Computer Sciences Commons^™

Monte Carlo Estimates Of Evaluation Metric Error And Bias: Work In Progress, Mucun Tian, Michael D. Ekstrand

Computer Science Faculty Publications and Presentations

Traditional offline evaluations of recommender systems apply metrics from machine learning and information retrieval in settings where their underlying assumptions no longer hold. This results in significant error and bias in measures of top-N recommendation performance, such as precision, recall, and nDCG. Several of the specific causes of these errors, including popularity bias and misclassified decoy items, are well-explored in the existing literature. In this paper we survey a range of work on identifying and addressing these problems, and report on our work in progress to simulate the recommender data generation and evaluation processes to quantify the extent of …

Retrieving And Recommending For The Classroom: Stakeholders, Objectives, Resources, And Users, Michael D. Ekstrand, Ion Madrazo Azpiazu, Katherine Landau Wright, Maria Soledad Pera

Computer Science Faculty Publications and Presentations

In this paper, we consider the promise and challenges of deploying recommendation and information retrieval technology to help teachers locate resources for use in classroom instruction. The classroom setting is a complex environment presenting a number of challenges for recommendation, due to its inherent multi-stakeholder nature, the multiple objectives that quality educational resources and experiences must simultaneously satisfy, and potential disconnect between the direct user of the system and the end users of the resources it provides. In this paper, we outline these challenges, highlight opportunities for new research, and describe our work in progress in this area including insights …

Inverse Tree-Olap: Definition, Complexity And First Solution, Domenico Saccà, Edoardo Serra, Alfredo Cuzzocrea

Computer Science Faculty Publications and Presentations

Count constraint is a data dependency that requires the results of given count operations on a relation to be within a certain range. By means of count constraints a new decisional problem, called the Inverse OLAP, has been recently introduced: given a flat fact table, does there exist an instance satisfying a set of given count constraints? This paper focus on a special case of Inverse OLAP, called Inverse Tree-OLAP, for which the flat fact table key is modeled by a Dimensional Fact Model (DFM) with a tree structure.

From Recommendation To Curation: When The System Becomes Your Personal Docent, Nevena Dragovic, Ion Madrazo Azpiazu, Maria Soledad Pera

Computer Science Faculty Publications and Presentations

Curation is the act of selecting, organizing, and presenting content. Some applications emulate this process by turning users into curators, while others use recommenders to select items, seldom achieving the focus or selectivity of human curators. We bridge this gap with a recommendation strategy that more closely mimics the objectives of human curators. We consider multiple data sources to enhance the recommendation process, as well as the quality and diversity of the provided suggestions. Further, we pair each suggestion with an explanation that showcases why a book was recommended with the aim of easing the decision making process for the …

Broncovote: Secure Voting System Using Ethereum’S Blockchain, Gaby G. Dagher, Praneeth Babu Marella, Matea Milojkovic, Jordan Mohler

Computer Science Faculty Publications and Presentations

Voting is a fundamental part of democratic systems; it gives individuals in a community the faculty to voice their opinion. In recent years, voter turnout has diminished while concerns regarding integrity, security, and accessibility of current voting systems have escalated. E-voting was introduced to address those concerns; however, it is not cost-effective and still requires full supervision by a central authority. The blockchain is an emerging, decentralized, and distributed technology that promises to enhance different aspects of many industries. Expanding e-voting into blockchain technology could be the solution to alleviate the present concerns in e-voting. In this paper, we propose …

2nd Fatrec Workshop: Responsible Recommendation, Toshihiro Kamishima, Pierre-Nicolas Schwab, Michael D. Ekstrand

Computer Science Faculty Publications and Presentations

The second Workshop on Responsible Recommendation (FATREC 2018) was held in conjunction with the 12th ACM Conference on Recommender Systems on October 6th, 2018 in Vancouver, Canada. This full-day workshop brought together researchers and practitioners to discuss several topics under the banner of social responsibility in recommender systems: fairness, accountability, transparency, privacy, and other ethical and social concerns.

Predicting Perceived Age: Both Language Ability And Appearance Are Important, Sarah Plane, Ariel Marvasti, Tyler Egan, Casey Kennington

Computer Science Faculty Publications and Presentations

When interacting with robots in a situated spoken dialogue setting, human dialogue partners tend to assign anthropomorphic and social characteristics to those robots. In this paper, we explore the age and educational level that human dialogue partners assign to three different robotic systems, including an un-embodied spoken dialogue system. We found that how a robot speaks is as important to human perceptions as the way the robot looks. Using the data from our experiment, we derived prosodic, emotional, and linguistic features from the participants to train and evaluate a classifier that predicts perceived intelligence, age, and education level.

A Certificateless One-Way Group Key Agreement Protocol For End-To-End Email Encryption, Jyh-Haw Yeh, Srisarguru Sridhar, Gaby G. Dagher, Hung-Min Sun, Ning Shen, Kathleen Dakota White

Computer Science Faculty Publications and Presentations

Over the years, email has evolved into one of the most widely used communication channels for both individuals and organizations. However, despite near ubiquitous use in much of the world, current information technology standards do not place emphasis on email security. Not until recently, webmail services such as Yahoo's mail and Google's gmail started to encrypt emails for privacy protection. However, the encrypted emails will be decrypted and stored in the service provider's servers. If the servers are malicious or compromised, all the stored emails can be read, copied and altered. Thus, there is a strong need for end-to-end (E2E) …

Generating Classification Rules From Training Samples, Arun D. Kulkarni

Computer Science Faculty Publications and Presentations

In this paper, we describe an algorithm to extract classification rules from training samples using fuzzy membership functions. The algorithm includes steps for generating classification rules, eliminating duplicate and conflicting rules, and ranking extracted rules. We have developed software to implement the algorithm using MATLAB scripts. As an illustration, we have used the algorithm to classify pixels in two multispectral images representing areas in New Orleans and Alaska. For each scene, we randomly selected 10 per cent of the samples from our training set data for generating an optimized rule set and used the remaining 90 per cent of samples …

Amake: Cached Builds Of Top-Level Targets, Jim Buffenbarger

Computer Science Faculty Publications and Presentations

This paper describes a software-build tool named Amake, an extension of GNU Make. Its additional features solve important problems that have, until now, only been addressed by “high-end” build tools (e.g., ClearCase and Vesta).

With a typical build tool, if a top-level target must be updated, intermediate targets must be built from sources, and then combined to build the top-level target. The enhancements described here allow a top-level target to be fetched from a shared cache, without building, or even fetching its intermediate-target dependencies. Thus, a developer’s workspace may need only contain sources and top-level targets. This reduces build time, …

On The Temporal Effects Of Mobile Blockers In Urban Millimeter-Wave Cellular Scenarios, Margarita Gapeyenko, Mikhail Gerasimenko, Andrey Samuylov, Dmitri Moltchanov, Sarabjot Singh, Mustafa Riza Akdeniz, Ehsan Aryafar, Nageen Himayat, Sergey Andreev, Yevgeni Koucheryavy

Computer Science Faculty Publications and Presentations

Millimeter-wave (mmWave) propagation is known to be severely affected by the blockage of the line-of-sight (LoS) path. In contrast to microwave systems, at shorter mmWave wavelengths such blockage can be caused by human bodies, where their mobility within environment makes wireless channel alternate between the blocked and non-blocked LoS states. Following the recent 3GPP requirements on modeling the dynamic blockage as well as the temporal consistency of the channel at mmWave frequencies, in this paper a new model for predicting the state of a user in the presence of mobile blockers for representative 3GPP scenarios is developed: urban micro cell …

Fatrec Workshop On Responsible Recommendation Proceedings, Michael Ekstrand, Amit Sharma

Computer Science Faculty Publications and Presentations

We sought with this workshop, to foster a discussion of various topics that fall under the general umbrella of responsible recommendation: ethical considerations in recommendation, bias and discrimination in recommender systems, transparency and accountability, social impact of recommenders, user privacy, and other related concerns. Our goal was to encourage the community to think about how we build and study recommender systems in a socially-responsible manner.

Recommendation systems are increasingly impacting people's decisions in different walks of life including commerce, employment, dating, health, education and governance. As the impact and scope of recommendations increase, developing systems that tackle issues of …

Spatial-Semantic Image Search By Visual Feature Synthesis, Mai Long, Hailin Jin, Chen Fang, Feng Liu

Computer Science Faculty Publications and Presentations

The performance of image retrieval has been improved tremendously in recent years through the use of deep feature representations. Most existing methods, however, aim to retrieve images that are visually similar or semantically relevant to the query, irrespective of spatial configuration. In this paper, we develop a spatial-semantic image search technology that enables users to search for images with both semantic and spatial constraints by manipulating concept text-boxes on a 2D query canvas. We train a convolutional neural network to synthesize appropriate visual features that captures the spatial-semantic constraints from the user canvas query. We directly optimize the retrieval performance …

Multispectral Image Analysis Using Decision Trees, Arun D. Kulkarni, Anmol Shrestha

Computer Science Faculty Publications and Presentations

Many machine learning algorithms have been used to classify pixels in Landsat imagery. The maximum likelihood classifier is the widely-accepted classifier. Non-parametric methods of classification include neural networks and decision trees. In this research work, we implemented decision trees using the C4.5 algorithm to classify pixels of a scene from Juneau, Alaska area obtained with Landsat 8, Operation Land Imager (OLI). One of the concerns with decision trees is that they are often over fitted with training set data, which yields less accuracy in classifying unknown data. To study the effect of overfitting, we have considered noisy training set data …

The Necst Program - Networking And Engaging In Computer Science And Information Technology Program, Jerry Alan Fails

Computer Science Faculty Publications and Presentations

In this paper, we describe the NECST Program and its innovative mentorship structure for transitioning graduate students in computer science whose undergraduate experiences may be in other disciplines. NECST employs several activities that provide the additional scaffolding to support students as they make this transition. While we believe these activities may be suited for other situations, the program helps address the unique challenges northern New Jersey faces with relation to graduate studies in computing fields.

Kidrec: Children & Recommender Systems: Workshop Co-Located With Acm Conference On Recommender Systems (Recsys 2017), Jerry Alan Fails, Maria Soledad Pera, Franca Garzotto, Mirko Gelsomini

Computer Science Faculty Publications and Presentations

The 1^st Workshop on Children and Recommender Systems (KidRec) is taking place in Como, Italy August 27^th, 2017 in conjunction with the ACM RecSys 2017 conference. The goals of the workshop are threefold: (1) discuss and identify issues related to recommender systems used by children including specific challenges and limitations, (2) discuss possible solutions to the identified challenges and plan for future research, and (3) build a community to directly work on these important issues.

Grace's Inheritance, James Noble, Andrew P. Black, Kim B. Bruce, Michael Homer, Timothy Jones

Computer Science Faculty Publications and Presentations

This article is an apologia for the design of inheritance in the Grace educational programming language: it explains how the design of Grace’s inheritance draws from inheritance mechanisms in predecessor languages, and defends that design as the best of the available alternatives. For simplicity, Grace objects are generated from object constructors, like those of Emerald, Lua, and Javascript; for familiarity, the language also provides classes and inheritance, like Simula, Smalltalk and Java. The design question we address is whether or not object constructors can provide an inheritance semantics similar to classes.

Temporal Alignment Using The Incremental Unit Framework, Casey Kennington, Ting Han, David Schlangen

Computer Science Faculty Publications and Presentations

We propose a method for temporal alignments--a precondition of meaningful fusions--of multimodal systems, using the incremental unit dialogue system framework, which gives the system flexibility in how it handles alignment: either by delaying a modality for a specified amount of time, or by revoking (i.e., backtracking) processed information so multiple information sources can be processed jointly. We evaluate our approach in an offline experiment with multimodal data and find that using the incremental framework is flexible and shows promise as a solution to the problem of temporal alignment in multimodal systems.

Panel: Influencing Culture And Curriculum Via Revolution, Amit Jain

Computer Science Faculty Publications and Presentations

The goal of this panel session is to introduce audience members to the challenges and successes of significant cultural and curricular change as enacted by awardees in the NSF program Revolutionizing Engineering and Computer Science Departments (RED). This panel will explore how organizations go about the process of cultural investigation and how they embark on culture change, using RED awardees of 2016 as the featured panelists (the second cohort). These teams are engaged in high-risk, high-trust-required activities focused on both the organizational and operational structure of their departments, and on re-envisioning engineering and computer science curricula to create professionals able …

Analysis On The Security And Use Of Password Managers, Carlos Luevanos, John Elizarraras, Khai Hirschi, Jyh-Haw Yeh

Computer Science Faculty Publications and Presentations

Cybersecurity has become one of the largest growing fields in computer science and the technology industry. Faulty security has cost the global economy immense losses. Oftentimes, the pitfall in such financial loss is due to the security of passwords. Companies and regular people alike do not do enough to enforce strict password guidelines like the NIST (National Institute of Standard Technology) recommends. When big security breaches happen, thousands to millions of passwords can be exposed and stored into files, meaning people are susceptible to dictionary and rainbow table attacks. Those are only two examples of attacks that are used to …

Capia: Cloud Assisted Privacy-Preserving Image Annotation, Yifan Tian, Yantian Hou, Jiawei Yuan

Computer Science Faculty Publications and Presentations

Using public cloud for image storage has become a prevalent trend with the rapidly increasing number of pictures generated by various devices. For example, today's most smartphones and tablets synchronize photo albums with cloud storage platforms. However, as many images contain sensitive information, such as personal identities and financial data, it is concerning to upload images to cloud storage. To eliminate such privacy concerns in cloud storage while keeping decent data management and search features, a spectrum of keywords-based searchable encryption (SE) schemes have been proposed in the past decade. Unfortunately, there is a fundamental gap remains open for their …

Silence, Please!: Interrupting In-Car Phone Conversations, Soledad López Gambino, Casey Kennington, David Schlangen

Computer Science Faculty Publications and Presentations

Holding phone conversations while driving is dangerous not only because it occupies the hands, but also because it requires attention. Where driver and passenger can adapt their conversational behavior to the demands of the situation, and e.g. interrupt themselves when more attention is needed, an interlocutor on the phone cannot adjust as easily. We present a dialogue assistant which acts as 'bystander' in phone conversations between a driver and an interlocutor, interrupting them and temporarily cutting the line during potentially dangerous situations. The assistant also informs both conversation partners when the line has been cut, as well as when it …

A Graphical Digital Personal Assistant That Grounds And Learns Autonomously, Casey Kennington, Aprajita Shukla

Computer Science Faculty Publications and Presentations

We present a speech-driven digital personal assistant that is robust despite little or no training data and autonomously improves as it interacts with users. The system is able to establish and build common ground between itself and users by signaling understanding and by learning a mapping via interaction between the words that users actually speak and the system actions. We evaluated our system with real users and found an overall positive response. We further show through objective measures that autonomous learning improves performance in a simple itinerary filling task.

Edos: Edge Assisted Offloading System For Mobile Devices, Hank H. Harvey, Ying Mao, Yantian Hou, Bo Sheng

Computer Science Faculty Publications and Presentations

Offloading resource-intensive jobs to the cloud and nearby users is a promising approach to enhance mobile devices. This paper investigates a hybrid offloading system that takes both infrastructure-based networks and Ad-hoc networks into the scope. Specifically, we propose EDOS, an edge assisted offloading system that consists of two major components, an Edge Assistant (EA) and Offload Agent (OA). EA runs on the routers/towers to manage registered remote cloud servers and local service providers and OA operates on the users’ devices to discover the services in proximity. We present the system with a suite of protocols to collect the potential service …

Coms: Customer Oriented Migration Service, Kai Huang, Xing Gao, Fengwei Zhang, Jidong Xiao

Computer Science Faculty Publications and Presentations

Virtual machine live migration has been studied for more than a decade, and this technique has been implemented in various commercial hypervisors. However, currently in the cloud environment, virtual machine migration is initiated by system administrators. Cloud customers have no say on this: They can not initiate a migration, and they do not even know whether or not their virtual machines have been migrated. In this paper, we propose the COMS framework, which is short for "Customer Oriented Migration Service". COMS gives more control to cloud customers so that migration becomes a service option and customers are more aware of …

Development Of An Intelligent Equipment Lock Management System With Rfid Technology, Yeh-Cheng Chen, C. N. Chu, H. M. Sun, Jyh-Haw Yeh, Ruey-Shun Chen, Chorng-Shiuh Koong

Computer Science Faculty Publications and Presentations

The equipment lock has been an important tool for the power company to protect the electricity metering equipment. however, the conventional equipment lock has two potential problems: vandalism and counterfeiting. To fulfill the control and track the potential illegal behavior, the human labor and paper are required to proceed with related operations, resulting in the consumption of a large amount of human resources and maintenance costs.

This study focused on the design of RFID technology applied to the traditional equipment lock, which, through the mobile and electronic technology, strengthens the management/operating convenience of the lock and provides the solutions for …

Fast And Adaptive Indexing Of Multi-Dimensional Observational Data, Sheng Wang, David Maier, Beng Chin Ooi

Computer Science Faculty Publications and Presentations

Sensing devices generate tremendous amounts of data each day, which include large quantities of multi-dimensional measurements. These data are expected to be immediately available for real-time analytics as they are streamed into storage. Such scenarios pose challenges to state-of-the-art indexing methods, as they must not only support efficient queries but also frequent updates. We propose here a novel indexing method that ingests multi-dimensional observational data in real time. This method primarily guarantees extremely high throughput for data ingestion, while it can be continuously refined in the background to improve query efficiency. Instead of representing collections of points using Minimal Bounding …

Rapid Retrieval Of Lung Nodule Ct Images Based On Hashing And Pruning Methods, Lian Pan, Yan Qiang, Jie Yuan, Lidong Wu

Computer Science Faculty Publications and Presentations

The similarity-based retrieval of lung nodule computed tomography (CT) images is an important task in the computer-aided diagnosis of lung lesions. It can provide similar clinical cases for physicians and help them make reliable clinical diagnostic decisions. However, when handling large-scale lung images with a general-purpose computer, traditional image retrieval methods may not be efficient. In this paper, a new retrieval framework based on a hashing method for lung nodule CT images is proposed. This method can translate high-dimensional image features into a compact hash code, so the retrieval time and required memory space can be reduced greatly. Moreover, a …

Active Object Localization In Visual Situations, Max H. Quinn, Anthony Rhodes, Melanie Mitchell

Computer Science Faculty Publications and Presentations

—We describe a method for performing active localization of objects in instances of visual situations. A visual situation is an abstract concept—e.g., “a boxing match”, “a birthday party”, “walking the dog”, “waiting for a bus”—whose image instantiations are linked more by their common spatial and semantic structure than by low-level visual similarity. Our system combines given and learned knowledge of the structure of a particular situation, and adapts that knowledge to a new situation instance as it actively searches for objects. More specifically, the system learns a set of probability distributions describing spatial and other relationships among relevant objects. The …

A Framework For Measuring Security As A System Property In Cyberphysical Systems, Janusz Zalewski, Ingrid A. Buckley, Bogdan Czejdo, Steven Drager, Andrew J. Kornecki, Nary Subramanian

Computer Science Faculty Publications and Presentations

This paper addresses the challenge of measuring security, understood as a system property, of cyberphysical systems, in the category of similar properties, such as safety and reliability. First, it attempts to define precisely what security, as a system property, really is. Then, an application context is presented, in terms of an attack surface in cyberphysical systems. Contemporary approaches related to the principles of measuring software properties are also discussed, with emphasis on building models. These concepts are illustrated in several case studies, based on previous work of the authors, to conduct experimental security measurements.