Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
Machine Learning VLSI CAD Experiments Should Consider Atomic Data Groups
MLCAD '24: Proceedings of the 2024 ACM/IEEE International Symposium on Machine Learning for CADArticle No.: 32, Pages 1–8https://doi.org/10.1145/3670474.3685970Machine learning (ML) has proved useful across a wide range of applications in the very-large-scale integration computer-aided design (VLSI CAD) domain. To avoid overestimating ML models' generalization capabilities for real-world deployments, best ...
- ArticleSeptember 2024
X-Vector-Based Speaker Diarization Using Bi-LSTM and Interim Voting-Driven Post-processing
AbstractIn this work, we propose a voting-driven post-processing strategy for enhancing the efficacy of supervised speaker diarization models. Speaker embeddings, x-vectors, are used to train deep learning architectures such as convolutional neural ...
- research-articleJuly 2024
Towards realistic problem-space adversarial attacks against machine learning in network intrusion detection
ARES '24: Proceedings of the 19th International Conference on Availability, Reliability and SecurityArticle No.: 113, Pages 1–8https://doi.org/10.1145/3664476.3669974Current trends in network intrusion detection systems (NIDS) capitalize on the extraction of features from network traffic and the use of up-to-date machine and deep learning techniques to infer a detection model; in consequence, NIDS can be vulnerable ...
- posterAugust 2024
Evolutionary Data Subset Selection for Class-Incremental Learning on Memory-Constrained Systems
GECCO '24 Companion: Proceedings of the Genetic and Evolutionary Computation Conference CompanionPages 255–258https://doi.org/10.1145/3638530.3654109Training Machine Learning classifiers on extreme edge devices with non-volatile memory size ≤ 10 MB is challenging because of a) the small number of data examples that can be preserved on-device and b) the dynamic nature of the training dataset caused by ...
- research-articleJuly 2024
NEvoFed: A Decentralized Approach to Federated NeuroEvolution of Heterogeneous Neural Networks
GECCO '24: Proceedings of the Genetic and Evolutionary Computation ConferencePages 295–303https://doi.org/10.1145/3638529.3654029In the past few years, Federated Learning (FL) has emerged as an effective approach for training neural networks (NNs) over a computing network while preserving data privacy. Most of the existing FL approaches require the user to define a priori the same ...
-
- research-articleMay 2024
A Heterogeneous Ensemble Method for Handling Class Noise in Supervised Machine Learning
SAC '24: Proceedings of the 39th ACM/SIGAPP Symposium on Applied ComputingPages 902–909https://doi.org/10.1145/3605098.3635936The goal of machine learning is to approximate an unknown input function by learning based on a set of labeled training samples. Noisy labels due to class noise in the training data can have three negative consequences: (i) the prediction accuracy may ...
- abstractMarch 2024
Enhancing American Sign Language Classification by Leveraging Hand Landmark Extraction
SIGCSE 2024: Proceedings of the 55th ACM Technical Symposium on Computer Science Education V. 2Page 1879https://doi.org/10.1145/3626253.3635406This research explores a novel approach to enhance the accuracy of static American Sign Language (ASL) sign classification by employing hand landmark extraction through computer vision. Traditional Convolutional Neural Networks (CNN) often operate on raw ...
- extended-abstractMarch 2024
Framework for Bias Detection in Machine Learning Models: A Fairness Approach
WSDM '24: Proceedings of the 17th ACM International Conference on Web Search and Data MiningPages 1152–1154https://doi.org/10.1145/3616855.3635731The research addresses bias and inequity in binary classification problems in machine learning. Despite existing ethical frameworks for artificial intelligence, detailed guidance on practices and tech niques to address these issues is lacking. The main ...
- research-articleAugust 2024
Prediction of Locally Stationary Data Using Expert Advice
Problems of Information Transmission (PRIT), Volume 60, Issue 1Pages 35–52https://doi.org/10.1134/S0032946024010058AbstractWe address the lifelong machine learning problem. Within the game-theoretic approach, in the calculation of the next prediction we use no assumptions on the stochastic nature of a source that generates the data flow: the source can be either ...
- research-articleJuly 2024
Multi Task-Guided 6D Object Pose Estimation
- Thu-Uyen Nguyen,
- Van-Duc Vu,
- Van-Thiep Nguyen,
- Ngoc-Anh Hoang,
- Duy-Quang Vu,
- Duc-Thanh Tran,
- Khanh-Toan Phan,
- Anh-Truong Mai,
- Van-Hiep Duong,
- Cong-Trinh Tran,
- Ngoc-Trung Ho,
- Quang-Tri Duong,
- Phuc-Quan Ngo,
- Dinh-Cuong Hoang
ICIIT '24: Proceedings of the 2024 9th International Conference on Intelligent Information TechnologyPages 215–222https://doi.org/10.1145/3654522.3654576Object pose estimation remains a fundamental challenge in computer vision, with cutting-edge methods relying on both RGB and depth data. Depth information is pivotal, offering crucial geometric cues that enable algorithms to navigate occlusions, ...
- research-articleJuly 2024
Grasp Generation with Depth Estimation from Color Images
- Nguyen Van Thiep,
- Vu Van Duc,
- Hoang Ngoc Anh,
- Nguyen Thu Uyen,
- Vu Duy Quang,
- Tran Duc Thanh,
- Phan Khanh Toan,
- Mai Truong Anh,
- Duong Van Hiep,
- Tran Cong Trinh,
- Ho Ngoc Trung,
- Duong Quang Tri,
- Ngo Phuc Quan,
- Hoang Dinh Cuong
ICIIT '24: Proceedings of the 2024 9th International Conference on Intelligent Information TechnologyPages 209–214https://doi.org/10.1145/3654522.3654575Grasp generation plays a fundamental role in robot manipulation, often relying on three-dimensional (3D) point cloud data acquired through specialized depth cameras. However, the limited availability of such sensors in practical scenarios emphasizes the ...
- research-articleJuly 2024
Predictive modelling for fake news detection using TF-IDF and count vectorizers
International Journal of Electronic Security and Digital Forensics (IJESDF), Volume 16, Issue 4Pages 503–519https://doi.org/10.1504/ijesdf.2024.139672Most people choose to acquire their news quickly and affordably via the internet, yet this encourages the fast spread of false information. Today's society depends heavily on data, and by 2023, 120 zeta bytes will be released every second. This enormous ...
- research-articleMay 2024
Comparative analysis of supervised learning algorithms for prediction of cardiovascular diseases
Technology and Health Care (TAHC), Volume 32, Issue S1Pages 241–251https://doi.org/10.3233/THC-248021BACKGROUND:With the advent of artificial intelligence technology, machine learning algorithms have been widely used in the area of disease prediction.
OBJECTIVE:Cardiovascular disease (CVD) seriously jeopardizes human health worldwide, thereby ...
- ArticleDecember 2023
Transfer Learning: Kernel-Based Domain Adaptation with Distance-Based Penalization
Pattern Recognition and Machine IntelligencePages 189–198https://doi.org/10.1007/978-3-031-45170-6_20AbstractThis paper introduces a novel approach to address the challenges of transfer learning, which aims to efficiently train a classifier for a new domain using supervised information from similar domains. Traditional transfer learning methods may fail ...
- research-articleApril 2024
2D and 3D Physics Informed Neural Networks to Model Pollution Spread with Obstructions
BDCAT '23: Proceedings of the IEEE/ACM 10th International Conference on Big Data Computing, Applications and TechnologiesArticle No.: 28, Pages 1–2https://doi.org/10.1145/3632366.3632380Pollution simulations rely on math models to solve Partial Differential Equations (PDEs). Although accurate, they are slow, as they sequentially compute one timestep at a time. Recent research advancements in Physics Informed Neural Networks (PINNs) like ...
- posterNovember 2023
Poster: RPAL-Recovering Malware Classifiers from Data Poisoning using Active Learning
CCS '23: Proceedings of the 2023 ACM SIGSAC Conference on Computer and Communications SecurityPages 3561–3563https://doi.org/10.1145/3576915.3624391Intuitively, poisoned machine learning (ML) models may forget their adversarial manipulation via retraining. However, can we quantify the time required for model recovery? From an adversarial perspective, is a small amount of poisoning sufficient to ...
- research-articleOctober 2023
Ground‐based cloud recognition method based on an improved DeepLabV3+ model
Cognitive Computation and Systems (CCS2), Volume 5, Issue 4Pages 280–287https://doi.org/10.1049/ccs2.12091AbstractAn improved method for recognising clouds on the ground map is proposed incorporating the DeepLabV3+ model to solve three issues. Firstly, an image preprocessing module is developed to enrich image quality, particularly at night, as clouds can ...
- research-articleOctober 2023
Joint Local Relational Augmentation and Global Nash Equilibrium for Federated Learning with Non-IID Data
- Xinting Liao,
- Chaochao Chen,
- Weiming Liu,
- Pengyang Zhou,
- Huabin Zhu,
- Shuheng Shen,
- Weiqiang Wang,
- Mengling Hu,
- Yanchao Tan,
- Xiaolin Zheng
MM '23: Proceedings of the 31st ACM International Conference on MultimediaPages 1536–1545https://doi.org/10.1145/3581783.3612178Federated learning (FL) is a distributed machine learning paradigm that needs collaboration between a server and a series of clients with decentralized data. To make FL effective in real-world applications, existing work devotes to improving the modeling ...
- ArticleDecember 2023
Learning Hierarchical Representations in Temporal and Frequency Domains for Time Series Forecasting
AbstractLong-term time series forecasting is a critical task in many domains, including finance, healthcare, and weather forecasting. While Transformer-based models have made significant progress in time series forecasting, their high computational ...
- research-articleSeptember 2023
A modulized lane‐follower for driverless vehicles using multi‐frame
Cognitive Computation and Systems (CCS2), Volume 5, Issue 3Pages 218–230https://doi.org/10.1049/ccs2.12092AbstractAs a fundamental function, lane following plays an important role for driverless vehicles. Unfortunately, lane followers generally confront great difficulty in lane line missed situations caused by vague line, shadows etc. However, for most lane ...