To see the other types of publications on this topic, follow the link: User Intent Prediction.
Journal articles on the topic 'User Intent Prediction'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'User Intent Prediction.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Santos, Eugene, Hien Nguyen, Qunhua Zhao, and Hua Wang. "User Modelling for Intent Prediction in Information Analysis." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 47, no. 8 (2003): 1034–38. http://dx.doi.org/10.1177/154193120304700818.
Full text
2
Anirudh, Reddy Pathe. "Multi-Modal Feature Analysis for User Intent Prediction: A Framework for Enhanced Look-to-Book Ratio in Digital Platforms." INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH AND CREATIVE TECHNOLOGY 5, no. 1 (2019): 1–10. https://doi.org/10.5281/zenodo.14282008.
Full textAbstract:
This research introduces an innovative framework for predicting user intent through multi-modal feature analysis, specifically designed to enhance look-to-book ratios in digital platforms. We present a comprehensive approach that leverages advanced machine learning techniques to process and analyze visual, textual, and behavioral data streams simultaneously. The framework incorporates novel feature fusion mechanisms and adaptive learning strategies to improve prediction accuracy while maintaining computational efficiency. Our theoretical analysis demonstrates the framework's potential for significant improvements in user intent prediction and conversion rate optimization, with particular emphasis on scalability and real-time processing capabilities.
3
Para, Raghu K. "Intent Prediction in AR Shopping Experiences Using Multimodal Interactions of Voice, Gesture, and Eye Tracking: A Machine Learning Perspective." Journal of Artificial Intelligence General science (JAIGS) ISSN:3006-4023 7, no. 01 (2024): 52–62. https://doi.org/10.60087/jaigs.v7i01.295.
Full textAbstract:
Augmented Reality (AR) is revolutionizing the shopping experience by allowing consumers to interact with virtual products in real-time. Intent prediction – the mechanism of predicting a consumer’s intention based on their behavioral patterns and actions – is crucial for enhancing the personalization of AR shopping environments. This paper explores how multimodal interactions, including voice commands, gesture recognition, and eye tracking, can be integrated into AR shopping experiences to predict user intent more effectively. We review current advancements in multimodal interaction systems, discuss the importance of intent prediction in AR, and assess the impact of combining multiple input modalities on prediction accuracy. Our research identifies the challenges and future directions for intent prediction in AR shopping landscapes, aiming to improve user engagement, personalization, and the overall shopping experience.
4
Xiong, Wei, Michael Recce, and Brook Wu. "Intent-Based User Segmentation with Query Enhancement." International Journal of Information Retrieval Research 3, no. 4 (2013): 1–17. http://dx.doi.org/10.4018/ijirr.2013100101.
Full textAbstract:
With the rapid advancement of the internet, accurate prediction of user's online intent underlying their search queries has received increasing attention from online advertising community. This paper aims to address the major challenges with user queries in the context of behavioral targeting advertising by proposing a query enhancement mechanism that augments user's queries by leveraging a user query log. The empirical evaluation demonstrates that the authors' methodology for query enhancement achieves greater improvement than the baseline models in both intent-based user classification and user segmentation. Different from traditional user segmentation methods, which take little semantics of user behaviors into consideration, the authors propose a novel user segmentation strategy by incorporating the query enhancement mechanism with a topic model to mine the relationships between users and their behaviors in order to segment users in a semantic manner. Comparing with a classical clustering algorithm, K-means, the experimental results indicate that the proposed user segmentation strategy helps improve behavioral targeting effectiveness significantly. This paper also proposes an alternative to define user's search intent for the evaluation purpose, in the case that the dataset is sanitized. This approach automatically labels users in a click graph, which are then used in training an intent-based user classifier.
5
Isomoto, Toshiya, Shota Yamanaka, and Buntarou Shizuki. "Dwell Selection with ML-based Intent Prediction Using Only Gaze Data." Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 6, no. 3 (2022): 1–21. http://dx.doi.org/10.1145/3550301.
Full textAbstract:
We developed a dwell selection system with ML-based prediction of a user's intent to select. Because a user perceives visual information through the eyes, precise prediction of a user's intent will be essential to the establishment of gaze-based interaction. Our system first detects a dwell to roughly screen the user's intent to select and then predicts the intent by using an ML-based prediction model. We created the intent prediction model from the results of an experiment with five different gaze-only tasks representing everyday situations. The intent prediction model resulted in an overall area under the curve (AUC) of the receiver operator characteristic curve of 0.903. Moreover, it could perform independently of the user (AUC=0.898) and the eye-tracker (AUC=0.880). In a performance evaluation experiment with real interactive situations, our dwell selection method had both higher qualitative and quantitative performance than previously proposed dwell selection methods.
6
Xiao, Jingyu, Qingsong Zou, Qing Li, et al. "I Know Your Intent." Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 7, no. 3 (2023): 1–28. http://dx.doi.org/10.1145/3610906.
Full textAbstract:
With the booming of smart home market, intelligent Internet of Things (IoT) devices have been increasingly involved in home life. To improve the user experience of smart homes, some prior works have explored how to use machine learning for predicting interactions between users and devices. However, the existing solutions have inferior User Device Interaction (UDI) prediction accuracy, as they ignore three key factors: routine, intent and multi-level periodicity of human behaviors. In this paper, we present SmartUDI, a novel accurate UDI prediction approach for smart homes. First, we propose a Message-Passing-based Routine Extraction (MPRE) algorithm to mine routine behaviors, then the contrastive loss is applied to narrow representations among behaviors from the same routines and alienate representations among behaviors from different routines. Second, we propose an Intent-aware Capsule Graph Attention Network (ICGAT) to encode multiple intents of users while considering complex transitions between different behaviors. Third, we design a Cluster-based Historical Attention Mechanism (CHAM) to capture the multi-level periodicity by aggregating the current sequence and the semantically nearest historical sequence representations through the attention mechanism. SmartUDI can be seamlessly deployed on cloud infrastructures of IoT device vendors and edge nodes, enabling the delivery of personalized device service recommendations to users. Comprehensive experiments on four real-world datasets show that SmartUDI consistently outperforms the state-of-the-art baselines with more accurate and highly interpretable results.
7
Cubuktepe, Murat, and Ufuk Topcu. "Intent Prediction in Shared Control with Delayed Feedback." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 61, no. 1 (2017): 733–34. http://dx.doi.org/10.1177/1541931213601668.
Full textAbstract:
In shared control, a robot and a human works together to accomplish a task in order to increase the efficiency of tele-operation. To assist the user in shared control, the robot has to predict the intent of the user accurately and quickly, but this may not be possible when the user can not adapt to the delay as the prediction of the robot depends of the inputs of the user. In this work, we propose an algorithm for intent prediction in shared control while providing performance guarantees when the user has a feedback delay. We assess the feasibility of our algorithm on a case study.
8
Nematov, Ikhtiyor, Dimitris Sacharidis, Katja Hose, and Tomer Sagi. "AIDE: Antithetical, Intent-based, and Diverse Example-Based Explanations." Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society 7 (October 16, 2024): 1051–62. http://dx.doi.org/10.1609/aies.v7i1.31702.
Full textAbstract:
For many use-cases, it is often important to explain the prediction of a black-box model by identifying the most influential training data samples. Existing approaches lack customization for user intent and often provide a homogeneous set of explanation samples, failing to reveal the model's reasoning from different angles. In this paper, we propose AIDE, an approach for providing antithetical (i.e., contrastive), intent-based, diverse explanations for opaque and complex models. AIDE distinguishes three types of explainability intents: interpreting a correct, investigating a wrong, and clarifying an ambiguous prediction. For each intent, AIDE selects an appropriate set of influential training samples that support or oppose the prediction either directly or by contrast. To provide a succinct summary, AIDE uses diversity-aware sampling to avoid redundancy and increase coverage of the training data. We demonstrate the effectiveness of AIDE on image and text classification tasks, in three ways: quantitatively, assessing correctness and continuity; qualitatively, comparing anecdotal evidence from AIDE and other example-based approaches; and via a user study, evaluating multiple aspects of AIDE. The results show that AIDE addresses the limitations of existing methods and exhibits desirable traits for an explainability method.
9
Li, Hourun, Yifan Wang, Zhiping Xiao, et al. "DisCo: Graph-Based Disentangled Contrastive Learning for Cold-Start Cross-Domain Recommendation." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 11 (2025): 12049–57. https://doi.org/10.1609/aaai.v39i11.33312.
Full textAbstract:
Recommender systems are widely used in various real-world applications, but they often encounter the persistent challenge of the user cold-start problem. Cross-domain recommendation (CDR), which leverages user interactions from one domain to improve prediction performance in another, has emerged as a promising solution. However, users with similar preferences in the source domain may exhibit different interests in the target domain. Therefore, directly transferring embeddings may introduce irrelevant source-domain collaborative information. In this paper, we propose a novel graph-based disentangled contrastive learning framework to capture fine-grained user intent and filter out irrelevant collaborative information, thereby avoiding negative transfer. Specifically, for each domain, we use a multi-channel graph encoder to capture diverse user intents. We then construct the affinity graph in the embedding space and perform multi-step random walks to capture high-order user similarity relationships. Treating one domain as the target, we propose a disentangled intent-wise contrastive learning approach, guided by user similarity, to refine the bridging of user intents across domains.Extensive experiments on four benchmark CDR datasets demonstrate that DisCo consistently outperforms existing state-of-the-art baselines, thereby validating the effectiveness of both DisCo and its components.
10
Taplin, Tyler, Alexander E. Lyall, and Ashwin P. Dani. "Multiple User Intent Prediction Using Interacting Multiple Model Joint Probabilistic Data Association Filter." IFAC-PapersOnLine 56, no. 2 (2023): 6946–51. http://dx.doi.org/10.1016/j.ifacol.2023.10.515.
Full text
11
Narkar, Anish S., Jan J. Michalak, Candace E. Peacock, and Brendan David-John. "GazeIntent: Adapting Dwell-time Selection in VR Interaction with Real-time Intent Modeling." Proceedings of the ACM on Human-Computer Interaction 8, ETRA (2024): 1–18. http://dx.doi.org/10.1145/3655600.
Full textAbstract:
The use of ML models to predict a user's cognitive state from behavioral data has been studied for various applications which includes predicting the intent to perform selections in VR. We developed a novel technique that uses gaze-based intent models to adapt dwell-time thresholds to aid gaze-only selection. A dataset of users performing selection in arithmetic tasks was used to develop intent prediction models (F1 = 0.94). We developed GazeIntent to adapt selection dwell times based on intent model outputs and conducted an end-user study with returning and new users performing additional tasks with varied selection frequencies. Personalized models for returning users effectively accounted for prior experience and were preferred by 63% of users. Our work provides the field with methods to adapt dwell-based selection to users, account for experience over time, and consider tasks that vary by selection frequency.
12
Shabarriesh,, Arjarapu, M. B. V. Sandeep Reddy, A. V. Rohith Kumar, and DR Sampath A K. "Reduce the Amount of Push Notifications for E-commerce Apps." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 09, no. 01 (2025): 1–9. https://doi.org/10.55041/ijsrem40482.
Full textAbstract:
Push notifications play a critical role in the engagement strategies of e-commerce apps, but excessive or irrelevant notifications often lead to user frustration, app uninstalls, or opt-outs. Traditional notification strategies, which rely on time-based schedules or trigger-based systems, fail to account for the nuances of user behavior and intent. This project proposes an AI-driven solution to optimize the push notification system by minimizing the number of notifications sent while maximizing their relevance and timeliness. The approach leverages user behavior analysis, predictive modeling, and intent recognition through machine learning algorithms. By monitoring and analyzing user interactions, purchase patterns, and engagement metrics, the AI system identifies moments of genuine purchase intent. Notifications are then strategically sent only when they are most likely to align with the user's current needs and interests. KEY WORDS: Push notifications, e-commerce apps, notification fatigue, AI-driven solution, user behavior analysis, predictive modeling, machine learning algorithms, personalized notifications, engagement metrics, purchase intent prediction, notification management, real-time data analysis, intent recognition, behavioral analytics, notification optimization.
13
Wang, Jiayi, Qiwen Zhao, and Yue Xi. "Cross-lingual Search Intent Understanding Framework Based on Multi-modal User Behavior." International Journal of Language Studies (ISSN : 3078 - 2244) 1, no. 2 (2024): 65–73. https://doi.org/10.60087/ijls.v1.n2.007.
Full textAbstract:
This paper proposes a novel cross-lingual search intent understanding framework leveraging multi-modal user behavior analysis. With the increasing complexity of network traffic and the diversity of user behaviors across languages, traditional approaches often struggle to capture and interpret user search intent in multilingual contexts accurately. Our framework integrates multiple behavioral signals, including query patterns, click sequences, and temporal dynamics, through a sophisticated neural tensor network architecture. The system employs a dual-encoder structure with shared parameters to maintain semantic consistency across languages while incorporating a dynamic behavior sequence learning mechanism to capture temporal dependencies. Experimental evaluation was conducted on a large-scale dataset comprising over 6 million user interactions across four language pairs (EN-ZH, EN-ES, EN-FR, EN-DE) collected over six months. The framework significantly improves over baseline methods, demonstrating an average cross-lingual accuracy of 0.923 and behavior prediction precision of 0.891. Ablation studies reveal the critical role of multi-head attention mechanisms and temporal modeling in maintaining system performance. The framework retains real-time processing capabilities with an average latency of 45ms per request under standard load conditions. Our research advances the field of cross-lingual information retrieval by introducing a practical approach to integrating behavioral signals with linguistic features, providing valuable insights for developing more sophisticated multilingual search systems.
14
WU, SHAOFEI. "AN USER INTENTION MINING MODEL BASED ON FRACTAL TIME SERIES PATTERN." Fractals 28, no. 08 (2020): 2040017. http://dx.doi.org/10.1142/s0218348x20400174.
Full textAbstract:
Users use the network more and more frequently, and more and more data is published on the network. Therefore, how to find, organize, and use the useful information behind these massive data through effective means, and analyze user intentions is a huge challenge. There are many time series problems in user intentions. Time series have complex characteristics such as randomness and multi-scale variability. Effectively identifying the inherent laws and objective phenomena contained in time series is the purpose of analyzing and processing time series data. Fractal theory provides a new way to analyze time series, and obtains the characteristics and rules of time series from a new perspective. Therefore, this paper introduces the fractal theory to analyze the time series problem, and proposes an improved G-P algorithm to realize the prediction and mining of user intentions. First, the method of array storage instead of repeated calculations is used to improve the method of saturated correlation dimension. Second, the Hurst exponent of the time series is obtained by the variable scale range analysis method. Finally, a fractal model for predicting user intent in short time series is established using the accumulation and transformation method. The experimental results show that the use of fractal theory can effectively describe the relevant characteristics of time series, the development trend of user intentions can be mined from big data, and the prediction model for short time series can be established to achieve information mining of user intentions.
15
Petersen, Christine M., and Patricia R. DeLucia. "Perception of Intention in Traffic Environments: A Systematic Review." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 66, no. 1 (2022): 953–57. http://dx.doi.org/10.1177/1071181322661396.
Full textAbstract:
To navigate safely in traffic environments, road users must correctly predict another road users’ intentions. Understanding how road users correctly predict the intent of other road users can help create possible countermeasures for collision avoidance. The aim of this paper is to examine what cues road users (drivers, bicyclists, and pedestrians) use to successfully predict other road user’s intentions and to highlight gaps and outline future research directions. A systematic literature search using the PRISMA method was conducted, and twenty-seven articles were included in the review. Overall, the results from these studies suggest that observers use body language, cues exhibited by the road user, and seek eye contact, when making predictions of intent about another road user. Future research should aim to understand how specific cues impact a road user’s decision-making process and what factors (e.g., point of view or eye contact) modulate a road user’s prediction performance.
16
Iyoloma, Collins Iyaminapu. "An Intent Prediction System for Wireless Fidelity (Wi-Fi) Sensor Data Using an Emerging Neural Machine Intelligence." International Journal for Research in Applied Science and Engineering Technology 13, no. 6 (2025): 1743–54. https://doi.org/10.22214/ijraset.2025.72505.
Full textAbstract:
This paper presents a User Intent (UI) mining scheme based on an emerging neural machine intelligence technique called the Neuronal Auditory Machine Intelligence (NeuroAMI) and considering a Wi-Fi sessions dataset containing about 8000 data points for intent prediction. The results of simulations considering graded increase in samples from 50samples to 999samples showed that substantial increases in accuracies are achievable. When compared to the Long Short-Term Memory (LSTM) method, the results showed that the NeuroAMI will outperform the LSTM by a factor of about 2 considering percentage accuracies.
17
Stephen, Rainey. ""A Steadying Hand": Ascribing Speech Acts to Users of Predictive Speech Assistive Technologies." Journal of Law and Medicine 26, no. 1 (2019): 44–53. https://doi.org/10.5281/zenodo.2535459.
Full textAbstract:
Neuroprosthetic speech technologies are in development for patients suffering profound paralysis, such as can result from amyotrophic lateral sclerosis (ALS). These patients would be unable to speak without intervention, but with neurotechnology can be offered the chance to communicate. The nature of the technology introduces a neuroprosthesis that mediates neural activity to generate synthesised speech. How word prediction coheres with speaker intentions requires scrutiny. Some future forms of prostheses, using statistical language models to predict word patterns, could be thought of as participating with communicative intent – not merely channelling it. Concepts relating to vicarious liability, may serve to clarify these issues. This paper is about showing how technology might interact with speaker intent in cases of delegated action, and how it should be seen as participating in the implementation of user ‘instructions’.
18
Sanae, Achsas, and Habib Nfaoui El. "Vertical intent prediction approach based on Doc2vec and convolutional neural networks for improving vertical selection in aggregated search." International Journal of Electrical and Computer Engineering (IJECE) 10, no. 4 (2020): 3869–82. https://doi.org/10.11591/ijece.v10i4.pp3869-3882.
Full textAbstract:
Vertical selection is the task of selecting the most relevant verticals to a given query in order to improve the diversity and quality of web search results. This task requires not only predicting relevant verticals but also these verticals must be those the user expects to be relevant for his particular information need. Most existing works focused on using traditional machine learning techniques to combine multiple types of features for selecting several relevant verticals. Although these techniques are very efficient, handling vertical selection with high accuracy is still a challenging research task. In this paper, we propose an approach for improving vertical selection in order to satisfy the user vertical intent and reduce user’s browsing time and efforts. First, it generates query embeddings vectors using the doc2vec algorithm that preserves syntactic and semantic information within each query. Secondly, this vector will be used as input to a convolutional neural network model for increasing the representation of the query with multiple levels of abstraction including rich semantic information and then creating a global summarization of the query features. We demonstrate the effectiveness of our approach through comprehensive experimentation using various datasets. Our experimental findings show that our system achieves significant accuracy. Further, it realizes accurate predictions on new unseen data.
19
Chen, Jia, Jiaxin Mao, Yiqun Liu, et al. "A Hybrid Framework for Session Context Modeling." ACM Transactions on Information Systems 39, no. 3 (2021): 1–35. http://dx.doi.org/10.1145/3448127.
Full textAbstract:
Understanding user intent is essential for various retrieval tasks. By leveraging contextual information within sessions, e.g., query history and user click behaviors, search systems can capture user intent more accurately and thus perform better. However, most existing systems only consider intra-session contexts and may suffer from the problem of lacking contextual information, because short search sessions account for a large proportion in practical scenarios. We believe that in these scenarios, considering more contexts, e.g., cross-session dependencies, may help alleviate the problem and contribute to better performance. Therefore, we propose a novel Hybrid framework for Session Context Modeling (HSCM), which realizes session-level multi-task learning based on the self-attention mechanism. To alleviate the problem of lacking contextual information within current sessions, HSCM exploits the cross-session contexts by sampling user interactions under similar search intents in the historical sessions and further aggregating them into the local contexts. Besides, application of the self-attention mechanism rather than RNN-based frameworks in modeling session-level sequences also helps (1) better capture interactions within sessions, (2) represent the session contexts in parallelization. Experimental results on two practical search datasets show that HSCM not only outperforms strong baseline solutions such as HiNT, CARS, and BERTserini in document ranking, but also performs significantly better than most existing query suggestion methods. According to the results in an additional experiment, we have also found that HSCM is superior to most ranking models in click prediction.
20
Haile, Tegegne Tesfaye, and Mincheol Kang. "Mobile Augmented Reality in Electronic Commerce: Investigating User Perception and Purchase Intent Amongst Educated Young Adults." Sustainability 12, no. 21 (2020): 9185. http://dx.doi.org/10.3390/su12219185.
Full textAbstract:
Even though the presence and use of mobile augmented reality (MAR) technology has become increasingly popular in the field of marketing and advertising in recent years, it has largely been neglected in the study of consumer behavior research. This paper utilizes a single-group posttest-only quasi-experimental design to investigate how the feature of mobile augmented reality application influences consumers’ attitude and purchasing intention as explained by the dimensions of persuasion (i.e., consumers’ cognitive, affective, and conative dimensions). Structural Equation Modeling (SEM) with SPSS and AMOS is used to analyze the psychometric survey data collected from 179 participants. The results supported the prediction that MAR application’s real-time interactivity and entertainment increase cognition and affection, respectively; while irritation with MAR application decreases affection. The unsupported hypothesis, which predicted a positive relationship between informativeness and cognition, came as a surprise. The overall result of the study demonstrates the positive influence of MAR application in enhancing consumers’ purchasing intention. Finally, implications and future research directions are discussed.
21
Qadeer, Shaik, and Mohammed Yousuf Khan. "Design of a prediction system for anticipating the consumer's purchase intention of durable goods." International Journal of Microsystems and IoT 1, no. 6 (2023): 418–22. https://doi.org/10.5281/zenodo.10406064.
Full textAbstract:
their purchase intent for durables. Amazon was chosen as an e-commerce platform to collect real-time search and review data from the client. In general, Amazon predicts the customer's purchase intent and promotes the goods in a variety of ways on its website. The suggestion approach was developed with the goal of making the program simple and user-friendly in the e-commerce industry, and research in this subject is still ongoing. Amazon's recommendation algorithms, which have been successful since 2003, employ item-based collaborative filtering. We used the Amazon product database for this study and projection, which contains over 1,500 user reviews for various Amazon items, including the Fire TV Stick, Kindle, and more. The dataset contains basic product characteristics, rating, review text, and more for each product. A powerful e-commerce platform was created for customers by developing a prediction model with attribute level decision support. To build the prediction model, the social perception score of brands and the polarity of feedback are calculated using social network mining and sentiment analysis, respectively. In order to forecast the relevant product attributes for each attribute, a suitable regression analysis and appropriate cases were then constructed for each attribute. In order to use the SVM Algorithm to execute and forecast the model more correctly, we incorporated some additional potent factors, such seasonality and polarity.
22
Omotayo, Emmanuel Omoyemi. "Machine learning for predictive AAC: Improving speech and gesture-based communication systems." World Journal of Advanced Research and Reviews 24, no. 1 (2024): 2569–75. https://doi.org/10.5281/zenodo.15063261.
Full textAbstract:
Augmentative and alternative communication (AAC) systems play a crucial role in supporting individuals with severe communication disabilities by providing accessible means of expression and engagement. However, many conventional AAC devices rely on manual input or basic predictive functions, which can limit communication efficiency and responsiveness. The application of machine learning (ML) to AAC offers new opportunities to enhance these systems, enabling them to provide faster, more accurate, and contextually relevant communication assistance. Advances in ML, particularly in predictive text, speech recognition, and gesture interpretation, allow AAC systems to adapt more intuitively to user needs, predicting intent based on usage patterns and multimodal data, such as voice and gestures. Current research highlights the potential of ML to address key gaps in AAC technology by creating more responsive, personalized systems that align with individual user behaviours. This study proposes a novel ML framework designed to integrate these capabilities, promising improvements in communication speed, user autonomy, and accuracy. By addressing the challenges and limitations of traditional AAC devices, this research aims to advance accessible communication solutions that empower users and improve quality of life.
23
Achsas, Sanae, and El Habib Nfaoui. "Vertical intent prediction approach based on Doc2vec and convolutional neural networks for improving vertical selection in aggregated search." International Journal of Electrical and Computer Engineering (IJECE) 10, no. 4 (2020): 3869. http://dx.doi.org/10.11591/ijece.v10i4.pp3869-3882.
Full textAbstract:
Vertical selection is the task of selecting the most relevant verticals to a given query in order to improve the diversity and quality of web search results. This task requires not only predicting relevant verticals but also these verticals must be those the user expects to be relevant for his particular information need. Most existing works focused on using traditional machine learning techniques to combine multiple types of features for selecting several relevant verticals. Although these techniques are very efficient, handling vertical selection with high accuracy is still a challenging research task. In this paper, we propose an approach for improving vertical selection in order to satisfy the user vertical intent and reduce user’s browsing time and efforts. First, it generates query embeddings vectors using the doc2vec algorithm that preserves syntactic and semantic information within each query. Secondly, this vector will be used as input to a convolutional neural network model for increasing the representation of the query with multiple levels of abstraction including rich semantic information and then creating a global summarization of the query features. We demonstrate the effectiveness of our approach through comprehensive experimentation using various datasets. Our experimental findings show that our system achieves significant accuracy. Further, it realizes accurate predictions on new unseen data.
24
Qu, Huiying, Yiying Zhang, Kun Liang, Siwei Li, and Xianxu Huo. "A Knowledge-Graph-Driven Method for Intelligent Decision Making on Power Communication Equipment Faults." Electronics 12, no. 18 (2023): 3939. http://dx.doi.org/10.3390/electronics12183939.
Full textAbstract:
The grid terminal deploys numerous types of communication equipment for the digital construction of the smart grid. Once communication equipment failure occurs, it might jeopardize the safety of the power grid. The massive amount of communication equipment leads to a dramatic increase in fault research and judgment data, making it difficult to locate fault information in equipment maintenance. Therefore, this paper designs a knowledge-graph-driven method for intelligent decision making on power communication equipment faults. The method consists of two parts: power knowledge extraction and user intent multi-feature learning recommendation. The power knowledge extraction model utilizes a multi-layer bidirectional encoder to capture the global features of the sentence and then characterizes the deep local semantics of the sentence through a convolutional pooling layer, which achieves the joint extraction and visual display of the fault entity relations. The user intent multi-feature learning recommendation model uses a graph convolutional neural network to aggregate the higher-order neighborhood information of faulty entities and then the cross-compression matrix to solve the feature interaction degree of the user and graph, which achieves accurate prediction of fault retrieval. The experimental results show that the method is optimal in knowledge extraction compared to classical models such as BERT-CRF, in which the F1 value reaches 81.7%, which can effectively extract fault knowledge. User intent multi-feature learning recommendation works best, with an F1 value of 87%. Compared with the classical models such as CKAN and KGCN, it is improved by 5%~11%, which can effectively solve the problem of insufficient mining of user retrieval intent. This method realizes accurate retrieval and personalized recommendation of fault information of electric power communication equipment.
25
Guo, Long, Lifeng Hua, Rongfei Jia, Fei Fang, Binqiang Zhao, and Bin Cui. "EdgeDIPN." Proceedings of the VLDB Endowment 14, no. 3 (2020): 320–28. http://dx.doi.org/10.14778/3430915.3430922.
Full textAbstract:
With the rapid growth of e-commerce in recent years, e-commerce platforms are becoming a primary place for people to find, compare and ultimately purchase products. To improve online shopping experience for consumers and increase sales for sellers, it is important to understand user intent accurately and be notified of its change timely. In this way, the right information could be offered to the right person at the right time. To achieve this goal, we propose a unified deep intent prediction network, named EdgeDIPN, which is deployed at the edge, i.e., mobile device, and able to monitor multiple user intent with different granularity simultaneously in real-time. We propose to train EdgeDIPN with multi-task learning, by which EdgeDIPN can share representations between different tasks for better performance and saving edge resources in the meantime. In particular, we propose a novel task-specific attention mechanism which enables different tasks to pick out the most relevant features from different data sources. To extract the shared representations more effectively, we utilize two kinds of attention mechanisms, where the multi-level attention mechanism tries to identify the important actions within each data source and the inter-view attention mechanism learns the interactions between different data sources. In the experiments conducted on a large-scale industrial dataset, EdgeDIPN significantly outperforms the baseline solutions. Moreover, EdgeDIPN has been deployed in the operational system of Alibaba. Online A/B testing results in several business scenarios reveal the potential of monitoring user intent in real-time. To the best of our knowledge, EdgeDIPN is the first full-fledged real-time user intent understanding center deployed at the edge and serving hundreds of millions of users in a large-scale e-commerce platform.
26
Chowdhury, Sakib, Md Badsha, Atia Farzana Chowdury, et al. "Machine Learning and Deep Learning Models for Predicting Mental Health Disorders and Performance Analysis through Chatbot Interactions." European Journal of Computer Science and Information Technology 12, no. 9 (2024): 38–60. https://doi.org/10.37745/ejcsit.2013/vol12n93860.
Full textAbstract:
Mental health disorders have recently been prompting increased concern globally and finding new ways of diagnosing and treating them efficiently. Machine learning (ML) and deep learning (DL) enabled chatbots are enormous tool for predicting and supporting mental health. This work aims to carry out an assessment of several AI models for prognostics of mental health disorders based on the comparison of intents, patterns, and responses in a structured chatbot-based dataset. Since it is intent-based, our dataset is best suited to classifying user inputs accurately into different mental health thematic buckets such as anxiety, stress, and proved suicide ideation. To assess the models, we compared basic models such as Multinomial Naïve Bayes, Random Forest and SVM as well as deep learning models including LSTM networks. SVM and LSTM showed promising results among the tested models with the accuracy of 94.6%. LSTM was proved to address the problem of sequential context dependence typical for conversational data. For further improvement in the model’s accuracy, we used ensemble methods whose accuracy came out near like the highest accuracy models, 94.2% accurate. This work is new in the sense that it involves the use of data from an intent-based chatbot, and a comparison of the ML and DL models designed specifically for the prediction of mental health outcomes. Also, it is important to note that we dealt with underrepresented intents, including suicide ideation, using data augmentation and ensemble approach. It fills the gaps in the deployment of AI for mental health by providing recommendations concerning the model’s performance and possible ethical concerns as well as integrating it into conversational assistance. We also found the relevance of an AI chatbot in the delivery of efficient and easily deployable intervention for mental health.
27
Zhang, Xiyuan, Chengxi Li, Dian Yu, Samuel Davidson, and Zhou Yu. "Filling Conversation Ellipsis for Better Social Dialog Understanding." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 05 (2020): 9587–95. http://dx.doi.org/10.1609/aaai.v34i05.6505.
Full textAbstract:
The phenomenon of ellipsis is prevalent in social conversations. Ellipsis increases the difficulty of a series of downstream language understanding tasks, such as dialog act prediction and semantic role labeling. We propose to resolve ellipsis through automatic sentence completion to improve language understanding. However, automatic ellipsis completion can result in output which does not accurately reflect user intent. To address this issue, we propose a method which considers both the original utterance that has ellipsis and the automatically completed utterance in dialog act and semantic role labeling tasks. Specifically, we first complete user utterances to resolve ellipsis using an end-to-end pointer network model. We then train a prediction model using both utterances containing ellipsis and our automatically completed utterances. Finally, we combine the prediction results from these two utterances using a selection model that is guided by expert knowledge. Our approach improves dialog act prediction and semantic role labeling by 1.3% and 2.5% in F1 score respectively in social conversations. We also present an open-domain human-machine conversation dataset with manually completed user utterances and annotated semantic role labeling after manual completion.
28
Li, Qixuan. "Joint Modelling of Slot Filling and Intent Detection in Constrained Resource Scenarios." Frontiers in Computing and Intelligent Systems 5, no. 2 (2023): 111–15. http://dx.doi.org/10.54097/fcis.v5i2.13124.
Full textAbstract:
In the era of pervasive smart devices, natural language understanding (NLU) holds a pivotal role for facilitating intelligent interactions and decision-making. Core to NLU are slot filling and intent recognition, essential tasks for comprehending user input. While joint modelling of these tasks has gained prominence, the challenges of realizing efficient joint models on resource-constrained devices have emerged as significant. These devices possess limited computational capacity and real-time requirements, necessitating lightweight and efficient models. In this study, we explore the design of a resource-efficient joint model for slot filling and intent recognition. Through leveraging BERT, , graph neural networks, and mask mechanisms, our model achieves the dual goals of semantic slot prediction and intent classification. We focus on model design, training, and real-time inference, aiming to contribute to the paradigm of resource-constrained natural language understanding. Our investigation demonstrates the efficacy of our approach, even when working with a reduced dataset, underscoring the model's applicability to real-world scenarios with limited resources.
29
Edwards, Ann L., Michael R. Dawson, Jacqueline S. Hebert, et al. "Application of real-time machine learning to myoelectric prosthesis control: A case series in adaptive switching." Prosthetics and Orthotics International 40, no. 5 (2016): 573–81. http://dx.doi.org/10.1177/0309364615605373.
Full textAbstract:
Background: Myoelectric prostheses currently used by amputees can be difficult to control. Machine learning, and in particular learned predictions about user intent, could help to reduce the time and cognitive load required by amputees while operating their prosthetic device. Objectives: The goal of this study was to compare two switching-based methods of controlling a myoelectric arm: non-adaptive (or conventional) control and adaptive control (involving real-time prediction learning). Study design: Case series study. Methods: We compared non-adaptive and adaptive control in two different experiments. In the first, one amputee and one non-amputee subject controlled a robotic arm to perform a simple task; in the second, three able-bodied subjects controlled a robotic arm to perform a more complex task. For both tasks, we calculated the mean time and total number of switches between robotic arm functions over three trials. Results: Adaptive control significantly decreased the number of switches and total switching time for both tasks compared with the conventional control method. Conclusion: Real-time prediction learning was successfully used to improve the control interface of a myoelectric robotic arm during uninterrupted use by an amputee subject and able-bodied subjects. Clinical relevance Adaptive control using real-time prediction learning has the potential to help decrease both the time and the cognitive load required by amputees in real-world functional situations when using myoelectric prostheses.
30
Severitt, Björn Rene, Nora Castner, and Siegfried Wahl. "Bi-Directional Gaze-Based Communication: A Review." Multimodal Technologies and Interaction 8, no. 12 (2024): 108. https://doi.org/10.3390/mti8120108.
Full textAbstract:
Bi-directional gaze-based communication offers an intuitive and natural way for users to interact with systems. This approach utilizes the user’s gaze not only to communicate intent but also to obtain feedback, which promotes mutual understanding and trust between the user and the system. In this review, we explore the state of the art in gaze-based communication, focusing on both directions: From user to system and from system to user. First, we examine how eye-tracking data is processed and utilized for communication from the user to the system. This includes a range of techniques for gaze-based interaction and the critical role of intent prediction, which enhances the system’s ability to anticipate the user’s needs. Next, we analyze the reverse pathway—how systems provide feedback to users via various channels, highlighting their advantages and limitations. Finally, we discuss the potential integration of these two communication streams, paving the way for more intuitive and efficient gaze-based interaction models, especially in the context of Artificial Intelligence. Our overview emphasizes the future prospects for combining these approaches to create seamless, trust-building communication between users and systems. Ensuring that these systems are designed with a focus on usability and accessibility will be critical to making them effective communication tools for a wide range of users.
31
Beshley, Mykola, Andriy Prislupskiy, and Halyna Beshley. "Quality of service management for an intent-based heterogeneous network using mobile QoE application." Problemi telekomunìkacìj, no. 1(28) (December 22, 2021): 45–64. http://dx.doi.org/10.30837/pt.2021.1.04.
Full textAbstract:
Traditional Service Level Agreement (SLA) based on the quality of service (QoS) management methods are insufficient to ensure quality-related contracts between service providers and users. This article proposes a user-centric method for QoS management in heterogeneous mobile networks. Based on a new QoE metric on a scale of 1 to 5, this method considers the commercial value of electronic services to end-users. With this approach, the configuration and functionality of the network automatically change depending on the requirements of the end-users. The work proposes a conceptual model for constructing an intent-based software-defined heterogeneous network, which effectively manages shared resources and adapts to users’ needs. A prototype of a mobile and operator application for adaptive client-oriented service delivery in a heterogeneous network has been developed, which makes it possible to obtain the ordered QoE based on the feedback between the user and the network operator. Using this approach will allow network operators to provide individualization of service users with a certain level of QoS by analyzing their estimates of QoE (ordered through the developed mobile application). And the use of machine learning algorithms will allow to react to unfavorable combinations of values of quality indicators and prevent the situation when the user is not satisfied with the quality of services received for adaptive prediction of the moment of network reconfiguration. We propose a method for managing the QoS provision in a heterogeneous wireless network using Big Data technology and a mobile QoE application, which considers and analyzes the estimates of the ordered QoE and allows users QoS improvement according to the demand. It is demonstrated that using the proposed method in a heterogeneous wireless network allows reducing the number of dissatisfied users with the quality of service by up to 60% using an experimental study.
32
Wang, Xin, Amin Hosseininasab, Pablo Colunga, Serdar Kadıoğlu, and Willem-Jan Van Hoeve. "Seq2Pat: Sequence-to-Pattern Generation for Constraint-Based Sequential Pattern Mining." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 11 (2022): 12665–71. http://dx.doi.org/10.1609/aaai.v36i11.21542.
Full textAbstract:
Pattern mining is an essential part of knowledge discovery and data analytics. It is a powerful paradigm, especially when combined with constraint reasoning. In this paper, we present Seq2Pat, a constraint-based sequential pattern mining tool with a high-level declarative user interface. The library finds patterns that frequently occur in large sequence databases subject to constraints. We highlight key benefits that are desirable, especially in industrial settings where scalability, explainability, rapid experimentation, reusability, and reproducibility are of great interest. We then showcase an automated feature extraction process powered by Seq2Pat to discover high-level insights and boost downstream machine learning models for customer intent prediction.
33
Oguntola, Olurotimi, and Steven Simske. "Context-Aware Personalization: A Systems Engineering Framework." Information 14, no. 11 (2023): 608. http://dx.doi.org/10.3390/info14110608.
Full textAbstract:
This study proposes a framework for a systems engineering-based approach to context-aware personalization, which is applied to e-commerce through the understanding and modeling of user behavior from their interactions with sales channels and media. The framework is practical and built on systems engineering principles. It combines three conceptual components to produce signals that provide content relevant to the users based on their behavior, thus enhancing their experience. These components are the ‘recognition and knowledge’ of the users and their behavior (persona); the awareness of users’ current contexts; and the comprehension of their situation and projection of their future status (intent prediction). The persona generator is implemented by leveraging an unsupervised machine learning algorithm to assign users into cohorts and learn cohort behavior while preserving their privacy in an ethical framework. The component of the users’ current context is fulfilled as a microservice that adopts novel e-commerce data interpretations. The best result of 97.3% accuracy for the intent prediction component was obtained by tokenizing categorical features with a pre-trained BERT (bidirectional encoder representations from transformers) model and passing these, as the contextual embedding input, to an LSTM (long short-term memory) neural network. Paired cohort-directed prescriptive action is generated from learned behavior as a recommended alternative to users’ shopping steps. The practical implementation of this e-commerce personalization framework is demonstrated in this study through the empirical evaluation of experimental results.
34
Lin, Will Y. "Prototyping a Chatbot for Site Managers Using Building Information Modeling (BIM) and Natural Language Understanding (NLU) Techniques." Sensors 23, no. 6 (2023): 2942. http://dx.doi.org/10.3390/s23062942.
Full textAbstract:
Amidst the domestic labor shortage and worldwide pandemic in recent years, there has been an urgent need for a digital means that allows construction site workers, particularly site managers, to obtain information more efficiently in support of their daily managerial tasks. For workers who move around the site, traditional software applications that rely on a form-based interface and require multiple finger movements such as key hits and clicks can be inconvenient and reduce their willingness to use such applications. Conversational AI, also known as a chatbot, can improve the ease of use and usability of a system by providing an intuitive interface for user input. This study presents a demonstrative Natural Language Understanding (NLU) model and prototypes an AI-based chatbot for site managers to inquire about building component dimensions during their daily routines. Building Information Modeling (BIM) techniques are also applied to implement the answering module of the chatbot. The preliminary testing results show that the chatbot can successfully predict the intents and entities behind the inquiries raised by site managers with satisfactory accuracy for both intent prediction and the answer. These results provide site managers with alternative means to retrieve the information they need.
35
Shahid Anwar, Muhammad, Jing Wang, Sadique Ahmad, Asad Ullah, Wahab Khan, and Zesong Fei. "Evaluating the Factors Affecting QoE of 360-Degree Videos and Cybersickness Levels Predictions in Virtual Reality." Electronics 9, no. 9 (2020): 1530. http://dx.doi.org/10.3390/electronics9091530.
Full textAbstract:
360-degree Virtual Reality (VR) videos have already taken up viewers’ attention by storm. Despite the immense attractiveness and hype, VR conveys a loathsome side effect called “cybersickness” that often creates significant discomfort to the viewers. It is of great importance to evaluate the factors that induce cybersickness symptoms and its deterioration on the end user’s Quality-of-Experience (QoE) when visualizing 360-degree videos in VR. This manuscript’s intent is to subjectively investigate factors of high priority that affect a user’s QoE in terms of perceptual quality, presence, and cybersickness. The content type (fast, medium, and slow), the effect of camera motion (fixed, horizontal, and vertical), and the number of moving targets (none, single, and multiple) in a video can be the factors that may affect the QoE. The significant effect of such factors on end-user QoE under various stalling events (none, single, and multiple) is evaluated in a subjective experiment. The results from subjective experiments show a notable impact of these factors on end-user QoE. Finally, to label the viewing safety concern in VR, we propose a neural network-based QoE prediction method that can predict the degree of cybersickness influenced by 360-degree videos under various stalling events in VR. The performance accuracy of the proposed method is then compared against well-known Machine Learning (ML) algorithms and existing QoE prediction models. The proposed method achieved a 90% prediction accuracy rate and performed well against existing models and other ML methods.
36
Pingfen Liu. "Consumer Behavior Prediction and Market Application Exploration Based on Social Network Data Analysis." Journal of Electrical Systems 20, no. 6s (2024): 806–11. http://dx.doi.org/10.52783/jes.2744.
Full textAbstract:
It examines the junction of consumer behavior prediction and market application exploration using social network data analysis. Using the massive quantity of information available on social media sites, they use complex data mining tools to estimate consumer opinions, preferences, and behaviours. They discover useful insights that inform strategic decision-making processes for enterprises across several industry domains by combining approaches such as predictive modelling, natural language processing, and social network analysis. Results show that social network data analysis can effectively anticipate consumer actions and detect market trends. They employ sentiment analysis to categorize user sentiments regarding products, companies, and marketing campaigns, delivering actionable insights for marketing plan optimization. Furthermore, predictive modelling helps us to estimate purchase intent, segment clients, and spot new trends, allowing businesses to customize their products and improve customer engagement. Additionally, this study emphasizes the significance of addressing ethical concerns and privacy consequences in social network data analysis. Businesses that embrace transparent and responsible data policies can create consumer trust while also mitigating the dangers related to data misuse.
37
He, Jie. "Construction of Internet TV Industry Ecosystem Based on Data Mining Technology." Wireless Communications and Mobile Computing 2022 (March 3, 2022): 1–9. http://dx.doi.org/10.1155/2022/3719372.
Full textAbstract:
While the Internet provides people with convenience, it also comes with security concerns. Users can more easily form groups, distort facts, and contribute to some sensitive topics on the internet. As a result, identifying and analyzing users’ online behaviors are critical. This paper creates a new Internet TV industry ecosystem using DM (data mining) technology. The recommendation system model is established based on data from users’ on-demand viewing behavior across the entire network, and the functions of various system modules and their coordination ability are described in detail. The evolution of users’ online time is examined, providing data to support and explain the prediction analysis of users’ click behavior and the analysis of users’ search intent. The type of web page that the user clicks on can reveal the user’s behavior tendency.
38
Dr., Vandana Kalra, Supreet Kaur Sahi Dr., and Kohli Yajat. "AI-Driven Assistive Technology for Speech Disabilities: Transforming Communication with Natural Language Processing Techniques." INTERNATIONAL JOURNAL OF MULTIDISCIPLINARY RESEARCH AND ANALYSIS 08, no. 03 (2025): 933–39. https://doi.org/10.5281/zenodo.15010148.
Full textAbstract:
Speech disabilities are considered a core barrier to achieving effective communication, independence and social engagement, and therefore assistive devices are needed which are unconventional and fit a myriad of complex user requirements. Many people often have nonstandard speech and assistive devices usually do not cater to their needs hence their ability to use such devices gets compromised. This research suggests that deep learning techniques such as reinforcement learning and model founded approaches like BERT and GPT should be incorporated. Also, the scientists recommend a combination of feedbacks systems with real-time tailoring and individualization. Such integration can qualify individuals to use previously challenging semi-automated systems without restrictions. It provides that view of systems which uses Artificial Intelligence (AI) and generates user’s intent prediction alongside conversion of text to speech that sounds natural to the user. Considering the need for broader and inclusive solutions, the research discusses key issues of how to ensure cost-efficient and easy training of users in order to remove barriers to using assistive technologies. Through novel and sweeping changes, this research aims to further the understanding of how the autonomy and quality of life for people with speech disabilities can be greatly improved.
39
Song, Mofei. "Personalized Image Classification by Semantic Embedding and Active Learning." Entropy 22, no. 11 (2020): 1314. http://dx.doi.org/10.3390/e22111314.
Full textAbstract:
Currently, deep learning has shown state-of-the-art performance in image classification with pre-defined taxonomy. However, in a more real-world scenario, different users usually have different classification intents given an image collection. To satisfactorily personalize the requirement, we propose an interactive image classification system with an offline representation learning stage and an online classification stage. During the offline stage, we learn a deep model to extract the feature with higher flexibility and scalability for different users’ preferences. Instead of training the model only with the inter-class discrimination, we also encode the similarity between the semantic-embedding vectors of the category labels into the model. This makes the extracted feature adapt to multiple taxonomies with different granularities. During the online session, an annotation task iteratively alternates with a high-throughput verification task. When performing the verification task, the users are only required to indicate the incorrect prediction without giving the exact category label. For each iteration, our system chooses the images to be annotated or verified based on interactive efficiency optimization. To provide a high interactive rate, a unified active learning algorithm is used to search the optimal annotation and verification set by minimizing the expected time cost. After interactive annotation and verification, the new classified images are used to train a customized classifier online, which reflects the user-adaptive intent of categorization. The learned classifier is then used for subsequent annotation and verification tasks. Experimental results under several public image datasets show that our method outperforms existing methods.
40
Raghu, Dinesh, Nikhil Gupta, and Mausam. "Unsupervised Learning of KB Queries in Task-Oriented Dialogs." Transactions of the Association for Computational Linguistics 9 (2021): 374–90. http://dx.doi.org/10.1162/tacl_a_00372.
Full textAbstract:
Abstract Task-oriented dialog (TOD) systems often need to formulate knowledge base (KB) queries corresponding to the user intent and use the query results to generate system responses. Existing approaches require dialog datasets to explicitly annotate these KB queries—these annotations can be time consuming, and expensive. In response, we define the novel problems of predicting the KB query and training the dialog agent, without explicit KB query annotation. For query prediction, we propose a reinforcement learning (RL) baseline, which rewards the generation of those queries whose KB results cover the entities mentioned in subsequent dialog. Further analysis reveals that correlation among query attributes in KB can significantly confuse memory augmented policy optimization (MAPO), an existing state of the art RL agent. To address this, we improve the MAPO baseline with simple but important modifications suited to our task. To train the full TOD system for our setting, we propose a pipelined approach: it independently predicts when to make a KB query (query position predictor), then predicts a KB query at the predicted position (query predictor), and uses the results of predicted query in subsequent dialog (next response predictor). Overall, our work proposes first solutions to our novel problem, and our analysis highlights the research challenges in training TOD systems without query annotation.
41
Xia, Xin, Hongzhi Yin, Junliang Yu, Qinyong Wang, Lizhen Cui, and Xiangliang Zhang. "Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 5 (2021): 4503–11. http://dx.doi.org/10.1609/aaai.v35i5.16578.
Full textAbstract:
Session-based recommendation (SBR) focuses on next-item prediction at a certain time point. As user profiles are generally not available in this scenario, capturing the user intent lying in the item transitions plays a pivotal role. Recent graph neural networks (GNNs) based SBR methods regard the item transitions as pairwise relations, which neglect the complex high-order information among items. Hypergraph provides a natural way to capture beyond-pairwise relations, while its potential for SBR has remained unexplored. In this paper, we fill this gap by modeling session-based data as a hypergraph and then propose a dual channel hypergraph convolutional network -- DHCN to improve SBR. Moreover, to enhance hypergraph modeling, we innovatively integrate self-supervised learning into the training of our network by maximizing mutual information between the session representations learned via the two channels in DHCN, serving as an auxiliary task to improve the recommendation task. Extensive experiments on three benchmark datasets demonstrate the superiority of our model over the SOTA methods, and the ablation study validates the effectiveness and rationale of hypergraph modeling and self-supervised task. The implementation of our model is available via https://github.com/xiaxin1998/DHCN.
42
Schuster, W. "Trajectory prediction for future air traffic management – complex manoeuvres and taxiing." Aeronautical Journal 119, no. 1212 (2015): 121–43. http://dx.doi.org/10.1017/s0001924000010307.
Full textAbstract:
AbstractThe future air traffic management (ATM) concept envisaged by the Single European Sky ATM Research – SESAR – and the USA equivalent NextGen, mark a paradigm shift from the current reactive approach of ATM towards holistic strategic collaborative decision making. The core of the future ATM concept relies on common situational awareness over potentially large time-horizons, based upon the user operational intent. This is beyond human capabilities and requires the support of automation tools to predict aircraft state throughout the operation and provide support to optimal decision making long before any potential conflict may arise. This is achieved with trajectory predictors and conflict detectors and resolvers respectively. Numerous tools have been developed, typically geared towards addressing specific airborne applications. However, a comprehensive literature search suggests that none of the tools was designed to predict trajectories throughout the entire operation of an aircraft, i.e. gate-to-gate. Yet, such functionality is relevant in the holistic optimisation of aircraft operations. To address this gap, this paper builds on an existing en route trajectory prediction (TP) model and develops novel techniques to predict aircraft trajectories for the transitions between the ground- and enroute-phases of operation and for the ground-phase, thereby enabling gate-to-gate (or enroute -to-enroute) TP. The model is developed on the basis of Newtonian physics and operational procedures. Real recorded data obtained from a flight data record (FDR) were used to estimate some of the input parameters required by the model. The remaining parameters were taken from the BADA 3.7 model. Performance results using these flight data demonstrate that the proposed TP model has the potential to accurately predict gate-to-gate trajectories and to support future ATM applications such as gate-to-gate synchronisation.
43
Jang, DaeSung, and JongChan Kim. "Generative AI-Driven Multimodal Interaction System Integrating Voice and Motion Recognition." International Journal on Advanced Science, Engineering and Information Technology 15, no. 2 (2025): 617–24. https://doi.org/10.18517/ijaseit.15.2.20945.
Full textAbstract:
This research proposes a two-way interactive algorithm based on voice and motion recognition using generative AI technology to overcome the limitations of existing systems limited to simple command recognition. Current voice and motion recognition technologies are essential in enabling interaction between smart devices and users to enhance user experience. Still, they are mainly limited to recognizing and executing prescribed commands, which do not meet the diverse and complex needs of users. To solve these problems, this research aims to develop a technology that fuses and integrates voice and motion data based on advanced learning and prediction capabilities of generative AI, provides customized data optimized for each user's personality and situation in real-time, and enables more natural and efficient interactions. The main research content includes developing data analysis and processing algorithms that can integrally process multiple input channels, designing generative AI-based models for providing customized data to users, and implementing a two-way interactive system that maintains a natural conversation flow. In particular, the research is intended to combine generative AI language models with computer vision technology to comprehensively analyze user voice and motion data, enabling smart devices to understand and respond to user intent accurately. These technologies can potentially revolutionize the user experience in various areas, including smart homes, healthcare, education, and more. This study's results are expected to significantly contribute to the development of next-generation smart device interaction systems that could improve both efficiency and engagement of interactions.
44
Sigdel, Yubraj, Sujan Shrestha, and Nabin Neupane. "College Chatbot Using RASA." KEC Journal of Science and Engineering 8, no. 1 (2024): 38–43. http://dx.doi.org/10.3126/kjse.v8i1.69263.
Full textAbstract:
The rapid advancement of Artificial Intelligence, Machine Learning, etc., has brought about significant changes in the technological sphere for decades. One such transformative technology is a Chatbot, a Conversational AI capable of addressing users’ queries. These chatbots are tailored to serve various objectives, one of which is to streamline tasks in education through automation. In line with this, a paper titled “College Chatbot Using RASA” has been written, which can effectively respond to questions based on college and other college-related information. The chatbot has been made accessible via an API utilizing the Streamlit framework. The RASA framework, a key open-source technology, has been harnessed to enable the chatbot. RASA plays a vital role in the chatbot's functionality by combining two main components, Rasa Core and Rasa Natural Language Understanding (NLU). Rasa NLU component is used to deduce intent and extract necessary entities from user input, while Rasa Core generates output by constructing a probabilistic model. The model is evaluated by getting a confusion matrix and prediction confidence distribution. The chatbot, upon testing, showcases the best result of 1 for each accuracy, precision, recall, and F1 score.
45
Gadhave, Kiran, Jochen Görtler, Zach Cutler, et al. "Predicting intent behind selections in scatterplot visualizations." Information Visualization 20, no. 4 (2021): 207–28. http://dx.doi.org/10.1177/14738716211038604.
Full textAbstract:
Predicting and capturing an analyst’s intent behind a selection in a data visualization is valuable in two scenarios: First, a successful prediction of a pattern an analyst intended to select can be used to auto-complete a partial selection which, in turn, can improve the correctness of the selection. Second, knowing the intent behind a selection can be used to improve recall and reproducibility. In this paper, we introduce methods to infer analyst’s intents behind selections in data visualizations, such as scatterplots. We describe intents based on patterns in the data, and identify algorithms that can capture these patterns. Upon an interactive selection, we compare the selected items with the results of a large set of computed patterns, and use various ranking approaches to identify the best pattern for an analyst’s selection. We store annotations and the metadata to reconstruct a selection, such as the type of algorithm and its parameterization, in a provenance graph. We present a prototype system that implements these methods for tabular data and scatterplots. Analysts can select a prediction to auto-complete partial selections and to seamlessly log their intents. We discuss implications of our approach for reproducibility and reuse of analysis workflows. We evaluate our approach in a crowd-sourced study, where we show that auto-completing selection improves accuracy, and that we can accurately capture pattern-based intent.
46
Gardner, Marcus, C. Sebastian Mancero Castillo, Samuel Wilson, et al. "A Multimodal Intention Detection Sensor Suite for Shared Autonomy of Upper-Limb Robotic Prostheses." Sensors 20, no. 21 (2020): 6097. http://dx.doi.org/10.3390/s20216097.
Full textAbstract:
Neurorobotic augmentation (e.g., robotic assist) is now in regular use to support individuals suffering from impaired motor functions. A major unresolved challenge, however, is the excessive cognitive load necessary for the human–machine interface (HMI). Grasp control remains one of the most challenging HMI tasks, demanding simultaneous, agile, and precise control of multiple degrees-of-freedom (DoFs) while following a specific timing pattern in the joint and human–robot task spaces. Most commercially available systems use either an indirect mode-switching configuration or a limited sequential control strategy, limiting activation to one DoF at a time. To address this challenge, we introduce a shared autonomy framework centred around a low-cost multi-modal sensor suite fusing: (a) mechanomyography (MMG) to estimate the intended muscle activation, (b) camera-based visual information for integrated autonomous object recognition, and (c) inertial measurement to enhance intention prediction based on the grasping trajectory. The complete system predicts user intent for grasp based on measured dynamical features during natural motions. A total of 84 motion features were extracted from the sensor suite, and tests were conducted on 10 able-bodied and 1 amputee participants for grasping common household objects with a robotic hand. Real-time grasp classification accuracy using visual and motion features obtained 100%, 82.5%, and 88.9% across all participants for detecting and executing grasping actions for a bottle, lid, and box, respectively. The proposed multimodal sensor suite is a novel approach for predicting different grasp strategies and automating task performance using a commercial upper-limb prosthetic device. The system also shows potential to improve the usability of modern neurorobotic systems due to the intuitive control design.
47
Im, Il, Brian Kimball Dunn, Dong Il Lee, Dennis F. Galletta, and Seok-Oh Jeong. "Predicting the intent of sponsored search users: An exploratory user session-level analysis." Decision Support Systems 121 (June 2019): 25–36. http://dx.doi.org/10.1016/j.dss.2019.04.001.
Full text
48
Keshinro, Babatunde, Younho Seong, and Sun Yi. "Deep Learning-based human activity recognition using RGB images in Human-robot collaboration." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 66, no. 1 (2022): 1548–53. http://dx.doi.org/10.1177/1071181322661186.
Full textAbstract:
In human-robot interaction, to ensure safety and effectiveness, robots need to be able to accurately predict human intentions. Hidden Markov Model, Bayesian Filtering, and deep learning methods have been used to predict human intentions. However, few studies have explored deep learning methods to predict variant human intention. Our study aims to evaluate the performance of the human intent recognition inference algorithm, and its impact on the human-robot team for collaborative tasks. Two deep learning algorithms ConvLSTM and LRCN were used to predict human intention. A dataset of 10 participants performing Pick, Throw, Wave, and Carry actions was used. The ConvLSTM method had a prediction accuracy of 74%. The LRCN method had a lower prediction accuracy of 25% compared to ConvLSTM. This result shows that deep learning methods using RGB images can predict human intent with high accuracy. The proposed method is successful in predicting human intents underlying human behavior.
49
Salampasis, Michail, Alkiviadis Katsalis, Theodosios Siomos, et al. "A Flexible Session-Based Recommender System for e-Commerce." Applied Sciences 13, no. 5 (2023): 3347. http://dx.doi.org/10.3390/app13053347.
Full textAbstract:
Research into session-based recommendation systems (SBSR) has attracted a lot of attention, but each study focuses on a specific class of methods. This work examines and evaluates a large range of methods, from simpler statistical co-occurrence methods to embeddings and SotA deep learning methods. This paper analyzes theoretical and practical issues in developing and evaluating methods for SBSR in e-commerce applications, where user profiles and purchase data do not exist. The major tasks of SBRS are reviewed and studied, namely: prediction of next-item, next-basket and purchase intent. For physical retail shopping where no information about the current session exists, we treat the previous baskets purchased by the user as previous sessions drawn from a loyalty system. Mobile application scenarios such as push notifications and calling tune recommendations are also presented. Recommender models using graphs, embeddings and deep learning methods are studied and evaluated in all SBRS tasks using different datasets. Our work contributes a number of very interesting findings. Among all tested models, LSTMs consistently outperform other methods of SBRS in all tasks. They can be applied directly because they do not need significant fine-tuning. Additionally, they naturally model the dynamic browsing that happens in e-commerce web applications. On the other hand, another important finding of our work is that graph-based methods can be a good compromise between effectiveness and efficiency. Another important conclusion is that a “temporal locality principle” holds, implying that more recent behavior is better suited for prediction. In order to evaluate these systems further in realistic environments, several session-based recommender methods were integrated into an e-shop and an A/B testing method was applied. The results of this A/B testing are in line with the experimental results, which represents another important contribution of this paper. Finally, important parameters such as efficiency, application of business rules, re-ranking issues, and the utilization of hybrid methods are also considered and tested, providing comprehensive useful insights into SBRS and facilitating the transferability of this research work to other domains and recommendation scenarios.
50
Ding, Yi. "I hope and I continue." Industrial Management & Data Systems 118, no. 4 (2018): 728–44. http://dx.doi.org/10.1108/imds-06-2017-0261.
Full textAbstract:
PurposeContinued usage of information systems (ISs) is highly critical to a firm’s sustained success. The expectancy-disconfirmation framework has been effective in explaining continuance. However, our own experiences suggest that we may continue using an IS despite low satisfaction. One of the reasons is that the prediction of future user intent in existing models is predominantly retrospective. The purpose of this paper is to address this gap by incorporating forward-looking considerations into the expectancy-disconfirmation model.Design/methodology/approachA questionnaire survey was conducted for two types of mobile applications: photo-sharing and note-taking, and 593 valid responses were collected. The partial least squares method was employed for structural model analysis for each type of applications.FindingsThe well-entrenched expectancy-disconfirmation model was empirically verified. This study further shows that the influence of satisfaction on continuance intention is higher when hope for the future of a mobile application is stronger, and vice versa, after controlling for the impact of past usage behaviour. In addition, hope is found to be induced by appraisals of perceived usefulness and importance of a mobile application.Originality/valueThis study demonstrates that the expectancy-disconfirmation model can be enhanced with considerations of future outcomes. It shows that emotions such as hope are inherent to continuance decisions. Moreover, it goes beyond the valence dimension of emotions and identified specific antecedents of hope based on the appraisal theory.