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 35941 - 35970 of 715350

Full-Text Articles in Entire DC Network

Quantifying Teaching Quality In University Chemistry Using Bipolar Neutrosophic Decision-Making Framework, Lina Sun, Feng Yi Mar 2025

Quantifying Teaching Quality In University Chemistry Using Bipolar Neutrosophic Decision-Making Framework, Lina Sun, Feng Yi

Neutrosophic Sets and Systems

There is no doubt that the teaching of university Chemistry plays a critical role in enriching the students’ knowledge with analytical and problem-solving skills that are necessary for achieving academic and professional progress in many fields. However, the process of evaluating the quality of Chemistry teaching remains a challenging task because it usually relies on subjective judgments, diversity of criteria, and variability in human perception, leading to inherent uncertainty. Bipolar Neutrosophic Sets (NS) provide appropriate representation for uncertainty setting ls with three levels of membership, each with positive and negative degrees. Inspired by that, this study contributes to the body …

Go to article

Topsis Approach For Madm Based On Quadripartitioned Single Valued Neutrosophic Refined Hamacher Aggregation Operations, Arokia Pratheesha S V, Annapoorna M S, Radha R, Parul Arora, Ritika Wason, Divya Baliga B Mar 2025

Topsis Approach For Madm Based On Quadripartitioned Single Valued Neutrosophic Refined Hamacher Aggregation Operations, Arokia Pratheesha S V, Annapoorna M S, Radha R, Parul Arora, Ritika Wason, Divya Baliga B

Neutrosophic Sets and Systems

Hamacher operators are extensively utilized in multicriteria attribute group decision-making (MAGDM) problems due to their remarkable adaptability provided by an adjustable parameter. Here, the Hamacher T-norm and T-conorm operations for two QSVNRNs are formulated.Using these Hamacher op erations, we present the quadripartitioned single-valued neutrosophic refined Hamacher weighted averaging (QSVNRHWA) operators within the QSVNR framework and analyze their properties.Finally, we explore a TOPSIS-based approach for multi-attribute decision-making problems that employs the QSVNRHWA opera tors, demonstrating its application in evaluating practical scenarios related to converting solid waste into energy.

Go to article

Different Operators Via Weighted Averaging And Geometric Approach Using Trigonometric Neutrosophic Interval-Valued Set And Its Extension, Raed Hatamleh, Ahmed Salem Heilat, M. Palanikumar, Abdallah Al-Husban Mar 2025

Different Operators Via Weighted Averaging And Geometric Approach Using Trigonometric Neutrosophic Interval-Valued Set And Its Extension, Raed Hatamleh, Ahmed Salem Heilat, M. Palanikumar, Abdallah Al-Husban

Neutrosophic Sets and Systems

This work presents a new method for generating tangent trigonometric neutrosophic interval-valued sets. This article will cover tangent trigonometric neutrosophic interval-valued weighted averaging, geometric, generalized notions. We used an aggregating model to get the weighted average and geometric. Several sets with substantial characteristics will be further studied using the algebraic techniques

Go to article

Robust Seismic Performance Evaluation Of Super High-Rise Concrete Structures Using Mcdm And Plithogenic-Ram Approach, Kaifeng Xing, Xiaoping Wang, Peng Chen Mar 2025

Robust Seismic Performance Evaluation Of Super High-Rise Concrete Structures Using Mcdm And Plithogenic-Ram Approach, Kaifeng Xing, Xiaoping Wang, Peng Chen

Neutrosophic Sets and Systems

More reinforced concrete supertall and megatall high-rise structures are being built due to the growing global demand for high-rise buildings, recent advancements in concrete technology, and improvements in construction techniques. When using concrete in these structures, additional care must be taken. Evaluating Super High-Rise Concrete Structures using various criteria is a multi-criteria decision-making (MCDM) challenge. We propose an MCDM method with a set of criteria and alternatives. The Root Assessment Method (RAM) is applied in this study to rank the alternatives. The RAM method is integrated with plithogenic sets to handle uncertain information. Plithogenic operators are used to combine the …

Go to article

Algebraic Properties Of Interval -Valued Quadri Partitioned Neutrosophic Fuzzy Matrices And Their Application In Multi-Criteria Decision- Making Problem, P. Tharini, C. Devi Shyamala Mary, P. Tharaniya, S. Prathap, S. Ramkumar, G. Dhanavel Mar 2025

Algebraic Properties Of Interval -Valued Quadri Partitioned Neutrosophic Fuzzy Matrices And Their Application In Multi-Criteria Decision- Making Problem, P. Tharini, C. Devi Shyamala Mary, P. Tharaniya, S. Prathap, S. Ramkumar, G. Dhanavel

Neutrosophic Sets and Systems

– In this study, we introduce two novel matrix concepts in the neutrosophic fuzzy domain: range-symmetric Interval-Valued Quadri Partitioned Neutrosophic Fuzzy Matrices and kernel symmetric Interval-Valued Quadri Partitioned Neutrosophic Fuzzy Matrices. These matrices are defined analogously to EP-matrices within the complex domain. Initially, we establish fundamental characterizations of range-symmetric matrices and then derive the necessary and sufficient conditions under which an Interval-Valued Quadri Partitioned Neutrosophic Fuzzy Matrices becomes kernel-symmetric . A detailed analysis follows to explore the relationship between range symmetric and kernel-symmetric Interval-Valued Quadri Partitioned Neutrosophic Fuzzy Matrices. Additionally, we introduce the concepts of Kernel and k-Kernel Symmetric Interval-Valued …

Go to article

Distance Measure For Fermatean Neutrosophic Sets: A Comparative Framework For Qualitative Evaluation, S. Bhuvaneshwari, C. Antony Crispin Sweety, Broumi Said Mar 2025

Distance Measure For Fermatean Neutrosophic Sets: A Comparative Framework For Qualitative Evaluation, S. Bhuvaneshwari, C. Antony Crispin Sweety, Broumi Said

Neutrosophic Sets and Systems

This work introduces a novel distance measure specifically designed for Fermatean Neutrosophic sets (FNS), extending upon existing measures such as the intuitionistic fuzzy distance and single-valued Neutrosophy distance measures. The study proposes a Hypothetical Framework for Fermatean Neutrosophic Sets to evaluate minimum distances and compares six different distance measures. These measures are applied within the contexts of both Fermatean Neutrosophic Sets and Neutrosophic Sets. The primary objective is to identify the shortest distance, enabling precise and appropriate decision-making. The study highlights the importance of false membership in FNS, which alters the ranking of FNS and establishes the Fermatean Neutrosophic set …

Go to article

Neutrosophic Non-Newtonian And Geometric Measures: A Consistent Analytical Framework, Amer Darweesh, Kamel Al-Khaled, Mohammed Shakhatreh, Mahmood Shareef Ajeel, Nermin Abo Hasan Mar 2025

Neutrosophic Non-Newtonian And Geometric Measures: A Consistent Analytical Framework, Amer Darweesh, Kamel Al-Khaled, Mohammed Shakhatreh, Mahmood Shareef Ajeel, Nermin Abo Hasan

Neutrosophic Sets and Systems

The neutrosophic measure is a generalization of the classical measure in situations when the space contains some indeterminacy. In this paper, we introduce the concept of the Neutrosophic Geometric Measure, we also provide some results, and examples related to the Neutrosophic Geometric Measure. A classical measure of the objects determinate component, a classical measure of its indeterminate part, and a further classical measure of the objects opposite determinate part are the three classical measures that make up the neutrosophic measure. To de ne the Neutrosophic Geometric Measure, we introduce a new measure on R+ and call it the geometric Lebesgue …

Go to article

, Combine Knowledge And Similarity Measure To Solve Single Valued Neutrosophic Set Mcdm Problems, Nguyen Xuan Thao, Truong Thi Thuy Duong Mar 2025

, Combine Knowledge And Similarity Measure To Solve Single Valued Neutrosophic Set Mcdm Problems, Nguyen Xuan Thao, Truong Thi Thuy Duong

Neutrosophic Sets and Systems

The Neutrosophics set have been paid attention of researchers using in many fields in the practice. It is a useful tool to deal with those complex problems. In this paper, we first investigat the knowledge measures on the Single neutrosophic set. Then, we introduce a new similarity measure of SNS that overcomes the restriction of some already existing similarity measure cases. A proposed measure-based multi-criteria decision-making (MCDM) model was constructed. In this model the knowledge measure to determine the weight of each criterion and similarity measure to rank the alternatives. This model applied to solve the agricultural land selection. Finally, …

Go to article

University Mathematics Classroom Teaching Quality Assessment Based On Core Competencies Using The Dematel Approach And Single-Valued Neutrosophic Hypersoft Sets, Jingjing Qiao Mar 2025

University Mathematics Classroom Teaching Quality Assessment Based On Core Competencies Using The Dematel Approach And Single-Valued Neutrosophic Hypersoft Sets, Jingjing Qiao

Neutrosophic Sets and Systems

This study proposes a multi-criteria decision-making (MCDM) approach to evaluate the quality of University Mathematics Classroom Teaching based on core competencies. The MCDM approach is applied within the framework of the neutrosophic set to address vague and uncertain data. Unlike the hypersoft set, which handles multiple disjoint attribute-valued sets corresponding to various characteristics, the soft set operates with a single set of attributes. This study introduces the concept of Single-Valued Neutrosophic Hypersoft Expert Sets (SVNS), which integrate single-valued neutrosophic sets and hypersoft expert sets. Eight criteria were employed to construct the pairwise comparison matrix. The Decision-Making Trial and Evaluation Laboratory …

Go to article

Intuitionistic Quadri-Partitioned Neutrosophic Sets With Extended Operators, Sai Anu P, Arulselvam A, Bobin A Mar 2025

Intuitionistic Quadri-Partitioned Neutrosophic Sets With Extended Operators, Sai Anu P, Arulselvam A, Bobin A

Neutrosophic Sets and Systems

We present the concept of intuitionistic quadri-partitioned neutrosophic sets (IQ-PNSs) and extend it to intuitionistic quadri-partitioned neutrosophic soft sets (IQ-PNSSs). These sets introduce a constraint where the combined membership values for truth and falsity must not exceed one, while the indeterminacy and contradiction membership values are restricted to the interval [01], ensuring the total sum of all membership values remains below three. In addition, we de ne necessity and possibility operators, along with two novel operators, ( and ), on IQ-PNSSs and explore their properties. Furthermore, we introduce and analyze the operators , , and , as well as the …

Go to article

Neutrosophic Analysis Of The Cultural Impact Of The Pinkullo In Llata: Integrating Chatgpt And Fsqca, Fredy Romulo Marcellini Morales, Betty Leon Trujillo, Esio Ocana Igarza, Roberto Carlos Cardenas Viviano Mar 2025

Neutrosophic Analysis Of The Cultural Impact Of The Pinkullo In Llata: Integrating Chatgpt And Fsqca, Fredy Romulo Marcellini Morales, Betty Leon Trujillo, Esio Ocana Igarza, Roberto Carlos Cardenas Viviano

Neutrosophic Sets and Systems

This study explores the cultural impact of the Pinkullo, a traditional Andean aerophone, on the community of Llata, Peru, through an innovative approach that integrates neutrosophic set theory with computational methods. By employing fuzzy-set Qualitative Comparative Analysis (fsQCA) and a novel application of ChatGPT for neutrosophic sentiment analysis, the research investigates the complex interplay between the Pinkullo and various aspects of community life, including cultural participation, social impact, and cultural preservation. Textual data collected from surveys was analyzed using the "ChatGPT Constructor" add-on in Orange Data Mining to generate neutrosophic scores, representing the truth, indeterminacy, and falsity of expressed sentiments …

Go to article

Implication-Based Neutrosophic Finite State Machine Over A Finite Group, S. Jafari, N. Rajesh, G. Nordo, M. Gorgone Mar 2025

Implication-Based Neutrosophic Finite State Machine Over A Finite Group, S. Jafari, N. Rajesh, G. Nordo, M. Gorgone

Neutrosophic Sets and Systems

In this paper, we define and investigate the concept of the implication-based neutrosophic finite state machine (IB-IFSA) over a finite group. Building upon the framework of neutrosophic logic, we introduce the implication-based neutrosophic kernel and the implication-based neutrosophic subsemiautomaton, establishing their formal definitions and properties. Additionally, we explore the structural interplay between these concepts and their implications within algebraic systems

Go to article

The Improper Neutrosophic Integrals, Yaser Ahmad Alhasan, Issam Mohammed Abdallah Abdalaziz, Raja Abdullah Abdulfatah, Florentin Smarandache Mar 2025

The Improper Neutrosophic Integrals, Yaser Ahmad Alhasan, Issam Mohammed Abdallah Abdalaziz, Raja Abdullah Abdulfatah, Florentin Smarandache

Neutrosophic Sets and Systems

In light of the expansion of research that dealt with the logic of the neutrosophic and its clear spread at the level of science, it was necessary for us to continue in the series of research that covers the calculus of neutrosophic integration, and this is what led us to study the improper neutrosophic integrals. This study dealt with the types of the improper neutrosophic integrals of the first and second kind. In addition, we discussed the concept of convergent and divergent neutrosophic integrals. As well as providing a set of examples related to these ideas.

Go to article

Enhancing Competency-Based Learning With Neutrosophic Regression And The Deming Cycle, Dr Hortencio Flores Flores, Dr. Irma Reyes Blácido, Dr. Magda Patricia Ramos Cevallos, Dr. Nemesia Hidalgo Penadillo Hidalgo Penadillo, Mg. Luz Magali Villarroel Nuñez Mar 2025

Enhancing Competency-Based Learning With Neutrosophic Regression And The Deming Cycle, Dr Hortencio Flores Flores, Dr. Irma Reyes Blácido, Dr. Magda Patricia Ramos Cevallos, Dr. Nemesia Hidalgo Penadillo Hidalgo Penadillo, Mg. Luz Magali Villarroel Nuñez

Neutrosophic Sets and Systems

This article introduces a novel approach to enhance competency-based learning by combining the Deming Cycle with neutrosophic statistics. Competency-based education focuses on practical skills, but uncertainty in student performance and assessment can hinder its effectiveness. Neutrosophic statistics, unlike traditional methods, explicitly models indeterminacy, providing a more complete picture of uncertainty in educational data. This approach integrates neutrosophic numbers into re gression analysis to predict learning outcomes and quantify the confidence level of those predictions. These predictions, with their associated indeterminacy, then inform the Deming Cycle (Plan-Do Check-Act), enabling educators to dynamically adjust teaching strategies based on data-driven in sights. This …

Go to article

A Concise Introduction To Hyperfuzzy, Hyperneutrosophic, Hyperplithogenic, Hypersoft, And Hyperrough Sets With Practical Examples, Takaaki Fujita, Florentin Smarandache Mar 2025

A Concise Introduction To Hyperfuzzy, Hyperneutrosophic, Hyperplithogenic, Hypersoft, And Hyperrough Sets With Practical Examples, Takaaki Fujita, Florentin Smarandache

Neutrosophic Sets and Systems

Various set concepts are widely recognized for effectively addressing u ncertainty, including fuzzy sets, neutrosophic sets, plithogenic sets, rough sets, and soft sets. These concepts have been further extended through hyperstructures (based on powersets) and superhyperstructures (based on n-th powersets, which are sets with repeated power set structures) [5,12–14,32]. These extensions are commonly referred to as HyperUncertain, SuperUncertain, and SuperHyperUncertain Sets/Logics/Probabilities/Statistics, and they were introduced by Smarandache in 2016-2017 [32] as parts of HyperStructures, SuperStructures, and SuperHyperStructures respectively. This paper recalls these concepts along with concrete examples.

Go to article

Stock Price Predictions With Lstm-Arima Hybrid Model Under Neutrosophic Treesoft Sets With Mcdm Interaction, G. Dhanalakshmi, Dr. S. Sandhiya, Florentin Smarandache Mar 2025

Stock Price Predictions With Lstm-Arima Hybrid Model Under Neutrosophic Treesoft Sets With Mcdm Interaction, G. Dhanalakshmi, Dr. S. Sandhiya, Florentin Smarandache

Neutrosophic Sets and Systems

The stock market is regarded as volatile, complex, tumultuous, and dynamic. Forecasting stock performance has proven to be a challenging endeavour due to its increasing need for investment and growth prospects. At the forefront of machine learning, deep learning models facilitate the straightforward and efficient exploration and identification of optimal stocks, the hybrid forecasting models (LSTM and ARIMA) are used in the prediction of stock increase. This paper incorporated the MCDM technique to determine the optimal stocks for investment. The Analytic Hierarchy Process (AHP) is used to assign weights to various financial factors. These weights are then used by the …

Go to article

Risk Assessment Of Steel Structure Engineering Cost Using Multi-Criteria Decision-Making Approach Under Uncertainty, Bijun Ni Mar 2025

Risk Assessment Of Steel Structure Engineering Cost Using Multi-Criteria Decision-Making Approach Under Uncertainty, Bijun Ni

Neutrosophic Sets and Systems

Choosing options with complex, ambiguous, and contradicting criteria is a common challenge for decision-makers. To choose the optimal option, they typically use multicriteria decision-making techniques, in which specialists manage the relative importance of conflicting tangible and intangible criteria to identify and evaluate possible courses of action. Making decisions involves one or more people selecting the best option from a range of potential options. This study proposes multi-criteria decision making (MCDM) method to compute the criteria weights are rank the alternatives. The MCDM approach is applied for risk assessment to cost in steel structure engineering. This problem includes many criteria and …

Go to article

Single-Valued Neutrosophic Graph With Heptapartitioend Structure, Hanaa Fathi, M. Myvizhi, Ahmed Abdelhafeez, Mohamed Refaat Abdellah, Mohamed Eassa, Mohamed S. Sawah, Hussam Elbehiery Mar 2025

Single-Valued Neutrosophic Graph With Heptapartitioend Structure, Hanaa Fathi, M. Myvizhi, Ahmed Abdelhafeez, Mohamed Refaat Abdellah, Mohamed Eassa, Mohamed S. Sawah, Hussam Elbehiery

Neutrosophic Sets and Systems

This study applies single-valued neutrosophic sets, which extend the frameworks of fuzzy and intuitionistic fuzzy sets, to graph theory. We introduce a new category of graphs called Single-Valued Heptapartitioned Neutrosophic Graphs (SVHNG) and investigate their characteristics through comprehensive proofs and illustrative examples.

Go to article

Retrieval Augmented Recipe Generation, Guoshan Liu, Hailong Yin, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yu-Gang Jiang Mar 2025

Retrieval Augmented Recipe Generation, Guoshan Liu, Hailong Yin, Bin Zhu, Jingjing Chen, Chong-Wah Ngo, Yu-Gang Jiang

Research Collection School Of Computing and Information Systems

The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method—first predicting ingredients from a food image and then generating instructions from both the image and ingredients. Large Multi-modal Models (LMMs), which have achieved notable success across a variety of vision and language tasks, shed light on generating both ingredients and instructions directly from images. Nevertheless, LMMs still face the common issue of hallu- cinations during recipe generation, leading to suboptimal performance. To tackle this issue, we propose a retrieval augmented large multimodal …

Go to article

Divide-And-Conquer: Confluent Triple-Flow Network For Rgb-T Salient Object Detection, Hao Tang, Zechao Li, Dong Zhang, Shengfeng He, Jinhui Tang Mar 2025

Divide-And-Conquer: Confluent Triple-Flow Network For Rgb-T Salient Object Detection, Hao Tang, Zechao Li, Dong Zhang, Shengfeng He, Jinhui Tang

Research Collection School Of Computing and Information Systems

RGB-Thermal Salient Object Detection (RGB-T SOD) aims to pinpoint prominent objects within aligned pairs of visible and thermal infrared images. A key challenge lies in bridging the inherent disparities between RGB and Thermal modalities for effective saliency map prediction. Traditional encoder-decoder architectures, while designed for cross-modality feature interactions, may not have adequately considered the robustness against noise originating from defective modalities, thereby leading to suboptimal performance in complex scenarios. Inspired by hierarchical human visual systems, we propose the ConTriNet, a robust Confluent Triple-Flow Network employing a "Divide-and-Conquer"strategy. This framework utilizes a unified encoder with specialized decoders, each addressing different subtasks …

Go to article

Imageinthat: Manipulating Images To Convey User Instructions To Robots, Karthik Mahadevan, Blaine Lewis, Jiannan Li, Bilge Mutlu, Anthony Tang, Tovi Grossman Mar 2025

Imageinthat: Manipulating Images To Convey User Instructions To Robots, Karthik Mahadevan, Blaine Lewis, Jiannan Li, Bilge Mutlu, Anthony Tang, Tovi Grossman

Research Collection School Of Computing and Information Systems

Foundation models are rapidly improving the capability of robots in performing everyday tasks autonomously such as meal preparation, yet robots will still need to be instructed by humans due to model performance, the difficulty of capturing user preferences, and the need for user agency. Robots can be instructed using various methods---natural language conveys immediate instructions but can be abstract or ambiguous, whereas end-user programming supports longer-horizon tasks but interfaces face difficulties in capturing user intent. In this work, we propose using direct manipulation of images as an alternative paradigm to instruct robots, and introduce a specific instantiation called ImageInThat which …

Go to article

Improving Multimodal Human Pose Estimation By Adversarial Modality Enhancement, Jiangnan Xia, Qilong Wu, Yanyin Guo, Yi Li, Jianghan Cheng, Junwei Li, Zhiyuan Zhang Mar 2025

Improving Multimodal Human Pose Estimation By Adversarial Modality Enhancement, Jiangnan Xia, Qilong Wu, Yanyin Guo, Yi Li, Jianghan Cheng, Junwei Li, Zhiyuan Zhang

Research Collection School Of Computing and Information Systems

Human pose estimation in computer vision predominantly focuses on the visible modality, with limited research on the infrared modality. No existing methods demonstrate robust performance across both modalities, missing their complementary strengths. This gap arises from the lack of a multimodal benchmark and the difficulty of developing robust multimodal capabilities. To address this, we introduce MMPD, a novel visible-infrared multimodal pose benchmark with high-quality annotations for both modalities. Leveraging MMPD, we expose the limitations of state-of-the-art methods due to modality variance. To overcome this challenge, we propose a novel method-agnostic scheme called AMMPE. By employing the Modality Adversarial Enhancement Stage …

Go to article

A Contrastive Framework With User, Item And Review Alignment For Recommendation, Viet Hoang Dong, Yuan Fang, Hady Wirawan Lauw Mar 2025

A Contrastive Framework With User, Item And Review Alignment For Recommendation, Viet Hoang Dong, Yuan Fang, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

Learning effective latent representations for users and items is the cornerstone of recommender systems. Traditional approaches rely on user-item interaction data to map users and items into a shared latent space, but the sparsity of interactions often poses challenges. While leveraging user reviews could mitigate this sparsity, existing review-aware recommendation models often exhibit two key limitations. First, they typically rely on reviews as additional features, but reviews are not universal, with many users and items lacking them. Second, such approaches do not integrate reviews into the useritem space, leading to potential divergence or inconsistency among user, item, and review representations. …

Go to article

Selecting Comparative Sets Of Reviews Across Multiple Items, Trung Hoang Le, Hady Wirawan Lauw Mar 2025

Selecting Comparative Sets Of Reviews Across Multiple Items, Trung Hoang Le, Hady Wirawan Lauw

Research Collection School Of Computing and Information Systems

While choosing among several products, users may look up reviews from each product they are considering. Due to the large number of reviews of products, selecting representative reviews from one product alone is already a challenging problem. In this work, we further aim to conduct review selection for multiple products simultaneously for comparative purposes. We formulate objective functions that synchronize the review selection and design efficient algorithms to optimize for the objective functions. To narrow down the potentially long list of comparison items into a shorter list of more similar items, we construct a graph representing items’ similarity and design …

Go to article

Neurovig: Integrating Event Cameras For Resource-Efficient Video Grounding, Dulanga Weerakoon, Vigneshwaran Subbaraju, Joo Hwee Lim, Archan Misra Mar 2025

Neurovig: Integrating Event Cameras For Resource-Efficient Video Grounding, Dulanga Weerakoon, Vigneshwaran Subbaraju, Joo Hwee Lim, Archan Misra

Research Collection School Of Computing and Information Systems

Spatio-Temporal Video Grounding (STVG) - the task of identifying the target object in the field-of-view that the language instruction refers to - is a fundamental vision-language task. Current STVG approaches typically utilize feeds from an RGB camera that is assumed to be always-on and process the video frames using complex neural network pipelines. As a result they often impose prohibitive system overheads (energy latency) on pervasive devices. To address this we propose NeuroViG with two key innovations: (a) leveraging on event streams from a low-power neuromorphic event camera sensor to perform selective triggering of the more energy-hungry RGB camera for …

Go to article

Explainable Neural Networks With Guarantees: A Sparse Estimation Approach, Antoine Ledent, Peng Liu Mar 2025

Explainable Neural Networks With Guarantees: A Sparse Estimation Approach, Antoine Ledent, Peng Liu

Research Collection School Of Computing and Information Systems

Balancing predictive power and interpretability has long been a challenging research area, particularly in powerful yet complex models like neural networks, where nonlinearity obstructs direct interpretation. This paper introduces a novel approach to constructing an explainable neural network that harmonizes predictiveness and explainability. Our model is designed as a linear combination of a sparse set of jointly learned features, each derived from a different trainable function applied to a single 1-dimensional input feature. Leveraging the ability to learn arbitrarily complex relationships, our neural network architecture enables automatic selection of a sparse set of important features, with the final prediction being …

Go to article

Multi-Uav Reconnaissance Mission Planning Via Deep Reinforcement Learning With Simulated Annealing, Mingfeng Fan, Huan Liu, Guohua Wu, Aldy Gunawan, Guillaume Sartoretti Mar 2025

Multi-Uav Reconnaissance Mission Planning Via Deep Reinforcement Learning With Simulated Annealing, Mingfeng Fan, Huan Liu, Guohua Wu, Aldy Gunawan, Guillaume Sartoretti

Research Collection School Of Computing and Information Systems

Unmanned aerial vehicles (UAVs) are widely used in reconnaissance missions due to their autonomy and flexibility. Efficient mission planning for multiple UAVs is crucial for tasks such as traffic monitoring and data collection. However, existing approaches to multi-UAV reconnaissance mission planning problem (MURMPP) often struggle with high computational demands, leading to suboptimal solutions. To overcome this challenge, we introduce a divide-and-conquer framework that splits the problem into two phases: target allocation and UAV routing, effectively reducing computational complexity. Specifically, we propose a hybrid method, SA-NNO-DRL, which combines the nearest neighbor optima-based deep reinforcement learning (NNO-DRL) approach with simulated annealing (SA). …

Go to article

Multisfl: Towards Accurate Split Federated Learning Via Multi-Model Aggregation And Knowledge Replay, Zeke Xia, Ming Hu, Dengke Yan, Ruixuan Liu, Anran Li, Xiaofei Xie, Mingsong Chen Mar 2025

Multisfl: Towards Accurate Split Federated Learning Via Multi-Model Aggregation And Knowledge Replay, Zeke Xia, Ming Hu, Dengke Yan, Ruixuan Liu, Anran Li, Xiaofei Xie, Mingsong Chen

Research Collection School Of Computing and Information Systems

Although Split Federated Learning (SFL) effectively enables knowledge sharing among resource-constrained clients, it suffers from low training performance due to the neglect of data heterogeneity and catastrophic forgetting problems. To address these issues, we propose a novel SFL approach named MultiSFL, which adopts i) an effective multimodel aggregation mechanism to alleviate gradient divergence caused by heterogeneous data and ii) a novel knowledge replay strategy to deal with the catastrophic forgetting problem. MultiSFL adopts two servers (i.e., the fed server and main server) to maintain multiple branch models for local training and an aggregated master model for knowledge sharing among branch …

Go to article

Birdie: Natural Language-Driven Table Discovery Using Differentiable Search Index, Yuxiang Guo, Zhonghao Hu, Yuren Mao, Baihua Zheng, Yunjun Gao, Mingwei Zhou Mar 2025

Birdie: Natural Language-Driven Table Discovery Using Differentiable Search Index, Yuxiang Guo, Zhonghao Hu, Yuren Mao, Baihua Zheng, Yunjun Gao, Mingwei Zhou

Research Collection School Of Computing and Information Systems

Natural language (NL)-driven table discovery identifies relevant tables from large table repositories based on NL queries. While current deep-learning-based methods using the traditional dense vector search pipeline, i.e., representation-index-search, achieve remarkable accuracy, they face several limitations that impede further performance improvements: (i) the errors accumulated during the table representation and indexing phases affect the subsequent search accuracy; and (ii) insufficient query-table interaction hinders effective semantic alignment, impeding accuracy improvements. In this paper, we propose a novel framework Birdie, using a differentiate search index. It unifies the indexing and search into a single encoder-decoder language model, thus getting rid of error …

Go to article

Ragg: Retrieval-Augmented Grasp Generation Model, Zhenhua Tang, Bin Zhu, Yanbin Hao, Chong-Wah Ngo, Richang Hong Mar 2025

Ragg: Retrieval-Augmented Grasp Generation Model, Zhenhua Tang, Bin Zhu, Yanbin Hao, Chong-Wah Ngo, Richang Hong

Research Collection School Of Computing and Information Systems

Intent-based grasp generation inherently involves challenges such as manipulation ambiguity and modality gaps. To address these, we propose a novel Retrieval-Augmented Grasp Generation model (RAGG). Our key insight is that when humans manipulate new objects, they initially mimic the interaction patterns observed in similar objects, then progressively adjust hand-object contact. Consequently, we develop RAGG as a two-stage approach, encompassing retrieval-guided generation and structurally stable grasp refinement. In the first stage, we propose a Retrieval-Augmented Diffusion Model (ReDim), which identifies the most relevant interaction instance from a knowledge base to explicitly guide grasp generation, thereby mitigating ambiguity and bridging modality gaps …

Go to article

First Prev Next Last