Matching Items (20)

Filtering by

Clear all filters

130936-Thumbnail Image.png

Hana: An Open-Domain Chatbot Application for Language Learning

Description

Learning a new language can be very challenging. One significant aspect of learning a language is learning how to have fluent verbal and written conversations with other people in that language. However, it can be difficult to find other people

Learning a new language can be very challenging. One significant aspect of learning a language is learning how to have fluent verbal and written conversations with other people in that language. However, it can be difficult to find other people available with whom to practice conversations. Additionally, total beginners may feel uncomfortable and self-conscious when speaking the language with others. In this paper, I present Hana, a chatbot application powered by deep learning for practicing open-domain verbal and written conversations in a variety of different languages. Hana uses a pre-trained medium-sized instance of Microsoft's DialoGPT in order to generate English responses to user input translated into English. Google Cloud Platform's Translation API is used to handle translation to and from the language selected by the user. The chatbot is presented in the form of a browser-based web application, allowing users to interact with the chatbot in both a verbal or text-based manner. Overall, the chatbot is capable of having interesting open-domain conversations with the user in languages supported by the Google Cloud Translation API, but response generation can be delayed by several seconds, and the conversations and their translations do not necessarily take into account linguistic and cultural nuances associated with a given language.

Contributors

Agent

Created

Date Created
2020-12

133339-Thumbnail Image.png

Prescription Information Extraction from Electronic Health Records using BiLSTM-CRF and Word Embeddings

Description

Medical records are increasingly being recorded in the form of electronic health records (EHRs), with a significant amount of patient data recorded as unstructured natural language text. Consequently, being able to extract and utilize clinical data present within these records

Medical records are increasingly being recorded in the form of electronic health records (EHRs), with a significant amount of patient data recorded as unstructured natural language text. Consequently, being able to extract and utilize clinical data present within these records is an important step in furthering clinical care. One important aspect within these records is the presence of prescription information. Existing techniques for extracting prescription information — which includes medication names, dosages, frequencies, reasons for taking, and mode of administration — from unstructured text have focused on the application of rule- and classifier-based methods. While state-of-the-art systems can be effective in extracting many types of information, they require significant effort to develop hand-crafted rules and conduct effective feature engineering. This paper presents the use of a bidirectional LSTM with CRF tagging model initialized with precomputed word embeddings for extracting prescription information from sentences without requiring significant feature engineering. The experimental results, run on the i2b2 2009 dataset, achieve an F1 macro measure of 0.8562, and scores above 0.9449 on four of the six categories, indicating significant potential for this model.

Contributors

Agent

Created

Date Created
2018-05

132574-Thumbnail Image.png

Pose Estimation with Convolutional Neural Networks

Description

Convolutional neural networks boast a myriad of applications in artificial intelligence, but one of the most common uses for such networks is image extraction. The ability of convolutional layers to extract and combine data features for the purpose of image

Convolutional neural networks boast a myriad of applications in artificial intelligence, but one of the most common uses for such networks is image extraction. The ability of convolutional layers to extract and combine data features for the purpose of image analysis can be leveraged for pose estimation on an object - detecting the presence and attitude of corners and edges allows a convolutional neural network to identify how an object is positioned. This task can assist in working to grasp an object correctly in robotics applications, or to track an object more accurately in 3D space. However, the effectiveness of pose estimation may change based on properties of the object; the pose of a complex object, complexity being determined by internal occlusions, similar faces, etcetera, can be difficult to resolve.
This thesis is part of a collaboration between ASU’s Interactive Robotics Laboratory and NASA’s Jet Propulsion Laboratory. In this thesis, the training pipeline from Sharma’s paper “Pose Estimation for Non-Cooperative Spacecraft Rendezvous Using Convolutional Neural Networks” was modified to perform pose estimation on a complex object - specifically, a segment of a hollow truss. After initial attempts to replicate the architecture used in the paper and train solely on synthetic images, a combination of synthetic dataset generation and transfer learning on an ImageNet-pretrained AlexNet model was implemented to mitigate the difficulty of gathering large amounts of real-world data. Experimentation with pose estimation accuracy and hyperparameters of the model resulted in gradual test accuracy improvement, and future work is suggested to improve pose estimation for complex objects with some form of rotational symmetry.

Contributors

Created

Date Created
2019-05

132649-Thumbnail Image.png

Privacy-guaranteed Data Collection: The Case for Efficient Resource Management of Nonprofit Organizations

Description

Through the personal experience of volunteering at ASU Project Humanities, an organization that provides resources such as clothing and toiletries to the homeless population in Downtown Phoenix, I noticed efficiently serving the needs of the homeless population is an important

Through the personal experience of volunteering at ASU Project Humanities, an organization that provides resources such as clothing and toiletries to the homeless population in Downtown Phoenix, I noticed efficiently serving the needs of the homeless population is an important endeavor, but the current processes for Phoenix nonprofits to collect data are manual, ad-hoc, and inefficient. This leads to the research question: is it possible to improve this process of collecting statistics on client needs, tracking donations, and managing resources using technology? Background research includes an interview with ASU Project Humanities, articles by analysts, and related work including case studies of current technologies in the nonprofit community. Major findings include i) a lack of centralized communication in nonprofits collecting needs, tracking surplus donations, and sharing resources, ii) privacy assurance is important to homeless individuals, and iii) pre-existing databases and technological solutions have demonstrated that technology has the ability to make an impact in the nonprofit community. To improve the process, standardization, efficiency, and automation need to increase. As a result of my analysis, the thesis proposes a prototype solution which includes two parts: an inventory database and a web application with forms for user input and tables for the user to view. This solution addresses standardization by showing a consistent way of collecting data on need requests and surplus donations while guaranteeing privacy of homeless individuals. This centralized solution also increases efficiency by connecting different agencies that cater to these clients. Lastly, the solution demonstrates the ability for resources to be made available to each organization which can increase automation. In conclusion, this database and web application has the potential to improve nonprofit organizations’ networking capabilities, resource management, and resource distribution. The percentile of homeless individuals connected to these resources is expected to increase substantially with future live testing and large-scale implementation.

Contributors

Agent

Created

Date Created
2019-05

132750-Thumbnail Image.png

A Study on Resources Utilization of Deep Learning Workloads

Description

Deep learning and AI have grabbed tremendous attention in the last decade. The substantial accuracy improvement by neural networks in common tasks such as image classification and speech recognition has made deep learning as a replacement for many conventional machine

Deep learning and AI have grabbed tremendous attention in the last decade. The substantial accuracy improvement by neural networks in common tasks such as image classification and speech recognition has made deep learning as a replacement for many conventional machine learning techniques. Training Deep Neural networks require a lot of data, and therefore vast of amounts of computing resources to process the data and train the model for the neural network. The most obvious solution to solving this problem is to speed up the time it takes to train Deep Neural networks.
AI and deep learning workloads are different from the conventional cloud and mobile workloads, with respect to: (1) Computational Intensity, (2) I/O characteristics, and (3) communication pattern. While there is a considerable amount of research activity on the theoretical aspects of AI and Deep Learning algorithms that run with greater efficiency, there are only a few studies on the infrastructural impact of Deep Learning workloads on computing and storage resources in distributed systems.
It is typical to utilize a heterogeneous mixture of CPU and GPU devices to perform training on a neural network. Google Brain has a developed a reinforcement model that can place training operations across a heterogeneous cluster. Though it has only been tested with local devices in a single cluster. This study will explore the method’s capabilities and attempt to apply this method on a cluster with nodes across a network.

Contributors

Agent

Created

Date Created
2019-05

132669-Thumbnail Image.png

Honey, I Forgot the Milk: An Alexa Shopping Assistant

Description

If you’ve ever found yourself uttering the words “Honey, I forgot the—” or “how did I miss the—" when coming home from the grocery store, then you’re not alone. This everyday problem that we disregard as part of life may

If you’ve ever found yourself uttering the words “Honey, I forgot the—” or “how did I miss the—" when coming home from the grocery store, then you’re not alone. This everyday problem that we disregard as part of life may not seem like much, but it is the driving force behind my honors thesis.
Shopping Buddy is a complete Amazon Web Services solution to this problem which is so innate to the human condition. Utilizing Alexa to keep track of your pantry, this web application automates the daunting task of creating your shopping list, putting the power of the cloud at your fingertips while keeping your complete shopping list only a click away.
Say goodbye to the nights of spaghetti without the parmesan that you left on the store shelf or the strawberries that you forgot for the strawberry shortcake. With this application, you will no longer need to rely on your memory of what you think is in the back of your fridge nor that pesky shopping list that you always end up losing when you need it the most. Accessible from any web enabled device, Shopping Buddy has got your back through all your shopping adventures to come.

Contributors

Agent

Created

Date Created
2019-05

131274-Thumbnail Image.png

Improving upon the State-of-the-Art in Multimodal Emotional Recognition in Dialogue

Description

Emotion recognition in conversation has applications within numerous domains such as affective computing and medicine. Recent methods for emotion recognition jointly utilize conversational data over several modalities including audio, video, and text. However, state-of-the-art frameworks for this task do not

Emotion recognition in conversation has applications within numerous domains such as affective computing and medicine. Recent methods for emotion recognition jointly utilize conversational data over several modalities including audio, video, and text. However, state-of-the-art frameworks for this task do not focus on the feature extraction and feature fusion steps of this process. This thesis aims to improve the state-of-the-art method by incorporating two components to better accomplish these steps. By doing so, we are able to produce improved representations for the text modality and better model the relationships between all modalities. This paper proposes two methods which focus on these concepts and provide improved accuracy over the state-of-the-art framework for multimodal emotion recognition in dialogue.

Contributors

Agent

Created

Date Created
2020-05

132967-Thumbnail Image.png

Learning Generalized Heuristics Using Deep Neural Networks

Description

Classical planning is a field of Artificial Intelligence concerned with allowing autonomous agents to make reasonable decisions in complex environments. This work investigates
the application of deep learning and planning techniques, with the aim of constructing generalized plans capable of

Classical planning is a field of Artificial Intelligence concerned with allowing autonomous agents to make reasonable decisions in complex environments. This work investigates
the application of deep learning and planning techniques, with the aim of constructing generalized plans capable of solving multiple problem instances. We construct a Deep Neural Network that, given an abstract problem state, predicts both (i) the best action to be taken from that state and (ii) the generalized “role” of the object being manipulated. The neural network was tested on two classical planning domains: the blocks world domain and the logistic domain. Results indicate that neural networks are capable of making such
predictions with high accuracy, indicating a promising new framework for approaching generalized planning problems.

Contributors

Created

Date Created
2019-05

136179-Thumbnail Image.png

CourseKarma: Online Community of Student Collaboration

Description

CourseKarma is a web application that engages students in their own learning through peer-driven social networking. The influence of technology on students is advancing faster than the school system, and a major gap still lingers between traditional learning techniques and

CourseKarma is a web application that engages students in their own learning through peer-driven social networking. The influence of technology on students is advancing faster than the school system, and a major gap still lingers between traditional learning techniques and the fast-paced, online culture of today's generation. CourseKarma enriches the educational experience of today's student by creating a space for collaborative inquiry as well as illuminating the opportunities of self and group learning through online collaboration. The features of CourseKarma foster this student-driven environment. The main focus is on a news-feed and Question and Answer component that provides a space for students to share instant updates as well ask and answer questions of the community. The community can be as broad as the entire ASU student body, as specific as students in BIO155, or even more targeted via specific subjects and or skills. CourseKarma also provides reputation points, which are the sum of all of their votes received, identifying the individual's level and or ranking in each subject or class. This not only gamifies the usual day-to-day learning environment, but it also provides an in-depth analysis of the individual's skills, accomplishments, and knowledge. The community is also able to input and utilize course and professor descriptions/feedback. This will be in a review format providing the students an opportunity to share and give feedback on their experience as well as providing incoming students the opportunity to be prepared for their future classes. All of the student's contributions and collaborative activity within CourseKarma is displayed on their personal profile creating a timeline of their academic achievements. The application was created using modern web programming technologies such as AngualrJS, Javascript, jQuery, Bootstrap, HTML5, CSS3 for the styling and front-end development, Mustache.js for client side templating, and Firebase AngularFire as the back-end and NoSQL database. Other technologies such as Pivitol Tracker was used for project management and user story generation, as well as, Github for version control management and repository creation. Object-oreinted programming concepts were heavily present in the creation of the various data structures, as well as, a voting algorithm was used to manage voting of specific posts. Down the road, CourseKarma could even be a necessary add-on within LinkedIn or Facebook that provides a quick yet extremely in-depth look at an individuals' education, skills, and potential to learn \u2014 based all on their actual contribution to their academic community rather than just a text they wrote up.

Contributors

Agent

Created

Date Created
2015-05

135660-Thumbnail Image.png

Convolutional Neural Networks for Facial Expression Recognition

Description

This paper presents work that was done to create a system capable of facial expression recognition (FER) using deep convolutional neural networks (CNNs) and test multiple configurations and methods. CNNs are able to extract powerful information about an image using

This paper presents work that was done to create a system capable of facial expression recognition (FER) using deep convolutional neural networks (CNNs) and test multiple configurations and methods. CNNs are able to extract powerful information about an image using multiple layers of generic feature detectors. The extracted information can be used to understand the image better through recognizing different features present within the image. Deep CNNs, however, require training sets that can be larger than a million pictures in order to fine tune their feature detectors. For the case of facial expression datasets, none of these large datasets are available. Due to this limited availability of data required to train a new CNN, the idea of using naïve domain adaptation is explored. Instead of creating and using a new CNN trained specifically to extract features related to FER, a previously trained CNN originally trained for another computer vision task is used. Work for this research involved creating a system that can run a CNN, can extract feature vectors from the CNN, and can classify these extracted features. Once this system was built, different aspects of the system were tested and tuned. These aspects include the pre-trained CNN that was used, the layer from which features were extracted, normalization used on input images, and training data for the classifier. Once properly tuned, the created system returned results more accurate than previous attempts on facial expression recognition. Based on these positive results, naïve domain adaptation is shown to successfully leverage advantages of deep CNNs for facial expression recognition.

Contributors

Agent

Created

Date Created
2016-05