collection curated by joecohen https://academictorrents.com/collection/knowledge-discovery-lab-at-umass-boston @INPROCEEDINGS{6525195, author = {Cohen, J. and Wei Ding and Boisvert, D.}, booktitle = {To introduce computer science in one day: The Throw platform}, title={To introduce computer science in one day: The Throw platform}, year={2013}, month={March}, pages={1-4}, abstract={This paper presents an open source platform Throw [1] that is intended to be used for a one day event to increase interest in computer science as well as equip students with tools for self exploration. It is based on three years of hosting a one day event aimed at introducing computer science to 5-8th grade students. One major challenge in computer science education is fostering a commitment to learn, that is powerful and engaging enough for a student to be able to utilize learned skills to turn their ideas into reality and drive them to pursue computing. We present a theory for what is necessary for an effective introduction to computer science as well as present survey results from the first trial of the Throw platform which encompasses this theory.}, keywords={computer aided instruction;computer science education;public domain software;Throw open source platform;computer science education;Computer Science education;STEM education;web}, doi={10.1109/ISECon.2013.6525195},} https://academictorrents.com/download/dce77c0199e3a98f81caa7bd204f8efade63732a @article{cohen2013crater, title= {Crater Detection via Genetic Search Methods to Reduce Image Features}, author= {Joseph Paul Cohen and Wei Ding}, journal= {Advances in Space Research}, year= {2013}, publisher= {Elsevier}, abstract= {Recent approaches to crater detection have been inspired by face detection's use of gray-scale texture features. Using gray-scale texture features for supervised machine learning crater detection algorithms provides better classification of craters in planetary images than previous methods. When using Haar features it is typical to generate thousands of numerical values from each candidate crater image. This magnitude of image features to extract and consider can spell disaster when the application is an entire planetary surface. One solution is to reduce the number of features extracted and considered in order to increase accuracy as well as speed. Feature subset selection provides the operational classifiers with a concise and denoised set of features by reducing irrelevant and redundant features. Feature subset selection is known to be NP-hard. To provide an efficient suboptimal solution, four genetic algorithms are proposed to use greedy selection, weighted random selection, and simulated annealing to distinguish discriminate features from indiscriminate features. Inspired by analysis regarding the relationship between subset size and accuracy, a squeezing algorithm is presented to shrink the genetic algorithm's chromosome cardinality during the genetic iterations. A significant increase in the classification performance of a Bayesian classifier in crater detection using image texture features is observed.}, keywords= {}, terms= {} } https://academictorrents.com/download/8ae530c0c1466ba8feee9914236cc900ad2f708e @inproceedings{liu2011bernoulli, title={Bernoulli trials based feature selection for crater detection}, author={Liu, Siyi and Ding, Wei and Cohen, Joseph Paul and Simovici, Dan and Stepinski, Tomasz}, booktitle={Proceedings of the 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems}, pages={461--464}, year={2011}, organization={ACM}, abstract = {Counting craters is a fundamental task of planetary sci-ence because it provides the only tool for measuring relativeages of planetary surfaces. However, advances in surveyingcraters present in data gathered by planetary probes havenot kept up with advances in data collection. One chal-lenge of auto-detecting craters in images is to identify an images features that discriminate it between craters andother surface objects. The problem of optimal feature se-lection is known to be NP-hard and the search is compu-tationally intractable. In this paper we propose a wrapperbased randomized feature selection method to efficiently se-lect relevant features for crater detection. We design andimplement a dynamic programming algorithm to search fora relevant feature subset by removing irrelevant features andminimizing a cost objective function simultaneously. In or-der to only remove irrelevant features we use Bernoulli Tri-als to calculate the probability of such a case using the costfunction. Our proposed algorithms are empirically evaluatedon a large high-resolution Martian image exhibiting a heav-ily cratered Martian terrain characterized by heterogeneoussurface morphology. The experimental results demonstratethat the proposed approach achieves a higher accuracy thanother existing randomized approaches to a large extent withless runtime.} } https://academictorrents.com/download/37499de2b944dacc88cd295d3f9631670bd6abe6 @article{, title= {Crater Dataset}, journal= {}, author= {UMass Boston KDLab}, year= {2013}, url= {http://kdl.cs.umb.edu/w/datasets/craters/}, abstract= {Dataset Objective: Determine if the instance is a crater or not a crater. 1=Crater, 0=Not Crater Data Set Information: This dataset was generated using HRSC nadir panchromatic image h0905_0000 taken by the Mars Express spacecraft. The images is located in the Xanthe Terra, centered on Nanedi Vallis and covers mostly Noachian terrain on Mars. The image had a resolution of 12.5 meters/pixel. Data Set Generation: Using the technique described by L. Bandeira (Bandeira, Ding, Stepinski. 2010.Automatic Detection of Sub-km Craters Using Shape and Texture Information) we identify crater candidates in the image using the pipeline depicted in the figure below. Each crater candidate image block is normalized to a standard scale of 48 pixels. Each of the nine kinds of image masks probes the normalized image block in four different scales of 12 pixels, 24 pixels, 36 pixels, and 48 pixels, with a step of a third of the mask size (meaning 2/3 overlap). We totally extract 1,090 Haar-like attributes using nine types of masks as the attribute vectors to represent each crater candidate. The dataset was converted to the Weka ARFF format by Joseph Paul Cohen in 2012.}, keywords= {}, terms= {} } https://academictorrents.com/download/30748b1a7ac99b1c5ff66f0bc5c5f7428ed035c5 @article{cheungeffectiveness, title={Effectiveness of Cybersecurity Competitions}, author={Cheung, Ronald S and Cohen, Joseph Paul and Lo, Henry Z and Elia, Fabio and Carrillo-Marquez, Veronica}, abstract = {There has been a heightened interest among U.S.government agencies to fund cybersecurity workforce development. These efforts include offering universities funding forstudent scholarships, funding for building capacity in cybersecurity education, as well as sponsoring cybersecurity competitions, games, and outreach programs. This paper examines the effectiveness of cybersecurity competitions in educating students.Our study shows that though competitions do pique students interest, the effectiveness of this approach in producing more high quality professionals can be limited. One reason is that the knowledge barrier to compete in these competitions is high. To be successful, students have to be proficient in operating systems,application services, software engineering, system administration and networking. Many Computer Science and InformationTechnology students do not feel qualified, and consequently this reduces participation from a wider student audience. Our approach takes aims at lowering this barrier to entry. We employ a hands-on learning methodology where students attend lectures on background knowledge on weekdays and practice what they learn in weekend workshops. A virtual networking environment is provided for students to practice network defense in the workshops and on their own time} } https://academictorrents.com/download/30ec3bb79d95e4af3b92315a5a073fb10ec8a87d @inproceedings{cohen2012mars, title={Mars Weekend: A Panel and Games at the Museum of Science Boston}, author={Cohen, JP and Ding, W and Sable, J and Li, R and Stepinski, T}, booktitle={Lunar and Planetary Institute Science Conference Abstracts}, volume={43}, pages={1023}, year={2012}, abstract = {This ongoing outreach project uniquely combines the data, systems, and resources of four existing NASA funded research projects on Mars robotic navigation (MER Participating Scientist project and ExoMars Pan- Cam project), intelligent Mars data processing (AISR Crater Detection project), and Lunar mapping (LRO Par- ticipating Scientist project). The project aims to stimu- late the public excitement about Mars and Lunar science and exploration and to enrich the public with expertise developed at The Ohio State University (OSU), the University of Massachusetts Boston (UMB), and the Lunar and Planetary Institute (LPI) through our outreach partner, the Museum of Science, Boston.} } https://academictorrents.com/download/b0700675b5b7756ba6243420a9db09380a5d27b2 @inproceedings{Cohen:2011:GEF:2188812.2188820, author = {Cohen, Joseph Paul and Liu, Siyi and Ding, Wei}, title = {Genetically Enhanced Feature Selection of Discriminative Planetary Crater Image Features}, booktitle = {Proceedings of the 24th International Conference on Advances in Artificial Intelligence}, series = {AI'11}, year = {2011}, isbn = {978-3-642-25831-2}, location = {Perth, Australia}, pages = {61--71}, numpages = {11}, url = {http://dx.doi.org/10.1007/978-3-642-25832-9_7}, doi = {10.1007/978-3-642-25832-9_7}, acmid = {2188820}, publisher = {Springer-Verlag}, address = {Berlin, Heidelberg}, keywords = {bayesian classifier, crater detection, genetic algorithms, machine learning}, abstract = {Using gray-scale texture features has recently become a new trend in supervised machine learning crater detection algorithms. To provide better classification of craters in planetary images, feature subset selection is used to reduce irrelevant and redundant features. Feature selection is known to be NP-hard. To provide an efficient suboptimal solution, three genetic algorithms are proposed to use greedy selection, weighted random selection, and simulated annealing to distinguish discriminate features from indiscriminate features. A significant increase in the classification ability of a Bayesian classifier in crater detection using image texture features.} } https://academictorrents.com/download/cb1655a57dd24345c9ea7a43c5ec09e03c7a0979