Digital Commons Network^™

Faster Rates For Compressed Federated Learning With Client-Variance Reduction, Haoyu Zhao, Konstantin Burlachenko, Zhize Li, Peter Richtarik

Research Collection School Of Computing and Information Systems

Due to the communication bottleneck in distributed and federated learning applications, algorithms using communication compression have attracted significant attention and are widely used in practice. Moreover, the huge number, high heterogeneity, and limited availability of clients result in high client -variance. This paper addresses these two issues together by proposing compressed and clientvariance reduced methods COFIG and FRECON. We prove an O( (1+\omega)3/2\surdN+ (1+\omega)N2/3 S\epsilon2 S\epsilon2 ) bound on the number of communication rounds of COFIG in the nonconvex setting, where N is the total number of clients, S is the number of clients participating in each round, \epsilon is …

Reward Penalties On Augmented States For Solving Richly Constrained Rl Effectively, Jiang Hao, Tien Mai, Pradeep Varakanthan, Minh Huy Hoang

Research Collection School Of Computing and Information Systems

Constrained Reinforcement Learning employs trajectory-based cost constraints (such as expected cost, Value at Risk, or Conditional VaR cost) to compute safe policies. The challenge lies in handling these constraints effectively while optimizing expected reward. Existing methods convert such trajectory-based constraints into local cost constraints, but they rely on cost estimates, leading to either aggressive or conservative solutions with regards to cost. We propose an unconstrained formulation that employs reward penalties over states augmented with costs to compute safe policies. Unlike standard primal-dual methods, our approach penalizes only infeasible trajectories through state augmentation. This ensures that increasing the penalty parameter always …

Decentralized Multimedia Data Sharing In Iov: A Learning-Based Equilibrium Of Supply And Demand, Jiani Fan, Minrui Xu, Jiale Guo, Lwin Khin Shar, Jiawen Kang, Dusit Niyato, Kwok-Yan Lam

Research Collection School Of Computing and Information Systems

The Internet of Vehicles (IoV) has great potential to transform transportation systems by enhancing road safety, reducing traffic congestion, and improving user experience through onboard infotainment applications. Decentralized data sharing can improve security, privacy, reliability, and facilitate infotainment data sharing in IoVs. However, decentralized data sharing may not achieve the expected efficiency if there are IoV users who only want to consume the shared data but are not willing to contribute their own data to the community, resulting in incomplete information observed by other vehicles and infrastructure, which can introduce additional transmission latency. Therefore, in this paper, by modeling the …

Understanding The Impact Of Trade Policy Effect Uncertainty On Firm-Level Innovation Investment: A Deep Learning Approach, Daniel Chang, Nan Hu, Peng Liang, Morgan Swink

Research Collection School Of Computing and Information Systems

Integrating the real options perspective and resource dependence theory, this study examines how firms adjust their innovation investments to trade policy effect uncertainty (TPEU), a less studied type of firm specific, perceived environmental uncertainty in which managers have difficulty predicting how potential policy changes will affect business operations. To develop a text-based, context-dependent, time-varying measure of firm-level perceived TPEU, we apply Bidirectional Encoder Representations from Transformers (BERT), a state-of-the-art deep learning approach. We apply BERT to analyze the texts of mandatory Management Discussion and Analysis (MD&A) sections of annual reports for a sample of 22,669 firm-year observations from 3,181 unique …

Stopguess: A Framework For Public-Key Authenticated Encryption With Keyword Search, Tao Xiang, Zhongming Wang, Biwen Chen, Xiaoguo Li, Peng Wang, Fei Chen

Research Collection School Of Computing and Information Systems

Public key encryption with keyword search (PEKS) allows users to search on encrypted data without leaking the keyword information from the ciphertexts. But it does not preserve keyword privacy within the trapdoors, because an adversary (e.g., untrusted server) might launch inside keyword-guessing attacks (IKGA) to guess keywords from the trapdoors. In recent years, public key authenticated encryption with keyword search (PAEKS) has become a promising primitive to counter the IKGA. However, existing PAEKS schemes focus on the concrete construction of PAEKS, making them unable to support modular construction, intuitive proof, or flexible extension. In this paper, our proposal called “StopGuess” …

Leveraging Multimodal Features And Item‑Level User Feedback For Bundle Construction, Yunshan Ma, Xiaohao Liu, Yinwei Wei, Zhulin Tao, Xiang Wang, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

Automatic bundle construction is a crucial prerequisite step in various bundle-aware online services. Previous approaches are mostly designed to model the bundling strategy of existing bundles. However, it is hard to acquire large-scale well-curated bundle dataset, especially for those platforms that have not offered bundle services before. Even for platforms with mature bundle services, there are still many items that are included in few or even zero bundles, which give rise to sparsity and cold-start challenges in the bundle construction models. To tackle these issues, we target at leveraging multimodal features, item-level user feedback signals, and the bundle composition information, …

Ddos Family: A Novel Perspective For Massive Types Of Ddos Attacks, Ziming Zhao, Zhaoxuan Li, Zhihao Zhou, Jiongchi Yu, Zhuoxue Song, Xiaofei Xie, Fan Zhang, Rui Zhang

Research Collection School Of Computing and Information Systems

Distributed Denial of Service (DDoS) defense is a profound research problem. In recent years, adversaries tend to complicate their attack strategies by crafting vast DDoS variants. On the one hand, this trend exacerbates both extremes of classification granularity (i.e., binary and attack level) in existing machine learning methods. On the other hand, massive attack categories make the filter rule table bulky, as well as cause problems of slow reaction presented in the recent state-of-the-art DDoS mitigation system. Therefore, we propose the concept of a DDoS family to reconcile/cope with these issues. The specific technical roadmap includes traffic pattern characterization, attack …

From Asset Flow To Status, Action And Intention Discovery: Early Malice Detection In Cryptocurrency, Ling Cheng, Feida Zhu, Yong Wang, Ruicheng Liang, Huiwen Liu

Research Collection School Of Computing and Information Systems

Cryptocurrency has been subject to illicit activities probably more often than traditional financial assets due to the pseudo-anonymous nature of its transacting entities. An ideal detection model is expected to achieve all three critical properties of early detection, good interpretability, and versatility for various illicit activities. However, existing solutions cannot meet all these requirements, as most of them heavily rely on deep learning without interpretability and are only available for retrospective analysis of a specific illicit type. To tackle all these challenges, we propose Intention Monitor for early malice detection in Bitcoin, where the on-chain record data for a certain …

Understanding Newcomers' Onboarding Process In Deep Learning Projects, Junxiao Han, Jiahao Zhang, David Lo, Xin Xia, Shuigang Deng, Minghui Wu

Research Collection School Of Computing and Information Systems

Attracting and retaining newcomers are critical for the sustainable development of Open Source Software (OSS) projects. Considerable efforts have been made to help newcomers identify and overcome barriers in the onboarding process. However, fewer studies focus on newcomers’ activities before their successful onboarding. Given the rising popularity of deep learning (DL) techniques, we wonder what the onboarding process of DL newcomers is, and if there exist commonalities or differences in the onboarding process for DL and non-DL newcomers. Therefore, we reported a study to understand the growth trends of DL and non-DL newcomers, mine DL and non-DL newcomers’ activities before …

Revisiting The Markov Property For Machine Translation, Cunxiao Du, Hao Zhou, Zhaopeng Tu, Jing Jiang

Research Collection School Of Computing and Information Systems

In this paper, we re-examine the Markov property in the context of neural machine translation. We design a Markov Autoregressive Transformer (MAT) and undertake a comprehensive assessment of its performance across four WMT benchmarks. Our findings indicate that MAT with an order larger than 4 can generate translations with quality on par with that of conventional autoregressive transformers. In addition, counter-intuitively, we also find that the advantages of utilizing a higher-order MAT do not specifically contribute to the translation of longer sentences.

Knowledge Generation For Zero-Shot Knowledge-Based Vqa, Rui Cao, Jing Jiang

Research Collection School Of Computing and Information Systems

Previous solutions to knowledge-based visual question answering (K-VQA) retrieve knowledge from external knowledge bases and use supervised learning to train the K-VQA model. Recently pre-trained LLMs have been used as both a knowledge source and a zero-shot QA model for K-VQA and demonstrated promising results. However, these recent methods do not explicitly show the knowledge needed to answer the questions and thus lack interpretability. Inspired by recent work on knowledge generation from LLMs for text-based QA, in this work we propose and test a similar knowledge-generation-based K-VQA method, which first generates knowledge from an LLM and then incorporates the generated …

Temporal Implicit Multimodal Networks For Investment And Risk Management, Meng Kiat Gary Ang, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Many deep learning works on financial time-series forecasting focus on predicting future prices/returns of individual assets with numerical price-related information for trading, and hence propose models designed for univariate, single-task, and/or unimodal settings. Forecasting for investment and risk management involves multiple tasks in multivariate settings: forecasts of expected returns and risks of assets in portfolios, and correlations between these assets. As different sources/types of time-series influence future returns, risks, and correlations of assets in different ways, it is also important to capture time-series from different modalities. Hence, this article addresses financial time-series forecasting for investment and risk management in a …

Attack As Detection: Using Adversarial Attack Methods To Detect Abnormal Examples, Zhe Zhao, Guangke Chen, Tong Liu, Taishan Li, Fu Song, Jingyi Wang, Jun Sun

Research Collection School Of Computing and Information Systems

As a new programming paradigm, deep learning (DL) has achieved impressive performance in areas such as image processing and speech recognition, and has expanded its application to solve many real-world problems. However, neural networks and DL are normally black-box systems; even worse, DL-based software are vulnerable to threats from abnormal examples, such as adversarial and backdoored examples constructed by attackers with malicious intentions as well as unintentionally mislabeled samples. Therefore, it is important and urgent to detect such abnormal examples. Although various detection approaches have been proposed respectively addressing some specific types of abnormal examples, they suffer from some limitations; …

Xfuzz: Machine Learning Guided Cross-Contract Fuzzing, Yinxing Xue, Jiaming Ye, Wei Zhang, Jun Sun, Lei Ma, Haijun Wang, Jianjun Zhao

Research Collection School Of Computing and Information Systems

Smart contract transactions are increasingly interleaved by cross-contract calls. While many tools have been developed to identify a common set of vulnerabilities, the cross-contract vulnerability is overlooked by existing tools. Cross-contract vulnerabilities are exploitable bugs that manifest in the presence of more than two interacting contracts. Existing methods are however limited to analyze a maximum of two contracts at the same time. Detecting cross-contract vulnerabilities is highly non-trivial. With multiple interacting contracts, the search space is much larger than that of a single contract. To address this problem, we present xFuzz , a machine learning guided smart contract fuzzing framework. …

Representation Learning For Stack Overflow Posts: How Far Are We?, Junda He, Xin Zhou, Bowen Xu, Ting Zhang, Kisub Kim, Zhou Yang, Thung Ferdian, Ivana Clairine Irsan, David Lo

Research Collection School Of Computing and Information Systems

The tremendous success of Stack Overflow has accumulated an extensive corpus of software engineering knowledge, thus motivating researchers to propose various solutions for analyzing its content. The performance of such solutions hinges significantly on the selection of representation models for Stack Overflow posts. As the volume of literature on Stack Overflow continues to burgeon, it highlights the need for a powerful Stack Overflow post representation model and drives researchers’ interest in developing specialized representation models that can adeptly capture the intricacies of Stack Overflow posts. The state-of-the-art (SOTA) Stack Overflow post representation models are Post2Vec and BERTOverflow, which are built …

Math Word Problem Generation Via Disentangled Memory Retrieval, Wei Qin, Xiaowei Wang, Zhenzhen Hu, Lei Wang, Yunshi Lan, Richang Hong

Research Collection Lee Kong Chian School Of Business

The task of math word problem (MWP) generation, which generates an MWP given an equation and relevant topic words, has increasingly attracted researchers’ attention. In this work, we introduce a simple memory retrieval module to search related training MWPs, which are used to augment the generation. To retrieve more relevant training data, we also propose a disentangled memory retrieval module based on the simple memory retrieval module. To this end, we first disentangle the training MWPs into logical description and scenario description and then record them in respective memory modules. Later, we use the given equation and topic words as …

Relocating Lubra Village And Visualizing Himalayan Flood Damages With Remote Sensing, Ronan Wallace, Yungdrung Tsewang Gurung, Ryan Kastner

Journal of Critical Global Issues

As weather patterns change worldwide, isolated communities impacted by climate change go unnoticed and we need community-driven solutions. In Himalayan Mustang, Nepal, indigenous Lubra Village faces threats of increasing flash flooding. After every flood, residual muddy sediment hardens across the riverbed like concrete, causing the riverbed elevation to rise. As elevation increases, sediment encroaches on Lubra’s agricultural fields and homes, magnifying flood vulnerability. In the last monsoon season alone, the Lubra community witnessed floods swallowing several agricultural fields and damaging two homes. One solution considers relocating the village to a new location entirely. However, relocation poses a challenging task, as …

Identification Of Faults In Highways Using Approximation Methods And Algorithms, Khudayberdiyev Khakkulmirzayevich Mirzaakbar, Anvar Asatilloyevich Ravshanov

Chemical Technology, Control and Management

Many fast Fourier transforms are used to identify defective parts of uneven surfaces on roads and send information to relevant organizations on the road, using the " RAVON YO‘LLAR" application installed on a mobile device during car movement. We determine the uneven parts of the road. Smooth and well-maintained roads reduce the risk of vehicle collisions, skidding and other road-related incidents. Timely measures contribute to overall safety, comfort and economic efficiency.

Navigating The Digital Frontier: The Intersection Of Cybersecurity Challenges And Young Adult Life, Hannarae Lee

International Journal of Cybersecurity Intelligence & Cybercrime

Papers from this issue advocate for empowering young adults with knowledge and tools to navigate cyberspace safely, emphasizing the necessity of heightened cybersecurity measures and proactive education. As we advance into the digital abyss, this call becomes imperative, ensuring that the young adults' experience remains a journey of growth and enlightenment, unaffected by the shadows of unseen online threats.

The Need For A Cybersecurity Education Program For Internet Users With Limited English Proficiency: Results From A Pilot Study, Fawn T. Ngo, Rustu Deryol, Brian Turnbull, Jack Drobisz

International Journal of Cybersecurity Intelligence & Cybercrime

According to security experts, cybersecurity education and awareness at the user level are key in combating cybercrime. Hence, in the U.S., cybersecurity and Internet safety workshops, classes, and resources targeting children, adolescents, adults, and senior citizens abound. However, most cybercrime prevention programs are only available in English, thus, ignoring a substantial proportion of Internet users and potential cybercrime victims—Internet users with limited English proficiency (LEP). Yet, successfully combating cybercrime requires that all computer and Internet users, regardless of their language abilities and skills, have access to pertinent cybersecurity information and resources to protect themselves online. This paper presents the results …

Cancergpt For Few Shot Drug Pair Synergy Prediction Using Large Pretrained Language Models, Tianhao Li, Sandesh Shetty, Advaith Kamath, Ajay Jaiswal, Xiaoqian Jiang, Ying Ding, Yejin Kim

Faculty, Staff and Student Publications

Large language models (LLMs) have been shown to have significant potential in few-shot learning across various fields, even with minimal training data. However, their ability to generalize to unseen tasks in more complex fields, such as biology and medicine has yet to be fully evaluated. LLMs can offer a promising alternative approach for biological inference, particularly in cases where structured data and sample size are limited, by extracting prior knowledge from text corpora. Here we report our proposed few-shot learning approach, which uses LLMs to predict the synergy of drug pairs in rare tissues that lack structured data and features. …

Emojis And Miscommunication In Text-Based Interactions Among Nigerian Youths, Uduak Udoudom, Godwin William, Anthony Igiri, Ememobong Okon, Kalita Aruku

Journal of Informatics and Web Engineering

This paper explores the dynamic role of emojis in text-based communication among Nigerian youths and the potential implications for miscommunication. Emojis have become integral to contemporary digital conversations, offering users a visual means of expressing emotions, tone, and context within the constraints of text-based interactions. In the context of Nigeria, a country with a diverse linguistic landscape and a youthful population heavily engaged in online communication, understanding the impact of emojis on interpersonal exchanges becomes particularly pertinent. This paper examines the prevalence and patterns of emoji usage among Nigerian youths across various digital platforms. It investigates the cultural nuances and …

Editorial Preview, Su-Cheng Haw

Journal of Informatics and Web Engineering

This editorial highlights all 19 papers in the February issue that deal with the practical aspects of Machine Learning (ML), Artificial Intelligence (AI), Data Mining (DM), the Internet of Things (IoT), and other topics in Computer Science. This issue also includes suggestions for several worthwhile works that deserve further research. With effective from this volume, we will be publishing triannually in our February, June and October issues.

Term Standardisation With Lda Model To Detect Service Disruption Events Using English And Manglish Tweets, Noraysha Yusuf, Maizatul Akmar Ismail, Tasnim M.A. Zayet, Kasturi Dewi Varathan, Rafidah Md Noor

Journal of Informatics and Web Engineering

Rapid transit is one of Malaysia's most important transportation modes, where commuters use public transportation to travel. Any disruption in the rapid transit service affects their daily routines. Therefore, detecting such service disruption has become fundamental. In this study, the disruption in Malaysia's rapid transit service was assessed using English and Manglish (a combination of English and Malay) tweets through Latent Dirichlet Allocation (LDA). The gathered tweets were classified into event and non-event tweets and LDA was applied to the event tweets. Manglish event tweets were pre-processed using the proposed term standardisation technique. As a result, LDA has proved its …

A Campus-Based Chatbot System Using Natural Language Processing And Neural Network, Tuan-Jun Goh, Lee-Ying Chong, Siew-Chin Chong, Pey-Yun Goh

Journal of Informatics and Web Engineering

A chatbot is designed to simulate human conversation and provide instant responses to users. Chatbots have gained popularity in providing automated customer support and information retrieval among organisations. Besides, it also acts as a virtual assistant to communicate with users by delivering updated answers based on users' input. Most chatbots still use the traditional rule-based chatbot, which can only respond to pre-defined sentences, making the users unlikely to use the chatbot. This paper aims to design and build a campus chatbot for the Faculty of Information Science & Technology (FIST) of Multimedia University that facilitates the study life of FIST …

Personalized Healthcare: A Comprehensive Approach For Symptom Diagnosis And Hospital Recommendations Using Ai And Location Services, Seng-Keong Tan, Siew-Chin Chong, Kuok-Kwee Wee, Lee-Ying Chong

Journal of Informatics and Web Engineering

Utilizing digital advancements, an integrated Flask-based platform has been engineered to centralize personal health records and facilitate informed healthcare decisions. The platform utilizes a Random Forest model-based symptom checker and an OpenAI API-powered chatbot for preliminary disease diagnosis and integrates Google Maps API to recommend proximal hospitals based on user location. Additionally, it contains a comprehensive user profile encompassing general information, medical history, and allergies. The system includes a medicine reminder feature for medication adherence. This innovative amalgamation of technology and healthcare fosters a user-centric approach to personal health management.

Prediction Of Student’S Academic Performance Through Data Mining Approach, Muhammad Mubashar Hussain, Shahzad Akbar, Syed Ale Hassan, Muhammad Waqas Aziz, Farwa Urooj

Journal of Informatics and Web Engineering

The universities and institutes produce a large amount of student data that can be used in a disciplinary way and useful information can be extracted by using an automated approach. Educational Data Mining (EDM) is an emerging discipline used in the educational environment to deal with big student data and extract useful information. The data mining of students’ data can help the At-risk students as well as the stakeholders by the early warning. This study aims to predict the performance of the students based on student-related data to increase the overall performance. In existing studies, insufficient attributes and complexity of …

Mmwave Rat Optimization: Mac Layer Initial Access Design And Transport Layer Integration, Suresh Srinivasan

Dissertations and Theses

MmWave Radio Access Technology (RAT) is a promising technology for wireless communication due its large bandwidth and is already being deployed in 5G cellular and emerging WiFi technologies. MmWave systems use highly directional beams with narrow beamwidths to overcome the high path loss associated with their frequency bands. A mmWave radio can be used either in a standalone mode (where all radios use the same technology) or simultaneously with other technologies such as LTE and low frequency WiFi in a communication mode commonly referred to as integrated mode. This thesis proposes two methods to optimize mmWave RAT performance in both …

Chatgpt Can Offer Satisfactory Responses To Common Patient Questions Regarding Elbow Ulnar Collateral Ligament Reconstruction, William Johns, Alec Kellish, Dominic Farronato, Michael G. Ciccotti, Sommer Hammoud

Rothman Institute Papers

PURPOSE: To determine whether ChatGPT effectively responds to 10 commonly asked questions concerning ulnar collateral ligament (UCL) reconstruction.

METHODS: A comprehensive list of 90 UCL reconstruction questions was initially created, with a final set of 10 "most commonly asked" questions ultimately selected. Questions were presented to ChatGPT and its response was documented. Responses were evaluated independently by 3 authors using an evidence-based methodology, resulting in a grading system categorized as follows: (1) excellent response not requiring clarification; (2) satisfactory requiring minimal clarification; (3) satisfactory requiring moderate clarification; and (4) unsatisfactory requiring substantial clarification.

RESULTS: Six of 10 ten responses were …

Board Of Directors Role In Data Privacy Governance: Making The Transition From Compliance Driven To Good Business Stewardship, David Warner, Lisa Mckee

Journal of Cybersecurity Education, Research and Practice

Data collection, use, leveraging, and sharing as a business practice and advantage has proliferated over the past decade. Along with this proliferation of data collection is the increase in regulatory activity which continues to morph exponentially around the globe. Adding to this complexity are the increasing business disruptions, productivity and revenue losses, settlements, fines, and penalties which can amount to over $15 million, with many penalties now being ascribed to the organization’s leadership, to include the Board of Directors (BoD), the CEO and members of the senior leadership team (SLT). Thus, boards of directors can no longer ignore and in …