Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 258541 - 258570 of 5156606

Full-Text Articles in Entire DC Network

The Effectiveness Of Local Updates For Decentralized Learning Under Data Heterogeneity, Tongle Wu, Zhize Li, Ying Sun Jan 2025

The Effectiveness Of Local Updates For Decentralized Learning Under Data Heterogeneity, Tongle Wu, Zhize Li, Ying Sun

Research Collection School Of Computing and Information Systems

We revisit two fundamental decentralized optimization methods, Decentralized Gradient Tracking (DGT) and Decentralized Gradient Descent (DGD), with multiple local updates. We consider two settings and demonstrate that incorporating local update steps can reduce communication complexity. Specifically, for  $\mu$-strongly convex and $L$-smooth loss functions, we proved that local DGT  achieves communication complexity {}{$\tilde{\mathcal{O}} \Big(\frac{L}{\mu(K+1)} + \frac{\delta + {}{\mu}}{\mu (1 - \rho)} + \frac{\rho }{(1 - \rho)^2} \cdot \frac{L+ \delta}{\mu}\Big)$}, where $K$ is the number of additional local update}, $\rho$ measures the network connectivity and $\delta$ measures the second-order heterogeneity of the local losses. Our results reveal the tradeoff between communication and …

Go to article

Don’T Complete It! Preventing Unhelpful Code Completion For Productive And Sustainable Neural Code Completion Systems, Zhensu Sun, Xiaoning Du, Fu Song, Shangwen Wang, Mingze Ni, Li Li, David Lo Jan 2025

Don’T Complete It! Preventing Unhelpful Code Completion For Productive And Sustainable Neural Code Completion Systems, Zhensu Sun, Xiaoning Du, Fu Song, Shangwen Wang, Mingze Ni, Li Li, David Lo

Research Collection School Of Computing and Information Systems

Currently, large pre-trained language models are widely applied in neural code completion systems. Though large code models significantly outperform their smaller counterparts, around 70% of displayed code completions from Github Copilot are not accepted by developers. Being reviewed but not accepted, their help to developer productivity is considerably limited and may conversely aggravate the workload of developers, as the code completions are automatically and actively generated in state-of-the-art code completion systems as developers type out once the service is enabled. Even worse, considering the high cost of the large code models, it is a huge waste of computing resources and …

Go to article

Cfd Analysis Of Hydrodynamic Cavitation Through An Orifice: Influence Of Different Inlet Pressures And Number Of Orifice Holes, Lemthong Chanphavong, Vongsavanh Chanthaboune, Keophousone Phonhalath Jan 2025

Cfd Analysis Of Hydrodynamic Cavitation Through An Orifice: Influence Of Different Inlet Pressures And Number Of Orifice Holes, Lemthong Chanphavong, Vongsavanh Chanthaboune, Keophousone Phonhalath

ASEAN Journal on Science and Technology for Development

Hydrodynamic cavitation (HC) is considered an energy-efficient process with high potential for utilization in many chemical processes. This study presents a computational fluid dynamics (CFD) analysis of cavitating flow through an orifice with a constant flow area. The Reynolds-Averaged Navier-Stokes (RANS) equations, coupled with turbulence and cavitation models, are employed to capture the complex flow behaviors. The effects of inlet pressures and number of orifice-holes on cavitation behavior are investigated. Result of the numerical simulation is validated with the existing experimental data from the literature. The CFD study revealed that cavitation initiates just behind the inlet edge of the orifice …

Go to article

Impact Of Color, Shape, And Typeface On Visual Attention: An Eye Tracking Study On Brand Logo, Suzayana Rosidah, Fransiskus Xaverius Ivan, Suatmi Murnani, Hafzatin Nurlatifa, Kristian Adi Nugraha, Sunu Wibirama Jan 2025

Impact Of Color, Shape, And Typeface On Visual Attention: An Eye Tracking Study On Brand Logo, Suzayana Rosidah, Fransiskus Xaverius Ivan, Suatmi Murnani, Hafzatin Nurlatifa, Kristian Adi Nugraha, Sunu Wibirama

ASEAN Journal on Science and Technology for Development

In numerous cases, companies undertake logo redesigns to enhance brand perception. However, little attention has been paid to the impact of each element of the redesigned logo on visual attention and brand perception. To address this research gap, we collected data from eye tracking and self-report questionnaires of 30 participants during exposure to the old and new logos of a prominent bookstore in Indonesia. The results of the questionnaires revealed a significant relationship between the responses concerning color, shape, typeface, and those pertaining to visual attention (p < 0.05). Most participants were able to grasp the value of creativity, flexibility, progress, change, and strength in the new logo shape. The results of eye tracking show that color was the most influential factor that attracted visual attention in old (F(1.5, 43.4) = 14.905, p < 0.05) and new logos (F(1.7, 50) = 34.757, p < 0.05). This study suggests that companies should selectively choose a color scheme of a logo that better attracts the attention of consumers. In addition, our finding is promising as a practical guide for similar research, as well as a case study on how logo redesign affects brand perception and visual attention.

Go to article

Minimizing Cpu Utilization For Job Scheduling Problems By The Advanced Round Robin Method: A Pragmatic Perspective, Haribhau R Bhapkar, Pankaj R Chandre, Parikshit Mahalle Jan 2025

Minimizing Cpu Utilization For Job Scheduling Problems By The Advanced Round Robin Method: A Pragmatic Perspective, Haribhau R Bhapkar, Pankaj R Chandre, Parikshit Mahalle

ASEAN Journal on Science and Technology for Development

CPU scheduling issues include minimizing waiting time for processes, ensuring fairness in resource allocation, and optimizing throughput. Balancing these objectives can be challenging, as improving one aspect may negatively impact another, making it essential to design efficient scheduling algorithms. This work presents an innovative approach to enhance CPU utilization through the development of a Result-Based Round Robin Scheduling Algorithm. Traditional Round Robin Scheduling methods often face challenges in efficiently allocating CPU time, leading to suboptimal system performance. In response to these limitations, the proposed method introduces a result-oriented strategy that dynamically adjusts time quantum allocations based on the execution progress …

Go to article

Effect Of Build Orientation On Tensile Properties And Fractography Of Additive Manufactured Inconel 718 Alloy, Ajay Kumar Maurya, Amit Kumar, Swarnambuj Suman Jan 2025

Effect Of Build Orientation On Tensile Properties And Fractography Of Additive Manufactured Inconel 718 Alloy, Ajay Kumar Maurya, Amit Kumar, Swarnambuj Suman

ASEAN Journal on Science and Technology for Development

The additive manufacturing (AM) technique “Direct Metal Laser Sintering (DMLS)” is used to create 3D objects directly from 3D design data. A lightweight and complexity-free part without any expensive tooling can be fabricated easily using this method, but it is still challenging to achieve the desired mechanical strength from AM parts, as the mechanical properties of AM-produced parts vary with orientation, scan strategy, and process parameters. Inconel 718 alloy is most commonly utilized in the aerospace and automotive industries, because of its high resistance to corrosion and excellent mechanical qualities. This work presents a study to investigate the orientation-based mechanical …

Go to article

Regulation Of Haemodynamic Variables By Laguerre Polynomials Based Model Predictive Control., Sai Sandeep Boda, Hiren Kumar G. Patel, Khyati D. Mistry Jan 2025

Regulation Of Haemodynamic Variables By Laguerre Polynomials Based Model Predictive Control., Sai Sandeep Boda, Hiren Kumar G. Patel, Khyati D. Mistry

ASEAN Journal on Science and Technology for Development

Purpose: Cardiac output (CO) and Mean Arterial Pressure (MAP) are two haemodynamic variables that need regulation in clinical situations, particularly in post-cardiac surgery patients. As it is difficult for clinical personnel to monitor continuously, automatic drug infusion to regulate MAP and CO is recommended and essential in the medical environment. Methods: Two input and two output patient model was used in this work to study the variation of haemodynamic variables in response to the infusion of Dopamine (DP) and Sodium Nitroprusside (SNP) drugs. Model predictive control (MPC) algorithm was exercised here as it was a well-established technique to regulate output …

Go to article

From Theory To Practice: Simulating Zero Trust Architecture With Python For Cybersecurity, Pankaj R. Chandre, Bhagyashree D. Shendkar, Sulochana Sagar Madachane, Nikita Kulkarni, Sayalee Deshmukh Jan 2025

From Theory To Practice: Simulating Zero Trust Architecture With Python For Cybersecurity, Pankaj R. Chandre, Bhagyashree D. Shendkar, Sulochana Sagar Madachane, Nikita Kulkarni, Sayalee Deshmukh

ASEAN Journal on Science and Technology for Development

The increasing complexity and frequency of cyber threats have necessitated the adoption of advanced security models, such as Zero Trust Architecture (ZTA). ZTA runs on the tenet that no entity whether inside or outside the network should be trusted by default, in contrast to conventional perimeter-based security solutions. This paper describes a thorough method for simulating and implementing Zero Trust Architecture in Python. We examine the essential elements and procedures of ZTA, such as identity verification, access control, and continuous monitoring, through a thorough analysis and step-by-step manual. The simulation shows how ZTA works to ensure strong network security and …

Go to article

Distance Metric Learning Techniques For The Performance Improvement Of Ml-Knn And Ranking-Svm-Based Multi-Label Pattern Classification, Shajee Mohan B. S., Sneha S Mohan Jan 2025

Distance Metric Learning Techniques For The Performance Improvement Of Ml-Knn And Ranking-Svm-Based Multi-Label Pattern Classification, Shajee Mohan B. S., Sneha S Mohan

ASEAN Journal on Science and Technology for Development

A multi-label pattern classification system tries to predict the set of class labels of a test example by learning from the training examples with the relevant label sets. Classification that involve datasets having multiple labels found immense of applications in pattern analysis tasks involving image, music and video. A test sample can be labeled to indicate different objects, people, music categories or concepts. Classification problems involving data having multiple labels, have to consider training dataset associated with variety of labels. Multi-label extensions of popular algorithms, kNN and Support Vector Machine (SVM) called Multi-label kNN (ML-kNN) and Ranking-SVM are commonly used …

Go to article

Solid Waste Management Strategies In Coastal Areas Affected By Seawater Flood Disaster, Adib Khoirul Anas, Maryono Maryono, Hartuti Purnaweni Jan 2025

Solid Waste Management Strategies In Coastal Areas Affected By Seawater Flood Disaster, Adib Khoirul Anas, Maryono Maryono, Hartuti Purnaweni

ASEAN Journal on Science and Technology for Development

Solid waste in areas affected by seawater floods must be handled specifically because people often dispose of solid waste on flooded land. This research aims to identify the performance of the community to manage solid waste and solid waste management strategy, solid waste measurement using SNI method 19-3964-1994. Analysis of land affected by seawater floods shows that 12 villages are flooded. Communities in coastal areas are not optimal in managing solid waste because the government has never given directions to manage solid waste in a good way, the facilities and marketing are inadequate so that solid waste is often not …

Go to article

Neuro-Symbolic Ai: A Future Of Tomorrow, Pankaj Chandre, Parikshit Mahalle, Gitanjali Shinde, Bhagyashree Shendkar, Shraddha Kashid Jan 2025

Neuro-Symbolic Ai: A Future Of Tomorrow, Pankaj Chandre, Parikshit Mahalle, Gitanjali Shinde, Bhagyashree Shendkar, Shraddha Kashid

ASEAN Journal on Science and Technology for Development

Neuro-Symbolic AI: A Future of Tomorrow" explores the convergence of neural learning and symbolic reasoning to advance artificial intelligence (AI) systems. Symbolic reasoning makes use of knowledge representation techniques and rule-based systems, whereas neural learning analyzes data using deep learning models. AI becomes more adept at fusing data-driven insights with deductive reasoning when these methods are integrated using hybrid models and differentiable reasoning techniques. Applications show enhanced diagnostic precision and decision-making skills in a variety of industries, including robotics, healthcare, and finance. To promote responsible AI development, regulatory frameworks and ethical principles address issues like bias and transparency. Future paths …

Go to article

Exploring Dynamics And Effective Strategies For Tidal Flood Risk Reduction In Indonesia's Coastal Cities, Satria Yudha Adhitama, Diana Puspitasari, Lucia Sandra Budiman, Azis Musthofa Jan 2025

Exploring Dynamics And Effective Strategies For Tidal Flood Risk Reduction In Indonesia's Coastal Cities, Satria Yudha Adhitama, Diana Puspitasari, Lucia Sandra Budiman, Azis Musthofa

ASEAN Journal on Science and Technology for Development

Indonesia’s coastal regions have distinct charateristics. However, nearly all of these coastal regions are vulnerable to tidal floods. The purpose of this study is to determine the features of coastal regions in Indonesia that have been damaged by tidal floods, as well as the actions implemented to mitigate disaster risk. Thus study takes a qualitiative method with explanatory analysis. The Island Spatial Planning is used to classify Indonesia’s archipelagic regions.An urban area vulnerable to tidal flood was selected from each archipelagic region. The characteristics of coastal regions affected by tidal flood were identified by the tidal flood characteristics, coastal physiography. …

Go to article

Wind Speed Forecasting: A Comparative Study Of Decomposition Techniques, Manisha Galphade, V.B. Nikam, Nilkamal More, Biplab Banerjee, Arvind W. Kiwelekar, Priyanka Sharma Jan 2025

Wind Speed Forecasting: A Comparative Study Of Decomposition Techniques, Manisha Galphade, V.B. Nikam, Nilkamal More, Biplab Banerjee, Arvind W. Kiwelekar, Priyanka Sharma

ASEAN Journal on Science and Technology for Development

Renewable energy is sourced from natural resources that are continually available. Wind energy is a main category of renewable energy, which largely depends on wind speed. Accurate wind speed forecasting is essential for incorporating renewable energy into the electrical grid. Moreover, it is crucial to ensure the safety of wind turbines by anticipating extreme weather conditions and implementing necessary precautions. Predicting wind speed presents several challenges because of dynamic and complex nature of atmospheric conditions. Traditional methods for wind speed forecasting, such as statistical models and basic physical approaches, often face limitations in accuracy, flexibility, and handling of complex data …

Go to article

Improving Ethanol Purity By Methanol Adsorption Using Mcm-41: A Study Of Kinetics And Thermodynamics For Industrial Applications, Ali A. Yahya, Nisreen S. Ali, Basma B. Hameed, Talib M. Albayati, Issam K. Salih, Riyadh S. Almukhtar, Narges Elmi Fard Jan 2025

Improving Ethanol Purity By Methanol Adsorption Using Mcm-41: A Study Of Kinetics And Thermodynamics For Industrial Applications, Ali A. Yahya, Nisreen S. Ali, Basma B. Hameed, Talib M. Albayati, Issam K. Salih, Riyadh S. Almukhtar, Narges Elmi Fard

ASEAN Journal on Science and Technology for Development

One of the by-products of the fermentation process that produces ethanol, which is mostly utilized in industry and food, is methanol. For methanol adsorption in batch operations, mixed amines modified (MCM-41) was utilized. A batch adsorption technique loaded with MCM-41 sorbent was used in the study to separate methanol from ethanol. This study used methanol at varying initial concentrations (40-80 mg/L). As a result, the effect of temperature, duration of adsorption, amount of adsorbent and initial concentration of pollutant in the field of ethanol alcohol purification using MCM-41 was investigated through the adsorption mechanism. In addition, first and pseudo-second order …

Go to article

Snake Optimization Algorithm For Fractional Order Controller In Three-Area Load Frequency Regulation, Shubra Goel, Omveer Singh Jan 2025

Snake Optimization Algorithm For Fractional Order Controller In Three-Area Load Frequency Regulation, Shubra Goel, Omveer Singh

ASEAN Journal on Science and Technology for Development

The transition toward renewable energy-dominated power systems have accentuated the intricacies of frequency control, necessitating advanced regulatory mechanisms. This investigation articulates a tri-zonal frequency stabilization approach, employing a hybridized controller that synergizes Fuzzy Fractional-Order PI and Tilt-Integral-Derivative methodologies. The uniqueness of this approach is further amplified by the deployment of the Snake Optimization algorithm for precise parameter tuning. Set within a conventional grid topology integrated with assorted renewable energy sources, the study evaluates the controller’s adaptability and resilience through a series of comprehensive scenario-based analyses.

Go to article

Quality And Safety Analysis Of Integrated Bus Services And Feeder Transport In Surabaya, Indonesia, Desrina Yusi Irawati, Agrienta Bellanov, Armadeo Ruben Canariesa Jan 2025

Quality And Safety Analysis Of Integrated Bus Services And Feeder Transport In Surabaya, Indonesia, Desrina Yusi Irawati, Agrienta Bellanov, Armadeo Ruben Canariesa

ASEAN Journal on Science and Technology for Development

The Surabaya city government has developed public transportation through integrated bus services and feeder transport. These transportation systems include Trans Semanggi, Suroboyo Bus, and Wira Wiri Surabaya. The challenge facing these transportation programs is the low level of public participation in using public transportation. This research aims to provide a comprehensive investigation of the perceived service quality of integrated public transportation in Surabaya by combining the RESCA and SERVQUAL frameworks. The study contributes by highlighting service quality gaps across five customized dimensions and offering practical insights to improve user satisfaction and increase public transport usage. Each RESCA dimension incorporates RATER …

Go to article

The Effect Of Blanching And Steaming Pretreatment On The Quality Of Durian (Durio Zibenthinus Murr.) Seed Flour, Nabilah Daniel, Rosnah Shamsudin, Mohd Sabri Pak Dek, Jhauharotul Muchlisyiyah, Masmunira Rambli Jan 2025

The Effect Of Blanching And Steaming Pretreatment On The Quality Of Durian (Durio Zibenthinus Murr.) Seed Flour, Nabilah Daniel, Rosnah Shamsudin, Mohd Sabri Pak Dek, Jhauharotul Muchlisyiyah, Masmunira Rambli

ASEAN Journal on Science and Technology for Development

Durian (Durio zibethinus Murr.), the "King of Fruits," has seeds that offer nutritional benefits, including high fiber for gut health and high protein for muscle growth. However, natural browning enzymes can limit its use in baking. This study investigates the comparative effects of blanching and steaming durations (5, 10, 15, 20, and 25 minutes) on the color and techno-functional properties of durian seed flour (DSF), providing an optimization-based approach rarely reported for this material.. Durian seeds were sourced from various stalls in Malaysia, washed, soaked in 0.6% sodium metabisulfite, and then blanched or steamed for for varying durations as …

Go to article

Seismic Vulnerability Assessment With Rapid Visual Screening Of Hospital Buildings In Maguindanao Province, Philippines, Ebrahim B. Kayog, Kristine S. Companion, Kenny B. Cantila, Elizabeth Edan M. Albiento Jan 2025

Seismic Vulnerability Assessment With Rapid Visual Screening Of Hospital Buildings In Maguindanao Province, Philippines, Ebrahim B. Kayog, Kristine S. Companion, Kenny B. Cantila, Elizabeth Edan M. Albiento

ASEAN Journal on Science and Technology for Development

Hospitals are expected to maintain operations during and after earthquakes, yet many facilities in the Philippines remain structurally and non-structurally vulnerable. This study evaluates the seismic vulnerability of selected public hospitals in Maguindanao Province, located near the Cotabato Trench and the Western Mindanao Fault, using the FEMA P-154 (3rd ed.) Rapid Visual Screening (RVS) Level-1 procedure. Four government hospitals, comprising 53 buildings constructed between 1980 and 2025, were assessed through a systematic visual inspection and review of available secondary records. Basic structural hazard scores were adjusted using FEMA score modifiers (performance modification factors) to compute Final Level-1 scores (Sₗ₁) and …

Go to article

Assessing The Probable Sources Affecting The Water Quality Index Of The Panch Prayag Belt Of Uttarakhand, India, Debasis Sau, Indranil Mukherjee, Wasim Akram, Kakali Ghosh, Rimi Paul, Reshmi Paul, Athar Akram Jan 2025

Assessing The Probable Sources Affecting The Water Quality Index Of The Panch Prayag Belt Of Uttarakhand, India, Debasis Sau, Indranil Mukherjee, Wasim Akram, Kakali Ghosh, Rimi Paul, Reshmi Paul, Athar Akram

ASEAN Journal on Science and Technology for Development

The Water Quality Index (WQI) is an essential metric for evaluating the usability of surface water resources, particularly in ecologically sensitive and high-demand areas like the Panch Prayag belt of Uttarakhand, India. This region, comprising five major pilgrimage towns—Devaprayag, Nandprayag, Vishnuprayag, Karnaprayag, and Rudraprayag—faces seasonal fluctuations in water quality due to both natural and anthropogenic pressures. In this study, water samples were collected from 2021 to 2023 across pre-monsoon, monsoon, and post-monsoon seasons, and the WQI was computed using the Canadian Water Quality Index (CWQI 1.0). Results revealed that WQI values ranged from 36 to 45 across locations and seasons, …

Go to article

Manure Handling In Circular Farming: An In Vitro Study Of Fermented Poultry Manure As Unconventional Feed For Ruminants, Dimas Hand Vidya Paradhipta, De Lavida Padma Terrakota, Ali Agus, Andriyani Astuti, Viagian Pastawan, Kharisma Taufiqa Hidayah Jan 2025

Manure Handling In Circular Farming: An In Vitro Study Of Fermented Poultry Manure As Unconventional Feed For Ruminants, Dimas Hand Vidya Paradhipta, De Lavida Padma Terrakota, Ali Agus, Andriyani Astuti, Viagian Pastawan, Kharisma Taufiqa Hidayah

ASEAN Journal on Science and Technology for Development

The development of the poultry industry must consider the principle of circular economy. Therefore, this study aims to develop a method of fermenting poultry manure as a new, unconventional feed, which can support the model of circular farming. Poultry manure obtained from laying hens was mixed with cassava solid waste at a ratio of 7:3 to maintain proper moisture content. The mixed manure fermented for 14 days into a 30 kg silo in triplicate using different additives, namely Lactiplantibacillus plantarum FNCC 0020 at 1 x 105 cfu/g (LP), Bacillus cereus LS2B as proteolytic bacteria at 1 x …

Go to article

Numerical Modeling Of Performance And Phenomena In A Single Proton Exchange Membrane Fuel Cell, Doan Nguyen Cong, Hiep Nguyen Ha Jan 2025

Numerical Modeling Of Performance And Phenomena In A Single Proton Exchange Membrane Fuel Cell, Doan Nguyen Cong, Hiep Nguyen Ha

ASEAN Journal on Science and Technology for Development

One of the methods to protect our environment is to convert the fuel's chemical energy directly into electricity, bypassing the fuel's combustion process. This method is implemented in devices called fuel cells. Among them, the proton exchange membrane fuel cell (PEMFC) is widely used in practice because it has outstanding advantages such as high power density and efficiency, low operating temperature and noise, compactness, fast start-up, and, most importantly, only releases water, entirely safe for the environment. The paper presents a method for selecting materials for manufacturing PEMFC components, making a single PEMFC model based on the materials chosen, then …

Go to article

The Gender Wage Gap In An Online Labor Market: The Cost Of Interruptions, Abi Adams, Kotaro Hara, Kristy Milland, Chris Callison-Burch Jan 2025

The Gender Wage Gap In An Online Labor Market: The Cost Of Interruptions, Abi Adams, Kotaro Hara, Kristy Milland, Chris Callison-Burch

Research Collection School Of Computing and Information Systems

This paper analyses gender differences in working patterns and wages on Amazon Mechanical Turk, a popular online labour platform. Using information on 2 million tasks, we find no gender differences in task selection nor experience. Nonetheless, women earn 20% less per hour on average. Gender differences in working patterns are a significant driver of this wage gap. Women are more likely to interrupt their working time on the platform with consequences for their task completion speed. A follow-up survey shows that the gender differences in working patterns and hourly wages are concentrated amongst workers with children.

Go to article

Fedart: A Neural Model Integrating Federated Learning And Adaptive Resonance Theory, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan Jan 2025

Fedart: A Neural Model Integrating Federated Learning And Adaptive Resonance Theory, Shubham Pateria, Budhitama Subagdja, Ah-Hwee Tan

Research Collection School Of Computing and Information Systems

Federated Learning (FL) has emerged as a promising paradigm for collaborative model training across distributed clients while preserving data privacy. However, prevailing FL approaches aggregate the clients’ local models into a global model through multi-round iterative parameter averaging. This leads to the undesirable bias of the aggregated model towards certain clients in the presence of heterogeneous data distributions among the clients. Moreover, such approaches are restricted to supervised classification tasks and do not support unsupervised clustering. To address these limitations, we propose a novel one-shot FL approach called Federated Adaptive Resonance Theory (FedART) which leverages self-organizing Adaptive Resonance Theory (ART) …

Go to article

Marrying Top-K With Skyline Queries: Operators With Relaxed Preference Input And Controllable Output Size, Kyriakos Mouratidis, Keming Li, Bo Tang Jan 2025

Marrying Top-K With Skyline Queries: Operators With Relaxed Preference Input And Controllable Output Size, Kyriakos Mouratidis, Keming Li, Bo Tang

Research Collection School Of Computing and Information Systems

The two most common paradigms to identify records of preference in a multi-objective setting rely either on dominance (e.g., the skyline operator) or on a utility function defined over the records' attributes (typically, using a top-k query). Despite their proliferation, each of them has its own palpable drawbacks. Motivated by these drawbacks, we identify three hard requirements for practical decision support, namely, personalization, controllable output size, and flexibility in preference specification. With these requirements as a guide, we combine elements from both paradigms and propose two new operators, ORD and ORU. We perform a qualitative study to demonstrate how they …

Go to article

Lara : A Light And Anti-Overfitting Retraining Approach For Unsupervised Time Series Anomaly Detection, Feiyi Chen, Zhen Qin, Mengchu Zhou, Yingying Zhang, Shuiguang Deng, Lunting Fan, Guansong Pang, Qingsong Wen Jan 2025

Lara : A Light And Anti-Overfitting Retraining Approach For Unsupervised Time Series Anomaly Detection, Feiyi Chen, Zhen Qin, Mengchu Zhou, Yingying Zhang, Shuiguang Deng, Lunting Fan, Guansong Pang, Qingsong Wen

Research Collection School Of Computing and Information Systems

Most of current anomaly detection models assume that the normal pattern remains the same all the time. However, the normal patterns of web services can change dramatically and frequently over time. The model trained on old-distribution data becomes outdated and ineffective after such changes. Retraining the whole model whenever the pattern is changed is computationally expensive. Further, at the beginning of normal pattern changes, there is not enough observation data from the new distribution. Retraining a large neural network model with limited data is vulnerable to overfitting. Thus, we propose a Light Anti-overfitting Retraining Approach (LARA) based on deep variational …

Go to article

Bi-Objective Dynamic Tugboat Scheduling With Speed Optimization Under Stochastic And Time-Varying Service Demands, Xiaoyang Wei, Hoong Chuin Lau, Zhe Xiao, Xiuju Fu, Xiaocai Zhang, Zheng Qin Jan 2025

Bi-Objective Dynamic Tugboat Scheduling With Speed Optimization Under Stochastic And Time-Varying Service Demands, Xiaoyang Wei, Hoong Chuin Lau, Zhe Xiao, Xiuju Fu, Xiaocai Zhang, Zheng Qin

Research Collection School Of Computing and Information Systems

With the growing emphasis on green shipping to reduce the environmental impact of maritime transportation, optimizing fuel consumption with maintaining high service quality has become critical in port operations. Ports are essential nodes in global supply chains, where tugboats play a pivotal role in the safe and efficient maneuvering of ships within constrained environments. However, existing literature lacks approaches that address tugboat scheduling under realistic operational conditions. To fill the research gap, this is the first work to propose the bi-objective dynamic tugboat scheduling problem that optimizes speed under stochastic and time-varying demands, aiming to minimize fuel consumption and manage …

Go to article

Fuzzing Drones For Anomaly Detection: A Systematic Literature Review, Vikas Kumar Malviya, Wei Minn, Lwin Khin Shar, Lingxiao Jiang Jan 2025

Fuzzing Drones For Anomaly Detection: A Systematic Literature Review, Vikas Kumar Malviya, Wei Minn, Lwin Khin Shar, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Drones, also referred to as Unmanned Aerial Vehicles (UAVs), are becoming popular today due to their uses in different fields and recent technological advancements which provide easy control of UAVs via mobile apps. However, UAVs may contain vulnerabilities or software bugs that cause serious safety and security concerns. For example, the communication protocol used by the UAV may contain authentication and authorization vulnerabilities, which may be exploited by attackers to gain remote access over the UAV. Drones must therefore undergo extensive testing before being released or deployed to identify and fix any software bugs or security vulnerabilities. Fuzzing is one …

Go to article

Measuring Model Alignment For Code Clone Detection Using Causal Interpretation, Shamsa Abid, Xuemeng Cai, Lingxiao Jiang Jan 2025

Measuring Model Alignment For Code Clone Detection Using Causal Interpretation, Shamsa Abid, Xuemeng Cai, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

Deep Neural Network-based models have demonstrated high accuracy for semantic code clone detection. However, the lack of generalization poses a threat to the trustworthiness and reliability of these models. Furthermore, the black-box nature of these models makes interpreting the model’s decisions very challenging. Currently, there is only a limited understanding of the semantic code clone detection behavior of existing models. There is a lack of transparency in understanding how a model identifies semantic code clones and the exact code components influencing its prediction. In this paper, we introduce the use of a causal interpretation framework based on the Neyman-Rubin causal …

Go to article

Impact Of Achievement-Oriented Gamification In Erp Systems: Examining Subjective And Objective User Outcomes, E. Adeborna, Fiona Fui-Hoon Nah, L. Motiwalla Jan 2025

Impact Of Achievement-Oriented Gamification In Erp Systems: Examining Subjective And Objective User Outcomes, E. Adeborna, Fiona Fui-Hoon Nah, L. Motiwalla

Research Collection School Of Computing and Information Systems

This research explores the effect of gamification using achievement-oriented affordances in Enterprise Resource Planning (ERP) systems on subjective (behavioral intention) and objective (performance) outcomes. Drawing on the cognitive-affectiveconative (CAC) framework, a research model was developed to explain behavioral intention and tested in a pilot experiment with 63 participants. These participants completed a post-study questionnaire for assessing the impact of gamification on users’ behavioral intention that is mediated by CAC constructs: focused immersion, enjoyment, and selfrewarding experience. Preliminary results show that gamification enhances enjoyment and self-rewarding experience, which in turn positively influence and fully mediate behavioral intention. Objective performance outcomes were …

Go to article

Interactive Video Search With Multi-Modal Llm Video Captioning, Yu-Tong Cheng, Jiaxin Wu, Zhixin Ma, Jiangshan He, Xiao-Yong Wei, Chong-Wah Ngo Jan 2025

Interactive Video Search With Multi-Modal Llm Video Captioning, Yu-Tong Cheng, Jiaxin Wu, Zhixin Ma, Jiangshan He, Xiao-Yong Wei, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Cross-modal representation learning is essential for interactive text-to-video search tasks. However, the representation learning is limited by the size and quality of video-caption pairs. To improve the search accuracy, we propose to enlarge the size of available video-caption pairs by leveraging multi-model LLM on video captioning. Specifically, we use LLM to generate video captions for a large video collection (i.e., WebVid dataset) and use the generated video-caption pairs to pre-train a text-to-video search model. Additionally, we use LLM to generate fine-grained captions for test video collections to enable text-to-caption retrieval. Furthermore, we build a semantic overview of the retrieved rank …

Go to article

First Prev Next Last