Open Access

Article

Article ID: 2485

Predict and estimate the current stock prices by using Adaptive Neuro-Fuzzy Inference System

by Ying Bai, Dali Wang

Computing and Artificial Intelligence, Vol.3, No.2, 2025;

To correctly and accurately predict and estimate the stock prices to get the maximum profit is a challenging task, and it is critically important to all financial institutions under the current fluctuation situation. In this study, we try to use a popular AI method, Adaptive Neuro Fuzzy Inference System (ANFIS), to easily and correctly predict and estimate the current and future possible stock prices. Combining with some appropriate pre-data-processing techniques, the current stock prices could be accurately and quickly estimated via those models. A normalization preprocess for training and testing data was used to improve the prediction accuracy, which is our contribution and a plus to this method. In this research, an ANFIS algorithm is designed and built to help decision-makers working in the financial institutions to easily and conveniently predict the current stock prices. The minimum training and checking RMSE values for the ANFIS model can be 0.103842 and 0.0651076. The calculation of accuracy was carried out using the RMSE calculation. The experiments conducted found that the smallest RMSE calculation result was 0.103842 with training data. Other issuers can use this method because it can predict stock prices quite well.

Open Access

Article

Article ID: 2331

Design and implementation of an intelligent waste classification device

by Yung-Hsiang Chen, Chan-Hong Chao

Computing and Artificial Intelligence, Vol.3, No.1, 2025;

This study presents a guideline for an intelligent waste classification device developed using a Raspberry Pi, a camera, and Google’s Teachable Machine (TM) for image recognition. The device is designed to identify waste and classify it into recyclable and non-recyclable categories to improve recycling efficiency. The system is primarily controlled by the Raspberry Pi, with the camera capturing images, which are then processed by TM for image model training to facilitate waste classification. This paper describes the hardware and software components as well as their applications and verifies the effectiveness of the device in practical use. The device is cost-effective, offers good scalability, and is practical for waste classification in households, offices, and public spaces. This study provides valuable insights for the design and future applications of intelligent waste classification systems.

Open Access

Article

Article ID: 1819

Multilevel rules mining association for processing big data using genetic algorithm

by Gebeyehu Belay Gebremeskel, Teshale Wubie Yilma

Computing and Artificial Intelligence, Vol.3, No.1, 2025;

Data mining is a machine learning method and a subset of artificial intelligence that focuses on developing algorithms to enable a computer to learn from data and past experiences within its context. Multilevel association rules mining is a crucial area for discovering interesting relationships between data elements at various levels of abstraction. Many existing algorithms addressing this issue rely on exhaustive search methods such as Apriori and FP-growth. However, these methods incur significant computational costs when applied to big data applications searching for association rules. Therefore, we propose a novel genetic-based method with three key innovations to speed up the search for multilevel association rules and reduce excessive computation. Firstly, we utilize the category tree to describe multilevel application data sets as domain knowledge. Next, we introduce a unique tree-encoding schema based on the category tree to develop the heuristic multilevel association-mining algorithm. Lastly, we present a genetic algorithm based on the tree-encoding schema that greatly decreases the association rule search space. This method is valuable for mining multilevel association rules in big data applications.

Open Access

Article

Article ID: 1884

The potential role of domain vectors in optimizing digital data structure

by Wolfgang Orthuber

Computing and Artificial Intelligence, Vol.3, No.1, 2025;

Each piece of information represents a selection from a set of possibilities. This set is the “domain of information”, which must be uniformly known before any information transport. The components of digital information are also sequences of numbers that represent a selection from a domain of information. So far, however, there is no guarantee that this domain is uniformly known. There is still no infrastructure that makes it possible to publish the domain of digital information in a uniform manner. Therefore, a standardized machine-readable online definition of the binary format and the domain of digital number sequences is proposed. These are uniquely identified worldwide as domain vectors (DVs) by an efficient Internet address of the online definition. As a result, optimized, language-independent digital information can be uniformly defined, identified, efficiently exchanged and compared worldwide for more and more applications.

Open Access

Article

Article ID: 1786

Enhancing data curation with spectral clustering and Shannon entropy: An unsupervised approach within the data washing machine

by Erin Chelsea Hathorn, Ahmed Abu Halimeh

Computing and Artificial Intelligence, Vol.3, No.1, 2025;

In the realm of digital data proliferation, effective data curation is pivotal for extracting meaningful insights. This study explores the integration of spectral clustering and Shannon Entropy within the Data Washing Machine (DWM), a sophisticated tool designed for unsupervised data curation. Spectral clustering, known for its ability to handle complex and non-linearly separable data, is investigated as an alternative clustering method to enhance the DWM’s capabilities. Shannon Entropy is employed as a metric to evaluate and refine the quality of clusters, providing a measure of information content and homogeneity. The research involves rigorous testing of the DWM prototype on diverse datasets, assessing the performance of spectral clustering in conjunction with Shannon Entropy. Results indicate that spectral clustering, when combined with entropy-based evaluation, significantly improves clustering outcomes, particularly in datasets exhibiting varied density and complexity. This study highlights the synergistic role of spectral clustering and Shannon Entropy in advancing unsupervised data curation, offering a more nuanced approach to handling diverse data landscapes.

Open Access

Article

Article ID: 1577

Advancements in nutty quality: Segmentation for enhanced monitoring and determination

by P. Saranya, R. Durga

Computing and Artificial Intelligence, Vol.3, No.1, 2025;

 Segmentation of nut images plays a vital role in computer vision and agricultural applications. Precise segmentation enables the extraction and analysis of essential information about the nuts, supporting quality evaluation, yield estimation, and automated sorting processes. This study explores nuts image segmentation utilizing the cuckoo search algorithm. The cuckoo search algorithm, a nature-inspired optimization technique, is introduced to enhance the segmentation process, potentially optimizing parameters or guiding the segmentation algorithms. Performance evaluation emphasizes metrics such as MSE, IoU, and dice coefficient. CSA (cuckoo search algorithm) demonstrates superior results, showcasing its effectiveness in automated nuts segmentation. This research contributes to the advancement of nut image analysis, providing insights into segmentation methodologies that can enhance automated processes in agriculture and food industry applications. The findings underscore the significance of employing advanced algorithms like CSA for accurate and efficient segmentation of nuts in images.