Dissertation Defense

The Lightweight Virtual File System

Navid Golpayegani

10:00-12:00 Thursday, 20 July 2017, ITE 325, UMBC

A data center today is responsible for safely managing big data volumes and balancing the complex needs between data producers and consumers. This balance often involves reconciling the needs of easy access and rapid retrieval in ways desired by the consumers with the needs of long term availability, reliability, and expandability of data producers. The long term continuous support of data storage adds another layer of complexity for the file system. As storage architecture and big data volumes evolve, existing file system’s primary focus is performance while less attention is payed to addressing the problems of the above long term servicing needs of their clients.

I have developed the Lightweight Virtual File System (LVFS) to address these problems through the unique conceptual approach of separating the most common tasks involved in a file system; namely storing data, locating data, and organizing data. Standard file systems are developed as single monolithic systems performing all three tasks. LVFS replaces these tasks with an architecture which enables the dynamic combination of different algorithms for each of those tasks. Using this approach, LVFS is capable of constructing a storage system, which allows for ready availability, reliability, expandability, and long term support while, simultaneously, assuring the performance of a stable system customizable to meet the needs of data consumers.

After successful development and testing to allow for merging decades old storage architecture with new and incompatible ones, such as HGST Active Archive System, NASA Goddard Space Flight Center’s Terrestrial Information Systems Laboratory adopted LVFS for their production environment to create a single, integrated storage system without any software modifications. UMBC’s Center for Hybrid Multicore Productivity Research deployed an instance on the IBM iDataPlex ‘BlueWave’ cluster to utilize Seagate’s Active Drive systems as a storage and on-disk compute platform. With LVFS we show we were able to perform MapReduce computation directly on the drive with comparable performance to Hadoop running on BlueWave. It also shows a significant reduction in data leaving the active drive during computation thereby significantly increasing throughput.

Committee Members: Dr.s Milton Halem (Advisor), Yelena Yesha, John Dorband, Charles Nicholas, Curt Tilmes

The post PhD Defense: The Lightweight Virtual File System appeared first on Department of Computer Science and Electrical Engineering.

Dissertation Defense

Deep Representation of Lyrical Style and Semantics for Music Recommendation

Abhay L. Kashyap

11:00-1:00 Thursday, 20 July 2017, ITE 346

In the age of music streaming, the need for effective recommendations is important for music discovery and a personalized user experience. Collaborative filtering based recommenders suffer from popularity bias and cold-start which is commonly mitigated by content features. For music, research in content based methods have mainly been focused in the acoustic domain while lyrical content has received little attention. Lyrics contain information about a song’s topic and sentiment that cannot be easily extracted from the audio. This is especially important for lyrics-centric genres like Rap, which was the most streamed genre in 2016. The goal of this dissertation is to explore and evaluate different lyrical content features that could be useful for content, context and emotion based models for music recommendation systems.

With Rap as the primary use case, this dissertation focuses on featurizing two main aspects of lyrics; its artistic style of composition and its semantic content. For lyrical style, a suite of high level rhyme density features are extracted in addition to literary features like the use of figurative language, profanity and vocabulary strength. In contrast to these engineered features, Convolutional Neural Networks (CNN) are used to automatically learn rhyme patterns and other relevant features. For semantics, lyrics are represented using both traditional IR techniques and the more recent neural embedding methods.

These lyrical features are evaluated for artist identification and compared with artist and song similarity measures from a real-world collaborative filtering based recommendation system from Last.fm. It is shown that both rhyme and literary features serve as strong indicators to characterize artists with feature learning methods like CNNs achieving comparable results. For artist and song similarity, a strong relationship was observed between these features and the way users consume music while neural embedding methods significantly outperformed LSA. Finally, this work is accompanied by a web-application, Rapalytics.com, that is dedicated to visualizing all these lyrical features and has been featured on a number of media outlets, most notably, Vox, attn: and Metro.

Committee: Drs. Tim Finin (chair), Anupam Joshi, Tim Oates, Cynthia Matuszek and Pranam Kolari (Walmart Labs)

The post PhD defense: Deep Representation of Lyrical Style and Semantics for Music Recommendation appeared first on Department of Computer Science and Electrical Engineering.

That’s me! And my body.

A reflection on body acceptance and positivity while being a part of a water ballet by Special Projects Coordinator, Amelia Meman.

I tend to not write about my body much. It’s not that I don’t think about it. I’m preoccupied by it, actually. Rather, it’s that I don’t want to continue to bring attention to something that seems, to me, like a glaring error that folks can already pick apart.

It’s not just that I’m sort of fat. I am fat, and that’s something I’ve been able to tease out through years of BMI charts. There’s also everything else: I’m broad shouldered, hairy, weirdly proportioned, and I have a really large tongue. I have weird chubby baby cherub hands and my feet are callused because I use them to climb (read: fall out of) trees.

I could spend many more words on my weirdo body (as I’m sure many others could, too), but this summer I signed up to be in Fluid Movement’s annual water ballet, and now I am actually proud of what my body does. It’s a weird and foreign feeling for me–being proud of my body. After I have somersaulted and tread water for an hour and pin-wheeled and held people’s ankles while floating like perverse otters, I think I’m starting to really love this body.

One of my favorite performances, a water ballet inspired by Jeff Goldblum’s The Fly (1986). Photo retrieved from facebook.com/FluidMovementWB/

See, Fluid Movement’s water ballets are magic. They’ve been going on for almost 20 years now and they’re characterized by unabashed silliness, a heaping ton of glitter, and diverse folks from all over the place coming together in Baltimore’s public pools to dance in water.

I first heard about them through, who else, but my former professor and all-around life hero Dr. Kate Drabinski who had thought of me for their 2014 production of the War of 1812. I wasn’t able to do it, nor did I make it to the show, but I followed their page on Facebook, only to find out that the next year they were doing a water ballet inspired by the life of Jeff Goldblum. I know. They’re amazing. Anyways, my best friend Susie and I went to this show, and we couldn’t keep from crying in awe at how wonderful this whole thing was. We vowed to join the troupe. Now it’s 2017 and we’re starring in the [The Scottish Play] in this summer’s Sharkespeare production.

Poster designed by Justine Jones. Buy tickets to a performance here: https://www.mt.cm/events?title=Sharkespeare

Let me tell you about the phenomenon of being in a water ballet troupe with strangers: it is weird, it is awkward, it is incredible.

We started out doing land rehearsals and really spotting the whole production out. We would meet up at the Clifton Park Mansion where folks brought Jell-O Jigglers and clementines, and we would try our best to remember each other’s names. It felt a lot like marching band camp–we would move to the music, find spots, spin in circles, all that. Everyone was dressed in whatever they had come from work in or they had on some iteration of a “dealing with Baltimore heat” get up. It was all very comfortable and simple, but as we neared pool opening season, I became increasingly anxious.

I knew I would have to eventually strip down to a bathing suit and get in the water, but I still wasn’t all that ready when we finally did. It wasn’t just the bathing suit and all of the flesh it exposed, but that I was not a swimmer. Although I have a piscean affinity for being in water, I wasn’t some sort of avid water sportsperson. I only knew how to freestyle because I was obsessed with Michael Phelps’s arm flap stretch.

I was really afraid that not only would my body not work visually, but that it wouldn’t work physically.

But I think everyone was entering the pool with similar preoccupations. What if my body is too fat or too skinny? What if my butt is exposed? What if I can’t make it through the whole practice? What if I’m the first person to ever drown during a performance?

Getting in the water and futzing around with all of these other people who are just as adorably inelegant but enthusiastic as I am was the turning point. Many of us were new and doing something as simple as laying out was frustrating. But our directors were patient. Other folks who were returning to water ballet guided us through the moves. We kicked at each other and quickly apologized, only to laugh, because water ballet is just a very intimate activity. You trust and appreciate each other quickly, when you have to make a pentagram by spread eagle-ing in formation.

Otters are the original water ballerin(x)s.

The other night at practice was unusually hard. We were in a different pool, I had had a long day. The water was also choppy because a water aerobics battalion had blasted their way through enough EDM and disco to make a club tired. I inhaled quite a bit of water (use a noseclip, kids) and my mind was exhausted. But even after everyone started getting ready to leave, I stayed in the water, egg beatering, sculling, and flipping around. I kicked at the water and propelled up and out, I whipped my arms in circles and somersaulted, I folded my body and sunk slowly down. My body does all of this. It’s capable of learning and exerting force and taking up space and being–of all things–beautiful.

Yes, the visual idiosyncrasies of my body are still here, but so are everybody else’s and I like everybody else’s. I like the dimples of cellulite if you have them. I like that “hip dip,” I like your hair (whether it’s on your head, your chest, your legs, your toes), I like the way our boobs are oppositely asymmetrical. It doesn’t even really matter if I like them–I guess I just appreciate you for you and think you are beautiful.

Our body diversity (although fairly narrow as it is in this instance), our weird little eccentricities, our way of working together and genuinely appreciating each other; it’s all just another thing pushing me to earnestly fall in love with home, whether that’s Baltimore or my own body.

Resources and related posts:

Fluid Movement Website

Treat Your Body Lovingly: A Twelve-Step Program by Dan Willey

Unruly Bodies Class Blog

Note of Absence for 10/9/13 by Amelia Meman (when I was in Dr. Kate’s Unruly Bodies Class)

Analysis of Irregular Event Sequences using Deep Learning, Reinforcement Learning, and Visualization

Filip Dabek

11:00-1:00 Thursday 13 July 2017, ITE 346, UMBC

History is nothing but a catalogued series of events organized into data. Amazon, the largest online retailer in the world, processes over 2,000 orders per minute. Orders come from customers on a recurring basis through subscriptions or as one-off spontaneous purchases, resulting in each customer exhibiting their own behavioral pattern when it comes to the way in which they place orders throughout the year. For a company such as Amazon, that generates over $130 billion of revenue each year, understanding and uncovering the hidden patterns and trends within this data is paramount in improving the efficiency of their infrastructure ranging from the management of the inventory within their warehouses, distribution of their labor force, and preparation of their online systems for the load of users. With the ever increasingly availability of big data, problems such as these are no longer limited to large corporations but are experienced across a wide range of domains and faced by analysts and researchers each and every day.

While many event analysis and time series tools have been developed for the purpose of analyzing such datasets, most approaches tend to target clean and evenly spaced data. When faced with noisy or irregular data, it has been recommended to undergo a pre-processing step of converting and transforming the data into being regular. This transformation technique arguably interferes on a fundamental level as to how the data is represented, and may irrevocably bias the way in which results are obtained. Therefore, operating on raw data, in its noisy natural form, is necessary to ensure that the insights gathered through analysis are accurate and valid.

In this dissertation novel approaches are presented for analyzing irregular event sequences using a variety of techniques ranging from deep learning, reinforcement learning, and visualization. We show how common tasks in event analysis can be performed directly on an irregular event dataset without requiring a transformation that alters the natural representation of the process that the data was captured from. The three tasks that we showcase include: (i) summarization of large event datasets, (ii) modeling the processes that create events, and (iii) predicting future events that will occur.

Committee: Drs. Tim Oates (Chair), Jesus Caban, Penny Rheingans, Jian Chen, Tim Finin

The post PhD Proposal: Analysis of Irregular Event Sequences using Deep Learning, Reinforcement Learning & Visualization appeared first on Department of Computer Science and Electrical Engineering.

Name: Alex Hart

Educational Background: Bachelor’s degree in Accounting from the University of Maryland, College Park

Hometown: Baltimore, MD (Go O’s and Ravens!)

Current role: As an Accountant I, Alex provides business services support to the CSEE department in the areas of contracts and grants/projects, which includes account monitoring, financial reporting, projections, reconciliations, etc. She also provides backup support for payroll, and she is the property custodian of inventory for CSEE.

Favorite thing about UMBC: “Without a doubt, my favorite thing about UMBC is the people here. I have met a lot of different people who have provided me with a wealth of knowledge since I started working here just a year ago. Everyone has been very inclusive and helpful!”

Students should ask me about: “Students can ask me anything, but maybe about the college experience, since I’m still a recent graduate.”

Alex is originally from Baltimore, MD. She joined CSEE’s Department in February of 2016. She attended UMBC for her first two years of college, then transferred to the University of Maryland College Park’s Robert H. Smith School of Business. She has a BS in Accounting from UMCP.

When not working, Alex loves cheering on the Terps in football and basketball. She also enjoys traveling to new places, cooking, practicing yoga, and reading.

The post Meet the Staff: Alex Hart appeared first on Department of Computer Science and Electrical Engineering.