Computer Engineering Commons^™

The 2018 Nvidia Ai City Challenge, Milind Naphade, Ming-Ching Chang, Anuj Sharma, David Anastasiu, Vamsi Jagarlamudi, Pranamesh Chakraborty, Tingting Huang, Shuo Wang, Ming-Yu Liu, Rama Chellappa, Jenq-Neng Hwang, Siwei Lyu

Faculty Publications

The NVIDIA AI City Challenge has been created to accelerate intelligent video analysis that helps make cities smarter and safer. With millions of traffic video cameras acting as sensors around the world, there is a significant opportunity for real-time and batch analysis of these videos to provide actionable insights. These insights will benefit a wide variety of agencies, from traffic control to public safety. The second edition of the NVIDIA AI City Challenge, being organized as a CVPR workshop, provided a forum to more than 70 academic and industrial research teams to compete and solve real-world problems using traffic camera …

A Route Less Traveled: Principals’ Perceptions Of Alternative Licensed Cte Teachers, Scott R. Bartholomew, Emma P. Bullock, Louis S. Nadelson

Faculty Publications

The shortage of teachers prepared to teach career and technical education (CTE) courses, or willing to work in certain locations (e.g. inner city, rural), has motivated the desire to explore solutions such as alternative routes to teacher licensure (ARL). Most ARL programs bypass colleges of education and provide a different approach to preparing individuals to teach, leaving many to wonder about the quality and knowledge of these teachers. Specific areas, such as CTE, have seen a large influx of ARL teachers in recent years. We sought to determine school principals’ perceptions of ARL CTE teachers. We found principal support for …

Social Recommendations For Personalized Fitness Assistance, Saumil Dharia, Magdalini Eirinaki, Vijesh Jain, Jvalant Patel, Iraklis Varlamis, Jainikkumar Vora, Rizen Yamauchi

Faculty Publications

Wearable technology allows users to monitor their activity and pursue a healthy lifestyle through the use of embedded sensors. Such wearables usually connect to a mobile application that allows them to set their profile and keep track of their goals. However, due to the relatively “high maintenance” of such applications, where a significant amount of user feedback is expected, users who are very busy, or not as self-motivated, stop using them after a while. It has been shown that accountability improves commitment to an exercise routine. In this work, we present the PRO-Fit framework, a personalized fitness assistant aiming at …

A Bayesian Network Based Adaptability Design Of Product Structures For Function Evolution, Shaobo Li, Yongming Wu, Yan-Xia Xu, Jie Hu, Jianjun Hu

Faculty Publications

Structure adaptability design is critical for function evolution in product families, in which many structural and functional design factors are intertwined together with manufacturing cost, customer satisfaction, and final market sales. How to achieve a delicate balance among all of these factors to maximize the market performance of the product is too complicated to address based on traditional domain experts’ knowledge or some ad hoc heuristics. Here, we propose a quantitative product evolution design model that is based on Bayesian networks to model the dynamic relationship between customer needs and product structure design. In our model, all of the structural …

Aspie: A Framework For Active Sensing And Processing Of Complex Events In The Internet Of Manufacturing Things, Shaobo Li, Weixing Chen, Jie Hu, Jianjun Hu

Faculty Publications

Rapid perception and processing of critical monitoring events are essential to ensure healthy operation of Internet of Manufacturing Things (IoMT)-based manufacturing processes. In this paper, we proposed a framework (active sensing and processing architecture (ASPIE)) for active sensing and processing of critical events in IoMT-based manufacturing based on the characteristics of IoMT architecture as well as its perception model. A relation model of complex events in manufacturing processes, together with related operators and unified XML-based semantic definitions, are developed to effectively process the complex event big data. A template based processing method for complex events is further introduced to conduct …

A Novel Evolutionary Algorithm For Designing Robust Analog Filters, Shaobo Li, Wang Zou, Jianjun Hu

Faculty Publications

Designing robust circuits that withstand environmental perturbation and device degradation is critical for many applications. Traditional robust circuit design is mainly done by tuning parameters to improve system robustness. However, the topological structure of a system may set a limit on the robustness achievable through parameter tuning. This paper proposes a new evolutionary algorithm for robust design that exploits the open-ended topological search capability of genetic programming (GP) coupled with bond graph modeling. We applied our GP-based robust design (GPRD) algorithm to evolve robust lowpass and highpass analog filters. Compared with a traditional robust design approach based on a state-of-the-art …

Patent Keyword Extraction Algorithm Based On Distributed Representation For Patent Classification, Jie Hu, Shaobo Li, Yong Yao, Liya Yu, Guanci Yang, Jianjun Hu

Faculty Publications

Many text mining tasks such as text retrieval, text summarization, and text comparisons depend on the extraction of representative keywords from the main text. Most existing keyword extraction algorithms are based on discrete bag-of-words type of word representation of the text. In this paper, we propose a patent keyword extraction algorithm (PKEA) based on the distributed Skip-gram model for patent classification. We also develop a set of quantitative performance measures for keyword extraction evaluation based on information gain and cross-validation, based on Support Vector Machine (SVM) classification, which are valuable when human-annotated keywords are not available. We used a standard …

A Hierarchical Feature Extraction Model For Multi-Label Mechanical Patent Classification, Jie Hu, Shaobo Li, Jianjun Hu, Guanci Yang

Faculty Publications

Various studies have focused on feature extraction methods for automatic patent classification in recent years. However, most of these approaches are based on the knowledge from experts in related domains. Here we propose a hierarchical feature extraction model (HFEM) for multi-label mechanical patent classification, which is able to capture both local features of phrases as well as global and temporal semantics. First, a n-gram feature extractor based on convolutional neural networks (CNNs) is designed to extract salient local lexical-level features. Next, a long dependency feature extraction model based on the bidirectional long–short-term memory (BiLSTM) neural network model is proposed to …

A Survey Of Digital Systems Curriculum And Pedagogy In Electrical And Computer Engineering Programs, Hector A. Ochoa, Mukul V. Shirvaikar

Faculty Publications

Digital Systems is one of the basic foundational courses in Electrical and Computer Engineering. One of the challenges in designing and modifying the curriculum for the course is the fast pace of technology change in the area. TTL chips that were in vogue with students building physical circuits, have given way to new paradigms like FPGA based synthesis with hardware description languages such as VHDL. However, updating a course is not as simple as just changing the book, and changing the syllabus. A large amount of work needs to be done in terms of selecting the book that will accommodate …

Recommender Systems For Large-Scale Social Networks: A Review Of Challenges And Solutions, Magdalini Eirinaki, Jerry Gao, Iraklis Varlamis, Konstantinos Tserpes

Faculty Publications

Social networks have become very important for networking, communications, and content sharing. Social networking applications generate a huge amount of data on a daily basis and social networks constitute a growing field of research, because of the heterogeneity of data and structures formed in them, and their size and dynamics. When this wealth of data is leveraged by recommender systems, the resulting coupling can help address interesting problems related to social engagement, member recruitment, and friend recommendations.In this work we review the various facets of large-scale social recommender systems, summarizing the challenges and interesting problems and discussing some of the …

A Data-Driven Approach For Detecting Autism Spectrum Disorders, Manika Kapoor, David Anastasiu

Faculty Publications

No abstract provided.

Patient Friendly Kidney Function Screening, Ragwa El Sayed, Rathna Ramesh, Alessandro Bellofiore, David Anastasiu, Melinda Simon

Faculty Publications

No abstract provided.

Teaching With Jupyter In-Class Activities: Lessons Learned And Next Steps, David Anastasiu

Faculty Publications

No abstract provided.

Parallel Cosine Nearest Neighbor Graph Construction, David Anastasiu, George Karypis

Faculty Publications

The nearest neighbor graph is an important structure in many data mining methods for clustering, advertising, recommender systems, and outlier detection. Constructing the graph requires computing up to n2 similarities for a set of n objects. This high complexity has led researchers to seek approximate methods, which find many but not all of the nearest neighbors. In contrast, we leverage shared memory parallelism and recent advances in similarity joins to solve the problem exactly. Our method considers all pairs of potential neighbors but quickly filters pairs that could not be a part of the nearest neighbor graph, based on similarity …

Document Clustering, David Anastasiu, Andrea Tagarelli

Faculty Publications

In a world flooded with information, document clustering is an important tool that can help categorize and extract insight from text collections. It works by grouping similar documents, while simultaneously discriminating between groups. In this article, we provide a brief overview of the principal techniques used to cluster documents, and introduce a series of novel deep-learning based methods recently designed for the document clustering task. In our overview, we point the reader to salient works that can provide a deeper understanding of the topics discussed.

Reconstructing Yeasts Phylogenies And Ancestors From Whole Genome Data, Bing Feng, Yu Ling, Lingxi Zhou, Roufan Xia, Fei Hu, Chao Liu

Faculty Publications

Phylogenetic studies aim to discover evolutionary relationships and histories. These studies are based on similarities of morphological characters and molecular sequences. Currently, widely accepted phylogenetic approaches are based on multiple sequence alignments, which analyze shared gene datasets and concatenate/coalesce these results to a final phylogeny with maximum support. However, these approaches still have limitations, and often have conflicting results with each other. Reconstructing ancestral genomes helps us understand mechanisms and corresponding consequences of evolution. Most existing genome level phylogeny and ancestor reconstruction methods can only process simplified real genome datasets or simulated datasets with identical genome content, unique genome markers, …

Efficient Identification Of Tanimoto Nearest Neighbors; All Pairs Similarity Search Using The Extended Jaccard Coefficient, David Anastasiu, George Karypis

Faculty Publications

Tanimoto, or extended Jaccard, is an important similarity measure which has seen prominent use in fields such as data mining and chemoinformatics. Many of the existing state-of-the-art methods for market basket analysis, plagiarism and anomaly detection, compound database search, and ligand-based virtual screening rely heavily on identifying Tanimoto nearest neighbors. Given the rapidly increasing size of data that must be analyzed, new algorithms are needed that can speed up nearest neighbor search, while at the same time providing reliable results. While many search algorithms address the complexity of the task by retrieving only some of the nearest neighbors, we propose …

Improving Rolling Bearing Fault Diagnosis By Ds Evidence Theory Based Fusion Model, Xuemei Yao, Shaobo Li, Jianjun Hu

Faculty Publications

Rolling bearing plays an important role in rotating machinery and its working condition directly affects the equipment efficiency. While dozens of methods have been proposed for real-time bearing fault diagnosis and monitoring, the fault classification accuracy of existing algorithms is still not satisfactory. This work presents a novel algorithm fusion model based on principal component analysis and Dempster-Shafer evidence theory for rolling bearing fault diagnosis. It combines the advantages of the learning vector quantization (LVQ) neural network model and the decision tree model. Experiments under three different spinning bearing speeds and two different crack sizes show that our fusion model …

Formal Performance Guarantees For An Approach To Human In The Loop Robot Missions, Damian Lyons, Ron Arkin, Shu Jiang, Matt O'Brien, Feng Tang, Peng Tang

Faculty Publications

Abstract— A key challenge in the automatic verification of robot mission software, especially critical mission software, is to be able to effectively model the performance of a human operator and factor that into the formal performance guarantees for the mission. We present a novel approach to modelling the skill level of the operator and integrating it into automatic verification using a linear Gaussians model parameterized by experimental calibration. Our approach allows us to model different skill levels directly in terms of the behavior of the lumped, robot plus operator, system.

Using MissionLab and VIPARS (a behavior-based robot mission verification …

A Framework For Recommendation Of Highly Popular News Lacking Social Feedback, Nuno Moniz, Luís Torgo, Magdalini Eirinaki, Paula Branco

Faculty Publications

Social media is rapidly becoming the main source of news consumption for users, raising significant challenges to news aggregation and recommendation tasks. One of these challenges concerns the recommendation of very recent news. To tackle this problem, approaches to the prediction of news popularity have been proposed. In this paper, we study the task of predicting news popularity upon their publication, when social feedback is unavailable or scarce, and to use such predictions to produce news rankings. Unlike previous work, we focus on accurately predicting highly popular news. Such cases are rare, causing known issues for standard prediction models and …

Improvement Of Phylogenetic Method To Analyze Compositional Heterogeneity, Zehua Zhang, Kecheng Guo, Gaofeng Pan, Jijun Tang, Fei Guo

Faculty Publications

Background: Phylogenetic analysis is a key way to understand current research in the biological processes and detect theory in evolution of natural selection. The evolutionary relationship between species is generally reflected in the form of phylogenetic trees. Many methods for constructing phylogenetic trees, are based on the optimization criteria. We extract the biological data via modeling features, and then compare these characteristics to study the biological evolution between species.

Results: Here, we use maximum likelihood and Bayesian inference method to establish phylogenetic trees; multi-chain Markov chain Monte Carlo sampling method can be used to select optimal phylogenetic tree, resolving local …

Robust Classification Of City Roadway Objects For Traffic Related Applications, Niveditha Bhandary, Charles Mackay, Alex Richards, Ji Tong, David Anastasiu

Faculty Publications

The increasing prevalence of video data, particularly from traffic and surveillance cameras, is accompanied by a growing need for improved object detection, tracking, and classification techniques. In order to encourage development in this area, the AI City Challenge, sponsored by IEEE Smart World and NVIDIA, cultivated a competitive environment in which teams from all over the world sought to demonstrate the effectiveness of their models after training and testing on a common dataset of 114,766 unique traffic camera keyframes. Models were constructed for two distinct purposes; track 1 designs addressed object detection, localization and classification, while track 2 designs aimed …

The Nvidia Ai City Challenge, Milind Naphade, David Anastasiu, Anuj Sharma, Vamsi Jagrlamudi, Hyeran Jeon, Kaikai Liu, Ming-Ching Chang, Siwei Lyu, Zeyu Gao

Faculty Publications

Web image analysis has witnessed an AI renaissance. The ILSVRC benchmark has been instrumental in providing a corpus and standardized evaluation. The NVIDIA AI City Challenge is envisioned to provide similar impetus to the analysis of image and video data that helps make cities smarter and safer. In its first year, this Challenge has focused on traffic video data. While millions of traffic video cameras around the world capture data, albeit low-quality, very little automated analysis and value creation results. Lack of labeled data, and trained models that can be deployed at the edge of the city fabric, ensure that …

An Ameliorated Prediction Of Drug–Target Interactions Based On Multi-Scale Discrete Wavelet Transform And Network Features, Cong Shen, Yijie Ding, Jijun Tang, Xinying Xu, Fei Guo

Faculty Publications

The prediction of drug–target interactions (DTIs) via computational technology plays a crucial role in reducing the experimental cost. A variety of state-of-the-art methods have been proposed to improve the accuracy of DTI predictions. In this paper, we propose a kind of drug–target interactions predictor adopting multi-scale discrete wavelet transform and network features (named as DAWN) in order to solve the DTIs prediction problem. We encode the drug molecule by a substructure fingerprint with a dictionary of substructure patterns. Simultaneously, we apply the discrete wavelet transform (DWT) to extract features from target sequences. Then, we concatenate and normalize the target, drug, …

Optimal Constrained Wireless Emergency Network Antenna Placement, Swapnil Gaikwad, David Anastasiu

Faculty Publications

Communication is paramount, especially during a natural disaster or other emergency. Even when traditional lines of communication become unavailable, emergency response teams must be able to communicate with each other and the outside world. To facilitate this need, major cities across the United States are deploying wireless emergency networks (WENs) that serve as a secure communication channel between emergency response points (police stations, shelters, food banks, hospitals, etc.) and the outside world. An important question when designing such networks is identifying the locations within the city where access points (APs) should be placed to construct a reliable WEN. We propose …

An Ensemble Deep Convolutional Neural Network Model With Improved D-S Evidence Fusion For Bearing Fault Diagnosis, Shaobo Li, Guokai Liu, Xianghong Tang, Jianguang Lu, Jianjun Hu

Faculty Publications

Intelligent machine health monitoring and fault diagnosis are becoming increasingly important for modern manufacturing industries. Current fault diagnosis approaches mostly depend on expert-designed features for building prediction models. In this paper, we proposed IDSCNN, a novel bearing fault diagnosis algorithm based on ensemble deep convolutional neural networks and an improved Dempster–Shafer theory based evidence fusion. The convolutional neural networks take the root mean square (RMS) maps from the FFT (Fast Fourier Transformation) features of the vibration signals from two sensors as inputs. The improved D-S evidence theory is implemented via distance matrix from evidences and modified Gini Index. Extensive evaluations …

An Advanced Multi-Sensor Acousto-Ultrasonic Structural Health Monitoring System: Development And Aerospace Demonstration, Joel Smithard, Nik Rajic, Stephen Van Der Velden, Patrick Norman, Cedric Rosalie, Steve Galea, Hanfei Mei, Bin Lin, Victor Giurgiutiu

Faculty Publications

A key longstanding objective of the Structural Health Monitoring (SHM) research community is to enable the embedment of SHM systems in high value assets like aircraft to provide on-demand damage detection and evaluation. As against traditional non-destructive inspection hardware, embedded SHM systems must be compact, lightweight, low-power and sufficiently robust to survive exposure to severe in-flight operating conditions. Typical Commercial-Off-The-Shelf (COTS) systems can be bulky, costly and are often inflexible in their configuration and/or scalability, which militates against in-service deployment. Advances in electronics have resulted in ever smaller, cheaper and more reliable components that facilitate the development of compact and …

Custom 3d Printer And Resin For 18 Μm × 20 Μm Mi- Crofluidic Flow Channels, Hua Gong, Bryce P. Bickham, Adam T. Woolley, Gregory P. Nordin

Faculty Publications

While there is great interest in 3D printing for microfluidic device fabrication, to-date the achieved feature sizes have not been in the truly microfluidic regime (μm). In this paper we demonstrate that a custom Digital Light Processor stereolithographic (DLP-SLA) 3D printer and a specifically-designed, low cost, custom resin can readily achieve flow channel cross sections as small as 18 μm × 20 μm. Our 3D printer has a projected image plane resolution of 7.6 μm and uses a 385 nm LED, which dramatically increases the available selection of UV absorbers for resin formulation compared to 3D printers with 405 nm …

An Approach To Robust Homing With Stereovision, Fuqiang Fu, Damian Lyons

Faculty Publications

Visual Homing is a bioinspired approach to robot navigation which can be fast and uses few assumptions. However, visual homing in a cluttered and unstructured outdoor environment offers several challenges to homing methods that have been developed for primarily indoor environments. One issue is that any current image during homing may be tilted with respect to the home image. The second is that moving through a cluttered scene during homing may cause obstacles to interfere between the home scene and location and the current scene and location. In this paper, we introduce a robust method to improve a previous developed …

Analysis Of Co-Associated Transcription Factors Via Ordered Adjacency Differences On Motif Distribution, Gaofeng Pan, Jijun Tang, Fei Guo

Faculty Publications

Transcription factors (TFs) binding to specific DNA sequences or motifs, are elementary to the regulation of transcription. The gene is regulated by a combination of TFs in close proximity. Analysis of co-TFs is an important problem in understanding the mechanism of transcriptional regulation. Recently, ChIP-seq in mapping TF provides a large amount of experimental data to analyze co-TFs. Several studies show that if two TFs are co-associated, the relative distance between TFs exhibits a peak-like distribution. In order to analyze co-TFs, we develop a novel method to evaluate the associated situation between TFs. We design an adjacency score based on …