Intelligent Analysis Research Articles

Construction of Digital Models for Predicting the Specific Electrical Resistivity of a Polymer Composite Using Contemporary Intelligent Data Analysis

Construction of Digital Models for Predicting the Specific Electrical Resistivity of a Polymer Composite Using Contemporary Intelligent Data Analysis

LIMUNet: A Lightweight Neural Network for Human Activity Recognition Using Smartwatches

The rise of mobile communication, low-power chips, and the Internet of Things has made smartwatches increasingly popular. Equipped with inertial measurement units (IMUs), these devices can recognize user activities through artificial intelligence (AI) analysis of sensor data. However, most existing AI-based activity recognition algorithms require significant computational power and storage, making them unsuitable for low-power devices like smartwatches. Additionally, discrepancies between training data and real-world data often hinder model generalization and performance. To address these challenges, we propose LIMUNet and its smaller variant LIMUNet-Tiny—lightweight neural networks designed for human activity recognition on smartwatches. LIMUNet utilizes depthwise separable convolutions and residual blocks to reduce computational complexity and parameter count. It also incorporates a dual attention mechanism specifically tailored to smartwatch sensor data, improving feature extraction without sacrificing efficiency. Experiments on the PAMAP2 and LIMU datasets show that the LIMUNet improves recognition accuracy by 2.9% over leading lightweight models while reducing parameters by 88.3% and computational load by 58.4%. Compared to other state-of-the-art models, LIMUNet achieves a 9.6% increase in accuracy, with a 60% reduction in parameters and a 57.8% reduction in computational cost. LIMUNet-Tiny further reduces parameters by 75% and computational load by 80%, making it even more suitable for resource-constrained devices.

Tacit Knowledge Mapping for Business Intelligence Analysis

The tacit knowledge in a higher institution, especially in university libraries, contains a series of intuition and inspiration that a librarian arises in exploring solutions to the various problems. Thus, limited sources of knowledge or information is a critical factor in the failure to provide accurate information. The main problem of the BI system is to capture tacit knowledge and use tacit knowledge as one of the data sources for data analysis to enhance the analytic results. The unstructured data can define as tacit knowledge in the form of data and information presented in the Knowledge Management System (KMS), and the cognitive business use both structured and unstructured data with highly sophisticated analytical techniques to identify, evaluate, and recommend a business plan of actions. The idea of being able to capture knowledge from different sources can be very beneficial to the BI system. This paper explored the solution to extracting tacit knowledge from librarians in order to enhance the data sources to be used in the BI by exploring the library's academic services, which use much tacit knowledge for answering questions with the requirement of data analysis as online or offline queries.

Academic research contributions from Ibero-American countries to general knowledge, engineering, and computer science up to 2023 and COVID impact

Although commonly, competitive intelligence analysis is applied to companies, where new investments and operation expenditures are considered along with changes in the market, competitive intelligence can be applied to different countries' academic research production, which impacts science, technology and innovation making a difference in their competitiveness. This work shows the academic research production for all areas of knowledge, and also specifically for engineering and computer science, from all the Ibero-American countries, based on the SCOPUS database from 2001 to 2023. The results show that based on the volume of their academic production, for an affordable analysis, the Ibero-American countries can be classified into three groups, considering an order of magnitude difference for each group. The leading group is composed of countries producing between 200,000 and about 2 million documents, the second group of countries producing between 20,000 and 200,000 documents, and the third group of countries producing between 2,000 and 20,000 documents. The COVID pandemic impacted all the countries which showed a decrease in annual production over the last two years. The results also show the priority areas of knowledge that these countries invest in and the main countries that they collaborate with. The behavior of production for engineering and computer science is like that of general production, but there are some specific internal factors for specific countries such as in the case of Brazil, the country in which production fell most dramatically, followed by Spain and Colombia. On the other hand, Peru and Ecuador show a high interest in engineering and computer science. This work offers a high value decision-making tool to leaders in academic research, the principals of research driven institutions and investors from industry in Ibero-America. The academic production is related to the size of the GDP and the percentage of the GDP invested by a country in research development and innovation.

AI in Data Analysis

AI in Data Analysis Abstract: Welcome to the inaugural issue of AI Insights, a groundbreaking journal at the forefront of exploring the symbiotic relationship between artificial intelligence (AI) and data analysis. In this inaugural edition, we embark on a journey to unravel the transformative potential of AI-driven approaches in extracting actionable insights from complex datasets. Through a combination of theoretical discussions, practical applications, and visionary outlooks, this journal aims to chart a new course in the field of data analysis.

Ensuring AI Algorithm Fairness in Healthcare Decision-Making

This paper provides a comprehensive analysis of artificial intelligence (AI) implementation in Ghana's healthcare system, synthesizing findings from recent Ghanaian studies. It examines legal and regulatory frameworks, ethical considerations, bias and fairness, transparency and accountability, interdisciplinary approaches, patient rights and data protection, healthcare access and equity, and implementation and oversight. The analysis reveals both significant opportunities for AI to improve healthcare delivery in Ghana and substantial challenges in ensuring its ethical, equitable, and effective implementation. Key findings highlight the need for AI-specific healthcare regulations, investment in local capacity building, culturally sensitive AI design, robust fairness and accountability mechanisms, and ongoing stakeholder engagement. This paper contributes to the discourse on AI in healthcare in developing countries, offering insights into the unique challenges faced by lower-middle-income countries. It aims to inform evidence-based policymaking and enrich academic understanding of AI implementation in diverse cultural and economic contexts.

Advancing Algorithmic Justice: A Systematic Review of Fair Decision-Making Protocols in Healthcare AI

This paper provides a comprehensive analysis of artificial intelligence (AI) implementation in Ghana’s healthcare system, synthesizing findings from recent Ghanaian studies. It examines legal and regulatory frameworks, ethical considerations, bias and fairness, transparency and accountability, interdisciplinary approaches, patient rights and data protection, healthcare access and equity, and implementation and oversight. The analysis reveals both significant opportunities for AI to improve healthcare delivery in Ghana and substantial challenges in ensuring its ethical, equitable, and effective implementation. Key findings highlight the need for AI-specific healthcare regulations, investment in local capacity building, culturally sensitive AI design, robust fairness and accountability mechanisms, and ongoing stakeholder engagement. This paper contributes to the discourse on AI in healthcare in developing countries, offering insights into the unique challenges faced by lower-middle-income countries. It aims to inform evidence-based policymaking and enrich academic understanding of AI implementation in diverse cultural and economic contexts.

A Multimodal conceptual framework to achieve automated software evolution for context-rich intelligent applications

AbstractWhile AI is extensively transforming Software Engineering (SE) fields, SE is still in need of a framework to consider overall all phases to facilitate Automated Software Evolution (ASEv), particularly for intelligent applications that are context-rich instead of conquering each division independently. Its complexity comes from the intricacy of the intelligent applications, the heterogeneity of the data sources, and the constant changes in the context. This study proposes a conceptual framework for achieving automated software evolution, emphasizing the importance of multimodality learning. A Selective Sequential Scope Model (3 S) model is developed based on the conceptual framework, and it can be used to categorize existing and future research when it covers different SE phases and multimodal learning tasks. This research is a preliminary step toward the blueprint of a higher-level ASEv. The proposed conceptual framework can act as a practical guideline for practitioners to prepare themselves for diving into this area. Although the study is about intelligent applications, the framework and analysis methods may be adapted for other types of software as AI brings more intelligence into their life cycles.

Data Mining Methods in Educational Process Management

The paper addresses the challenge of effectively managing the educational process by leveraging intelligent data analysis of student performance during learning activities. It introduces an approach centered around data clustering, specifically applied to the study of programming disciplines and languages. By utilizing clustering techniques, the paper aims to identify the most challenging topics within a given academic subject, track students’ learning paths, evaluate and enhance teaching methodologies, and create personalized learning plans tailored to individual students’ needs. This approach enables educators to better understand and address the diverse learning requirements of students, ultimately enhancing the overall educational experience.

A Wushu Leg Gesture Recognition Algorithm Based on Random Forest and Bone Feature Extraction (RF-SFE)

Addressing the challenges of complex movement trajectories and rapid action changes in martial arts performances, this study introduces a novel posture recognition algorithm based on Random Forest and Skeletal Feature Extraction (RF-SFE) for martial arts leg movements. Unlike traditional posture recognition methods that struggle with accuracy, RF-SFE aims to provide intelligent analysis of training postures to assist practitioners in efficient training. The algorithm initially employs advanced skeletal feature extraction techniques to identify and articulate the relative positions and movements specific to martial arts. These extracted spatial features enhance the flexibility in modeling the unique dynamics of martial arts. Subsequently, Random Forest classification is utilized to categorize different leg movements, leveraging its strength in handling high-dimensional data and providing robust classification. Comparative experiments on diverse martial arts posture datasets demonstrate a significant improvement in recognition rates over baseline methods. This validates the effectiveness of the RF-SFE method in recognizing martial arts postures, offering scientific guidance for practitioners’ training regimens.

SYSAI for System Health Management - a Statistical Framework for the Analysis of Diagnosis Systems

On-board failure diagnosis and health management systems (HMS) are crucial for the operation of complex autonomous aerospace systems. False alarms (false positives, FPs) or false negatives (FNs) can lead to lower system performance or even loss of mission or the autonomous vehicle. Therefore, a careful verification and validation (V&V) is important. Due to the high dimensionality of the system’s state space, however, exhaustive testing of the HMS is usually not possible. In this paper, we present how our SYSAI (System Analysis for Systems with AI components) framework can support intelligent analysis and testing of HMS on the system level. SYSAI’s capabilities to efficiently explore high-dimensional state and parameter spaces and to identify diagnosability regions and their boundaries, makes a comprehensive analysis of the diagnosis system possible and can provide feedback to the designer. We will illustrate our approach using the ADAPT (Advanced Diagnostics and Prognostics Testbed) redundant power storage and distribution system.

Microfluidics for foodborne bacteria analysis: Moving toward multiple technologies integration.

Food security related to bacterial pathogens has seriously threatened human life and caused public health problems. Most of the reported methods are targeted at known major pathogens commonly found in food samples, but to some extent, they have the disadvantage of lacking simplicity, speed, high throughput, and high sensitivity. Microfluidics has become a promising tool for foodborne bacteria analysis and addresses the above limitations. In this perspective, we briefly discussed the ongoing research and development in this field. We outline the major types of microfluidics, the strategies of target biorecognition, and signal amplification technologies in the microfluidic system for the foodborne bacteria analysis. We also proposed the future directions of microfluidics for foodborne bacterial analysis, which aims to integrate multiple technologies toward intelligent analysis with high selectivity and sensitivity for unknown samples, multiple bacterial detection, and simultaneous detection of multiple food pollutants.

A bibliometric analysis of artificial intelligence in L2 teaching and applied linguistics between 1995 and 2022 – ADDENDUM

A bibliometric analysis of artificial intelligence in L2 teaching and applied linguistics between 1995 and 2022 – ADDENDUM

A Unified Model for Chinese Cyber Threat Intelligence Flat Entity and Nested Entity Recognition

In recent years, as cybersecurity threats have become increasingly severe and cyberattacks have occurred frequently, higher requirements have been put forward for cybersecurity protection. Therefore, the Named Entity Recognition (NER) technique, which is the cornerstone of Cyber Threat Intelligence (CTI) analysis, is particularly important. However, most existing NER studies are limited to recognizing single-layer flat entities, ignoring the possible nested entities in CTI. On the other hand, most of the existing studies focus on English CTIs, and the existing models performed poorly in a limited number of Chinese CTI studies. Given the above challenges, we propose in this paper a novel unified model, RBTG, which aims to identify flat and nested entities in Chinese CTI effectively. To overcome the difficult boundary recognition problem and the direction-dependent and distance-dependent properties in Chinese CTI NER, we use Global Pointer as the decoder and TENER as the encoder layer, respectively. Specifically, the Global Pointer layer solves the problem of the insensitivity of general NER methods to entity boundaries by utilizing the relative position information and the multiplicative attention mechanism. The TENER layer adapts to the Chinese CTI NER task by introducing an attention mechanism with direction awareness and distance awareness. Meanwhile, to cope with the complex feature capture of hierarchical structure and dependencies among Chinese CTI nested entities, the TENER layer solves the problem by following the structure of multiple self-attention layers and feed-forward network layers superimposed on each other in the Transformer. In addition, to fill the gap in the Chinese CTI nested entity dataset, we further apply the Large Language Modeling (LLM) technique and domain knowledge to construct a high-quality Chinese CTI nested entity dataset, CDTinee, which consists of six entity types selected from STIX, including nearly 4000 entity types extracted from more than 3000 threatening sentences. In the experimental session, we conduct extensive experiments on multiple datasets, and the results show that the proposed model RBTG outperforms the baseline model in both flat NER and nested NER.

Common laboratory results-based artificial intelligence analysis achieves accurate classification of plasma cell dyscrasias.

Plasma cell dyscrasias encompass a diverse set of disorders, where early and precise diagnosis is essential for optimizing patient outcomes. Despite advancements, current diagnostic methodologies remain underutilized in applying artificial intelligence (AI) to routine laboratory data. This study seeks to construct an AI-driven model leveraging standard laboratory parameters to enhance diagnostic accuracy and classification efficiency in plasma cell dyscrasias. Data from 1,188 participants (609 with plasma cell dyscrasias and 579 controls) collected between 2018 and 2023 were analyzed. Initial variable selection employed Kruskal-Wallis and Wilcoxon tests, followed by dimensionality reduction and variable prioritization using the Shapley Additive Explanations (SHAP) approach. Nine pivotal variables were identified, including hemoglobin (HGB), serum creatinine, and β2-microglobulin. Utilizing these, four machine learning models (gradient boosting decision tree (GBDT), support vector machine (SVM), deep neural network (DNN), and decision tree (DT) were developed and evaluated, with performance metrics such as accuracy, recall, and area under the curve (AUC) assessed through 5-fold cross-validation. A subtype classification model was also developed, analyzing data from 380 cases to classify disorders such as multiple myeloma (MM) and monoclonal gammopathy of undetermined significance (MGUS). 1. Variable selection: The SHAP method pinpointed nine critical variables, including hemoglobin (HGB), serum creatinine, erythrocyte sedimentation rate (ESR), and β2-microglobulin. 2. Diagnostic model performance: The GBDT model exhibited superior diagnostic performance for plasma cell dyscrasias, achieving 93.5% accuracy, 98.1% recall, and an AUC of 0.987. External validation reinforced its robustness, with 100% accuracy and an F1 score of 98.5%. 3. Subtype Classification: The DNN model excelled in classifying multiple myeloma, MGUS, and light-chain myeloma, demonstrating sensitivity and specificity above 90% across all subtypes. AI models based on routine laboratory results significantly enhance the precision of diagnosing and classifying plasma cell dyscrasias, presenting a promising avenue for early detection and individualized treatment strategies.

Critical Discourse Analysis of Artificial Intelligence in Gates' Social Media Content

Critical Discourse Analysis of Artificial Intelligence in Gates' Social Media Content

INTELLIGENCE GATHERING AND ITS CONTRIBUTION TO NIGERIA'S NATIONAL SECURITY: A CRITICAL ASSESSMENT

The Nigerian intelligence sector faces institutional limitations that hinder the successful implementation of intelligence collecting, which is widely acknowledged as a crucial tool in tackling these issues. This paper provides a thorough evaluation of the function of intelligence gathering within Nigeria's national security framework, analysing its effectiveness in dealing with current security challenges. This study seeks to offer a thorough examination of the intelligence cycle in the Nigerian setting, including the gathering, analysis, and use of intelligence in national security strategy. The research used a mixed-methods methodology, combining quantitative data obtained from a questionnaire with qualitative insights obtained from an empirical literature analysis. The Network Theory (TNT) functions as the conceptual framework, providing a perspective to examine the intricate connections and transmission of information within the intelligence network. Statistical analysis is conducted on the questionnaire results using descriptive and inferential methods, while the findings of the literature review are consolidated to offer context and depth. The study results highlight a significant dependence on Human Intelligence (HUMINT) and source intelligence (OSINT) in Nigeria, with a lack of implementation of Geospatial Intelligence (GEOINT) and a disregard for Measurement and Signature Intelligence (MASINT). Furthermore, the investigation exposes inadequate levels of trust and collaboration between intelligence agencies and other security organizations. The major obstacles mentioned are insufficient financial resources, insufficient training and knowledge, technical constraints, competition among different agencies, and legal and bureaucratic restrictions. The research findings indicate that although intelligence gathering is of utmost importance for Nigeria's national security, its efficacy is hindered by structural and operational obstacles. personnel growth and comprehensive strategy to improve intelligence capabilities, which involves bolstering inter- agency collaboration, allocating resources to technical progress and skilled personnel growth, and creating a strong legal and ethical structure.

Hyper attack graph: Constructing a hypergraph for cyber threat intelligence analysis

Cybersecurity experts are actively exploring and implementing automated technologies to extract and present attack information from Cyber Threat Intelligence. However, there are multiple relations among security entities within Cyber Threat Intelligence, a feature that existing technologies often overlook. Additionally, integrating external security knowledge into cyber threat intelligence intuitively during analysis and presentation poses challenges. We propose the Hyper Attack Graph (HAG) framework, the first work to apply hypergraph data structures in the analysis of cyber threat intelligence. Our approach uses a joint extraction model that incorporates a multi-head selection mechanism, effectively addressing the extraction of multiple relations among security entities. We use hypergraph to display tactics and techniques in cyber threat intelligence. Our evaluation of the HAG framework on 685 real-world cyber threat intelligence reports shows an increase in the F1 score for security entity extraction by 11.12% and for relation extraction by 6.71% over existing efforts. Furthermore, HAG’s ability to visually represent external security knowledge on hypergraphs demonstrates its potential as a valuable tool in cybersecurity analysis.

DeepSecure: A computational design science approach for interpretable threat hunting in cybersecurity decision making

Businesses and industries are placing a greater emphasis on information systems for cybersecurity decision-making due to the rising cybersecurity threat landscape and the critical need to protect their digital assets. Threat hunting provides a data-driven and proactive approach to cybersecurity, enabling organizations to efficiently detect, analyze, and respond to cyber threats in real-time. Despite playing a crucial role, these systems face several obstacles, including the manual analysis of technical threat intelligence, the non-Gaussian nature of real-world data, the high rate of false positives produced during threat hunting, and the lack of interpretation and justification for these complex models. This article adopts the computational design science paradigm to develop a novel IT artifact for threat-hunting named DeepSecure. First, to automatically extract latent patterns from multivariate time series datasets, we propose a dynamic vector quantized variational autoencoder technique. Second, a multiscale hierarchical attention bi-directional gated recurrent unit-based threat-hunting mechanism is designed. Finally, we provide the visualization of attention scores to aid in model interpretation. We evaluate the DeepSecure against state-of-the-art benchmarks on two publicly available datasets, namely, ToN-IoT and CSE-CIC-IDS2018. The experimental evaluation proves that our model can efficiently identify threat types. Beyond demonstrating practical utility, the proposed framework can help address the lack of interpretation and justification for complex models in cyber threat detection and will allow organizations to respond to potential security incidents quickly.

UNet-like transformer for 1D soil stratification using cone penetration test and borehole data

Subsurface stratification is crucial for the construction safety of underground projects. The one-dimensional (1D) soil stratification aims at identifying segmentation points that separate soil strata. Current engineering practice mainly requires human judgement, which is time-consuming, labour-intensive, and heavily relies on domain expertise. Other probabilistic methods, such as Bayesian approaches, usually involve complex expressions. With the advent of artificial intelligence, deep learning has emerged as a powerful tool in various domains. The UNet, as a typical convolutional neural network, has been extensively utilized for its superior performance in segmentation tasks, but struggles to capture global and long-range semantic information due to the locality of convolution operations. To realize intelligent and automatic 1D soil stratification, this paper introduces a UNet-like Transformer (ULTra) that integrates multiple data sources, including cone penetration test and borehole data, to incorporate prior knowledge. The architecture features a multi-level Transformer with shifted windows in both the encoder and decoder to extract context features and restore spatial resolution, respectively. Experimental results demonstrate that the ULTra outperforms other UNet variants, particularly in detecting minor textures and local details, underscoring the benefits of integrating Transformers into a standard UNet. Case studies indicate that compared with probabilistic methods, the ULTra enables automatic 1D soil stratification using original exploration data with less human intervention, which is fast, effective, and could be continuously improved through interaction with human knowledge, thus streamlining the intelligent data analysis.