2017 International Conference on Machine Learning and Data Science (MLDS)最新文献

Influence of Different Fields of View on Decision-Making in a Search-and-Shoot Scenario 搜索射击场景中不同视场对决策的影响

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.23

Akash K Rao, Utkrisht Dhankar, Chandan Satyarthi, Sushil Chandra, V. Dutt

{"title":"Influence of Different Fields of View on Decision-Making in a Search-and-Shoot Scenario","authors":"Akash K Rao, Utkrisht Dhankar, Chandan Satyarthi, Sushil Chandra, V. Dutt","doi":"10.1109/MLDS.2017.23","DOIUrl":"https://doi.org/10.1109/MLDS.2017.23","url":null,"abstract":"Indirect visual displays (IVDs) play a significant role in providing full-spectrum views of the immediate environment in closed systems (e.g., tanks). However, currently little is known about how different fields of views (FoVs) in IVDs influence operator’s decision-making in scenarios requiring search and shoot operations. The primary objective of this study was to determine the influence of varying degrees of FoVs on human decision-making in a terrainbased search-and-shoot scenario. A total of 25 participants performed in two FoV designs that were presented to them in a random order: A 180*2 FoV, where the computer screen was split into two sections (top and bottom) and each section provided a 180° FoV of the outside scene (front and back); and, a 90*4 FoV, where the computer screen was split into four sections, where each section provided a 90° FoV of the outside scene (front, back, left, and right). Results revealed that performance was better, frustration was less, and effort was less in the 180*2 FoV compared to the 90*4 FoV; however, the mental demand was more in the 180*2 FoV compared to the 90*4 FoV. We highlight the implication of our results for operator’s decision-making in IVD tasks.","PeriodicalId":248656,"journal":{"name":"2017 International Conference on Machine Learning and Data Science (MLDS)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125179527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Modeling Decisions in Games Using Reinforcement Learning 使用强化学习在游戏中建模决策

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.13

Himanshu Singal, Palvi Aggarwal, V. Dutt

{"title":"Modeling Decisions in Games Using Reinforcement Learning","authors":"Himanshu Singal, Palvi Aggarwal, V. Dutt","doi":"10.1109/MLDS.2017.13","DOIUrl":"https://doi.org/10.1109/MLDS.2017.13","url":null,"abstract":"Reinforcement-learning (RL) algorithms have been used to model human decisions in different decision-making tasks. Recently, certain deep RL algorithms have been proposed; however, there is little research that compares deep RL algorithms with traditional RL algorithms in accounting for human decisions. The primary objective of this paper is to compare deep and traditional RL algorithms in a virtual environment concerning their performance, learning speed, ability to account for human decisions, and ability to extract features from the decision environment. We implemented traditional RL algorithms like imitation learning, Q-Learning, and a deep RL algorithm, DeepQ Learning, to train an agent for playing a platform jumper game. For model comparison, we collected human data from 15 human players on the platform jumper game. As part of our evaluation, we also increased the speed of the moving platform in the jumper game to test how humans and model agents responded to the changing game conditions. Results showed that DeepQ approach took more training episodes than the traditional RL algorithms to learn the gameplay. However, the DeepQ algorithm could extract features directly from images of gameplay; whereas, other algorithms had to be fed the extracted features. Furthermore, conventional algorithms performed more human-like in a slow version of the game; however, the DeepQ algorithm performed more humanlike in the fast version of the game.","PeriodicalId":248656,"journal":{"name":"2017 International Conference on Machine Learning and Data Science (MLDS)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123207877","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Feature Selection Using Autoencoders 使用自动编码器进行特征选择

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.20

Dhananjay Tomar, Yamuna Prasad, M. Thakur, K. K. Biswas

引用次数: 2

Modeling Choice Variation in Search Strategies with Multi-Armed Bandit Problems 多臂盗匪问题搜索策略的建模选择变化

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.18

Neha Sharma, V. Dutt

{"title":"Modeling Choice Variation in Search Strategies with Multi-Armed Bandit Problems","authors":"Neha Sharma, V. Dutt","doi":"10.1109/MLDS.2017.18","DOIUrl":"https://doi.org/10.1109/MLDS.2017.18","url":null,"abstract":"Prior research in decisions from experience (DFE) involving multi-armed bandit problems has used the sampling paradigm. In this paradigm, decision-makers search for information between multiple options before making a final consequential choice. Prior research in the sampling paradigm has accounted for information search and final choices using computational cognitive models. However, little is known on how cognitive models could account for final choices of participants with different exploration strategies in the presence or absence of an intermediate option. In this paper, we perform an individual-differences analysis and test the ability of computational models to explain final choices of participants with different exploration strategies in the absence or presence of an intermediate option. Specifically, we take an Instance-Based Learning (IBL) model, which relies on recency and frequency processes, and we calibrate this model to final choices of participants exhibiting more-switching (piecewise strategy) or less-switching (comprehensive strategy) between options in different problems. Also, a Natural Mean Heuristic (NMH) model, relying on frequency of experienced outcomes, is used as a baseline. Results revealed that both IBL and NMH models explained aggregate and individual choices better when participants followed piecewise strategy compared to the comprehensive strategy. Overall, the IBL model, calibrated to individual participants using a single set of parameters, performed better compared to the NMH model. We highlight the implications of our results for DFE research involving exploration before consequential decisions.","PeriodicalId":248656,"journal":{"name":"2017 International Conference on Machine Learning and Data Science (MLDS)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126915600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Extractive Text Summarization Using Word Vector Embedding 使用词向量嵌入提取文本摘要

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.12

Aditya Jain, Divij Bhatia, M. Thakur

引用次数: 40

A Support Vector Machine Based Approach for Code Smell Detection 基于支持向量机的代码气味检测方法

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.8

Amandeep Kaur, Sushma Jain, S. Goel

引用次数: 28

A Comparison of Class Imbalance Techniques for Real-World Landslide Predictions 类不平衡技术在实际滑坡预测中的比较

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.21

Kapil Agrawal, Yashasvi Baweja, Deepti Dwivedi, Ritwik Saha, P. Prasad, Shubham Agrawal, S. Kapoor, Pratik Chaturvedi, N. Mali, Venkata Uday Kala, V. Dutt

{"title":"A Comparison of Class Imbalance Techniques for Real-World Landslide Predictions","authors":"Kapil Agrawal, Yashasvi Baweja, Deepti Dwivedi, Ritwik Saha, P. Prasad, Shubham Agrawal, S. Kapoor, Pratik Chaturvedi, N. Mali, Venkata Uday Kala, V. Dutt","doi":"10.1109/MLDS.2017.21","DOIUrl":"https://doi.org/10.1109/MLDS.2017.21","url":null,"abstract":"Landslides cause lots of damage to life and property world over. There has been research in machine-learning that aims to predict landslides based on the statistical analysis of historical landslide events and its triggering factors. However, prediction of landslides suffers from a class-imbalance problem as landslides and land-movement are very rare events. In this paper, we apply state-of-the-art techniques to correct the class imbalance in landslide datasets. More specifically, to overcome the class-imbalance problem, we use different synthetic and oversampling techniques to a real-world landslide data collected from the Chandigarh - Manali highway. Also, we apply several machine-learning algorithms to the landslide data set for predicting landslides and evaluating our algorithms. Different algorithms have been assessed using techniques like the area under the ROC curve (AUC) and sensitivity index (d'). Results suggested that random forest algorithm performed better compared to other classification techniques like neural networks, logistic regression, support vector machines, and decision trees. Furthermore, among class-imbalance methods, the Synthetic Minority Oversampling Technique with iterative partitioning filter (SMOTE-IPF) performed better than other techniques. We highlight the implications of our results and methods for predicting landslides in the real world.","PeriodicalId":248656,"journal":{"name":"2017 International Conference on Machine Learning and Data Science (MLDS)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115753219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 17

Categorical Classification and Deletion of Spam Images on Smartphones Using Image Processing and Machine Learning 使用图像处理和机器学习在智能手机上分类和删除垃圾图像

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.10

Arjit Sachdeva, R. Kapoor, Amit Sharma, Akshit Mishra

引用次数: 3

Patient Journey Visualizer: A Tool for Visualizing Patient Journeys 病人旅程可视化:一个可视化病人旅程的工具

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.19

K. K. Kaushal, S. Kaushik, Abhinav Choudhury, Krish Viswanathan, Balaji Chellappa, Sayee Natarajan, Larry A. Pickett, V. Dutt

{"title":"Patient Journey Visualizer: A Tool for Visualizing Patient Journeys","authors":"K. K. Kaushal, S. Kaushik, Abhinav Choudhury, Krish Viswanathan, Balaji Chellappa, Sayee Natarajan, Larry A. Pickett, V. Dutt","doi":"10.1109/MLDS.2017.19","DOIUrl":"https://doi.org/10.1109/MLDS.2017.19","url":null,"abstract":"To provide sufficient healthcare to patients, it is important to visualize patient journey(s), i.e., the journey from sickness to recovery. However, current visualization tools do not allow us to imagine patient journeys at both the individual and aggregate levels. In this paper, we aim to understand patient journeys via powerful visualization charts, that help mine patterns in Big-Data relating to patients at both the individual and aggregate levels. We developed a Patient Journey Visualizer (PJV) tool that can help in visualizing patient journeys via Parallel Coordinates, Sankey, and Sunburst charts. Parallel Coordinates assists in visualizing multivariate data concerning patient journeys in PJV at the individual level. Sankey charts help in visualizing the aggregate flow of patients between various phases of patient journeys in PJV. Sunburst charts represent hierarchical relationships between diagnoses, procedures, and prescription medications in PJV. Different visualization charts in PJV were compared across increasing number of data points. Results revealed that the Parallel Coordinates chart took less time to render compared to the Sankey and Sunburst charts when dataset size increased. The main implications of our findings are for improving healthcare by providing useful visualizations of patient journeys.","PeriodicalId":248656,"journal":{"name":"2017 International Conference on Machine Learning and Data Science (MLDS)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122087777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

An Empirical Investigation to Overcome Class-Imbalance in Inspection Reviews 检视评鉴中克服阶层失衡的实证研究

2017 International Conference on Machine Learning and Data Science (MLDS) Pub Date : 2017-12-01 DOI: 10.1109/MLDS.2017.15

Maninder Singh, G. Walia, Anurag Goswami

{"title":"An Empirical Investigation to Overcome Class-Imbalance in Inspection Reviews","authors":"Maninder Singh, G. Walia, Anurag Goswami","doi":"10.1109/MLDS.2017.15","DOIUrl":"https://doi.org/10.1109/MLDS.2017.15","url":null,"abstract":"Background: software inspection results in reviews that report the presence of faults. Requirements author must manually read through the reviews and differentiate between true-faults and false-positives. Problem: post-inspection decisions (fault or nonfault) are difficult and time consuming. It is difficult to employ machine learning (ML) techniques directly to raw (unstructured) data because of class imbalance problem and possible fault-slippage through misclassification of fault. Aim: The aim of this research is to solve this problem with the help of ensemble approach and priority analysis to achieve significant accuracy in determining true-fault and false-positive reviews without losing any listed fault. Method: We conducted empirical experiment using two trained models (with reviews from inspection domain vs. movies domain) to address class imbalance problem. Our approach uses ensemble methods to develop classification confidence of inspection reviews and assigns them to appropriate priority class. Results: The results showed that movies trained model performed better than inspection trained and restricted any possible fault-slippage.","PeriodicalId":248656,"journal":{"name":"2017 International Conference on Machine Learning and Data Science (MLDS)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122124707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 7