Matching Items (253)
Filtering by
- All Subjects: artificial intelligence
- Member of: ASU Electronic Theses and Dissertations
Description
With the advent of new advanced analysis tools and access to related published data, it is getting more difficult for data owners to suppress private information from published data while still providing useful information. This dual problem of providing useful, accurate information and protecting it at the same time has been challenging, especially in healthcare. The data owners lack an automated resource that provides layers of protection on a published dataset with validated statistical values for usability. Differential privacy (DP) has gained a lot of attention in the past few years as a solution to the above-mentioned dual problem. DP is defined as a statistical anonymity model that can protect the data from adversarial observation while still providing intended usage. This dissertation introduces a novel DP protection mechanism called Inexact Data Cloning (IDC), which simultaneously protects and preserves information in published data while conveying source data intent. IDC preserves the privacy of the records by converting the raw data records into clonesets. The clonesets then pass through a classifier that removes potential compromising clonesets, filtering only good inexact cloneset. The mechanism of IDC is dependent on a set of privacy protection metrics called differential privacy protection metrics (DPPM), which represents the overall protection level. IDC uses two novel performance values, differential privacy protection score (DPPS) and clone classifier selection percentage (CCSP), to estimate the privacy level of protected data. In support of using IDC as a viable data security product, a software tool chain prototype, differential privacy protection architecture (DPPA), was developed to utilize the IDC. DPPA used the engineering security mechanism of IDC. DPPA is a hub which facilitates a market for data DP security mechanisms. DPPA works by incorporating standalone IDC mechanisms and provides automation, IDC protected published datasets and statistically verified IDC dataset diagnostic report. DPPA is currently doing functional, and operational benchmark processes that quantifies the DP protection of a given published dataset. The DPPA tool was recently used to test a couple of health datasets. The test results further validate the IDC mechanism as being feasible.
Contributorsthomas, zelpha (Author) / Bliss, Daniel W (Thesis advisor) / Papandreou-Suppappola, Antonia (Committee member) / Banerjee, Ayan (Committee member) / Shrivastava, Aviral (Committee member) / Arizona State University (Publisher)
Created2023
Description
Detection of anomalies before they are included in the downstream diagnosis/prognosis models is an important criterion for maintaining the medical AI imaging model performance across internal and external datasets. Furthermore, the need to curate huge amounts of data to train supervised models that produce precise results also requires an automated model that can accurately identify in-distribution (ID) and out-of-distribution (OOD) data for ensuring the training dataset quality. However, the core challenges for designing such as system are – (i) given the infinite variations of the anomaly, curation of training data is in-feasible; (ii) making assumptions about the types of anomalies are often hypothetical. The proposed work designed an unsupervised anomaly detection model using a cascade variational autoencoder coupled with a zero-shot learning network that maps the latent vectors to semantic attributes. The performance of the proposed model is shown on two different use cases – skin images and chest radiographs and also compare against the same class of state-of-the-art generative OOD detection models.
ContributorsRamasamy, Gokul (Author) / Banerjee, Imon (Thesis advisor) / Sanyal, Arindam (Thesis advisor) / Jayasuriya, Suren (Committee member) / Arizona State University (Publisher)
Created2023
Description
This dissertation explores the use of artificial intelligence and machine learningtechniques for the development of controllers for fully-powered robotic prosthetics.
The aim of the research is to enable prosthetics to predict future states and control
biomechanical properties in both linear and nonlinear fashions, with a particular focus
on ergonomics.
The research is motivated by the need to provide amputees with prosthetic devices
that not only replicate the functionality of the missing limb, but also offer a high
level of comfort and usability. Traditional prosthetic devices lack the sophistication to
adjust to a user’s movement patterns and can cause discomfort and pain over time.
The proposed solution involves the development of machine learning-based controllers
that can learn from user movements and adjust the prosthetic device’s movements
accordingly.
The research involves a combination of simulation and real-world testing to evaluate
the effectiveness of the proposed approach. The simulation involves the creation of a
model of the prosthetic device and the use of machine learning algorithms to train
controllers that predict future states and control biomechanical properties. The real-
world testing involves the use of human subjects wearing the prosthetic device to
evaluate its performance and usability.
The research focuses on two main areas: the prediction of future states and the
control of biomechanical properties. The prediction of future states involves the
development of machine learning algorithms that can analyze a user’s movements
and predict the next movements with a high degree of accuracy. The control of
biomechanical properties involves the development of algorithms that can adjust the
prosthetic device’s movements to ensure maximum comfort and usability for the user.
The results of the research show that the use of artificial intelligence and machine
learning techniques can significantly improve the performance and usability of pros-
thetic devices. The machine learning-based controllers developed in this research are
capable of predicting future states and adjusting the prosthetic device’s movements in
real-time, leading to a significant improvement in ergonomics and usability. Overall,
this dissertation provides a comprehensive analysis of the use of artificial intelligence
and machine learning techniques for the development of controllers for fully-powered
robotic prosthetics.
ContributorsCLARK, GEOFFEY M (Author) / Ben Amor, Heni (Thesis advisor) / Dasarathy, Gautam (Committee member) / Papandreou-Suppappola, Antonia (Committee member) / Ward, Jeffrey (Committee member) / Arizona State University (Publisher)
Created2023
Description
Artificial Intelligence (AI) is a rapidly advancing field with the potential to impact every aspect of society, including the inventive practices of science and technology. The creation of new ideas, devices, or methods, commonly known as inventions, is typically viewed as a process of combining existing knowledge. To understand how AI can transform scientific and technological inventions, it is essential to comprehend how such combinatorial inventions have emerged in the development of AI.This dissertation aims to investigate three aspects of combinatorial inventions in AI using data-driven and network analysis methods. Firstly, how knowledge is combined to generate new scientific publications in AI; secondly, how technical com- ponents are combined to create new AI patents; and thirdly, how organizations cre- ate new AI inventions by integrating knowledge within organizational and industrial boundaries. Using an AI publication dataset of nearly 300,000 AI publications and an AI patent dataset of almost 260,000 AI patents granted by the United States Patent and Trademark Office (USPTO), this study found that scientific research related to AI is predominantly driven by combining existing knowledge in highly conventional ways, which also results in the most impactful publications. Similarly, incremental improvements and refinements that rely on existing knowledge rather than radically new ideas are the primary driver of AI patenting. Nonetheless, AI patents combin- ing new components tend to disrupt citation networks and hence future inventive practices more than those that involve only existing components.
To examine AI organizations’ inventive activities, an analytical framework called the Combinatorial Exploitation and Exploration (CEE) framework was developed to measure how much an organization accesses and discovers knowledge while working within organizational and industrial boundaries. With a dataset of nearly 500 AI organizations that have continuously contributed to AI technologies, the research shows that AI organizations favor exploitative over exploratory inventions. However, local exploitation tends to peak within the first five years and remain stable, while exploratory inventions grow gradually over time.
Overall, this dissertation offers empirical evidence regarding how inventions in AI have emerged and provides insights into how combinatorial characteristics relate to AI inventions’ quality. Additionally, the study offers tools to assess inventive outcomes and competence.
ContributorsWang, Jieshu (Author) / Maynard, Andrew (Thesis advisor) / Lobo, Jose (Committee member) / Michael, Katina (Committee member) / Motsch, Sebastien (Committee member) / Arizona State University (Publisher)
Created2023
Description
The study aims to develop and evaluate failure prediction models that accurately predict crack initiation sites, fatigue life in additively manufactured Ti-6Al-4V, and burst pressure in relevant applications.The first part proposes a classification model to identify crack initiation sites in AM-built Ti-6Al-4V alloy. The model utilizes surface and pore-related parameters and achieves high accuracy (0.97) and robustness (F1 score of 0.98). Leveraging CT images for characterization and data extraction from the CT-images built STL files, the model effectively detects crack initiation sites while minimizing false positives and negatives. Data augmentation techniques, including SMOTE+Tomek Links, are employed to address imbalanced data distributions and improve model performance.
This study proposes the Probabilistic Physics-guided Neural Network 2.0 (PPgNN) for probabilistic fatigue life estimation. The presented approach overcomes the limitations of classical regression machine models commonly used to analyze fatigue data. One key advantage of the proposed method is incorporating known physics constraints, resulting in accurate and physically consistent predictions.
The efficacy of the model is demonstrated by training the model with multiple fatigue S-N curve data sets from open literature with relevant morphological data and tested using the data extracted from CT-built STL files. The results illustrate that PPgNN 2.0 is a flexible and robust model for predicting fatigue life and quantifying uncertainties by estimating the mean and standard deviation of the fatigue life. The loss function that trains the proposed model can capture the underlying distribution and reduce the prediction error.
A comparison study between the performance of neural network models highlights the benefits of physics-guided learning for fatigue data analysis. The proposed model demonstrates satisfactory learning capacity and generalization, providing accurate fatigue life predictions to unseen examples.
An elastic-plastic Finite Element Model (FEM) is developed in the second part to assess pipeline integrity, focusing on burst pressure estimation in high-pressure gas pipelines with interactive corrosion defects. The FEM accurately predicts burst pressure and evaluates the remaining useful life by considering the interaction between corrosion defects and neighboring pits. The FEM outperforms the well-known ASME-B31G method in handling interactive corrosion threats.
ContributorsBalamurugan, Rakesh (Author) / Liu, Yongming (Thesis advisor) / Zhuang, Houlong (Committee member) / Bhate, Dhruv (Committee member) / Arizona State University (Publisher)
Created2023
Description
In natural language processing, language models have achieved remarkable success over the last few years. The Transformers are at the core of most of these models. Their success can be mainly attributed to an enormous amount of curated data they are trained on. Even though such language models are trained on massive curated data, they often need specific extracted knowledge to understand better and reason. This is because often relevant knowledge may be implicit or missing, which hampers machine reasoning. Apart from that, manual knowledge curation is time-consuming and erroneous. Hence, finding fast and effective methods to extract such knowledge from data is important for improving language models. This leads to finding ideal ways to utilize such knowledge by incorporating them into language models. Successful knowledge extraction and integration lead to an important question of knowledge evaluation of such models by developing tools or introducing challenging test suites to learn about their limitations and improve them further. So to improve the transformer-based models, understanding the role of knowledge becomes important. In the pursuit to improve language models with knowledge, in this dissertation I study three broad research directions spanning across the natural language, biomedical and cybersecurity domains: (1) Knowledge Extraction (KX) - How can transformer-based language models be leveraged to extract knowledge from data? (2) Knowledge Integration (KI) - How can such specific knowledge be used to improve such models? (3) Knowledge Evaluation (KE) - How can language models be evaluated for specific skills and understand their limitations?
I propose methods to extract explicit textual, implicit structural, missing textual, and missing structural knowledge from natural language and binary programs using transformer-based language models. I develop ways to improve the language model’s multi-step and commonsense reasoning abilities using external knowledge. Finally, I develop challenging datasets which assess their numerical reasoning skills in both in-domain and out-of-domain settings.
ContributorsPal, Kuntal Kumar (Author) / Baral, Chitta (Thesis advisor) / Wang, Ruoyu (Committee member) / Blanco, Eduardo (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2023
Description
In recent years, the proliferation of deep neural networks (DNNs) has revolutionized the field of artificial intelligence, enabling advancements in various domains. With the emergence of efficient learning techniques such as quantization and distributed learning, DNN systems have become increasingly accessible for deployment on edge devices. This accessibility brings significant benefits, including real-time inference on the edge, which mitigates communication latency, and on-device learning, which addresses privacy concerns and enables continuous improvement. However, the resource limitations of edge devices pose challenges in equipping them with robust safety protocols, making them vulnerable to various attacks. Two notable attacks that affect edge DNN systems are Bit-Flip Attacks (BFA) and architecture stealing attacks. BFA compromises the integrity of DNN models, while architecture stealing attacks aim to extract valuable intellectual property by reverse engineering the model's architecture. Furthermore, in Split Federated Learning (SFL) scenarios, where training occurs on distributed edge devices, Model Inversion (MI) attacks can reconstruct clients' data, and Model Extraction (ME) attacks can extract sensitive model parameters. This thesis aims to address these four attack scenarios and develop effective defense mechanisms. To defend against BFA, both passive and active defensive strategies are discussed. Furthermore, for both model inference and training, architecture stealing attacks are mitigated through novel defense techniques, ensuring the integrity and confidentiality of edge DNN systems. In the context of SFL, the thesis showcases defense mechanisms against MI attacks for both supervised and self-supervised learning applications. Additionally, the research investigates ME attacks in SFL and proposes countermeasures to enhance resistance against potential ME attackers. By examining and addressing these attack scenarios, this research contributes to the security and privacy enhancement of edge DNN systems. The proposed defense mechanisms enable safer deployment of DNN models on resource-constrained edge devices, facilitating the advancement of real-time applications, preserving data privacy, and fostering the widespread adoption of edge computing technologies.
ContributorsLi, Jingtao (Author) / Chakrabarti, Chaitali (Thesis advisor) / Fan, Deliang (Committee member) / Cao, Yu (Committee member) / Trieu, Ni (Committee member) / Arizona State University (Publisher)
Created2023
Description
Quantum computing is becoming more accessible through modern noisy intermediate scale quantum (NISQ) devices. These devices require substantial error correction and scaling before they become capable of fulfilling many of the promises that quantum computing algorithms make. This work investigates the current state of NISQ devices by implementing multiple classical computing scenarios with a quantum analog to observe how current quantum technology can be leveraged to achieve different tasks. First, quantum homomorphic encryption (QHE) is applied to the quantum teleportation protocol to show that this form of algorithm security is possible to implement with modern quantum computing simulators. QHE is capable of completely obscuring a teleported state with a liner increase in the number of qubit gates O(n). Additionally, the circuit depth increases minimally by only a constant factor O(c) when using only stabilizer circuits. Quantum machine learning (QML) is another potential application of NISQ technology that can be used to modify classical AI. QML is investigated using quantum hybrid neural networks for the classification of spoken commands on live audio data. Additionally, an edge computing scenario is examined to profile the interactions between a quantum simulator acting as a cloud server and an embedded processor board at the network edge. It is not practical to embed NISQ processors at a network edge, so this paradigm is important to study for practical quantum computing systems. The quantum hybrid neural network (QNN) learned to classify audio with equivalent accuracy (~94%) to a classical recurrent neural network. Introducing quantum simulation slows the systems responsiveness because it takes significantly longer to process quantum simulations than a classical neural network. This work shows that it is viable to implement classical computing techniques with quantum algorithms, but that current NISQ processing is sub-optimal when compared to classical methods.
ContributorsYarter, Maxwell (Author) / Spanias, Andreas (Thesis advisor) / Arenz, Christian (Committee member) / Dasarathy, Gautam (Committee member) / Arizona State University (Publisher)
Created2023
Description
In this work, I propose to bridge the gap between human users and adaptive control of robotic systems. The goal is to enable robots to consider user feedback and adjust their behaviors. A critical challenge with designing such systems is that users are often non-experts, with limited knowledge about the robot's hardware and dynamics. In the domain of human-robot interaction, there exist different modalities of conveying information regarding the desired behavior of the robot, most commonly used are demonstrations, and preferences. While it is challenging for non-experts to provide demonstrations of robot behavior, works that consider preferences expressed as trajectory rankings lead to users providing noisy and possibly conflicting information, leading to slow adaptation or system failures. The end user can be expected to be familiar with the dynamics and how they relate to their desired objectives through repeated interactions with the system. However, due to inadequate knowledge about the system dynamics, it is expected that the user would find it challenging to provide feedback on all dimension's of the system's behavior at all times. Thus, the key innovation of this work is to enable users to provide partial instead of completely specified preferences as with traditional methods that learn from user preferences. In particular, I consider partial preferences in the form of preferences over plant dynamic parameters, for which I propose Adaptive User Control (AUC) of robotic systems. I leverage the correlations between the observed and hidden parameter preferences to deal with incompleteness. I use a sparse Gaussian Process Latent Variable Model formulation to learn hidden variables that represent the relationships between the observed and hidden preferences over the system parameters. This model is trained using Stochastic Variational Inference with a distributed loss formulation. I evaluate AUC in a custom drone-swarm environment and several domains from DeepMind control suite. I compare AUC with the state-of-the-art preference-based reinforcement learning methods that are utilized with user preferences. Results show that AUC outperforms the baselines substantially in terms of sample and feedback complexity.
ContributorsBiswas, Upasana (Author) / Zhang, Yu (Thesis advisor) / Kambhampati, Subbarao (Committee member) / Berman, Spring (Committee member) / Liu, Lantao (Committee member) / Arizona State University (Publisher)
Created2023
Description
Multiple robotic arms collaboration is to control multiple robotic arms to collaborate with each other to work on the same task. During the collaboration, theagent is required to avoid all possible collisions between each part of the robotic arms.
Thus, incentivizing collaboration and preventing collisions are the two principles which
are followed by the agent during the training process. Nowadays, more and more
applications, both in industry and daily lives, require at least two arms, instead of
requiring only a single arm. A dual-arm robot satisfies much more needs of different
types of tasks, such as folding clothes at home, making a hamburger in a grill or
picking and placing a product in a warehouse.
The applications done in this paper are all about object pushing. This thesis
focuses on how to train the agent to learn pushing an object away as far as possible.
Reinforcement Learning (RL), which is a type of Machine Learning (ML), is then
utilized in this paper to train the agent to generate optimal actions. Deep Deterministic
Policy Gradient (DDPG) and Hindsight Experience Replay (HER) are the two RL
methods used in this thesis.
ContributorsLin, Steve (Author) / Ben Amor, Hani (Thesis advisor) / Redkar, Sangram (Committee member) / Zhang, Yu (Committee member) / Arizona State University (Publisher)
Created2023