{"title":"Exploring AV1 Encoder Potentials for Priority-Driven Wireless Multimedia Services","authors":"Evan Ballesteros, K. Ramamoorthy, Wei Wang","doi":"10.1109/ietc54973.2022.9796903","DOIUrl":"https://doi.org/10.1109/ietc54973.2022.9796903","url":null,"abstract":"World wide internet data usage is growing at a rapid rate and one of the main reasons for this high data usage is the increasing use of media streaming services. According to Cisco, video streaming will take up 82% of the world’s internet traffic by this year, 2022. Media streaming services use a large amount of data due to videos being inherently such large files which, for streaming services, need to be transferred over the internet. For this reason, we are researching methods to impact the use of a new generation open source video encoder, AV1, with wireless communications. Though the encoder is already more efficient at compressing video files than previous encoders, our goal was to research and understand AV1 in order to customize wireless protocols that optimize its usage in streaming scenarios. In our first attempt at understanding this encoder, we went through processes of tweaking settings built into the encoder in order to find optimal video quality when compared to file size. The file size is an important metric that correlates with how much data would have to be streamed. After this we went on to investigate how we could possibly estimate the per frame quality contribution of each frame transmitted. This goal was inspired by that of previous H.264/H.265 encoders’ I, P, and B frames, which each have their own distinguishable amount of quality contribution that can be split between 3 levels: high, medium, and low. We believe that the method provided could have a good indication of quality contribution similar to that of I, P and B frames with high, medium, or low quality contribution.","PeriodicalId":251518,"journal":{"name":"2022 Intermountain Engineering, Technology and Computing (IETC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124701999","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"John the Ripper: An Examination and Analysis of the Popular Hash Cracking Algorithm","authors":"Kaden Marchetti, P. Bodily","doi":"10.1109/ietc54973.2022.9796671","DOIUrl":"https://doi.org/10.1109/ietc54973.2022.9796671","url":null,"abstract":"In recent years, the viability of hash cracking has been questioned as industry encryption standards, salting, and timeouts have risen in popularity. John the Ripper has emerged as one of the most sophisticated open-source hash cracking tool on the market. The tool is used by cybercriminals as well as security specialists. Research Questions have been formulated to answer questions related to the viability of John the Ripper. To answer these questions, three experiments are defined and performed with varying results. We find that while John the Ripper struggles as a brute force attacker without complex customization, it has a bountiful collection of rainbow tables that make it a very efficient dictionary attacker when used against the most popular passwords and their variants. We find that John the Ripper is easily able to crack the thousand most popular passwords with its extensive open source rainbow-table; however, it struggles as a brute force attacker.","PeriodicalId":251518,"journal":{"name":"2022 Intermountain Engineering, Technology and Computing (IETC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122012240","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zheng Sun, Andrew W. Sumsion, Shad A. Torrie, Dah-Jye Lee
{"title":"Learn Dynamic Facial Motion Representations Using Transformer Encoder","authors":"Zheng Sun, Andrew W. Sumsion, Shad A. Torrie, Dah-Jye Lee","doi":"10.1109/ietc54973.2022.9796917","DOIUrl":"https://doi.org/10.1109/ietc54973.2022.9796917","url":null,"abstract":"Human face analysis is an essential topic in visual computing. Many of our daily applications, such as face-priority auto focus in camera, face-based identity verification, and TikTok stickers, are unattainable without face analysis techniques. In the past ten years, face-related visual computing tasks like face detection, face recognition, and facial expression classification have improved drastically in performance, benefiting from the rapid development of deep learning theory. This work explores how to model dynamic facial motion using a learning-based method. Our proposed model takes video clips containing customized facial motion as input and generates a uni-size vector (the embedding) as the output. We have inspected two different encoders–recurrent neural networks and transformers to extract the temporal features from the video clip. We collected our own facial motion analysis dataset because there is no suitable datasets for our facial motion analysis task. Although our domain-specific dataset is small compared to the well-known public datasets for ordinary face-related tasks, we adopt a transfer learning approach, and a data augmentation method (random trimming) to help the model converge. The experimental results show that the transformer-based encoder performs better than the RNN baseline, and the best F1-score with our validation data is 0.889.","PeriodicalId":251518,"journal":{"name":"2022 Intermountain Engineering, Technology and Computing (IETC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115468532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Audio Event Recognition in Noisy Environments using Power Spectral Density and Dimensionality Reduction","authors":"Md Siddat Bin Nesar, Bradley M. Whitaker","doi":"10.1109/ietc54973.2022.9796710","DOIUrl":"https://doi.org/10.1109/ietc54973.2022.9796710","url":null,"abstract":"Researchers are showing great interest in audio event detection due to its applications in surveillance, audio forensics, and other areas. However, one challenge in event detection is the usual presence of noisy environments. In this paper, we propose a robust system that is reliable when trained on quiet or noisy conditions. Another problem arises when considering the computational costs of collecting and analyzing long audio signals. In this work, we use power spectral density (PSD) and mel-frequency cepstral coefficients (MFCC) for feature extraction. and apply feature transformation and selection techniques to reduce the dimension significantly. Our system exhibits an overall accuracy of 99.05% with the raw features, and 87.10% with a significantly reduced number of features.","PeriodicalId":251518,"journal":{"name":"2022 Intermountain Engineering, Technology and Computing (IETC)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116153423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Adaptive Encrypted Traffic Characterization via Deep Representation Learning","authors":"Jonathan Wintrode, D. Detienne","doi":"10.1109/ietc54973.2022.9796734","DOIUrl":"https://doi.org/10.1109/ietc54973.2022.9796734","url":null,"abstract":"Near ubiquitous encryption poses a challenge for security and quality of service (QoS) applications that rely on deep packet inspection (DPI) techniques for categorizing traffic types or threats. However, recent work has shown that machine learning (ML) on temporal flow statistics as well as convolutional neural network (CNN) methods applied to raw packets are able to classify network traffic even in the face of encryption. Unfortunately, many such methods often lack the ability to generalize to new categories, a critical requirement in our constantly evolving networks. Building on previous approaches we apply CNN models to the characterization task within a deep representation learning framework. The network acts as a feature extractor which is input to a lightweight support vector machine (SVM) classifier for the final output. By training the networks with an angular softmax loss in addition to the typical crossentropy loss, we can improve on the state of the art in terms of both classification accuracy and detection error. Furthermore we demonstrate that learned features provide the ability to label traffic categories not seen in neural network training.","PeriodicalId":251518,"journal":{"name":"2022 Intermountain Engineering, Technology and Computing (IETC)","volume":"2009 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125983852","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Khaled Shaaban, Steven T. Taylor, R. Jackson, Dustin Wall
{"title":"Driver Compliance at All-Way Stop-Controlled Intersections","authors":"Khaled Shaaban, Steven T. Taylor, R. Jackson, Dustin Wall","doi":"10.1109/ietc54973.2022.9796668","DOIUrl":"https://doi.org/10.1109/ietc54973.2022.9796668","url":null,"abstract":"Many traffic crashes occur every year at intersections controlled by stops signs. The most severe of these are typically angle crashes caused by drivers not stopping at the stop signs. The purpose of this study is to measure the compliance rates of drivers at an all-way stopped control intersection in the state of Utah. The study examines several variables that could influence the stopping behavior and decisions of drivers when approaching a stop sign. In addition to age and gender, this study explored factors such as ethnicity, type of vehicle, presence of an approaching vehicle, and time of day. The results showed a low compliance rate. The results also indicated that young, male, and SUV drivers are less likely to come to a complete stop at all-way stop controlled intersections compared to the other groups of drivers.","PeriodicalId":251518,"journal":{"name":"2022 Intermountain Engineering, Technology and Computing (IETC)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121686951","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Offline Signature Verification: A Study on Total Variation versus CNN","authors":"Kateryna Anatska, Mohammad Shekaramiz","doi":"10.1109/ietc54973.2022.9796924","DOIUrl":"https://doi.org/10.1109/ietc54973.2022.9796924","url":null,"abstract":"This paper studies offline handwritten signature verification and the authenticity of a given signature. The research in this paper develops and compares two algorithms that predict forgery and authentic signatures based on the acquired set of images. For the first method, we use total variation technique as a measure of contiguity in the signatures to test its ability to verify the genuineness of a signature. Convolutional Neural Networks (CNN) was chosen as a second approach for signature validation. CNN is a powerful class of deep learning architecture. The algorithms described in the paper have been proven to be low cost as well as to make predictions with high accuracy in handwritten signature authentication.","PeriodicalId":251518,"journal":{"name":"2022 Intermountain Engineering, Technology and Computing (IETC)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124329787","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Review of Factors Affecting Public Transportation Ridership","authors":"Khaled Shaaban, A. Siam","doi":"10.1109/ietc54973.2022.9796772","DOIUrl":"https://doi.org/10.1109/ietc54973.2022.9796772","url":null,"abstract":"The use of different transport modes is affected by several factors such as economic, sociological, and geographical factors. To study the factors affecting public transport ridership, many studies have examined the influence of several parameters within those categories on public transport ridership. These studies focused on understanding the main factors affecting the usage of public transport systems from two standpoints, the first is from the user perspective, and what makes people use transit mode. In this group, the focus is on examining how people’s socio-demographics, accessibility measures and built environment, and mainly infrastructure affect the use of transit mode. The second is from the transit system perspective, which focuses on the system-level attributes affecting transit usage. The purpose of this paper is to review and summarize some of the studies focusing on the transit system perspective to identify the different variables used such as dependent variables, independent variables, and catchment areas.","PeriodicalId":251518,"journal":{"name":"2022 Intermountain Engineering, Technology and Computing (IETC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117081297","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"KAMI: Leveraging the power of crowd-sourcing to solve complex, real-world problems","authors":"Kaden Marchetti, P. Bodily","doi":"10.1109/ietc54973.2022.9796945","DOIUrl":"https://doi.org/10.1109/ietc54973.2022.9796945","url":null,"abstract":"Many of the complex problems facing the world today have been formally classified as what computational theorists call NP-complete problems, meaning problems for which no known algorithm exists for optimally solving the problem in a tractable time frame. On the other hand, humans often demonstrate a unique adeptness at being able to solve NP-complete problems. In this paper, we propose using the popular flood fill game KAMI as a crowd-sourced platform for representing arbitrary NP-Complete problems to human users. More than simply a game of problem-solving or strategy, KAMI derives its success from the fact that each puzzle is an artistic artifact whose popularity depends as much on the creative rendering of the problem as much as the challenge or intrigue of the problem itself. We discuss how the principles of computational creativity represent the key to representing NP-complete problems in this medium so as to be able to effectively harness the power of human problem-solving via crowd-sourcing methods.","PeriodicalId":251518,"journal":{"name":"2022 Intermountain Engineering, Technology and Computing (IETC)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124551605","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Nonlinear Control Algorithm for Systems with Convex Polytope Bounded Nonlinearities","authors":"Olli Jansson, Matt Harris","doi":"10.1109/ietc54973.2022.9796775","DOIUrl":"https://doi.org/10.1109/ietc54973.2022.9796775","url":null,"abstract":"This paper describes a technique for controlling nonlinear systems. It is assumed that the nonlinearity takes values in a convex polytope, the control appears linearly, and the system can be discretized in time. The technique requires the solution of a finite number of linear feasibility (programming) problems and reconstructs the nonlinear control from these solutions. Several examples are provided to illustrate the technique and results are compared to feedback linearization.","PeriodicalId":251518,"journal":{"name":"2022 Intermountain Engineering, Technology and Computing (IETC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133926878","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}