Computer Sciences Commons^™

The Interaction Of Different Primary Producers And Physical And Chemical Dynamics Of An Urban Shallow Lake, Majid Sahin

Dissertations, Theses, and Capstone Projects

An artificial urban shallow lake, Prospect Park Lake (PPL), is situated on a terminal moraine in Brooklyn New York, and supplied with municipal water treated with ortho-phosphates. The constant input of the phosphate nutrient is the primary source of eutrophication in the lake. The numerous pools along the water course houses various aquatic phototrophs, which influence the water quality and the state of the system, driving conditions into favoring the survival of their species. In the first half of the dissertation, the focus of the project is on analyzing how the different primary producers in different regions of PPL affect …

Finite Gaussian Neurons: Defending Against Adversarial Attacks By Making Neural Networks Say "I Don’T Know", Felix Grezes

Dissertations, Theses, and Capstone Projects

In this work, I introduce the Finite Gaussian Neuron (FGN), a novel neuron architecture for artificial neural networks aimed at protecting against adversarial attacks.
Since 2014, artificial neural networks have been known to be vulnerable to adversarial attacks, which can fool the network into producing wrong or nonsensical outputs by making humanly imperceptible alterations to inputs. While defenses against adversarial attacks have been proposed, they usually involve retraining a new neural network from scratch, a costly task.

My works aims to:
- easily convert existing models to Finite Gaussian Neuron architecture,
- while preserving the existing model's behavior on real …

Data-Centric Machine Learning For Speech And Audio, Ali Raza Syed

Dissertations, Theses, and Capstone Projects

There is growing recognition of the importance of data-centric methods for building machine learning systems. Data-centric methods assume a fixed model and iterate over the data to improve system performance. This is in contrast to traditional model-centric approaches, which assume a fixed dataset and iterate over models for the same ends. Data-centric machine learning is driven by the observation that, beyond the size of the training data, model performance depends on factors such as the quality of the annotations, and whether the data are representative of conditions in which models will be deployed. This is particularly of interest in the …

Two-Phase Matheuristic For The Vehicle Routing Problem With Reverse Cross-Docking, Aldy Gunawan, Audrey Tedja Widjaja, Pieter Vansteenwegen, Vincent F. Yu

Research Collection School Of Computing and Information Systems

Cross-dockingis a useful concept used by many companies to control the product flow. It enables the transshipment process of products from suppliers to customers. This research thus extends the benefit of cross-docking with reverse logistics, since return process management has become an important field in various businesses. The vehicle routing problem in a distribution network is considered to be an integrated model, namely the vehicle routing problem with reverse cross-docking (VRP-RCD). This study develops a mathematical model to minimize the costs of moving products in a four-level supply chain network that involves suppliers, cross-dock, customers, and outlets. A matheuristic based …

Deep Learning-Based Text Recognition Of Agricultural Regulatory Document, Hua Leong Fwa, Farn Haur Chan

Research Collection School Of Computing and Information Systems

In this study, an OCR system based on deep learning techniques was deployed to digitize scanned agricultural regulatory documents comprising of certificates and labels. Recognition of the certificates and labels is challenging as they are scanned images of the hard copy form and the layout and size of the text as well as the languages vary between the various countries (due to diverse regulatory requirements). We evaluated and compared between various state-of-the-art deep learningbased text detection and recognition model as well as a packaged OCR library – Tesseract. We then adopted a two-stage approach comprising of text detection using Character …

Contrastive Transformer-Based Multiple Instance Learning For Weakly Supervised Polyp Frame Detection, Tian Yu, Guansong Pang, Fengbei Liu, Yuyuan Liu, Chong Wang, Yuanhong Chen, Johan Verjans, Gustavo Carneiro

Research Collection School Of Computing and Information Systems

Current polyp detection methods from colonoscopy videos use exclusively normal (i.e., healthy) training images, which i) ignore the importance of temporal information in consecutive video frames, and ii) lack knowledge about the polyps. Consequently, they often have high detection errors, especially on challenging polyp cases (e.g., small, flat, or partially visible polyps). In this work, we formulate polyp detection as a weakly-supervised anomaly detection task that uses video-level labelled training data to detect frame-level polyps. In particular, we propose a novel convolutional transformer-based multiple instance learning method designed to identify abnormal frames (i.e., frames with polyps) from anomalous videos (i.e., …

Constrained Multiagent Reinforcement Learning For Large Agent Population, Jiajing Ling, Arambam James Singh, Duc Thien Nguyen, Akshat Kumar

Research Collection School Of Computing and Information Systems

Learning control policies for a large number of agents in a decentralized setting is challenging due to partial observability, uncertainty in the environment, and scalability challenges. While several scalable multiagent RL (MARL) methods have been proposed, relatively few approaches exist for large scale constrained MARL settings. To address this, we first formulate the constrained MARL problem in a collective multiagent setting where interactions among agents are governed by the aggregate count and types of agents, and do not depend on agents’ specific identities. Second, we show that standard Lagrangian relaxation methods, which are popular for single agent RL, do not …

Learning To Solve Multiple-Tsp With Time Window And Rejections Via Deep Reinforcement Learning, Rongkai Zhang, Cong Zhang, Zhiguang Cao, Wen Song, Puay Siew Tan, Jie Zhang, Bihan Wen, Justin Dauwels

Research Collection School Of Computing and Information Systems

We propose a manager-worker framework (the implementation of our model is publically available at: https://github.com/zcaicaros/manager-worker-mtsptwr) based on deep reinforcement learning to tackle a hard yet nontrivial variant of Travelling Salesman Problem (TSP), i.e. multiple-vehicle TSP with time window and rejections (mTSPTWR), where customers who cannot be served before the deadline are subject to rejections. Particularly, in the proposed framework, a manager agent learns to divide mTSPTWR into sub-routing tasks by assigning customers to each vehicle via a Graph Isomorphism Network (GIN) based policy network. A worker agent learns to solve sub-routing tasks by minimizing the cost in terms of both …

A Carbon-Aware Planning Framework For Production Scheduling In Mining, Nurual Asyikeen Azhar, Aldy Gunawan, Shih-Fen Cheng, Erwin Leonardi

Research Collection School Of Computing and Information Systems

Managing the flow of excavated materials from a mine pit and the subsequent processing steps is the logistical challenge in mining. Mine planning needs to consider various geometric and resource constraints while maximizing the net present value (NPV) of profits over a long horizon. This mine planning problem has been modelled and solved as a precedence constrained production scheduling problem (PCPSP) using heuristics, due to its NP-hardness. However, the recent push for sustainable and carbon-aware mining practices calls for new planning approaches. In this paper, we propose an efficient temporally decomposed greedy Lagrangian relaxation (TDGLR) approach to maximize profits while …

Products Pricing And Return Strategies For The Dual Channel Retailers, Jian Liu, Xinyue Sun, Yanyan Liu

Electrical and Computer Engineering Faculty Research & Creative Works

This paper analyzed how different return strategies and return rates affect dual-channel retailers' profits and channel pricings. Return can stimulate sales; however, the return has presented significant challenges to retailers. The return has long been studied to maximize profit and pricing; however, the different return strategies for dual-channel retailers affect channel both. This paper aimed to study whether or not dual-channel retailers should allow customers to return items in two channels and whether or not the retailer should contract with the manufacturers and pay extra fees to return products. This study indicated when the retailer should allow customers' returns to …

Deep Learning For Coverage-Guided Fuzzing: How Far Are We?, Siqi Li, Xiaofei Xie, Yun Lin, Yuekang Li, Ruitao Feng, Xiaohong Li, Weimin Ge, Jin Song Dong

Research Collection School Of Computing and Information Systems

Fuzzing is a widely-used software vulnerability discovery technology, many of which are optimized using coverage-feedback. Recently, some techniques propose to train deep learning (DL) models to predict the branch coverage of an arbitrary input owing to its always-available gradients etc. as a guide. Those techniques have proved their success in improving coverage and discovering bugs under different experimental settings. However, DL models, usually as a magic black-box, are notoriously lack of explanation. Moreover, their performance can be sensitive to the collected runtime coverage information for training, indicating potentially unstable performance. In this work, we conduct a systematic empirical study on …

Risk-Aware Procurement Optimization In A Global Technology Supply Chain, Jonathan Chase, Jingfeng Yang, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Supply chain disruption, from ‘Black Swan’ events like the COVID-19 pandemic or the Russian invasion of Ukraine, to more ordinary issues such as labour disputes and adverse weather conditions, can result in delays, missed orders, and financial loss for companies that deliver products globally. Developing a risk-tolerant procurement strategy that anticipates the logistical problems incurred by disruption involves both accurate quantification of risk and cost-effective decision-making. We develop a supplier-focused risk evaluation metric that constrains a procurement optimization model for a global technology company. Our solution offers practical risk tolerance and cost-effectiveness, accounting for a range of constraints that realistically …

Leveraging Subject Matter Expertise To Optimize Machine Learning Techniques For Air And Space Applications, Philip Y. Cho

Theses and Dissertations

We develop new machine learning and statistical methods that are tailored for Air and Space applications through the incorporation of subject matter expertise. In particular, we focus on three separate research thrusts that each represents a different type of subject matter knowledge, modeling approach, and application. In our first thrust, we incorporate knowledge of natural phenomena to design a neural network algorithm for localizing point defects in transmission electron microscopy (TEM) images of crystalline materials. In our second research thrust, we use Bayesian feature selection and regression to analyze the relationship between fighter pilot attributes and flight mishap rates. We …

Truncated Matrix Power Iteration For Differentiable Dag Learning, Zhen Zhang, Ignavier Ng, Dong Gong, Yuhang Liu, Ehsan M. Abbasnejad, Mingming Gong, Kun Zhang, Javen Qinfeng Shi

Machine Learning Faculty Publications

Recovering underlying Directed Acyclic Graph structures (DAG) from observational data is highly challenging due to the combinatorial nature of the DAG-constrained optimization problem. Recently, DAG learning has been cast as a continuous optimization problem by characterizing the DAG constraint as a smooth equality one, generally based on polynomials over adjacency matrices. Existing methods place very small coefficients on high-order polynomial terms for stabilization, since they argue that large coefficients on the higher-order terms are harmful due to numeric exploding. On the contrary, we discover that large coefficients on higher-order terms are beneficial for DAG learning, when the spectral radiuses of …

Exploiting Higher-Order Derivatives In Convex Optimization Methods, Dmitry Kamzolov, Alexander Gasnikov, Pavel Dvurechensky, Artem Agafonov, Martin Takac

Machine Learning Faculty Publications

Exploiting higher-order derivatives in convex optimization is known at least since 1970’s. In each iteration higher-order (also called tensor) methods minimize a regularized Taylor expansion of the objective function, which leads to faster convergence rates if the corresponding higher-order derivative is Lipschitz-continuous. Recently a series of lower iteration complexity bounds for such methods were proved, and a gap between upper an lower complexity bounds was revealed. Moreover, it was shown that such methods can be implementable since the appropriately regularized Taylor expansion of a convex function is also convex and, thus, can be minimized in polynomial time. Only very recently …

Sr-Dcsk Cooperative Communication System With Code Index Modulation: A New Design For 6g New Radios, Yi Fang, Wang Chen, Pingping Chen, Yiwei Tao, Mohsen Guizani

Machine Learning Faculty Publications

This paper proposes a high-throughput short reference differential chaos shift keying cooperative communication system with the aid of code index modulation, referred to as CIM-SR-DCSK-CC system. In the proposed CIM-SR-DCSK-CC system, the source transmits information bits to both the relay and destination in the first time slot, while the relay not only forwards the source information bits but also sends new information bits to the destination in the second time slot. To be specific, the relay employs an N-order Walsh code to carry additional log2N information bits, which are superimposed onto the SR-DCSK signal carrying the decoded source information bits. …

Interpreting Song Lyrics With An Audio-Informed Pre-Trained Language Model, Yixiao Zhang, Junyan Jiang, Gus Xia, Simon Dixon

Machine Learning Faculty Publications

Lyric interpretations can help people understand songs and their lyrics quickly, and can also make it easier to manage, retrieve and discover songs efficiently from the growing mass of music archives. In this paper we propose BART-fusion, a novel model for generating lyric interpretations from lyrics and music audio that combines a large-scale pre-trained language model with an audio encoder. We employ a cross-modal attention module to incorporate the audio representation into the lyrics representation to help the pre-trained language model understand the song from an audio perspective, while preserving the language model’s original generative performance. We also release the …

Fdrl Approach For Association And Resource Allocation In Multi-Uav Air-To-Ground Iomt Network, Abegaz Mohammed, Aiman Erbad, Hayla Nahom, Abdullatif Albaseer, Mohammed Abdallah, Mohsen Guizani

Machine Learning Faculty Publications

In 6G networks, unmanned aerial vehicles (UAVs) can serve as aerial flying base stations (AFBS) with aerial mobile edge computing (AMEC) server capabilities. AFBS is an increasingly popular solution for delivering time-sensitive applications, extending network coverage, and assisting ground base stations in the healthcare systems for remote areas with limited infrastructure. Furthermore, the UAVs are deployed in the healthcare system to support the Internet of medical things (IoMT) devices in data collection, medical equipment distribution, and providing smart services. However, ensuring the privacy and security of patients’ data with the limited UAV resources is a major challenge. In this paper, …

Reconfigurable Intelligent Surfaces And Capacity Optimization: A Large System Analysis, Aris L. Moustakas, George C. Alexandropoulos, Mérouane Debbah

Machine Learning Faculty Publications

Reconfigurable Intelligent Surfaces (RISs), comprising large numbers of low-cost and almost passive metamaterials with tunable reflection properties, have been recently proposed as an enabling technology for programmable wireless propagation environments. In this paper, we present asymptotic closed-form expressions for the mean and variance of the mutual information metric for a multi-antenna transmitter-receiver pair in the presence of multiple RISs, using methods from statistical physics. While nominally valid in the large system limit, we show that the derived Gaussian approximation for the mutual information can be quite accurate, even for modest-sized antenna arrays and metasurfaces. The above results are particularly useful …

Transformnet: Self-Supervised Representation Learning Through Predicting Geometric Transformations, Muhammad Ali, Sayed Hashim

Computer Vision Faculty Publications

Deep neural networks need a big amount of training data, while in the real world there is a scarcity of data available for training purposes. To resolve this issue unsupervised methods are used for training with limited data. In this report, we describe the unsupervised semantic feature learning approach for recognition of the geometric transformation applied to the input data. The basic concept of our approach is that if someone is unaware of the objects in the images, he/she would not be able to quantitatively predict the geometric transformation that was applied to them. This self supervised scheme is based …

An Analysis Of Android Malware Detection Using Tree Learning Techniques, Kyler D. Dickey

Student Theses and Dissertations

Android malware is a growing threat, coinciding with the increasing adoption of the Android platform. Malware detection methods used to maintain user privacy and system integrity are increasingly becoming the subject of research. Many new methods studied employ learning algorithms to detect malicious programs. This study investigates the use of byte and opcode frequency features as inputs for tree-based machine learning methods. The algorithm is optimized to reduce overfitting given input hyperparameter combinations and is tuned using cross-validation procedures. Lastly, the study deliberates on possible avenues for future research to gather more concrete evidence for the efficacy and cost-effectiveness of …

Image Dehazing Network Based On Densely Connected Residual Block And Channel Pixel Attention, Weidong Jin, Shuli Zhang, Peng Tang, Man Zhang

Journal of System Simulation

Abstract: Abstruct: A lot of research achievements have been made in image dehazing based on neural network,but there aiming at the fog residue, even the color distortion and texture loss, in complex outdoor image dehazing, an image dehazing network based on densely connected residual block and channel pixel attention is proposed. Densely connected residual blocks are used to extract and fuse the features of foggy images,and the repair module with channel pixel attention mechanism is used to repair the color and texture of the feature maps. The experimental results show that, compared with the existing methods, the proposed method and …

Research On Motion Recognition And Tracking For Space Survey And Launch Tasks, Bin Ren, Xiaoyu Wang

Journal of System Simulation

Abstract: Space survey and launch task has high precision and long cycle, and needs to be exposed to direct sunlight for a long time, so that the non-contact action calibration and comparison in a virtual working environment is an efficient way to improve the mission completion success rate. Aiming at the real-time motion tracking of aerospace personnel, a keyframe optimization algorithm for the action recognition is proposed. According to the bone data in the depth image, the bone features are extracted, and the keyframes are extracted by the feature threshold. The characteristic data of the keyframe is input into bi-directional …

Sensorless Control Of Pmsm Based On An Anfis Optimized Flux Sliding Mode Observer, Huilin Zhang, Yujie Jin, Haima Yang

Journal of System Simulation

Abstract: Aiming at the low estimation accuracy of rotor speed and position and the system chattering in sensorless control of permanent magnet synchronous motor (PMSM), an adaptive neuro-fuzzy inference system (ANFIS) is proposed to optimize the flux sliding mode observer(FSMO). Compared with the traditional sliding mode observer, the FSMO improves the estimation accuracy of the rotor flux. The FSMO optimized by ANFIS realizes the on-line adjustment of the observer gain and reduces the system chattering. The improved PLL improves the estimation accuracy of the rotor speed and position. A simulation platform is established to verify the results which show …

Simulation Of Unmanned Tank Clusters Cooperative Combat Based On Military Rules, Chunyan Wang, Hao Ren, Minchi Kuang, Danfeng Wu, Xiangshu Cao, Heng Shi

Journal of System Simulation

Abstract: Modern warfare is developing towards the unmanned, informatized, and intelligent form. Being the important combat equipment in the future land warfare, unmanned tanks have greater advantages of mobility, safety, and economy. Single unmanned tank can not fulfill the complex tasks of large-scale battles as the cooperation of unmanned tank clusters can do. Focuses on the collaborative applications of unmanned tank clusters, the single unmanned tank system model is established, including dynamic control, decision-making, and weapon armor. A collaborative perception model of unmanned tank clusters is designed considering the unmanned tank's own state and the fusion situation. Based on the …

Modeling Of Traffic Flow Velocity Control Strategy For Human-Machine Mixed Driving At Signalized Intersections, Jianxu Zhang, Shuai Hu, Hongyi Jin

Journal of System Simulation

Abstract: In order to analyze the influence of speed control strategy of autonomous vehicle on the operation characteristics of traffic flow, a deterministic decision-making model for intersections with artificially driven vehicles considering the driver's influence on the acquisition of driving information is constructed. An automatic driving speed control strategy considering the influence of the speed of preceding vehicle is proposed, and the continuous Cellular Automata update rules for signalized intersections are constructed respectively. By introducing the different penetration rates of automatic driving, road saturation and control area length parameters, the influence of CAV speed control strategy on the traffic …

Research On Passenger Ship Evacuation Simulation Based On Social Force Model, Qimiao Xie, Shuaishuai Guo

Journal of System Simulation

Abstract: Aiming at the influence of group behavior and different evacuation methods on the passenger ship evacuation process. Three evacuation methods of passengers arriving at the assembly stations with and without group behavior are provided, and the passenger assembly time, congestion area, congestion timing and duration are analyzed. The simulation results show that the group behavior has a significant effect on the passenger assembly time and increases the variation range of the passenger assembly time, and the congestion area with and without group behavior remains the same. The influences of group behavior on the congestion timing and duration are complicated, …

Layout Planning Of Metro-Based Underground Logistics System Network Considering Fuzzy Uncertainties, Wanjie Hu, Jianjun Dong, Rui Ren, Zhilong Chen

Journal of System Simulation

Abstract: Aming at the network design and optimization of metro-based urban underground logistics under uncertainties, the facility components of two-tier metro-based underground logistics system (M-ULS) are proposed. Focus on the comprehensive costs and system utilization rate, a M-ULS network flow assignment model is established based on the expectation of environmental benefits of underground freight transport. a M-ULS network location-allocation-routing fuzzy random programming model is established, and a crisp linearization method is presented. A solution portfolio combining discrete binary chaos particle swarm optimization-genetic algorithm and exact algorithms is designed for combinatorial optimization. Effectiveness of the presented models and algorithms is verified …

Variable Pitch Control Of Wind Power Generation System Based On Wiener Model, Yue Xu, Li Jia, Xuanyi Fu

Journal of System Simulation

Abstract: Strong nonlinearity and large fluctuation are the characteristics of wind power generation system. Quickly controlling the output power of wind turbines within the rated range under wind speed random changes is the major problem of wind power system control. Aiming at the pitch control of 5 MW wind turbines, a pitch control scheme for wind power generation systems based on the Wiener model is proposed. On the basis of the special structure in which the linear and nonlinear links of the Wiener model can be separated, the controlled object of a generalized wind power system with linear properties …

Parallel Live Performance Simulation Based On A Multidimensional Hierarchy And Application, Jingsi Yang, Tianyu Huang, Gangyi Ding, Lijie Li, Peng Li

Journal of System Simulation

Abstract: A parallel simulation method is proposed for modern live performance. By decomposing the live performance process from the top down, this method assists creators in delivering stage design and control with time and space constraints, which is unattainable for traditional live performances. A multi-layer constraint hierarchy is constructed to apply parallel simulation to art performances. The live performance procedure is continuously optimized by leveraging the circulation of data between virtual and physical stages. The parallel simulation method for stage space has been applied to a digital TV stage for ten years. The experiments show that parallel live performance simulation …