Artificial Intelligence and Robotics Commons^™

Developing Grounded Goals Through Instant Replay Learning, Lisa Meeden, Douglas S. Blank

Computer Science Faculty Research and Scholarship

This paper describes and tests a developmental architecture that enables a robot to explore its world, to find and remember interesting states, to associate these states with grounded goal representations, and to generate action sequences so that it can re-visit these states of interest. The model is composed of feed-forward neural networks that learn to make predictions at two levels through a dual mechanism of motor babbling for discovering the interesting goal states and instant replay learning for developing the grounded goal representations. We compare the performance of the model with grounded goal representations versus random goal representations, and find …

Designing An Ai That Cares

SIGNED: The Magazine of The Hong Kong Design Institute

The breakthrough that could change AI from being a plaything to being a playmate with which humans can have meaningful interations may be about to come from a seemingly unlikely source.

3½ Problems For Digital Assistants

SIGNED: The Magazine of The Hong Kong Design Institute

Digital home assistants promise to make life easier and happier. But a few problems stand in their way

Ai Centaurs

SIGNED: The Magazine of The Hong Kong Design Institute

As artificial intelligence outstrips human intelligence, AIs can now beat humans at any game. A pessimist might claim that this marks the end of the line for play. But a mythical beast has come to save playtime from the robots.

Improving Speech Recognition For Interviews With Both Clean And Telephone Speech, Sung Woo Choi

Journal of Undergraduate Research at Minnesota State University, Mankato

High quality automatic speech recognition (ASR) depends on the context of the speech. Cleanly recorded speech has better results than speech recorded over telephone lines. In telephone speech, the signal is band-pass filtered which limits frequencies available for computation. Consequently, the transmitted speech signal may be distorted by noise, causing higher word error rates (WER). The main goal of this research project is to examine approaches to improve recognition of telephone speech while maintaining or improving results for clean speech in mixed telephone-clean speech recordings, by reducing mismatches between the test data and the available models. The test data includes …

Machine Learning Approach To Retrieving Physical Variables From Remotely Sensed Data, Fazlul Shahriar

Dissertations, Theses, and Capstone Projects

Scientists from all over the world make use of remotely sensed data from hundreds of satellites to better understand the Earth. However, physical measurements from an instrument is sometimes missing either because the instrument hasn't been launched yet or the design of the instrument omitted a particular spectral band. Measurements received from the instrument may also be corrupt due to malfunction in the detectors on the instrument. Fortunately, there are machine learning techniques to estimate the missing or corrupt data. Using these techniques we can make use of the available data to its full potential.

We present work on four …

Comparing And Improving Facial Recognition Method, Brandon Luis Sierra

Electronic Theses, Projects, and Dissertations

Facial recognition is the process in which a sample face can be correctly identified by a machine amongst a group of different faces. With the never-ending need for improvement in the fields of security, surveillance, and identification, facial recognition is becoming increasingly important. Considering this importance, it is imperative that the correct faces are recognized and the error rate is as minimal as possible. Despite the wide variety of current methods for facial recognition, there is no clear cut best method. This project reviews and examines three different methods for facial recognition: Eigenfaces, Fisherfaces, and Local Binary Patterns to determine …

Machine Learning Algorithms For Automated Satellite Snow And Sea Ice Detection, George Bonev

Dissertations, Theses, and Capstone Projects

The continuous mapping of snow and ice cover, particularly in the arctic and poles, are critical to understanding the earth and atmospheric science. Much of the world's sea ice and snow covers the most inhospitable places, making measurements from satellite-based remote sensors essential. Despite the wealth of data from these instruments many challenges remain. For instance, remote sensing instruments reside on-board different satellites and observe the earth at different portions of the electromagnetic spectrum with different spatial footprints. Integrating and fusing this information to make estimates of the surface is a subject of active research.

In response to these challenges, …

The Future Is Coming : Research On Maritime Communication Technology For Realization Of Intelligent Ship And Its Impacts On Future Maritime Management, Jiacheng Ke

Maritime Safety & Environment Management Dissertations (Dalian)

No abstract provided.

Rating By Ranking: An Improved Scale For Judgement-Based Labels, Jack O'Neill, Sarah Jane Delany, Brian Mac Namee

Conference papers

Labels representing value judgements are commonly elicited using an interval scale of absolute values. Data collected in such a manner is not always reliable. Psychologists have long recognized a number of biases to which many human raters are prone, and which result in disagreement among raters as to the true gold standard rating of any particular object. We hypothesize that the issues arising from rater bias may be mitigated by treating the data received as an ordered set of preferences rather than a collection of absolute values. We experiment on real-world and artificially generated data, finding that treating label ratings …

Machine Learning Based Protein Sequence To (Un)Structure Mapping And Interaction Prediction, Sumaiya Iqbal

LSU New Orleans Theses and Dissertations

Proteins are the fundamental macromolecules within a cell that carry out most of the biological functions. The computational study of protein structure and its functions, using machine learning and data analytics, is elemental in advancing the life-science research due to the fast-growing biological data and the extensive complexities involved in their analyses towards discovering meaningful insights. Mapping of protein’s primary sequence is not only limited to its structure, we extend that to its disordered component known as Intrinsically Disordered Proteins or Regions in proteins (IDPs/IDRs), and hence the involved dynamics, which help us explain complex interaction within a cell that …

Hybrid Recommender Systems With Deep Learning, Fei Li

LSU Master's Theses

As one of the most popular recommendation algorithms, collaborative filtering (CF) suggests items favored by like-minded based on user ratings. However, CF performs worse for users and items with fewer ratings, which is known as the cold-start problem. On the other hand, the auxiliary information of items such as images and reviews can be helpful for relieving the cold-start issue and improving recommendation accuracy. How to effectively extract features from heterogeneous auxiliary information and integrate them with collaborative filtering remains a big challenge. In this thesis, we propose a tightly-coupled hybrid recommender system named Fusion-MF-Mix via a deep fusion framework, …

Ancr—An Adaptive Network Coding Routing Scheme For Wsns With Different-Success-Rate Links †, Xiang Ji, Anwen Wang, Chunyu Li, Chun Ma, Yao Peng, Dajin Wang, Qingyi Hua, Feng Chen, Dingyi Fang

Department of Computer Science Faculty Scholarship and Creative Works

As the underlying infrastructure of the Internet of Things (IoT), wireless sensor networks (WSNs) have been widely used in many applications. Network coding is a technique in WSNs to combine multiple channels of data in one transmission, wherever possible, to save node’s energy as well as increase the network throughput. So far most works on network coding are based on two assumptions to determine coding opportunities: (1) All the links in the network have the same transmission success rate; (2) Each link is bidirectional, and has the same transmission success rate on both ways. However, these assumptions may not be …

Comparison Of Visual Datasets For Machine Learning, Kent Gauen, Ryan Dailey, John Laiman, Yuxiang Zi, Nirmal Asokan, Yung-Hsiang Lu, George K. Thiruvathukal, Mei-Ling Shyu, Shu-Ching Chen

Computer Science: Faculty Publications and Other Works

One of the greatest technological improvements in recent years is the rapid progress using machine learning for processing visual data. Among all factors that contribute to this development, datasets with labels play crucial roles. Several datasets are widely reused for investigating and analyzing different solutions in machine learning. Many systems, such as autonomous vehicles, rely on components using machine learning for recognizing objects. This paper compares different visual datasets and frameworks for machine learning. The comparison is both qualitative and quantitative and investigates object detection labels with respect to size, location, and contextual information. This paper also presents a new …

Applying Machine Learning To Computational Chemistry: Can We Predict Molecular Properties Faster Without Compromising Accuracy?, Hanjing Xu, Pradeep Gurunathan, Lyudmila Slipchenko

The Summer Undergraduate Research Fellowship (SURF) Symposium

Non-covalent interactions are crucial in analyzing protein folding and structure, function of DNA and RNA, structures of molecular crystals and aggregates, and many other processes in the fields of biology and chemistry. However, it is time and resource consuming to calculate such interactions using quantum-mechanical formulations. Our group has proposed previously that the effective fragment potential (EFP) method could serve as an efficient alternative to solve this problem. However, one of the computational bottlenecks of the EFP method is obtaining parameters for each molecule/fragment in the system, before the actual EFP simulations can be carried out. Here we present a …

Improving Pattern Recognition And Neural Network Algorithms With Applications To Solar Panel Energy Optimization, Ernesto Zamora Ramos

UNLV Theses, Dissertations, Professional Papers, and Capstones

Artificial Intelligence is a big part of automation and with today's technological advances, artificial intelligence has taken great strides towards positioning itself as the technology of the future to control, enhance and perfect automation. Computer vision includes pattern recognition and classification and machine learning. Computer vision is at the core of decision making and it is a vast and fruitful branch of artificial intelligence. In this work, we expose novel algorithms and techniques built upon existing technologies to improve pattern recognition and neural network training, initially motivated by a multidisciplinary effort to build a robot that helps maintain and optimize …

Formresnet: Formatted Residual Learning For Image Restoration, Jianbo Jiao, Wei-Chih Tu, Shengfeng He

Research Collection School Of Computing and Information Systems

In this paper, we propose a deep CNN to tackle the image restoration problem by learning the structured residual. Previous deep learning based methods directly learn the mapping from corrupted images to clean images, and may suffer from the gradient exploding/vanishing problems of deep neural networks. We propose to address the image restoration problem by learning the structured details and recovering the latent clean image together, from the shared information between the corrupted image and the latent image. In addition, instead of learning the pure difference (corruption), we propose to add a 'residual formatting layer' to format the residual to …

Learning To Hallucinate Face Images Via Component Generation And Enhancement, Yibing Song, Jiawei Zhang, Shengfeng He, Linchao Bao, Qingxiong Yang

Research Collection School Of Computing and Information Systems

We propose a two-stage method for face hallucination. First, we generate facial components of the input image using CNNs. These components represent the basic facial structures. Second, we synthesize fine-grained facial structures from high resolution training images. The details of these structures are transferred into facial components for enhancement. Therefore, we generate facial components to approximate ground truth global appearance in the first stage and enhance them through recovering details in the second stage. The experiments demonstrate that our method performs favorably against state-of-the-art methods.

Dynamic Adversarial Mining - Effectively Applying Machine Learning In Adversarial Non-Stationary Environments., Tegjyot Singh Sethi

Electronic Theses and Dissertations

While understanding of machine learning and data mining is still in its budding stages, the engineering applications of the same has found immense acceptance and success. Cybersecurity applications such as intrusion detection systems, spam filtering, and CAPTCHA authentication, have all begun adopting machine learning as a viable technique to deal with large scale adversarial activity. However, the naive usage of machine learning in an adversarial setting is prone to reverse engineering and evasion attacks, as most of these techniques were designed primarily for a static setting. The security domain is a dynamic landscape, with an ongoing never ending arms race …

Accurate And Justifiable : New Algorithms For Explainable Recommendations., Behnoush Abdollahi

Electronic Theses and Dissertations

Websites and online services thrive with large amounts of online information, products, and choices, that are available but exceedingly difficult to find and discover. This has prompted two major paradigms to help sift through information: information retrieval and recommender systems. The broad family of information retrieval techniques has given rise to the modern search engines which return relevant results, following a user's explicit query. The broad family of recommender systems, on the other hand, works in a more subtle manner, and do not require an explicit query to provide relevant results. Collaborative Filtering (CF) recommender systems are based on algorithms …

Investigating Genetic Algorithm Optimization Techniques In Video Games, Nathan Ambuehl

Undergraduate Honors Theses

Immersion is essential for player experience in video games. Artificial Intelligence serves as an agent that can generate human-like responses and intelligence to reinforce a player’s immersion into their environment. The most common strategy involved in video game AI is using decision trees to guide chosen actions. However, decision trees result in repetitive and robotic actions that reflect an unrealistic interaction. This experiment applies a genetic algorithm that explores selection, crossover, and mutation functions for genetic algorithm implementation in an isolated Super Mario Bros. pathfinding environment. An optimized pathfinding AI can be created by combining an elitist selection strategy with …

Personas For Content Creators Via Decomposed Aggregate Audience Statistics, Jisun An, Haewoon Kwak, Bernard J. Jansen

Research Collection School Of Computing and Information Systems

We propose a novel method for generating personas based on online user data for the increasingly common situation of content creators distributing products via online platforms. We use non-negative matrix factorization to identify user segments and develop personas by adding personality such as names and photos. Our approach can develop accurate personas representing real groups of people using online user data, versus relying on manually gathered data.

Impact Of Artificial Intelligence, Robotics, And Automation On Higher Education, Keng Siau

Research Collection School Of Computing and Information Systems

What is the future of higher education in the AI age? Higher education is expected to be challenged by AI, Robotics, and Automation on multiple fronts. First and foremost, AI, robotics, and automation are replacing and will continue to replace jobs and revolutionalize every nation’s economy and disrupt economic development in the world. Millions of job are expected to be replaced by machines (Zhao & Siau, 2017). Many manufacturing jobs have already been replaced by robots and middle class jobs may be taken over by AI in the near future (Siau & Yang, 2017).The short and long term impact on …

Online Multitask Relative Similarity Learning, Shuji Hao, Peilin Zhao, Yong Liu, Steven C. H. Hoi, Chunyan Miao

Research Collection School Of Computing and Information Systems

Relative similarity learning (RSL) aims to learn similarity functions from data with relative constraints. Most previous algorithms developed for RSL are batch-based learning approaches which suffer from poor scalability when dealing with real world data arriving sequentially. These methods are often designed to learn a single similarity function for a specific task. Therefore, they may be sub-optimal to solve multiple task learning problems. To overcome these limitations, we propose a scalable RSL framework named OMTRSL (Online Multi-Task Relative Similarity Learning). Specifically, we first develop a simple yet effective online learning algorithm for multi-task relative similarity learning. Then, we also propose …

Deepfacade: A Deep Learning Approach To Facade Parsing, Hantang Liu, Jialiang Zhang, Jianke Zhu, Steven C. H. Hoi

Research Collection School Of Computing and Information Systems

The parsing of building facades is a key component to the problem of 3D street scenes reconstruction, which is long desired in computer vision. In this paper, we propose a deep learning based method for segmenting a facade into semantic categories. Man-made structures often present the characteristic of symmetry. Based on this observation, we propose a symmetric regularizer for training the neural network. Our proposed method can make use of both the power of deep neural networks and the structure of man-made architectures. We also propose a method to refine the segmentation results using bounding boxes generated by the Region …

Proactive And Reactive Coordination Of Non-Dedicated Agent Teams Operating In Uncertain Environments, Pritee Agrawal, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

Domains such as disaster rescue, security patrolling etc. often feature dynamic environments where allocations of tasks to agents become ineffective due to unforeseen conditions that may require agents to leave the team. Agents leave the team either due to arrival of high priority tasks (e.g., emergency, accident or violation) or due to some damage to the agent. Existing research in task allocation has only considered fixed number of agents and in some instances arrival of new agents on the team. However, there is little or no literature that considers situations where agents leave the team after task allocation. To that …

Mechanism Design For Strategic Project Scheduling, Pradeep Varakantham, Na Fu

Research Collection School Of Computing and Information Systems

Organizing large scale projects (e.g., Conferences, IT Shows, F1 race) requires precise scheduling of multiple dependent tasks on common resources where multiple selfish entities are competing to execute the individual tasks. In this paper, we consider a well studied and rich scheduling model referred to as RCPSP (Resource Constrained Project Scheduling Problem). The key change to this model that we consider in this paper is the presence of selfish entities competing to perform individual tasks with the aim of maximizing their own utility. Due to the selfish entities in play, the goal of the scheduling problem is no longer only …

An Analysis Of The Application Of Simplified Silhouette To The Evaluation Of K-Means Clustering Validity, Fei Wang, Hector-Hugo Franco-Penya, John D. Kelleher, John Pugh, Robert J. Ross

Conference papers

Silhouette is one of the most popular and effective internal measures for the evaluation of clustering validity. Simplified Silhouette is a computationally simplified version of Silhouette. However, to date Simplified Silhouette has not been systematically analysed in a specific clustering algorithm. This paper analyses the application of Simplified Silhouette to the evaluation of k-means clustering validity and compares it with the k-means Cost Function and the original Silhouette from both theoretical and empirical perspectives. The theoretical analysis shows that Simplified Silhouette has a mathematical relationship with both the k-means Cost Function and the original Silhouette, while empirically, we show that …

Motion-Capture-Based Hand Gesture Recognition For Computing And Control, Andrew Gardner

Doctoral Dissertations

This dissertation focuses on the study and development of algorithms that enable the analysis and recognition of hand gestures in a motion capture environment. Central to this work is the study of unlabeled point sets in a more abstract sense. Evaluations of proposed methods focus on examining their generalization to users not encountered during system training.

In an initial exploratory study, we compare various classification algorithms based upon multiple interpretations and feature transformations of point sets, including those based upon aggregate features (e.g. mean) and a pseudo-rasterization of the capture space. We find aggregate feature classifiers to be balanced across …

Speech Based Machine Learning Models For Emotional State Recognition And Ptsd Detection, Debrup Banerjee

Electrical & Computer Engineering Theses & Dissertations

Recognition of emotional state and diagnosis of trauma related illnesses such as posttraumatic stress disorder (PTSD) using speech signals have been active research topics over the past decade. A typical emotion recognition system consists of three components: speech segmentation, feature extraction and emotion identification. Various speech features have been developed for emotional state recognition which can be divided into three categories, namely, excitation, vocal tract and prosodic. However, the capabilities of different feature categories and advanced machine learning techniques have not been fully explored for emotion recognition and PTSD diagnosis. For PTSD assessment, clinical diagnosis through structured interviews is a …