Computational Intelligence Research Articles

Energy Efficiency Evaluation of Artificial Intelligence Algorithms

This article advances the discourse on sustainable and energy-efficient software by examining the performance and energy efficiency of intelligent algorithms within the framework of green and sustainable computing. Building on previous research, it explores the theoretical implications of Bremermann’s limit on efforts to enhance computer performance through more extensive methods. The study presents an empirical investigation into heuristic methods for search and optimisation, demonstrating the energy efficiency of various algorithms in both simple and complex tasks. It also identifies key factors influencing the energy consumption of algorithms and their potential impact on computational processes. Furthermore, the article discusses cognitive concepts and their interplay with computational intelligence, highlighting the role of cognition in the evolution of intelligent algorithms. The conclusion offers insights into the future directions of research in this area, emphasising the need for continued exploration of energy-efficient computing methodologies.

Survey on Unmanned Aerial Vehicle Communications for 6G

Although the application of the fifth-Generation (5G) mobile communication has brought tremendous innovations to the daily life of human beings, e.g., autonomous vehicles and internet of everything, the upcoming huger data requirement leads to the emergence of the sixth-Generation (6G) mobile communication. Compared to 5G, the transmission rate, time delay, and wireless coverage need to be improved significantly. Thus, in this paper the applications of Unmanned Aerial Vehicles (UAVs) to the ubiquitous, intelligent and coupling 6G network are surveyed. First, the utilization of UAVs in the framework of space-air-ground-sea integrated network is demonstrated, and the roles and functions of UAVs in different scenarios are emphasized, e.g., the swarm base stations, the deployment for holographic projection, the long-distance relaying and the data collection. Then, the potential 6G key techniques of terahertz, ultra-massive multiple-input and multiple-output, endogenous artificial intelligence, Intelligent Reflecting Surface (IRS), intelligent edge computing, blockchain and integrated sensing and communication for UAV communications are investigated. Finally, the future challenges of UAV communications for 6G, including the limited duration, integration of networks, compatibility of IRS, development of THz communications, and user security are discussed.

Research on the Path of Promoting Regional Financial Balance under the Background of the Digital Economy

The purpose of this paper is to explore the effective path to promote the balanced development of regional financial resources in the context of the digital economy. With the rapid development and wide application of digital technology, the digital economy has become a new engine to promote economic growth, but at the same time, it has also exacerbated the imbalance in the distribution of financial resources among regions. By analyzing the profound impact of the digital economy on the regional economic landscape, the study proposes strategies to optimize resource allocation, promote industrial upgrading, and broaden financing channels by using advanced technologies such as big data, cloud computing, and artificial intelligence, aiming at narrowing the gap in regional financial resources and achieving more balanced development. At the same time, the importance of policy guidance, regional cooperation, and talent cultivation is emphasized to provide theoretical support and practical paths for constructing a new pattern of balanced development of regional financial resources in the era of the digital economy.

Legal implications for clinicians in cybersecurity incidents: A review.

Cybersecurity incidents in healthcare present significant legal implications for clinicians, necessitating careful consideration of technological advancements and regulatory frameworks. This literature examines the healthcare cybersecurity landscape, emphasizing clinicians' challenges, and legal responsibilities. It explores the impact of advanced technologies such as artificial intelligence and quantum computing, highlighting the potential benefits and risks, including biases and ethical dilemmas. The review addresses international regulatory differences, offering a comparative analysis of how various countries handle cybersecurity incidents. This analysis provides insights into best practices and identifies areas for improvement. Practical recommendations are provided, tailored to different healthcare settings, including large hospitals and small clinics, to enhance cybersecurity preparedness. Case studies illustrate real-world scenarios, offering practical guidance for clinicians in managing cybersecurity challenges. The review also identifies critical gaps in the literature, particularly concerning artificial intelligence ethics and international regulatory frameworks, suggesting specific areas for future research. These findings underscore the need for robust cybersecurity policies, comprehensive training for healthcare professionals, and a nuanced understanding of the legal landscape. This review informs policymakers, clinicians, and researchers about the evolving nature of cybersecurity challenges in healthcare, addressing key concerns raised by reviewers and contributing to a comprehensive understanding of the field.

Triangular Fuzzy Cognitive Maps Method for Modelling Interrelation between Causal and Trigger Factors Towards Students' Mathematics Problem-Solving Ability

The purpose of this study is to model the interrelation between causal and trigger factors towards students' mathematics problem-solving ability by using the triangular fuzzy cognitive maps (TrFCM) method. Selection weaknesses and limitations in the method of relational analysis cause the interrelation and influence between variables not to be visualised and do not reveal the characteristics of the actual interaction. As a result, this study demonstrates TrFCM as a more effective way of analysing the relationship between variables based on the complexity that happens in analysing causal factors and triggers for students' problem-solving abilities in mathematics. The results of the influential relations map (IRM) demonstrate that emotion and metacognition are the triggers for problem-solving ability. While executive function is the main cause of success in completing mathematics problems, it is also influenced by additional factors such as motivation, attention, and working memory. These causal and triggering factors also mobilise parts of students' cognitive and behavioural performance to improve the process of solving mathematics problems. Based on the outcomes of this study, computational intelligence methods like fuzzy systems give useful procedures for analysing data from expert surveys. The TrFCM method offers a more accurate relational analysis procedure in modelling interrelation between human factors.

A novel approach for APT attack detection based on an advanced computing

To enhance the effectiveness of the Advanced Persistent Threat (APT) detection process, this research proposes a new approach to build and analyze the behavior profiles of APT attacks in network traffic. To achieve this goal, this study carries out two main objectives, including (i) building the behavior profile of APT IP in network traffic using a new intelligent computation method; (ii) analyzing and evaluating the behavior profile of APT IP based on a deep graph network. Specifically, to build the behavior profile of APT IP, this article describes using a combination of two different data mining methods: Bidirectional Long Short-Term Memory (Bi) and Attention (A). Based on the obtained behavior profile, the Dynamic Graph Convolutional Neural Network (DGCNN) is proposed to extract the characteristics of APT IP and classify them. With the flexible combination of different components in the model, the important information and behavior of APT attacks are demonstrated, not only enhancing the accuracy of detecting attack campaigns but also reducing false predictions. The experimental results in the paper show that the method proposed in this study has brought better results than other approaches on all measurements. In particular, the accuracy of APT attack prediction results (Precision) reached from 84 to 91%, higher than other studies of over 7%. These experimental results have proven that the proposed BiADG model for detecting APT attacks in this study is proper and reasonable. In addition, those experimental results have not only proven the effectiveness and superiority of the proposed method in detecting APT attacks but have also opened up a new approach for other cyber-attack detections such as distributed denial of service, botnets, malware, phishing, etc.

Reconfigurable Five-In-One Carbon Nanotube Optoelectronic Transistor for Intelligent Computing and Communication.

Advances in artificial general intelligence (AGI) necessitate the integration of diverse functionalities to address complex tasks. Carbon nanotubes (CNTs), with their unique physical properties, have broad applications in emerging research fields, providing a foundation for next-generation devices that could overcome the limits of Moore's Law. This work demonstrates a novel intelligent device that integrates five functions─sensors, memory, neuromorphic computing, logic, and communication─using CNT field-effect transistors (CNFETs) compatible with CMOS processes. Through passivation and annealing techniques, we have significantly enhanced the optoelectronic performance of CNFETs, leading to the development of multifunctional optoelectronic synaptic transistors. These optimized CNFETs enable dual-mode weight-tunable synaptic functions, including long-term plasticity and multilevel storage. Additionally, a CNT-based neural network has achieved high recognition accuracy on the MNIST data set, showcasing the potential of in-memory computing. This research also innovates by integrating logic functions with optoelectronic communication capabilities, paving the way for next-generation intelligent computing and communication integrated systems.

A generative-AI-based design methodology for car frontal forms design

With the advancement of artificial intelligence, big data, and cloud computing, numerous generative AI applications have surfaced. In contrast to conventional generative design and computer-aided design tools, these applications significantly enhance design productivity. However, there are currently few design methodologies based on generative AIs in the academic community to improve the efficiency of industrial designers and optimize the design process. This study introduces a creative and practical methodology for designing car frontal forms based on generative AIs. In this methodology, imagery adjectives describing car frontal forms are generated by sending valid prompts to the text-generative AI application GPT-4.0. Then input typical imagery adjectives into the image-generative AI Midjourney successively as prompts to generate many car frontal forms that align with the typical imagery adjectives, forming a reference form database. Subsequently, a base form is selected, and target imageries are defined. Simultaneously, forms from the reference form database, conforming to the target imageries, are chosen as the reference forms. The main form elements of the base and reference forms are then delineated using cubic Bézier curves. Finally, a form curve blending algorithm is applied to obtain a set of alternatives, and the image-generative AI application Vega AI is utilized to convert the alternatives into three-dimensional renderings. FAHP-based expert evaluation and consumer perceptual evaluation are employed to validate the alternatives. Results indicate that the alternatives effectively capture the imageries of the reference forms. The proposed generative-AI-based design methodology enhances the efficiency of industrial designers, thereby minimizing human and material costs in product development. Additionally, this study presents a design case using various generative AIs to inspire designers to re-examine the traditional design process.

Zero trust implementation in the emerging technologies era: a survey

This paper presents a comprehensive analysis of the shift from the traditional perimeter model of security to the Zero Trust (ZT) framework, emphasizing the key points in the transition and the practical application of ZT. It outlines the differences between ZT policies and legacy security policies, along with the significant events that have impacted the evolution of ZT. Additionally, the paper explores the potential impacts of emerging technologies, such as Artificial Intelligence and quantum computing, on the policy and implementation of ZT. The study thoroughly examines how Artificial Intelligence can enhance ZT by utilizing Machine Learning algorithms to analyze patterns, detect anomalies, and predict threats, thereby improving real-time decision-making processes. Furthermore, the paper demonstrates how a chaos theory-based approach, in conjunction with other technologies such as eXtended Detection and Response, can effectively mitigate cyberattacks. As quantum computing presents new challenges to ZT and cybersecurity as a whole, the paper delves into the intricacies of ZT migration, automation, and orchestration, addressing the complexities associated with these aspects. Finally, the paper provides a best practice approach for the seamless implementation of ZT in organizations, laying out the proposed guidelines to facilitate organizations in their transition towards a more secure ZT model. The study aims to support organizations in successfully implementing ZT and enhancing their cybersecurity measures.

Turing tests in chess: An experiment revealing the role of human subjectivity

With the growing capabilities of AI, technology is increasingly able to match or even surpass human performance. In the current study, focused on the game of chess, we investigated whether chess players could distinguish whether they were playing against a human or a computer, and how they achieved this. A total of 24 chess players each played eight 5 + 0 Blitz games from different starting positions. They played against (1) a human, (2) Maia, a neural network-based chess engine trained to play in a human-like manner, (3) Stockfish 16, the best chess engine available, downgraded to play at a lower level, and (4) Stockfish 16 at its maximal level. The opponent’s move time was fixed at 10 s. During the game, participants verbalized their thoughts, and after each game, they indicated by means of a questionnaire whether they thought they had played against a human or a machine and if there were particular moves that revealed the nature of the opponent. The results showed that Stockfish at the highest level was usually correctly identified as an engine, while Maia was often incorrectly identified as a human. The moves of the downgraded Stockfish were relatively often labeled as ‘strange’ by the participants. In conclusion, the Turing test, as applied here in a domain where computers can perform superhumanly, is essentially a test of whether the chess computer can devise suboptimal moves that correspond to human moves, and not necessarily a test of computer intelligence.

Bendable non-silicon RISC-V microprocessor.

Semiconductors have already had a very profound effect on society, accelerating scientific research and driving greater connectivity. Future semiconductor hardware will open up new possibilities in quantum computing, artificial intelligence and edge computing, for applications such as cybersecurity and personalized healthcare. By nature of its ethos, open hardware provides opportunities for even greater collaboration and innovations across education, academic research and industry. Here we present Flex-RV, a 32-bit microprocessor based on an open RISC-V (ref. 1) instruction set fabricated with indium gallium zinc oxide thin-film transistors2 on a flexible polyimide substrate, enabling an ultralow-cost bendable microprocessor. Flex-RV also integrates a programmable machine learning (ML) hardware accelerator inside the microprocessor and demonstrates new instructions to extend the RISC-V instruction set to run ML workloads. It is implemented, fabricated and demonstrated to operate at 60 kHz consuming less than 6 mW power. Its functionality when assembled onto a flexible printed circuit board is validated while executing programs under flat and tight bending conditions, achieving no worse than 4.3% performance variation on average. Flex-RV pioneers an era of sub-dollar open standard non-silicon 32-bit microprocessors and will democratize access to computing and unlock emerging applications in wearables, healthcare devices and smart packaging.

Energy-aware bio-inspired spiking reinforcement learning system architecture for real-time autonomous edge applications.

Mobile, low-cost, and energy-aware operation of Artificial Intelligence (AI) computations in smart circuits and autonomous robots will play an important role in the next industrial leap in intelligent automation and assistive devices. Neuromorphic hardware with spiking neural network (SNN) architecture utilizes insights from biological phenomena to offer encouraging solutions. Previous studies have proposed reinforcement learning (RL) models for SNN responses in the rat hippocampus to an environment where rewards depend on the context. The scale of these models matches the scope and capacity of small embedded systems in the framework of Internet-of-Bodies (IoB), autonomous sensor nodes, and other edge applications. Addressing energy-efficient artificial learning problems in such systems enables smart micro-systems with edge intelligence. A novel bio-inspired RL system architecture is presented in this work, leading to significant energy consumption benefits without foregoing real-time autonomous processing and accuracy requirements of the context-dependent task. The hardware architecture successfully models features analogous to synaptic tagging, changes in the exploration schemes, synapse saturation, and spatially localized task-based activation observed in the brain. The design has been synthesized, simulated, and tested on Intel MAX10 Field-Programmable Gate Array (FPGA). The problem-based bio-inspired approach to SNN edge architectural design results in 25X reduction in average power compared to the state-of-the-art for a test with real-time context learning and 30 trials. Furthermore, 940x lower energy consumption is achieved due to improvement in the execution time.

Wavelet-Based Computational Intelligence for Real-Time Anomaly Detection and Fault Isolation in Embedded Systems

In today’s technologically advanced landscape, sensors feed critical data for accurate decision-making and actions. Ensuring the integrity and reliability of sensor data is paramount to system performance and security. This paper introduces an innovative approach utilizing discrete wavelet transforms (DWT) embedded within microcontrollers to scrutinize sensor data meticulously. Our methodology aims to detect and isolate malfunctions, misuse, or any anomalies before they permeate the system, potentially causing widespread disruption. By leveraging the power of wavelet-based analysis, we embed computational intelligence directly into the microcontrollers, enabling them to monitor and validate their outputs in real-time. This proactive anomaly detection framework is designed to distinguish between normal and aberrant sensor behaviors, thereby safeguarding the system from erroneous data propagation. Our approach significantly enhances the reliability of embedded systems, providing a robust defense against false data injection attacks and contributing to overall cybersecurity.

Preface: Integrating computational intelligence with multiscale analysis and multidisciplinary design approaches

Preface: Integrating computational intelligence with multiscale analysis and multidisciplinary design approaches

Estimating Power, Performance, and Area for On-Sensor Deployment of AR/VR Workloads Using an Analytical Framework

Augmented Reality and Virtual Reality have emerged as the next frontier of intelligent image sensors and computer systems. In these systems, 3D die stacking stands out as a compelling solution, enabling in situ processing capability of the sensory data for tasks such as image classification and object detection at low power, low latency, and a small form factor. These intelligent 3D CMOS Image Sensor (CIS) systems present a wide design space, encompassing multiple domains (e.g., computer vision algorithms, circuit design, system architecture, and semiconductor technology, including 3D stacking) that have not been explored in-depth so far. This article aims to fill this gap. We first present an analytical evaluation framework, STAR-3DSim, dedicated to rapid pre-RTL evaluation of 3D-CIS systems capturing the entire stack from the pixel layer to the on-sensor processor layer. With STAR-3DSim, we then propose several knobs for PPA (power, performance, area) improvement of the Deep Neural Network (DNN) accelerator that can provide up to 53%, 41%, and 63% reduction in energy, latency, and area, respectively, across a broad set of relevant AR/VR workloads. Last, we present full-system evaluation results by taking image sensing, cross-tier data transfer, and off-sensor communication into consideration.

COMPUTER VISION METHODS FOR CONDUCTING OSINT INVESTIGATIONS

This paper researches the application of computer vision techniques in concern with OSINT (Open Source Intelligence) investigations. It explores how state-ofthe- art algorithms and models in computer vision can be used to automate and enhance the process of gathering, analyzing, and interpreting visual data from open sources. The research focuses on the critical steps of image scraping, data preprocessing, and embedding generation using advanced deep learning models such as CLIP. Additionally, the study examines the challenges of managing large-scale visual data and implementing efficient search mechanisms through vector databases like Faiss and Weaviate. By applying these technologies, the paper illustrates how investigators can improve the accuracy and efficiency of imagebased searches, which are later used for uncovering hidden connections and verifying information in OSINT investigations. The findings contribute to the growing field of computer vision and intelligence gathering, offering practical recommendations for enhancing investigative processes through the integration of computer vision methodologies.

Multimedia Cognitive Wireless Sensor Network Cluster Routing based on Intelligent Robot Edge Computing and Collection

Multimedia Cognitive Wireless Sensor Network Cluster Routing based on Intelligent Robot Edge Computing and Collection

Data Security Issues in Intelligent Cloud Computing Systems

This project takes the intelligent cloud computing system as the main research object. It mainly uses the literature analysis method to explore the data security problems in the intelligent cloud computing system. By investigating the development background of intelligent cloud computing, the author summarizes the definition of cloud computing and the characteristics of cloud computing. The author also makes a specific analysis of the advantages of cloud computing, and concludes that cloud computing is possible through safe and reliable data, low demand for clients, shared cloud data and unlimited possibilities. These four points are the main reasons major enterprises choose cloud computing to replace traditional computing resources. In the topic, the author studied the data security problems in cloud computing from three aspects: the problems exposed in the development process of cloud computing, the effective measures to protect data security in cloud computing and predicting the future development trend of improving data security. The authors believe that future research should focus on a balance between network security issues in cloud computing and building a secure and reliable data system.

An agent-based simulation modeling framework for Mobility-as-a-Service (MaaS)

This study develops an agent-based intelligent Mobility-as-a-Service (MaaS) simulation model consisting of three types of agents (i.e., MaaS fleet unit, travelers, and central intelligent mobility assignment module) to assess mobility service assignment processes balancing conflicting entities (e.g., demand and supply) within the MaaS ecosystem. The study follows a two-level optimization method (i.e., lower, and upper levels). It employs artificial intelligence and multicriteria decision making to solve two-dimensional mobility assignment problems (demand vs. supply). The novelty of this assignment process is that it implements an intelligence module accounting for the past system performance to make a future assignment decision in favor of both sides of the operation. This study processes 24-hour trip requests extracted from Nova Scotia Travel Activity (NovaTRAC) survey data in real-time. Two scenarios (1-D and 2-D assignments) are compared using the cost criteria, such as total waiting time, empty time, and idle time. The 1-D scenario refers to mobility assignment that emphasizes the demand side only, and the 2-D scenario formulates mobility assignment by balancing the demand and supply sides of the MaaS ecosystem. Experimental results indicate that a MaaS fleet of 350 units is the most balanced fleet in both scenarios. However, the 2-D optimization method reduces the overall supply cost by 25%. Moreover, 2-D operation demonstrates a higher fleet utilization over a considerable period, whereas the 1-D design guarantees a higher fleet utilization only during the peak period. Results of this study provide us with a benchmark for assessing more complex MaaS operation scenarios which will further aid in advancing the operational MaaS ecosystem. Our findings can help policymakers implement cost-effective MaaS solutions supporting sustainable urban mobility and SDG 13: Climate Action.

A preliminary discussion on data privacy and data security issues

With the expeditious evolution of technologies such as the internet, big data, cloud computing, and artificial intelligence, data has ascended to the status of an invaluable and indispensable resource within the intricate tapestry of modern society. Yet, the labyrinthine ethical quandaries that intertwine with the processes of data collection, storage, processing, and application have progressively surfaced, capturing the rapt attention of academia, industry, and government as they grapple with this nascent challenge. However, with the extensive application of data technology, issues of data ethics have become increasingly prominent, posing unprecedented challenges to personal privacy, data security, social equity, and justice. This article aims to delve deeply into the connotation and extension of data privacy and data security, as well as its significant role in current society. By examining relevant research findings at this stage, analyzing the major challenges faced by data ethics and exploring corresponding strategies, this paper delves into the multifaceted challenges faced by data privacy and data security, highlights the inadvertent data collection by smart devices, the potential for re-identification of blurred and anonymized information through big data analysis, as well as the ongoing threats posed by hacker attacks, internal vulnerabilities, and the complexity of data circulation.