Computer Sciences Commons^™

Creating In Our Own Image: Artificial Intelligence And The Image Of God, Noreen L. Herzfeld

Theology Faculty Publications

There is remarkable convergence between twentieth-century interpretations of the image of God (imago Dei), what it means for human beings to be created in God's image, and approaches toward creating in our own image in the field of artificial intelligence (AI). Both fields have viewed the intersection between God and humanity or humanity and computers in terms of either (1) a property or set of properties such as intelligence, (2) the functions we engage in or are capable of, or (3) the relationships we establish and maintain. Each of these three approaches reflects a different understanding of what …

Modular Machine Learning Methods For Computer-Aided Diagnosis Of Breast Cancer, Mia Kathleen Markey '94

Doctoral Dissertations

The purpose of this study was to improve breast cancer diagnosis by reducing the number of benign biopsies performed. To this end, we investigated modular and ensemble systems of machine learning methods for computer-aided diagnosis (CAD) of breast cancer. A modular system partitions the input space into smaller domains, each of which is handled by a local model. An ensemble system uses multiple models for the same cases and combines the models' predictions.

Five supervised machine learning techniques (LDA, SVM, BP-ANN, CBR, CART) were trained to predict the biopsy outcome from mammographic findings (BIRADS™) and patient age based on a …

Fuzzy Product -Limit Estimators: Soft Computing In The Presence Of Very Small And Highly Censored Data Sets, Kian Lawrence Pokorny

Doctoral Dissertations

When very few data are available and a high proportion of the data is censored, accurate estimates of reliability are problematic. Standard statistical methods require a more complete data set, and with any fewer data, expert knowledge or heuristic methods are required. In the current research a computational system is developed that obtains a survival curve, point estimate, and confidence interval about the point estimate.

The system uses numerical methods to define fuzzy membership functions about each data point that quantify uncertainty due to censoring. The “fuzzy” data are then used to estimate a survival curve, and the mean survival …

Driving In Traffic: Short-Range Sensing For Urban Collision Avoidance, Chuck Thorpe, Dave Duggins, Jay Gowdy, Rob Maclaughlin, Christoph Mertz, Mel Siegel, Arne Suppe, Bob Wang, Teruko Yata

Research Collection School Of Computing and Information Systems

Intelligent vehicles are beginning to appear on the market, but so far their sensing and warning functions only work on the open road. Functions such as runoff-road warning or adaptive cruise control are designed for the uncluttered environments of open highways. We are working on the much more difficult problem of sensing and driver interfaces for driving in urban areas. We need to sense cars and pedestrians and curbs and fire plugs and bicycles and lamp posts; we need to predict the paths of our own vehicle and of other moving objects; and we need to decide when to issue …

A New Approach For Weighted Constraint Satisfaction, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

We consider the Weighted Constraint Satisfaction Problem which is an important problem in Artificial Intelligence. Given a set of variables, their domains and a set of constraints between variables, our goal is to obtain an assignment of the variables to domain values such that the weighted sum of satisfied constraints is maximized. In this paper, we present a new approach based on randomized rounding of semidefinite programming relaxation. Besides having provable worst-case bounds for domain sizes 2 and 3, our algorithm is simple and efficient in practice, and produces better solutions than some other polynomial-time algorithms such as greedy and …

Investigation Of Cooperative Behavior In Autonomous Wide Search Munitions, Robert E. Dunkel Iii

Theses and Dissertations

The purpose of this research is to investigate the effectiveness of wide-area search munitions in various scenarios using different cooperative behavior algorithms. The general scenario involves multiple autonomous munitions searching for an unknown number of targets of different priority in unknown locations. Three cooperative behavior algorithms are used in each scenario: no cooperation, cooperative attack only, and cooperative classification and attack. In the cooperative cases, the munitions allocate tasks on-line as a group, using linear programming techniques to determine the optimum allocation. Each munition provides inputs to the task allocation routine in the form of probabilities of successfully being able …

A Genetic Algorithm Solution To The Shortest Path Problem In Ospf And Mpls, Wee Jing Tee Wee Jing

Student Works (2000-2009)

This project studies and explores the potential of using genetic algorithm to solve the shortest path problem in Open Shortest Path First (OSPF) and Multiprotocol Label Switching (MPLS). The most critical task for developing a genetic algorithm to the shortest path problem is to how to encode a path in a network. In this project, two genetic algorithm solutions arc developed for the above two problem domains, i.e. Previous-node-based Encoding to solve the shortest path problem in OSPF and Priority-based Encoding to solve the shortest path problem in MPLS. For each of the shortest path problem domains, the proposed solution …

Level Set Segmentation Of Mr Images For Extraction Of Femur Bone And Tissues, Christina Shanti Nayagam

Student Works (2000-2009)

This research explores a potentially useful segmentation algorithm, known as the level set method. It is suitable for images obtained from the Magnetic Resonance Imaging (MRJ) modality, despite the fact that MR images have low contrast between bone and tissue. The level set method is a numerical technique designed to track the evolution of an interface. The fast marching version of the method is implemented for two-dimensional (2-D) and three-dimensional (3-D) segmentation in this research. Femur segmentation is the main thrust of this thesis, however brain and heart images are also presented. Pre-processing steps are first performed for the 2-0 …

An Investigation Into The Concepts And Applicability Of Agent Technologies, Anne White

Theses

The software world is one of great richness and diversity

Even though the concept of software agents date back to the days of AI (Artificial Intelligence) work (1970’s) the word “Agent” is currently in vogue in the computing press and computer science communities.

This thesis presents a review of the ongoing evolution of software agents, places agents in context within today’s software domain, and takes a closer look at the ongoing debate of what really constitutes an '"Agenf\ The numerous dimensions of classification are studied and an opinion of the attributes that an agent should encompass is put forward. Leading …

The Cyborgian Self: Toward A Critical Social Theory Of Cyberspace, Michael Ian Borer

Reconstruction: Studies in Contemporary Culture

[First paragraph]

Contemporary social theory currently remains at a virtual standstill, quivering over the decision to radically leave the past behind or to continue within the historical narrative of the Enlightenment. Postmodern social theorists, advocating the position that we have, in fact, entered a new historical epoch, pose serious challenges to our perception of modernity and cultural identity. As an influential strategy that has infiltrated both the humanities and the social sciences for more than thirty years, postmodernism can no longer be dismissed as merely a fad or trend. In a world where the use of complex, and often mobile, …

Terra Incognita, Leslie Hill

Reconstruction: Studies in Contemporary Culture

No abstract provided.

Pickup And Delivery Problem With Time Windows: Algorithms And Test Case Generation, Hoong Chuin Lau, Zhe Liang

Research Collection School Of Computing and Information Systems

In the pickup and delivery problem with time windows (PDPTW), vehicles have to transport loads from origins to destinations respecting capacity and time constraints. In this paper, we present a two-phase method to solve the PDPTW. In the first phase, we apply a novel construction heuristics to generate an initial solution. In the second phase, a tabu search method is proposed to improve the solution. Another contribution of this paper is a strategy to generate good problem instances and benchmarking solutions for PDPTW, based on Solomon's benchmark test cases for VRPTW. Experimental results show that our approach yields very good …

A Multi-Agent Framework For Supporting Intelligent Fourth-Party Logistics, Hoong Chuin Lau, G. Lo

Research Collection School Of Computing and Information Systems

A distributed intelligent agent-based framework that supports fourth-party logistics optimization under a web-based e-Commerce environment has been proposed in this paper. In the framework, customer job requests come through an e-Procurement service. These requests are consolidated and pushed to the e-Market Place service periodically. The e-Market Place then serves as a broker that allows intelligent agents to bid to serve these requests optimally in real-time by solving multiple instances of underlying logistics optimization problem. The resulting system was implemented based on the Java 2 Enterprise Edition (J2EE) platform using distributed system technology for communication between objects.

Aurora Working Group: Dsr Front End Lvcsr Evaluation — Baseline Recognition System Description, Naveen Parihar, Joseph Picone

Publications

In this document we describe the features of the baseline system to be used in the Distributed Speech Recognition (DSR) front end large vocabulary continuous speech recognition (LVCSR) evaluations being conducted by the Aurora Working Group of the European Telecommunications Standards Institute (ETSI). The objective of these evaluations is to determine the robustness of different front ends for use in client/server type telecommunications applications. As such, our experiments are designed to test the following focus conditions on the DARPA Wall Street Journal (WSJ0) corpus using a 5000-word closed-loop vocabulary and a bigram language model:

1. Additive Noise: six noise conditions …

Comparison Of Two Distributed Fuzzy Logic Controllers For Flexible-Link Manipulators, Linda Z. Shi, Mohamed Trabia

Mechanical Engineering Faculty Presentations

The paper suggests that fuzzy logic controllers present a computationally efficient and robust alternative to conventional controllers. The paper presents two possible structures for the distributed fuzzy logic controller of a single-link flexible manipulator. A linear quadratic regulator method is used to prove the effectiveness of fuzzy logic controllers.

Topic Detection, Tracking, And Trend Analysis Using Self-Organizing Neural Networks, Kanagasabai Rajaraman, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

We address the problem of Topic Detection and Tracking (TDT) and subsequently detecting trends from a stream of text documents. Formulating TDT as a clustering problem in a class of self-organizing neural networks, we propose an incremental clustering algorithm. On this setup we show how trends can be identified. Through experimental studies, we observe that our method enables discovering interesting trends that are deducible only from reading all relevant documents.

Web Information Retrieval And Monitoring Using Adaptive Agent, Yuen Beng Chong

Student Works (2000-2009)

Internet is the information house. There are million of pages posted in the Internet, and still growing in exponential. Locate a web page, without a search engines, is like a blind explorer. There are many search engines in the existence world, but more new search engines is under construction. Each search engine has its advantage and disadvantage, depend on the need of the searchers. The projects aims to develop an agent, with some advanced features, to allow the searchers obtain the information from the Internet easily. The advanced features included, table of contents preview, chart of relevant, session review and …

To Explore Agent Technology In E-Commerce Mighty House Agent, Thirumalai Phiyadharshini

Student Works (2000-2009)

Agent technology is becoming more popular among system designers who want their system to be more personalized, continuously running and semi-autonomous. These properties make agents useful for a wide variety of information and process management tasks. It should come as no surprise that these same qualities are particularly useful for the information-rich and process-rich environment of electronic commerce. As such agent technology in electronic commerce (e-commerce) would be essential to improve on-line shopping which is becoming more and more popular these days. It is in these roles that agent system designers have the challenge to accurately identify and the opportunity …

Hopfield Model For Shortest Path Computation And Routing In Atm Network, Chee Weng Lee

Student Works (2000-2009)

This research focuses on the application of Hopfield neural network and Boltmann machine in solving the shortest path routing problem in the ATM network environment. Hopfield neural network and Boltzmann machine are two types of neural network which are commonly used for solving optimization problem such as the shortest path routing problem. The objectives of this research are to construct a Hopfield neural network and a Boltzmann machine for solving the shortest path routing problem in the ATM network. Both of these two types of neural network are built based on a chosen example of an A TM network. The …

Fingerprint Recognition Using Neural Networks, Eng Hoe Kennie Yeoh

Student Works (2000-2009)

Traditional methods of fingerprint verification uses either complicated feature detection algorithms that are not specific to each fingerprint, or compare two fingerprint images directly using image processing toots. The former involves very complicated calculations and tedious algorithms, and the latter tend to work poorly. In this paper it is described a new method which takes the middle ground. This paper studies the implementation of the Fast Fourier Transform and Artificial Neural Networks into the recognition of fingerprints. With tests conducted on the implementation of the Fourier Transform as a method of fingerprint feature extraction, the use of the Fourier Transform …

Sistem Pembelajaran Cerdas Dan Pengatucaraan C (Spc), Ahmad Norzam Yusri

Student Works (2000-2009)

Sistem pembelajaran cerdas dan pengatucaraan C (SPC) adalah Intelligent Tutoring system (ITS) yang dibangunkan untuk pelajar-pelajar univsersiti yang mengambil kursus Sains Komputer dan Teknologi Maklumat serta pelajar fakulti kejuruteraan di mana subjek Bahasa Pengatucaraan C merupakan suatu subjek yang wajib. SPC merupakan satu alat perisian untuk memerhatikan serta mengawal pembelajaraan pelajar dan menyelesaikan masalah-masalah subjek yang khusus. Sistem pembelajaran cerdas adalah pakej arahan berasaskan komputer yang menggunakan teknik-teknik yang ditemui dalam penyelidikan-penyelidikan Kepintaran Buatan untuk membantu dalam pengajaran sesuatu subjek atau kepakaran. Tidak seperti sistem konvensional lain, rekabentuk SPC menggunakan pendekatan Cognitivisim dan ia mempunyai tiga bahagian iaitu Model Pelajar, …

Intelligent Agent For Electronic Commerce Using Neural Network Approach \, Hui Sun Yap

Student Works (2000-2009)

This project is aims to developing a tool that able to collect relevant information from the World Wide Web and a tool that can be used to assists users in decision-making in the activities of e-commerce. It i been built by using the neural network of artificial intelligence approach. In more specific, the back propagation network was been used. This report contains seven chapters that uncovered the details of the project from the beginning through the end of the system evaluation and a conclusion chapter. These chapters and its contain are been arranged as the following: Chapter I - lntroduction, …

Intelligent Agent For Electronic Commerce, Siew Cheng Lai

Student Works (2000-2009)

The objective of this project is to develop a system that can assists a user to make decision in online transactions for residential houses. In order to achieve this objective, an intelligent agent will be built where it will help the user to find relevant information of the houses based on they requirement. Furthermore, a prediction tool will also be developed to predict the price of the required house on the market. Artificial neural network will be used here, where the LVQ network is used to build the system. The neural network will be implemented in the filtering module and …

Sistem Cerdas Pembelajaran Pembezaan Fungsi Matematik (Pfits), Sulaiman Zainab

Student Works (2000-2009)

Pembelajaran melalui komputer menjadi semakin popular dan pelbagai kajian dilakukan untuk menghasilkan sistem pembelajaran yang lebih baik dan efektif untuk menarik minat para pelajar dan meningkatkan fahaman dan kebolehan pelajar. Projek ini secara khususnya memberi penumpuan terhadap pembangunan Sistem Cerdas Pembelajaran (Intelligent Tutoring System - ITS) bagi Pembezaan Fungsi (PFITS). Pembezaan merupakan satu topik kalkulus yang melibatkan fahaman beberapa langkah penyelesaian dengan menggunakan petua-petua matematik seperti petua tambah dan petua rantai. Ia berbeza berbanding algebra yang lebih melibatkan kepada penggunaan rumus dan aplikasi rumus yang tidak melibatkan banyak langkah penyelesaian. PFITS ini juga dapat membantu pengajar untuk pembelajaan yang lebih …

Designing An Intelligent System For Genetic Biology Learning, Seenivasagam S.Gangatharan

Student Works (2000-2009)

With the changing education scenario, an issue which has come strongly on how to create intelligent tutoring system to educate learners in a more intelligent way. So a need has emerged for the development of an intelligent tutoring system. This part or thesis describes the design of a collection of intelligent systems under the name GENETIC BIOLOGY for basic genetic biology tutoring. GENETIC BIOLOGY consist of three intelligent systems which arc designed for cell, DNA and gene learning. GENETIC BIOLOGY systems employ natural language processing and various techniques normally used in the construction of intelligent systems. Production rules and frames …

Oces Sistem Pakar Kanser Ovari, Abd. Rahim Noreen

Student Works (2000-2009)

Sistem Pakar Kanser Ovari atau OCES merupakan projek tahun akhir bagi memenuhi keperluan dalam penganugerahan ljazah Sarjana Muda Sains Komputer. OCES merupakan sistem pakar yang cuba bertindak untuk menggantikan pakar pada bila-bila masa yang diperlukan dengan melakukan diagnosis ke atas pesakit kanser ovari berdasarkan gejala-gejala yang ada pada pesakit. Dalam menjalankan proses diagnosis, satu sesi soal jawab dikendalikan oleh OCES akan dijalankan dan daripada sesi ini, OCES akan mengenalpasti samada pesakit tersebut berpotensi mendapat kanser ovari dan seterusnya membcrikan cadangan tentang kaedah rawatan yang mungkin diperlukan oleh pesakit disamping mampu memberi sedikit sebanyak maklumat mengenai kanser ovari. Dengan wujudnya sistem …

Sistem Jadual Waktu Elektronik (Sjwe), Mohd Noh Mohd Nizam

Student Works (2000-2009)

Projek llmiah Tahap Akhir IT (WXES3182) ini merupakan salah satu keperluan kursus yang perlu diambil sebelum seseorang pelajar Ijazah Srujana Muda Sains Komputer itu bergelar graduan unversiti. Bagi tujuan itu saya telah membuat keputusan membina suatu sistem pentadbiran jadual waktu untuk FakuJti Sains Komputer & Teknologi Maklumat dan sistem ini saya namakan sebagai Sistem Jadual Waktu Elektronik (SJWE). SJWE ini dibangunkan oleh dua orang dan setiap orang membuat domain yang berlainan. Rakan saya Mohd. Sirhan Shabrani Bin Mt. Salleh membuat bahagian pentadbiran jadual waktu (Administration) di mana bahagian ini meliputi kerja-kerja yang perlu mempertimbangkan proses-proses yang perlu dijalankan sebelum suatu …

Online Counseling Assistant Ii (Oca Ii), Abdul Satar Roliana

Student Works (2000-2009)

Laporan projek latihan ilmiah tahap akhir ini mencadangkan tentang pembangunan sebuah sistem yang mampu membantu pelajar di dalam proses pembelajaran. Sistem yang akan dibangunkan ialah Online Counseling Assistant II (OCA II) di mana ia tertumpu kepada 3 bahagian paling utama iaitu temujanji, perbincangan dan pengumuman dalam talian. Sasaran utama pengguna sistem OCA II ini adalah terdiri daripada pelajar-pelajar di mana ia dapat mermbantu mereka meningkatkan kualiti dan prestasi pembelajaran. Pembangunan sistem ini adalah berdasarkan kepada matlamat untuk mengeksploitasikan teknologi maklumat di dalam pendidikan serta memberi kemudahan elektronik kepada masyarakat. Beberapa kajian dan penyelidikan telah dibuat menghasilkan satu analisis dan rekabentuk …

Knowledge Management Portal (Ai Department), Rahmat Nazariah

Student Works (2000-2009)

Portal pengurusan maklumat adalah satu sistem yang mana berfungsi sebagai tempat untuk mengumpul dan mencapai maklumat. Maklumat yang terdapat di dalam portal ini adalah maklumat yang terperinci tentang Jabatan Kepintaran Buatan, FSKTM, Universiti Malaya. Semua maklumat ini akan di olah kembali untuk mendapatkan sesuatu output yang berguna kepada pengguna sistem ini. Sistem portal pengurusan maklumat ini mengandungi dua modul utama iaitu Modul Pengguna Awam dan Modul Pentadbir. Modul pengguna awam membenarkan pengguna mencari informasi dan mencapai maklumat yang dipaparkan di dalam portal ini. Akan tetapi, capaian sebagai pengguna awam adalah agak terhad. Modul pihak pentadbir pula terdiri daripada 4 peringkat …

Dynamic Bandwidth Allocation Using Neural-Fuzzy In Atm Network, Yan Sing Chua

Student Works (2000-2009)

Dynamic bandwidth allocation is becoming one of the crucial issues in the design and research in the computer network. This is due to the continuous increasing demand of intensive applications that require more bandwidth while retaining higher quality. Dynamic bandwidth allocation utilises the current network state information to optimise the bandwidth distribution. The state information can be gathered through prediction using past data and measurement on current state. Agility and flexibility of dynamic bandwidth allocation using Neural-Fuzzy has the advantage that it can adapt to the state changes of the network. ATM network carries heterogeneous traffic and this causes the …