Generative AI could be used not only for classification or prediction, but also to generate images, music, etc. based on the input data. Generative AI was abused to generate deepfake and spear-phishing to cause social...
详细信息
In today's competitive business environment, companies aim to retain their existing customers. To achieve that, churn prediction is crucial. Predicting churning customers is not a simple task. It is even more chal...
详细信息
ISBN:
(纸本)9781728189246
In today's competitive business environment, companies aim to retain their existing customers. To achieve that, churn prediction is crucial. Predicting churning customers is not a simple task. It is even more challenging in the fast-food industry since there can be various reasons when a customer stops ordering. To overcome that situation, this study is proposed. The customer data structure is formed sequentially with customers' individual churn periods in different windowing approaches. A long short-term memory model is built with the sequential data to predict the customers' churn stages, and it is compared with the other common classification methods. The proposed model presents promising results and stands out with its personalized prediction among similar studies.
The goal of financial QA is to generate solution equations by solving problems about financial reports. Current financial QA models can suffer from two issues: expression fragmentation and number redundancy. We conduc...
详细信息
ISBN:
(数字)9798331529024
ISBN:
(纸本)9798331529031
The goal of financial QA is to generate solution equations by solving problems about financial reports. Current financial QA models can suffer from two issues: expression fragmentation and number redundancy. We conduct experiments to examine the impact of the two issues. The experimental results show that addressing the expression fragmentation issue in financial QA using EPT improves the execution accuracy by 0.09, and alleviating the number redundancy issue by removing redundant numbers in the input of the FinQANet generator improves the execution accuracy by 0.07.
We compare three publicly available Korean sentiment/emotion word dictionaries with emphasis on a newly accessible multi-label Korean emotion word dictionary developed by Humanities Research Institute, Chung-Ang Unive...
详细信息
We compare three publicly available Korean sentiment/emotion word dictionaries with emphasis on a newly accessible multi-label Korean emotion word dictionary developed by Humanities Research Institute, Chung-Ang University. The three dictionaries are KOSAC sentiment lexicon, KNU Korean sentiment lexicon, and a new multi-label Korean emotion word dictionary with 24 emotions.
This method proposes a deep learning-based approach to forecast dyeing color requirements for recycled polyester fabric to increase dyeing efficiency and decrease redundant re-dyeing. Out of the four models that were ...
详细信息
ISBN:
(数字)9798331529024
ISBN:
(纸本)9798331529031
This method proposes a deep learning-based approach to forecast dyeing color requirements for recycled polyester fabric to increase dyeing efficiency and decrease redundant re-dyeing. Out of the four models that were tested Random Forest Regression proved to be the best performing one because of comparatively better MSE and $\mathrm{R}^{\mathbf{2}}$ score.
The rapid growth of the internet and digital technologies has expanded access to digital content while increasing copyright infringement through illegal content-sharing websites. These platforms cause significant fina...
详细信息
ISBN:
(数字)9798331529024
ISBN:
(纸本)9798331529031
The rapid growth of the internet and digital technologies has expanded access to digital content while increasing copyright infringement through illegal content-sharing websites. These platforms cause significant financial losses to copyright holders and persist despite government monitoring efforts. This study proposes an automated method to analyze piracy site characteristics and classify sites involved in copyright infringement. By addressing the evolving nature of such platforms, the approach enhances detection and contributes to combating online piracy effectively.
smartphones equipped with motion sensors are widely used for data collection in research aimed at the establishment of smart transportation and at, more specifically, automatic road condition assessment. To perform th...
详细信息
ISBN:
(纸本)9781728189246
smartphones equipped with motion sensors are widely used for data collection in research aimed at the establishment of smart transportation and at, more specifically, automatic road condition assessment. To perform the assessment task, machine learning classifier systems are developed to analyze patterns of vibration signals recorded from a driver's smartphone. Obtaining a balanced training dataset required for the classifier system to work properly is, however, a difficult task. The presented study develops an approach based on an Unrolled Generative Adversarial Network (Unrolled GAN) to produce synthetic data for balancing the training dataset. Experiments conducted in the study demonstrated that the approach allows for generating high-quality synthetic data as long as the unrolled GAN are kept controlled to balance the discriminator and generator modules of the networks.
This paper introduces Text-to-Noise Influence Mapping (TNIM), a novel explainability framework for diffusion-based text-to-image models. TNIM combines cross-attention mechanisms with interpretability methods, such as ...
详细信息
ISBN:
(数字)9798331529024
ISBN:
(纸本)9798331529031
This paper introduces Text-to-Noise Influence Mapping (TNIM), a novel explainability framework for diffusion-based text-to-image models. TNIM combines cross-attention mechanisms with interpretability methods, such as advanced Layer-wise Relevance Propagation (LRP) and CAM, to generate heatmaps that reveal how individual text tokens influence the image generation process over multiple timesteps. By mapping the relationship between text conditions and noise removal, TNIM provides fine-grained insights into the diffusion process, enhancing model interpretability. As a position paper, we present the TNIM framework along with an experimental design, including setup and evaluation plans.
With the rapid expansion of data markets, accurately assessing the value of data has become critical to fostering trust and fairness in data transactions. However, the lack of standardized methods for evaluating the w...
详细信息
Social network platforms have made it possible to collect and store large amounts of text data. In the fields of defense, public safety, and security, social text data is used for data analysis research and network mo...
详细信息
ISBN:
(纸本)9781728189246
Social network platforms have made it possible to collect and store large amounts of text data. In the fields of defense, public safety, and security, social text data is used for data analysis research and network model learning. However, the authenticity of the text data causes distortion of the information or degrades the performance of the trained model. To solve this problem, we presented a binary classification model that distinguishes authenticity using a pre-trained language model and conducted an experiment using tweet data. As a result, we showed 81% accuracy and 0.61 Matthews correlation coefficient value.
暂无评论