检索结果-内蒙古大学图书馆

11th International Conference on ICT for Smart Society, ICISS 2024

作者： Oktavia, Tanty Utomo, Kawang Gaol, Ford Lumban Hosoda, Takaaki Bina Nusantara University Binus Graduate Program - Information System Management Information Systems Management Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia Advanced Institute of Industrial Technology Decision Science Department Tokyo Japan

ISBN: (纸本)9798350389654

Since the emergence of Pokémon Go in 2016, the world has been introduced to Augmented Reality (AR) games. Many IT companies have begun developing augmented reality (AR) games due to the great commercial potential in this industry. Certain products may have managed to remain viable in the market, while others were forced to close due to one or two factors. Since the emergence of Pokémon Go, no other game has managed to surpass its unprecedented success. The company responsible for developing Pokémon Go has decided to shut down one of their games due to a lack of consumer interest. The technology of augmented reality (AR) is consistently associated with the concept of immersion. Immersion is a key aspect of the game that allows users to deeply engage and feel fully involved in the experience. This study will employ a quantitative methodology, utilising a questionnaire that will be distributed to and completed by those who have engaged in augmented reality (AR) games. The data will be analysed using Smart PLS to examine the impact of user experience on immersion, which in turn influences intention. After gathering over 200 participants by spreading google form questionnaires and doing data analysis, the findings indicate that only a few aspects of user experience, namely Brand Experience and User Need Experience, have an impact on reasons. Niantic, the developer of Pokémon Go, was unable to replicate their success with a similar augmented reality game called Harry Potter: Wizards Unite. The initial release occurred on June 21, 2019, and the shutdown took place on December 21, 2021. In the beginning, they shown a profound enthusiasm for the game but were unable to sustain it, much as Pokémon Go. According to Niantic CEO John Hanke, the primary reason for the game's shutdown was its immersion. Immersion has a notable impact on User Confirmation, which in turn has a notable impact on Satisfaction, and Satisfaction has a notable impact on Intention. Moreover, there have be

关键词： Plant shutdowns

来源：评论

学校读者我要写书评

暂无评论

TaxDiff: taxonomic-guided diffusion model for protein sequence generation

引用

science China(Information sciences) 2025年第4期68卷 385-386页

作者： Zongying LIN Hao LI Liuzhenghao LV Yu WANG Bin LIN Junwu ZHANG Zijun CHEN Calvin Yu-Chian CHEN Li YUAN Yonghong TIAN School of Electronic and Computer Engineering Peking University AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Peng Cheng Laboratory School of Chemical Biology and Biotechnology Peking University

Protein design aims to generate protein variants with targeted biological functions, which is significant in multiple biological areas, including enzyme reaction catalysis, vaccine design, and fluorescence intensity. Protein design contains two paradigms: sequence generation and structure generation. Recently, EvoDiff [1] proposed a universal designing paradigm, combining structure and sequence generation using the diffusion framework, which improves the protein design efficiency.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Knowledge Graph-Enhanced Semantic Cache for Low-Latency and Cost-Effective Inference in Large Language Models 9

Knowledge Graph-Enhanced Semantic Cache for Low-Latency and ...

引用

9th International Conference on Information Management and Technology, ICIMTech 2024

作者： Dominic, Nicholas Pardamean, Bens Bina Nusantara University Bioinformatics & Data Science Research Center Jakarta11480 Indonesia BINUS Graduate Program - Master of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350390025

In organizational knowledge management, Large Language Model (LLM) caches act as a semantic repository gathered from previous LLM responses. Due to intensive calls from multiple users, LLM may suffer from high inference latency. While there are many prior available approaches to solve this problem, most of them are inherently complex. This paper introduced a Knowledge Graph-enhanced Semantic Cache mechanism as an alternative, lightweight technique to boost retrieval for similar prompts. The latest state-of-the-art open-source LLM, named Google's Gemma-2B-it, was used to generate sample prompts and responses as a draft, while a knowledge graph (KG) was built from Wikipedia sentences. To create embeddings of prompts and KG, all-MiniLM-L6-v2 from SentenceTransformer was used. This new cache system resulted in up to 28% improvement over a standard model. In particular, reinforcement with KG cache embeddings yielded more than 85% semantic cache accuracy. To map the next trajectory of this pilot study, an overview of the extended framework for LLM knowledge management was also presented in this paper. The framework includes the new KG- enhanced cache system equipped with scalable security and fallback mechanisms that can promote green technology through substantial improvements in latency, throughput, and overall LLM costs. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Diagnosing Diabetes Using Soft Voting Ensemble Machine Learning Model 10

Diagnosing Diabetes Using Soft Voting Ensemble Machine Learn...

引用

10th International Conference on ICT for Smart Society, ICISS 2023

作者： Kusuma, Christian Chandra Chandra, Nathalia Utomo, Galang Nurbudi Parimartha, Putu Agus Hidayat, Jessica Anggreainy, Maria Susan Parmonangan, Ivan Halim School of Computer Science Computer Science Department Bina Nusantara University Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program Doctor of Computer Science Computer Science Department Jakarta11530 Indonesia

ISBN: (纸本)9798350339543

Diabetes is a metabolic disorder caused by a dysfunction in insulin secretion which leads to an increase in blood sugar levels in the body. The disease has dangerous risks for those who suffer from it, as it can lead to various complications and even death. Because of the dangerous risks associated with diabetes, early detection of the disease is important. Machine learning can help the process of diagnosing diabetes quickly and accurately because of its ability to learn and process data independently. The goal of this research is to develop a diabetes detection system using ensemble learning with a soft voting classifier. In predicting diabetes, this research uses 14 types of algorithms with the help of the PyCaret library, including extra trees classifier, random forest, light gradient boosting, machine, gradient boosting classifier, decision tree, adaboost classifier, logistic regression, linear discriminant analysis, k-neighbors classifier, quadratic discriminant analysis, naive bayes, support vector machine-linear kernel, dummy classifier, and ridge classifier. From the evaluation process, the five best algorithms are chosen with an accuracy level of 91.3%, 91.3%, 89.5%, 92.2% and 85.3 % These five algorithms are then blended using ensemble learning with a soft voting classifier. The accuracy produced by the soft voting classifier method is higher than using a single classifier, at 97.3%. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Density Based Spatial Clustering of Applications with Noise and Sentence Bert Embedding for Indonesian Utterance Clustering

Density Based Spatial Clustering of Applications with Noise ...

引用

2023 International Conference on computer science, Information Technology and Engineering, ICCoSITE 2023

作者： Hasani, Muhammad Fikri Heryadi, Yaya Arifin, Yulyani Lukas Suparta, Wayan Bina Nusantara University BINUS Graduate Program Computer Science School of Computer Science Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program Computer Science Computer Science Department Jakarta11480 Indonesia Jakarta12930 Indonesia Institut Teknologi Nasional Yogyakarta Faculty of Industrial Technology Department of Electrical Engineering Yogyakarta55281 Indonesia

ISBN: (纸本)9798350320954

Task oriented chatbots are a sub-topic related to chatbots, where chatbots will perform certain tasks with specific goals. One part of creating a task-oriented chatbot is doing intent classification. Intent classification is a task of text classification. As in general text classification, the required dataset requires a label to carry out the classification process. To speed up and help the utterance analysis process, there is already a method, namely clustering, and Density-based clustering is a part of clustering that can determine cluster patterns based on arbitrary data, with DBScan as one of its algorithms. This research used 10000 client utterance data of awhatsapp based e-commerce conversation. SentenceBert also used as a state of art sentence embedding. This research yield silhouette score of 0.327 as the best result from eps of 0.1 and MinPts of 95. However, based on the cluster result, sentences labelled as noise can be further clustered. Text Preprocessing, text augmentation and sentence embedding techniques can be explored to increase the cluster performance. © 2023 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

The Impact of Emotion Recognition Models Towards Believability Factor of Chatbots 15

The Impact of Emotion Recognition Models Towards Believabili...

引用

15th International Congress on Advanced Applied Informatics Winter, IIAI-AAI-Winter 2023

作者： Sutoyo, Rhio Warnars, Harco Leslie Hendric Spits Muhamad Isa, Sani Budiharto, Widodo Bina Nusantara University Binus Graduate Program - Doctor of Computer Science Computer Science Department Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798350383829

Emotionally-aware chatbots are chatbots that are equipped with emotional intelligence. Based on the literature, using emotional elements in chatbots can improve user engagement and believability factors. This study attempts to make a novel contribution by empirically evaluating the impact of emotion recognition models on the believability factor of chatbots. This study examines the impact of the emotions model and avatar on chatbot interactions through three implementations. Thirty-one participants volunteered to evaluate emotionally aware chatbots. The participants evaluated the interaction with the chatbot using the Godspeed Questionnaire Series (GQS). The questionnaire results are utilized to measure the effect of the emotions model on the chatbot's believability factor. The evaluation results of the experiment show that implementing the emotion recognition model on the chatbot increases its believability factors. On average, the believability measures in interaction type B (with an emotion model) are enhanced 1.71 times compared to interaction type A (a basic model). Furthermore, the believability measures in interaction type C (with an emotion model and an avatar) are enhanced 2 times more than in interaction type A (a basic model). The believability factor is also heightened by integrating a chatbot avatar into the interaction system. Using avatars in chatbots increases the believability variables of the system by 1.17 times if compared with not using avatars. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Determining the Main Symptoms of Lung Cancer with Machine Learning Methods 10

Determining the Main Symptoms of Lung Cancer with Machine Le...

引用

10th International Conference on ICT for Smart Society, ICISS 2023

作者： Meylia, Belinda Christina Immanuel, David Gabriel Faustine, Regina Dharma, Surya Anggreany, Maria Susan Parmonangan, Ivan Halim School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University BINUS Graduate Program Doctor of Computer Science Computer Science Department Jakarta11530 Indonesia

ISBN: (纸本)9798350339543

The ability to identify cancer at an early stage is critical to increase the likelihood of effective treatment or stopping the progression of the disease in the body. Lung cancer is one of the most common deadly diseases and quickly kills the patient. The number of deaths caused by lung cancer surpasses those of colon, rectal, breast, and prostate cancers combined. Unfortunately, only two percent of patients with advanced lung cancer survive for five years or more. However, the survival rates are better, with 49 % of the patients surviving for five years or more, if the disease is detected early. On the other hand, in this modern era, machine learning has become one of the most reliable tools in the world for healthcare, as machine learning can learn from the data obtained and process the data that will later be used to help complete certain tasks. Therefore, in this research, machine learning or especially classification algorithms such as K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Random Forest, Logistic Regression, and XGBoost are used to identify three main symptoms that serve as markers for early detection of lung cancer. Determining the three main symptoms is done by combining the results of the feature importance score on each model using the rank-averaging method. The result is an average ranking of each feature based on its combined importance with an accuracy of 93.5 %. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Negation Handling on XLNet Using Dependency Parser for Sentiment Analysis 4

Negation Handling on XLNet Using Dependency Parser for Senti...

引用

4th International Conference on Intelligent Cybernetics Technology and Applications, ICICyTA 2024

作者： Winaya, Ferdinand Girsang, Abba Suganda Binus Graduate Program Bina Nusantara University Jakarta Indonesia School of Computer Science Bina Nusantara University Jakarta Indonesia

ISBN: (纸本)9798331506490

Negation handling is often overlooked in Indonesian sentiment analysis, making it difficult to automatically and accurately determine the polarity of sentences containing negation words. Negation is a challenging issue in natural language processing, as it can drastically alter the meaning of a sentence. For example, common Indonesian negation words such as 'tidak' (no/not), 'belum' (not yet), or 'jangan' (do not) can reverse the sentiment polarity in a text. Previous studies have proposed rule-based approaches, relying on linguistic rules or dependency parse trees to handle negation. However, negation is a complex problem that cannot be effectively addressed by simple rules alone, as they often lack flexibility in handling diverse sentence structures and negation complexities. Therefore, a more dynamic approach is needed, such as combining a dependency parser with an embedding layer, which can map syntactic relationships between words and learn vector representations of negation. This allows the model to flexibly determine the scope of negation words, enabling more accurate sentiment analysis even in complex sentences. This study evaluates the impact of negation handling on a transformer-based model, specifically XLNet, in Indonesian sentiment analysis. Using the proposed method, the model's F1 score increased by 2.13%, from 71.42% to 73.55%, compared to the baseline model. This demonstrates that the proposed negation handling strategy enhances sentiment prediction accuracy, making the model more effective at handling texts with negation. © 2024 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Dynamic Sampling-Based Meta-Learning Using Multilingual Acoustic Data for Under-Resourced Speech Recognition

引用

IEEE Access 2024年 12卷 106070-106083页

作者： Hsieh, I-Ting Wu, Chung-Hsien Zhao, Zhe-Hong National Cheng Kung University Graduate Program of Multimedia Systems and Intelligent Computing Tainan70101 Taiwan National Cheng Kung University Department of Computer Science and Information Engineering Tainan70101 Taiwan

Under-resourced automatic speech recognition (ASR) has become an active field of research and has experienced significant progress during the past decade. However, the performance of under-resourced ASR trained by existing methods is still far inferior to high-resourced ASR for practical applications. In this paper, speech data from languages that share the most phonemes with the under-resourced language are selected as supplementary resources for meta-training based on the Model-Agnostic Meta-Learning (MAML) strategy. Besides supplementary language selection, this paper proposes a dynamic sampling method instead of the original random sampling method to select support and query sets for each task in MAML to improve meta-training performance. In this study, Taiwanese is selected as the under-resourced language, and the speech corpus of five languages, including Mandarin, English, Japanese, Cantonese, and Thai, are chosen as supplementary training data for acoustic model training. The proposed dynamic sampling approach uses phonemes, pronunciation, and speech recognition models as the basis to determine the proportion of each supplementary language to select helpful utterances for MAML. For evaluation, with the selected utterances from each supplementary language for meta-training, we obtained a Word Error Rate of 20.24% and a Syllable Error Rate of 8.35% for Taiwanese ASR, which were better than the baseline model (26.18% and 13.99%) using only the Taiwanese corpus and other methods. © 2013 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

AI Chatbot Technology to Predict Disease: A Systematic Literature Review 4

AI Chatbot Technology to Predict Disease: A Systematic Liter...

引用

4th International Conference on Artificial Intelligence and Data sciences, AiDAS 2023

作者： Velasco, Vincent Dedy Setiawan, Kevin Robert Sanjaya, Renaldo Susan Anggreainy, Maria Kurniawan, Afdhal School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Doctor of Computer Science Computer Science Department Jakarta11530 Indonesia

ISBN: (纸本)9798350318432

Artificial Intelligence (AI) and chatbot technology have emerged as promising solutions to improve healthcare services. AI chatbots can mimic human-like interactions and assist with tasks such as triaging patients and providing medical advice. This review focuses on the use of AI chatbots in predicting diseases, aiming to explore their effectiveness and potential for early intervention and treatment. The purpose of this systematic literature review is to analyze studies related to AI chatbot technology in disease prediction. A systematic literature review was conducted, analyzing a total of 24 selected journals based on predefined inclusion and exclusion criteria. The review protocol involved examining studies published from various years, with a particular emphasis on articles from 2020. The findings indicate that AI chatbots have the potential to play a significant role in predicting diseases and assisting healthcare professionals in making informed decisions. AI chatbot technology shows tremendous potential in disease prediction. By utilizing machine learning algorithms and techniques, chatbots can enhance the accuracy and quickness of disease diagnosis. Continued research and development efforts are necessary to refine AI chatbots' capabilities and revolutionize healthcare delivery for improved patient outcomes and disease management. © 2023 IEEE.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：