloud provider and the client. In this paper, we present a reinforcement learning based algorithm that addresses the issues of slow convergence and lack of scalability in classical approaches such as Q-learning. We use the technique of adaptive tile coding and workload forecasting to ensure efficient utilization of resources. The effectiveness of the proposed method as compared to static, threshold-based and other reinforcement learning based allocation schemes is established with experiments on the Cloudsim platform.","PeriodicalId":153240,"journal":{"name":"2019 Grace Hopper Celebration India (GHCI)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117096006","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}

{"title":"Market Expansion Strategy for Teleradiology Services into Resource-Poor Healthcare Set-ups","authors":"Arti Thapliyal","doi":"10.1109/GHCI47972.2019.9071870","DOIUrl":"https://doi.org/10.1109/GHCI47972.2019.9071870","url":null,"abstract":"Healthcare sector is facing healthcare resource shortage globally and an acute doctor shortage in India is having a detrimental effect on healthcare outcomes. Resource-poor hospitals specifically struggle in this phenomenon on account of 4 reasons: not being able to hire enough doctors, poor infrastructure, cost of care and finally the compromised quality. Radiology is one such specialty which is very vital, scarce and is facing all above-mentioned challenges. Developing countries being resource-poor, specifically India which is the 2nd largest populated country in the world, is constantly struggling to provide quality care at low cost and improve healthcare outcomes. There is a need to innovate healthcare solutions to effectively deliver care in resource-poor set-ups. Specially getting radiology services everywhere as it's the backbone of diagnosis process in treatment and hence has a direct impact on healthcare outcomes. And telemedicine is an effective IT solution in getting excellent diagnostic expertise to resource-poor and remote hospitals & diagnostic centers; and hence making treatment outcomes better. 5C Network is one of a kind social enterprise trying to provide quality and cost effective teleradiology solution to resource-poor set-ups predominantly in the southern states of India and aspires to take their services to other states of India as well. The aim of the study is to propose a market expansion strategy for 5C Network to be able to take their services effectively to the Indian states of Maharashtra and Madhya Pradesh. The research questions will try to find out the current state of the service and how can it be made better in quality and usability for the end users (radiologists and radio-technicians). The study would further explore the bigger picture of ICT, other good practices around the world in teleradiology and make recommendation to the organization under consideration i.e. 5C Network. The marketing strategy will be devised using 5C analysis, 5M strategy, Segmentation, targeting and positioning recommendations and finally specific recommends will be made using 4P marketing.","PeriodicalId":153240,"journal":{"name":"2019 Grace Hopper Celebration India (GHCI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127764706","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}

{"title":"Multi-omics Integration based Predictive Model for Survival Prediction of Lung Adenocarcinaoma","authors":"Vidhi Malik, S. Dutta, Yogesh Kalakoti, D. Sundar","doi":"10.1109/GHCI47972.2019.9071831","DOIUrl":"https://doi.org/10.1109/GHCI47972.2019.9071831","url":null,"abstract":"Background: Lung adenocarcinoma (LUAD) patients majorly tend to poor clinical outcomes. A biomarker or gene signature built using multi-omics dataset along with clinical features that could predict survival in these patients would have a significant clinical impact, enabling earlier detection of mortality risk and personalized therapy. Methods: To identify a novel multi-omics signature along with clinical features associated with overall survival, we analyzed LUAD patient's single omics datasets for Copy number variations (CNV), protein, methylation, mutation, RNA, mi-RNA that were extracted from The Cancer Genome Atlas (TCGA). Neighborhood component analysis, a feature reduction algorithm was applied to the large feature space for all the single omics data set to select the optimal number of combinations of best feature predictors. These selected features for each singe omics dataset were coupled to integrate multiple inputs and fed into an Support vector machine (SVM), Neural network pattern recognizer and RUS ensemble boost to build the survival prediction model. An external cohort was used to validate the prediction models. Results: We identified a critical feature space for multi-omics-based integration that could effectively stratify these LUAD patients into our critical survival classes with 92.9% accuracy using our neural network-based model, and receiver operating characteristic (ROC) analysis indicated that the signature had a powerful predictive ability. Moreover, a predictive pipeline was established based on the above signature integrated with clinicopathological features. The performance in terms of prediction accuracy for single-omics data as input for validation was not as good as the performance of our model, as it requires multi-omics data as an input and improves performance accuracy of our classifier. Lastly, the signature was validated by an external cohort from excluded patients retrieved for Group I and II study on our best performing classifier, the neural network pattern recognizer. Conclusion: Finally, we developed a robust multi-omics signature as a self-sustaining factor to effectively classify LUAD patients into two survival classes, i.e., alive or dead with unprecedented accuracy of 92.9%, which might provide a basis for personalized treatments for these patients.","PeriodicalId":153240,"journal":{"name":"2019 Grace Hopper Celebration India (GHCI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126319372","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}