arXiv subjects
Publications and source records attributed to Ting Zhu.
This paper analyzes the proportion of Input/output devices made obsolete by changes in technology generations. This obsolescence may be by new software/hardware generations rendering otherwise functional devices unusable. Concluding with brief analysis on the economic and environmental impacts of the e-waste produced.
LPWAN service's inexpensive cost and long range capabilities make it a promising addition and countless satellite companies have started taking advantage of this technology to connect IoT users across the globe. However, LEO satellites have the unique challenge of using rechargeable batteries and green solar energy to power their components. LPWAN technology is not optimized to maximize battery lifespan of network nodes. By incorporating a MAC protocol that maximizes node the battery lifespan across the network, we can reduce battery waste and usage of scarce Earth resources to develop satellite batteries.
In satellite applications, managing thermal conditions is a significant challenge due to the extreme fluctuations in temperature during orbital cycles. One of the solutions is to heat the satellite when it is not exposed to sunlight, which could protect the satellites from extremely low temperatures. However, heat dissipation is necessary for Graphics Processing Units (GPUs) to operate properly and efficiently. In this way, this paper investigates the use of GPU as a means of passive heating in low-earth orbit (LEO) satellites. Our approach uses GPUs to generate heat during the eclipse phase of satellite orbits, substituting traditional heating systems, while the GPUs are also cooled down during this process. The results highlight the potential advantages and limitations of this method, including the cost implications, operational restrictions, and the technical complexity involved. Also, this paper explores the thermal behavior of GPUs under different computational loads, specifically focusing on execution-dominated and FLOP-dominated workloads. Moreover, this paper discusses future directions for improving GPU-based heating solutions, including further cost analysis, system optimization, and practical testing in real satellite missions.
This study investigates how the new release of MacBook Pro I/O devices affects the obsolescence of related accessories. We also explore how these accessories will impact the environment and the economic consequences. As technology progresses, each new MacBook Pro releases outdated prior accessories, making more electronic waste. This phenomenon makes modern people need to change their traditional consumption patterns. We analyze changes in I/O ports and compatibility between MacBook Pro versions to determine which accessories are obsolete and estimate their environmental impact. Our research focuses on the sustainability of current accessories. We explore alternate methods of reusing, recycling, and disposing of these accessories in order to reduce waste and environmental impact. In addition, we will explore the economic consequences of rapid technological advances that make accessories obsolete too quickly. Thereby assessing the impact of such changes on consumers, manufacturers, and the technology industry. This study aims to respond to the rapid advancement of technology while promoting more sustainable approaches to waste management and product design. As the MacBook Pro I/O unit evolves, certain accessories become obsolete with each subsequent version. The purpose of this study is to identify and quantify the environmental and economic impacts of parts end-of-life. We can detect which accessories have become obsolete and assess the environmental impact by comparing I/O port changes and compatibility across MacBook Pro generations. In response to these environmental images, methods are developed to reuse, recycle, and dispose of obsolete accessories to reduce waste and promote sustainable development. Additionally, we evaluate the economic impact of obsolete equipment on consumers and producers.
In decentralized multi-agent reinforcement learning, agents learning in isolation can lead to relative over-generalization (RO), where optimal joint actions are undervalued in favor of suboptimal ones. This hinders effective coordination in cooperative tasks, as agents tend to choose actions that are individually rational but collectively suboptimal. To address this issue, we introduce MaxMax Q-Learning (MMQ), which employs an iterative process of sampling and evaluating potential next states, selecting those with maximal Q-values for learning. This approach refines approximations of ideal state transitions, aligning more closely with the optimal joint policy of collaborating agents. We provide theoretical analysis supporting MMQ's potential and present empirical evaluations across various environments susceptible to RO. Our results demonstrate that MMQ frequently outperforms existing baselines, exhibiting enhanced convergence and sample efficiency.
Dysarthria speech contains the pathological characteristics of vocal tract and vocal fold, but so far, they have not yet been included in traditional acoustic feature sets. Moreover, the nonlinearity and non-stationarity of speech have been ignored. In this paper, we propose a feature enhancement algorithm for dysarthria speech called WHFEMD. It combines empirical mode decomposition (EMD) and fast Walsh-Hadamard transform (FWHT) to enhance features. With the proposed algorithm, the fast Fourier transform of the dysarthria speech is first performed and then followed by EMD to get intrinsic mode functions (IMFs). After that, FWHT is used to output new coefficients and to extract statistical features based on IMFs, power spectral density, and enhanced gammatone frequency cepstral coefficients. To evaluate the proposed approach, we conducted experiments on two public pathological speech databases including UA Speech and TORGO. The results show that our algorithm performed better than traditional features in classification. We achieved improvements of 13.8% (UA Speech) and 3.84% (TORGO), respectively. Furthermore, the incorporation of an imbalanced classification algorithm to address data imbalance has resulted in a 12.18% increase in recognition accuracy. This algorithm effectively addresses the challenges of the imbalanced dataset and non-linearity in dysarthric speech and simultaneously provides a robust representation of the local pathological features of the vocal folds and tracts.
The year 2022 saw a significant increase in Microsoft vulnerabilities, reaching an all-time high in the past decade. With new vulnerabilities constantly emerging, there is an urgent need for proactive approaches to harden systems and protect them from potential cyber threats. This project aims to investigate the vulnerabilities of the Windows Operating System and explore the effectiveness of key security features such as BitLocker, Microsoft Defender, and Windows Firewall in addressing these threats. To achieve this, various security threats are simulated in controlled environments using coded examples, allowing for a thorough evaluation of the security solutions' effectiveness. Based on the results, this study will provide recommendations for mitigation strategies to enhance system security and strengthen the protection provided by Windows security features. By identifying potential weaknesses and areas of improvement in the Windows security infrastructure, this project will contribute to the development of more robust and resilient security solutions that can better safeguard systems against emerging cyber threats.
Classification is one of the most important tasks in Machine Learning (ML) and with recent advancements in artificial intelligence (AI) it is important to find efficient ways to implement it. Generally, the choice of classification algorithm depends on the data it is dealing with, and accuracy of the algorithm depends on the hyperparameters it is tuned with. One way is to check the accuracy of the algorithms by executing it with different hyperparameters serially and then selecting the parameters that give the highest accuracy to predict the final output. This paper proposes another way where the algorithm is parallelly trained with different hyperparameters to reduce the execution time. In the end, results from all the trained variations of the algorithms are ensembled to exploit the parallelism and improve the accuracy of prediction. Python multiprocessing is used to test this hypothesis with different classification algorithms such as K-Nearest Neighbors (KNN), Support Vector Machines (SVM), random forest and decision tree and reviews factors affecting parallelism. Ensembled output considers the predictions from all processes and final class is the one predicted by maximum number of processes. Doing this increases the reliability of predictions. We conclude that ensembling improves accuracy and multiprocessing reduces execution time for selected algorithms.
Virtual file systems are a tool to centralize and mobilize a file system that could otherwise be complex and consist of multiple hierarchies, hard disks, and more. In this paper, we discuss the design of Unix-based file systems and how this type of file system layout using inode data structures and a disk emulator can be implemented as a single-file virtual file system in Linux. We explore the ways that virtual file systems are vulnerable to security attacks and introduce straightforward solutions that can be implemented to help prevent or mitigate the consequences of such attacks.
This document is the final project report for our advanced operating system class. During this project, we mainly focused on applying multiprocessing and multi-threading technology to our whole project and utilized the map-reduce algorithm in our data cleaning and data analysis process. In general, our project can be divided into two components: data scraping and data processing, where the previous part was almost web wrangling with employing potential multiprocessing or multi-threading technology to speed up the whole process. And after we collect and scrape a large amount value of data as mentioned above, we can use them as input to implement data cleaning and data analysis, during this period, we take advantage of the map-reduce algorithm to increase efficiency.
As 5G networks become more mainstream, privacy has come to the forefront of end users. More scrutiny has been shown to previous generation cellular technologies such as 3G and 4G on how they handle sensitive metadata transmitted from an end user mobile device to base stations during registration with a cellular network. These generation cellular networks do not enforce any encryption on this information transmitted during this process, giving malicious actors an easy way to intercept the information. Such an interception can allow an adversary to locate end users with shocking accuracy. This paper investigates this problem in great detail and discusses how a newly introduced approach in 5G networks is helping combat this problem. The paper discusses the implications of this vulnerability and the technical details of the new approach, including the encryption schemes used to secure this sensitive information. Finally, the paper will discuss any limitations to this new approach.
Video smmarization is a crucial method to reduce the time of videos which reduces the spent time to watch/review a long video. This apporach has became more important as the amount of publisehed video is increasing everyday. A single or multiple videos can be summarized into a relatively short video using various of techniques from multimodal audio-visual techniques, to natural language processing approaches. Audiovisual techniques may be used to recognize significant visual events and pick the most important parts, while NLP techniques can be used to evaluate the audio transcript and extract the main sentences (timestamps) and corresponding video frames from the original video. Another approach is to use the best of both domain. Meaning that we can use audio-visual cues as well as video transcript to extract and summarize the video. In this paper, we combine a variety of NLP techniques (extractive and contect-based summarizers) with video processing techniques to convert a long video into a single relatively short video. We design this toll in a way that user can specify the relative length of the summarized video. We have also explored ways of summarizing and concatenating multiple videos into a single short video which will help having most important concepts from the same subject in a single short video. Out approach shows that video summarizing is a difficult but significant work, with substantial potential for further research and development, and it is possible thanks to the development of NLP models.
The lack of an available emotion pathology database is one of the key obstacles in studying the emotion expression status of patients with dysarthria. The first Chinese multimodal emotional pathological speech database containing multi-perspective information is constructed in this paper. It includes 29 controls and 39 patients with different degrees of motor dysarthria, expressing happy, sad, angry and neutral emotions. All emotional speech was labeled for intelligibility, types and discrete dimensional emotions by developed WeChat mini-program. The subjective analysis justifies from emotion discrimination accuracy, speech intelligibility, valence-arousal spatial distribution, and correlation between SCL-90 and disease severity. The automatic recognition tested on speech and glottal data, with average accuracy of 78% for controls and 60% for patients in audio, while 51% for controls and 38% for patients in glottal data, indicating an influence of the disease on emotional expression.
BERTScore is an effective and robust automatic metric for referencebased machine translation evaluation. In this paper, we incorporate multilingual knowledge graph into BERTScore and propose a metric named KG-BERTScore, which linearly combines the results of BERTScore and bilingual named entity matching for reference-free machine translation evaluation. From the experimental results on WMT19 QE as a metric without references shared tasks, our metric KG-BERTScore gets higher overall correlation with human judgements than the current state-of-the-art metrics for reference-free machine translation evaluation.1 Moreover, the pre-trained multilingual model used by KG-BERTScore and the parameter for linear combination are also studied in this paper.
Semantic segmentation works on the computer vision algorithm for assigning each pixel of an image into a class. The task of semantic segmentation should be performed with both accuracy and efficiency. Most of the existing deep FCNs yield to heavy computations and these networks are very power hungry, unsuitable for real-time applications on portable devices. This project analyzes current semantic segmentation models to explore the feasibility of applying these models for emergency response during catastrophic events. We compare the performance of real-time semantic segmentation models with non-real-time counterparts constrained by aerial images under oppositional settings. Furthermore, we train several models on the Flood-Net dataset, containing UAV images captured after Hurricane Harvey, and benchmark their execution on special classes such as flooded buildings vs. non-flooded buildings or flooded roads vs. non-flooded roads. In this project, we developed a real-time UNet based model and deployed that network on Jetson AGX Xavier module.
This survey of heterogeneous computing systems will help in analyzing the technological trends that will be at the basis of heterogeneous computing systems, highlighting the major opportunities and challenges such technologies will bring with them. This will help to understand the importance of heterogeneous computing systems, which are becoming common architectural elements of not only the modern data centers but also highly integrated devices (IoT). Identify problems related to it, such as the resource allocation problem, middleware, processing architectures, programming challenges, etc. from the perspective of heterogeneous resources.
Security issues in processor architectures remain really critical since users and devices continue to share computing as well as networking resources. So, preserving data privacy in such an environment is really a critical concern. We know that there is a continuous growth in security and privacy issues that need to be addressed. Here, we have chosen a microservice architecture, which is a small or even an independent microprocess that interacts, acts, and responds to messages via lightweight technologies such as Thrift, HTTP, or REST API.
As wireless network technology becomes more and more popular, mutual interference between various signals has become more and more severe and common. Therefore, there is often a situation in which the transmission of its own signal is interfered with by occupying the channel. Especially in a confrontational environment, Jamming has caused great harm to the security of information transmission. So I propose ML-based secure ultra-low power communication, which is an approach to use machine learning to predict future wireless traffic by capturing patterns of past wireless traffic to ensure ultra-low-power transmission of signals via backscatters. In order to be more suitable for the adversarial environment, we use backscatter to achieve ultra-low power signal transmission, and use frequency-hopping technology to achieve successful confrontation with Jamming information. In the end, we achieved a prediction success rate of 96.19%.