vehicular communication has numerous advantageous features including autonomy safety, communication skills with other vehicle or pedestrian or an infrastructure. mmWave communication in a type of wireless communicatio...
详细信息
People with autism spectrum disorder (ASD) show distinguishing preferences for specific visual stimuli compared to typically developed (TD) individuals, opening the door for objective and quantitative screening by eye...
详细信息
ISBN:
(纸本)9783031439032;9783031439049
People with autism spectrum disorder (ASD) show distinguishing preferences for specific visual stimuli compared to typically developed (TD) individuals, opening the door for objective and quantitative screening by eye-tracking dataanalysis. However, existing eye-tracking-based ASD screening approaches often assume that there are no individual differences and that all stimuli contribute equally to the prediction of an ASD. Consequently, a fixed number of images are usually selected by a pre-defined strategy for further training and testing, ignoring the distinct characteristics of various subjects viewing the same image. To address the aforementioned difficulties, we propose a novel Uncertainty-inspired ASD Screening Network (UASN) that dynamically modifies the contribution of each stimulus viewed by different subjects. Specifically, we estimate the uncertainty of each stimulus by considering the variation between the subject's fixation map and the ones of the two clinical groups (i.e., ASD and TD) and further utilize it for weighting the training loss. Besides, to reduce the diagnosis time, instead of the shuffle-appeared mode of image viewing, we propose an uncertainty-based personalized diagnosis method to dynamically rank the viewing images according to the preferences of different subjects, which can achieve high prediction accuracy with only a small set of images. Experiments demonstrate the superior performance of our proposed UASN.
The proceedings contain 21 papers. The special focus in this conference is on Modelling and Development of Intelligent Systems. The topics include: Morphology of Convolutional Neural Network with Diagonalize...
ISBN:
(纸本)9783031270338
The proceedings contain 21 papers. The special focus in this conference is on Modelling and Development of Intelligent Systems. The topics include: Morphology of Convolutional Neural Network with Diagonalized Pooling;challenges and Opportunities in Deep Learning Driven Fashion Design and Textiles Patterns Development;feature Selection and Extreme Learning Machine Tuning by Hybrid Sand Cat Optimization Algorithm for Diabetes Classification;Enriching SQL-Driven dataexploration with Different Machine Learning Models;analytical Solution of the Simplest Entropiece Inversion Problem;latent Semantic Structure in Malicious Programs;innovative Lattice Sequences Based on Component by Component Construction Method for Multidimensional Sensitivity analysis;on an Optimization of the Lattice Sequence for the Multidimensional Integrals Connected with Bayesian Statistics;numerical Optimization Identification of a Keller-Segel Model for Thermoregulation in Honey Bee Colonies in Winter;gaze Tracking: A Survey of Devices, Libraries and Applications;gradient Optimization in Reconstruction of the Diffusion Coefficient in a Time Fractional Integro-Differential Equation of Pollution in Porous Media;Flash Flood Simulation Between Slănic and vărbilău Rivers in vărbilău village, Prahova County, Romania, Using Hydraulic Modeling and GIS Techniques;group Decision-Making Involving Competence of Experts in Relation to Evaluation Criteria: Case Study for e-Commerce Platform Selection;Transparency and Traceability for AI-Based Defect Detection in PCB Production;tasks Management Using Modern Devices;a Method for Target Localization by Multistatic Radars;Intrusion Detection by XGBoost Model Tuned by Improved Social Network Search Algorithm;bridging the Resource Gap in Cross-Lingual Embedding Space;classification of Microstructure Images of Metals Using Transfer Learning.
The development of superior recognition/ classification techniques is essential for real-time Natural Language Processing (NLP) applications. Sentiment analysis (SA) is a task of NLP that aims to extract the sentiment...
详细信息
We demonstrate QeNoBi, a system for mining and querying customer behavioral patterns. QeNoBi combines an interactive visual interface, on-demand mining, and efficient top-k processing, to provide the exploration of cu...
详细信息
ISBN:
(纸本)9781728191843
We demonstrate QeNoBi, a system for mining and querying customer behavioral patterns. QeNoBi combines an interactive visual interface, on-demand mining, and efficient top-k processing, to provide the exploration of customer behavior over time. QeNoBi relies on two distinct data models: a customer-centric graph that represents customers with similar purchasing behaviors and is annotated with a change algebra to reflect their behavior evolution, and product-centric time series that reflect the evolution of customer purchases over time. Users can query both representations along three dimensions: shape (the sketched trend of the behavior), scope (the set of customers/products of interest), and time granularity. QeNoBi provides a holistic behavior exploration capability by allowing users to seamlessly switch between customer-centric and product-centric views in a coordinated manner, thereby catering to various needs. A demonstration of QeNoBi is available at https://***/2HlcO3S.
This study investigates the feature extraction capabilities of two prominent convolutional neural network (CNN) architectures, Inception v3 and AlexNet, in the context of website visuals. With the growing need for aut...
详细信息
ISBN:
(数字)9798331528799
ISBN:
(纸本)9798331528805
This study investigates the feature extraction capabilities of two prominent convolutional neural network (CNN) architectures, Inception v3 and AlexNet, in the context of website visuals. With the growing need for automated visualdataanalysis on the web, effective feature extraction is critical for tasks such as image classification, object detection, and visual content analysis. Inception v3 and AlexNet were selected due to their distinct architectural approaches and widespread use in various computer vision applications. The research employed a controlled experimental design, utilizing a dataset of website visuals collected from platforms like Themeforest. data preprocessing included image resizing, normalization, and augmentation techniques to enhance model robustness. Both models were fine-tuned on the specific dataset to adapt their pretrained weights from ImageNet to the unique characteristics of website visuals. Performance metrics were used to evaluate the models' effectiveness, including precision, recall, F1 score, Mean Average Precision (MAP), and Normalized Discounted Cumulative Gain (NDCG). Results indicated that AlexNet outperformed Inception v3 in precision (0.7062 vs. 0.6860) and recall (0.5914 vs. 0.0506), highlighting its efficiency and suitability for more straightforward feature extraction tasks with lower computational costs. In contrast, Inception v3 exhibited superior potential in capturing complex visual patterns but struggled with computational efficiency, as evidenced by its significantly longer inference time (222.9552 seconds compared to 63.2978 seconds for AlexNet). The findings underscore the importance of model selection based on specific application requirements, such as prioritizing speed or depth of feature extraction. Recommendations for practitioners include leveraging AlexNet for resource-constrained environments and opting for Inception v3 when handling complex, multi-scale visualdata. Future research could explore additional
In response to the existing university book recommendation systems that mostly recommend readers based on library resources and lack exploration of recommended books, this paper proposes a system service architecture ...
ISBN:
(纸本)9798400709517
In response to the existing university book recommendation systems that mostly recommend readers based on library resources and lack exploration of recommended books, this paper proposes a system service architecture that accurately pushes both readers and libraries simultaneously. The system is designed using technologies such as web spiders, big data, NLP, and visualanalysis. The system integrates reader data entry, web crawler, user profile, book similarity measurement, and intelligent push functions. Book managers can use the system to push books accurately and discover recommended books. The system fully utilizes book attribute data and reader attribute data, avoiding common cold start issues in recommendation systems, and providing support for improving the service level of the library and scientifically allocating collection resources.
A city’s history and culture studies involves understanding the literary works and historical events that have shaped the city’s identity. Increased availability of quantitative historical data has provided new oppo...
详细信息
ISBN:
(数字)9798350393804
ISBN:
(纸本)9798350393811
A city’s history and culture studies involves understanding the literary works and historical events that have shaped the city’s identity. Increased availability of quantitative historical data has provided new opportunities. Taking Nanjing as an example, this paper proposes EmoGeoCity, a visual analytics system to study a city’s cultural and historical evolution, through the use of digital humanities methods and emotional geography. The system incorporates sentiment analysis into historical research to quantify the emotional content of works and synthesize an overall emotion trend within a specific location. A dynamic emotional map, integrating locations, works, and events, enables a macroscopic observation of city emotions over time. An emotional polyline is designed to provide a microscopic interpretation of the emotion trend of a single location. exploration through the system reveals the evolution of the city from an emotional geographic perspective, which gives insights for humanities researchers studying a city’s history and literature, as well as for the general public interested in gaining knowledge on historical sites. Case and user studies illustrate the effectiveness and usability of our system.
Many literature enthusiasts join communities to discuss their favourite fictional characters and novels, but meaningful insights may be slow to achieve and share when attempting to recall or verify the textual basis o...
详细信息
ISBN:
(纸本)9798400717079
Many literature enthusiasts join communities to discuss their favourite fictional characters and novels, but meaningful insights may be slow to achieve and share when attempting to recall or verify the textual basis of their personal perspectives. Information visualisations can present text-derived data to make its summarisation and exploration both accessible and intuitive, yet visualisations of literary works are mostly tailored to expert workflows. This design study addresses this gap, comprehensively detailing our process of uncovering the tasks, data, and visual design requirements to implement Clover Connections, a visualisation of text-derived data for non-experts. Its layout features clover-shaped glyphs, storylines, and arcs to visually represent and connect temporal, social and personal data on characters in novels, which we demonstrate using datasets built from two popular novels. A formative user evaluation study with non-expert participants showed Clover Connections supports multiple general character analysis tasks, and provided qualitative insights that encourage future work.
Sequence decoding is the core component of systems that deal with sequence alignment problems like continuous speech recognition, visual scene labelling, multimedia storage and retrieval. In this paper, we address the...
详细信息
暂无评论