In the world of database education, SQL (Structured Query Language) is often the first and crucial step toward developing data analysis and manipulation skills. As the world moves on to data-driven technologies and businesses, the need to educate students in writing accurate and efficient SQL queries has become paramount. Traditional SQL evaluation modes often rely on limited, subjective, and labor-intensive manual grading, which impedes the integration of practical assignments into the curriculum. This poster introduces SQLearn, an innovative automated assessment tool for SQL education. We aim to build a comprehensive platform that addresses submission, evaluation, and review needs amongst students and educators. Here we highlight our assessment approach which breaks down student-submitted queries into Abstract Syntax Trees (AST) and uses cosine similarity to evaluate them. Experimental results show that the proposed approach is effective, not only in binary grading of queries but also in assigning partial grades. The tool also offers an interactive platform to submit and receive feedback, enabling students to refine their SQL skills and gain insights into query structure and optimization. By automating the assessment process, educators can focus on refining the curriculum and channel more time into instruction and research.

Machine learning, a scientific model, has been developed over the years for predictions and is now very advanced with modern technology of high performance computing. It is widely used in classification and prediction problems. While using Machine Learning for regression we may come across datasets that have large amount of missing values, which have significant impact on the prediction results. The BRanching Artificial Neural Ensemble (BRANE), a machine learning algorithm, has been developed and proposed in this paper to address missing values in attributes. The proposed algorithm is an extension of Ensemble approach and utilizes one multilayer perceptron for data points, one multilayer perceptron for missing values as a flag entity, and one multilayer perceptron to combine the experts and predict the final outcome. Dataset to train and test this model has been taken from Zillow Competition from Kaggle database and is implemented in Python.

Cloud Computing leverages Hadoop framework for processing BigData in parallel. Hadoop has certain limitations that could be exploited to execute the job efficiently. These limitations are mostly because of data locality in the cluster, jobs and tasks scheduling, and resource allocations in Hadoop. Efficient resource allocation remains a challenge in Cloud Computing MapReduce platforms. We propose H2Hadoop, which is an enhanced Hadoop architecture that reduces the computation cost associated with BigData analysis. The proposed architecture also addresses the issue of resource allocation in native Hadoop. H2Hadoop provides a better solution for “text data”, such as finding DNA sequence and the motif of a DNA sequence. Also, H2Hadoop provides an efficient Data Mining approach for Cloud Computing environments. H2Hadoop architecture leverages on NameNode's ability to assign jobs to the TaskTrakers (DataNodes) within the cluster. By adding control features to the NameNode, H2Hadoop can intelligently direct and assign tasks to the DataNodes that contain the required data without sending the job to the whole cluster. Comparing with native Hadoop, H2Hadoop reduces CPU time, number of read operations, and another Hadoop factors.

This paper discusses part of the main work in field of data science, mining and analytics. Family of algorithms is developed to predict the educational relevance of individuals' talents through lens of personality features (unstructured and semi-structured) and academic/career data. This paper presents progress of results in Good Fit Students (GFS) algorithms and math construct. This work addresses the problems of poor academic performances, low retention rates, drop outs, school transfers, costly readmissions, poor job performances, early job transfers and inefficient utilization/consideration of natural talents. GFS builds a framework and algorithms by correlating and blending social networking personality traits data with academic and career data. The results are promising at this stage of research and show improved predictions and relevant probabilities. Future work is focused on improving the results with more data and adding few more algorithms to the main research/framework.

With the advances in computing power, high-performance computing (HPC) platforms have had an impact on not only scientific research in advanced organizations but also computer science curriculum in the educational community. For example, multicore programming and parallel systems are highly desired courses in the computer science major. However, the high cost of HPC equipment and maintenance makes it hard to be adapted into a conventional computer science curriculum. Specifically, teaching-oriented institutions cannot afford an HPC system due to the high cost, lack of experience, and smaller research infrastructure. The main objective of this article is to present an affordable and easy-to-use high-performance cluster system for teaching-oriented computer science curriculums. In order to address this, we have designed and implemented an affordable high-performance cluster system based on the PlayStation 3 (PS3). For the performance evaluation of the PS3 cluster, we conducted a benchmarking test, that is, matrix multiplication, with different numbers of synergistic processing elements (SPEs) and nodes. As a result, it was concluded that the PS3Cluster provides enough computing power as an HPC for computer science courses, while the total cost is less than 10% of an existing cluster system on the market that has similar performance. In addition, the implemented PS3Cluster system has been used for computer science courses, such as Parallel and Distributed Databases and Parallel Programming.

We study the problem of predicting home locations of Twitter users using contents of their tweet messages. Using three probability models for locations, we compare both the Gaussian Mixture Model (GMM) and the Maximum Likelihood Estimation (MLE). In addition, we propose two novel unsupervised methods based on the notions of Non-Localness and Geometric-Localness to prune noisy data from tweet messages. In the experiments, our unsupervised approach improves the baselines significantly and shows comparable results with the supervised state-of-the-art method. For 5,113 Twitter users in the test set, on average, our approach with only 250 selected local words or less is able to predict their home locations (within 100 miles) with the accuracy of 0.499, or has 509.3 miles of average error distance at best.

Wireless Capsule Endoscopy (WCE) is a painless and noninvasive technique that allows physicians to visualize the entire small bowel. Before WCE was introduced, examining the entire small bowel was impossible without surgical procedure. Although WCE is a technology breakthrough, the manual video diagnosis session is time consuming and is prone to human cognition errors. Therefore, gastroenterologists urge computer vision researchers to develop computer-aided diagnosis systems to assist the review session. In this paper, we would like to present an ulcer detection scheme that identifies ulcers in WCE video. A saliency map is created by means of channel mixer to highlight suspicious regions. Once the suspicious regions are identified, we extract textural features along the contour and classify them using a trained classifier for ulcer validation.

Matching two images with similar contents is one of the most fundamental tasks in image processing. Due to its importance, in recent years, many novel techniques have been proposed with great successes. Toward this effort, in this paper, we propose a radically different idea by bridging two seemingly unrelated fields - Image Processing and Biology - i.e., we propose to use the popular gene sequence alignment algorithm in Biology, BLAST, in determining the similarity between images. In this proposal, we map image features to a sequence of gene alphabets (e.g., A, C, G, and T in DNA, or 23 letters in protein) to utilize a wealth of advanced algorithms and tools in BLAST. Under the new idea, in particular, we study various image features and gene sequence generation methods that impact the accuracy and performance in matching similar images. Our proposal, termed as BLASTed Image Matching (BIM), is empirically validated using real data sets. Our work can be viewed as the ¿first¿ step toward bridging Image Processing and Biology fields in the application of the well-studied image matching problem.

We present our vision and preliminary design toward Web-crawled academic video search engine, named as LeeDeo, that can search, crawl, archive, index, and browse ldquoacademicrdquo videos from the Web. Our proposal differs from existing general-purpose search engines such as Google or MSN whose focus is on the search of textual HTML documents or metadata of multimedia objects. Similarly, our proposal also differs from existing academic bibliographic search engines such as CiteSeer, arXiv, or Google Scholar whose focus is on the search and analysis of PDF or PS documents of academic papers. As desiderata of such an academic video search engine, we discuss various issues as follows: (1) Crawling: how to crawl, identify, and download academic videos from the Web? (2) Classification: how to determine the so-called academic videos from the rest? (3) Extraction: how to extract metadata and transcripts from the classified videos? (4) Indexing: how to build indexes for search engines? and (5) Interface: how to provide interface for efficient browse and search of academic videos?

In this work, we propose new graph-based data model and indexing to organize and manage video data. To consider spatial and temporal characteristics of video, we introduce a new graph-based data model called spatio-temporal region graph (STRG). Unlike existing graph-based data structures which provide only spatial features, the proposed STRG further provides temporal features, which represent temporal relationships among spatial objects. The STRG is decomposed into its subgraphs object graphs (OGs) and background graphs (BGs). In addition, a new distance measure, called extended graph edit distance (EGED), is introduced in metric space for matching and indexing. Based on clustering and EGED, we propose a new indexing method STRG-index, which is faster and more accurate. We compare the STRG-Index with the M-tree, which is a popular tree-based indexing method for multimedia data. The STRG-index outperforms the M-tree in terms of cost and speed

We propose a new graph-based data structure, called Spatio Temporal Region Graph (STRG) which can represent the content of video sequence. Unlike existing ones which consider mainly spatial information in the frame level of video, the proposed STRG is able to formulate its temporal information in the video level additionally. After an STRG is constructed from a given video sequence, it is decomposed into its subgraphs called Object Graphs (OGs), which represent the temporal characteristics of video objects. For unsupervised learning, we cluster similar OGs into a group, in which we need to match two OGs. For this graph matching, we introduce a new distance measure, called Extended Graph Edit Distance (EGED), which can handle the temporal characteristics of OGs. For actual clustering, we exploit Expectation Maximization (EM) with EGED. The experiments have been conducted on real video streams, and their results show the effectiveness and robustness of the proposed schemes.

Colonoscopy is the accepted screening method for detection of colorectal cancer or its precursor lesions, colorectal polyps. Indeed, colonoscopy has contributed to a decline in the number of colorectal cancer related deaths. However, not all cancers or large polyps are detected at the time of colonoscopy, and methods to investigate why this occurs are needed. We present a new computer-based method that allows automated measurement of a number of metrics that likely reflect the quality of the colonoscopic procedure. The method is based on analysis of a digitized video file created during colonoscopy, and produces information regarding insertion time, withdrawal time, images at the time of maximal intubation, the time and ratio of clear versus blurred or non-informative images, and a first estimate of effort performed by the endoscopist. As these metrics can be obtained automatically, our method allows future quality control in the day-to-day medical practice setting on a large scale. In addition, our method can be adapted to other healthcare procedures. Last but not least, our method may be useful to assess progress during colonoscopy training, or as part of endoscopic skills assessment evaluations.

In this paper, we present scenario based dynamic video abstractions using graph matching. Our approach has two main components: multi-level scenario generations and dynamic video abstractions. Multi-level scenarios are generated by a graph-based video segmentation and a hierarchy of the segments. Dynamic video abstractions are accomplished by accessing the generated hierarchy level by level. The first step in the proposed approach is to segment a video into shots using Region Adjacency Graph (RAG). A RAG expresses spatial relationships among segmented regions of a frame. To measure the similarity between two consecutive RAGs, we propose a new similarity measure, called Graph Similarity Measure (GSM). Next, we construct a tree structure called scene tree based on the correlation between the detected shots. The correlation is computed by the GSM since it considers the relations between the detected shots properly. Multi-level scenarios which provide various levels of video abstractions are generated using the constructed scene tree. We provide two types of abstraction using multi-level scenarios: multi-level highlights and multi-length summarizations. Multi-level highlights are made by entire shots in each scenario level. To summarize a video in various lengths, we select key frames by considering temporal relationships among RAGs computed by the GSM. We have developed a system, called Automatic Video Analysis System (AVAS), by integrating the proposed techniques to show their effectiveness. The experimental results show that the proposed techniques are promising.

In this paper, we propose new graph-based data structure and indexing to organize and retrieve video data. Several researches have shown that a graph can be a better candidate for modeling semantically rich and complicated multimedia data. However, there are few methods that consider the temporal feature of video data, which is a distinguishable and representative characteristic when compared with other multimedia (i.e., images). In order to consider the temporal feature effectively and efficiently, we propose a new graph-based data structure called Spatio-Temporal Region Graph (STRG). Unlike existing graph-based data structures which provide only spatial features, the proposed STRG further provides temporal features, which represent temporal relationships among spatial objects. The STRG is decomposed into its subgraphs in which redundant subgraphs are eliminated to reduce the index size and search time, because the computational complexity of graph matching (subgraph isomorphism) is NP-complete. In addition, a new distance measure, called Extended Graph Edit Distance (EGED), is introduced in both non-metric and metric spaces for matching and indexing respectively. Based on STRG and EGED, we propose a new indexing method STRG-Index, which is faster and more accurate since it uses tree structure and clustering algorithm. We compare the STRG-Index with the M-tree, which is a popular tree-based indexing method for multimedia data. The STRG-Index outperforms the M-tree for various query loads in terms of cost and speed.