Intelligent System Approach Research Articles

Dynamic assessment approach for intelligent power distribution systems based on runtime verification with requirements updates

The study aims to address the challenge of dynamic assessment in power systems by proposing a design scheme for an intelligent adaptive power distribution system based on runtime verification. The system architecture is built upon cloud–edge-end collaboration, enabling comprehensive monitoring and precise management of the power grid through coordinated efforts across different levels. Specifically, the study employs the adaptive observer approach, allowing dynamic adjustments to observers to reflect updates in requirements and ensure system reliability. This method covers both structural and parametric adjustments to specifications, including updating time protection conditions, updating events, and adding or removing responses. The results demonstrate that with the implementation of adaptive observers, the system becomes more flexible in responding to changes, significantly enhancing its level of efficiency. By employing dynamically changing verification specifications, the system achieves real-time and flexible verification. This research provides technical support for the safe, efficient, and reliable operation of electrical power distribution systems.

Fully Binarized Graph Convolutional Network Accelerator Based on In‐Memory Computing with Resistive Random‐Access Memory

Artificial intelligence for graph‐structured data has achieved remarkable success in applications such as recommendation systems, social networks, drug discovery, and circuit annotation. Graph convolutional networks (GCNs) are an effective way to learn representations of various graphs. The increasing size and complexity of graphs call for in‐memory computing (IMC) accelerators for GCN to alleviate massive data transmission between off‐chip memory and processing units. However, GCN implementation with IMC is challenging because of the large memory consumption, irregular memory access, and device nonidealities. Herein, a fully binarized GCN (BGCN) accelerator based on computational resistive random‐access memory (RRAM) through software–hardware codesign is presented. The essential operations including aggregation and combination in GCN are implemented on the RRAM crossbar arrays with cooperation between multiply‐and‐accumulation and content‐addressable memory operations. By leveraging the model quantization and IMC on the RRAM, the BGCN accelerator demonstrates less RRAM usage, high robustness to the device variations, high energy efficiency, and comparable classification accuracy compared to the current state‐of‐the‐art GCN accelerators on both graph classification task using the MUTAG and PTC datasets and node classification task using the Cora and CiteSeer datasets. These results provide a promising approach for edge intelligent systems to efficiently process graph‐structured data.

Intelligent parameters reconfiguration system for enhancing machine tools sustainability using real-time data-driven: an experimental cutting speed investigation

ABSTRACT Industrial manufacturing is not trivial and complex since there are dimensional and tolerance product changes, differences in raw material and variations in machine models. Hence, this research proposes an Intelligent Parameters Reconfiguration System (IPRS) approach for enhancing manufacturing performance and extending cutting tool lifespan through detailed machining parameter setup. The approach joins real-time data acquisition and cutting-edge machine learning techniques to improve the turning machining setup. This research uses related works to conceptualise the IPRS structure in four main steps: machining sensing, data acquisition, data processing and parameters prediction, and automatic machine reconfiguration. The approach enabled dynamic adjustments in cutting speed based on predicted wear, resulting in a notable reduction of 5.6 minutes in manufacturing time and an improvement of 0.2 µm in surface finish. However, it is important to highlight that the experimental solution evaluation was carried out in a controlled scenario using a potentiometer to control the cutting speed on CNC lathes. Therefore, the applicability and scalability of the solution in a real scenario have significant limitations, and the cutting speed control must have direct integration with the machine’s numerical control. As future research, the IPRS approach should consider other influential parameters like cutting depth and feed rate.

A novel block-chain based secure cross-domain interaction approach for intelligent transportation systems

In the Intelligent Transportation System (ITS), secure and efficient data communication among vehicles, road testing equipment, computing nodes, and transportation agencies is important for building a smart city integrated transportation system. However, the traditional centralized processing approach may face threats in terms of data leakage and trust. The use of distributed, tamper-proof blockchain technology can improve the decentralized storage and security of data in the ITS network. However, the cross-trust domain devices, terminals, and transportation agencies in the heterogeneous blockchain network of the ITS still face great challenges in trusted data communication and interoperability. In this paper, we propose a heterogeneous cross-chain interaction mechanism based on relay nodes and identity encryption to solve the problem of data cross-domain interaction between devices and agencies in the ITS. First, we propose the ITS cross-chain communication framework and improve the cross-chain interaction model. The relay nodes are interconnected through LibP2P to form a relay node chain, which is used for cross-chain information verification and transmission. Secondly, we propose a relay node secure access scheme based on identity-based encryption (IBE) to provide reliable identity authentication for relay nodes. Finally, we build a standard cross-chain communication protocol and cross-chain transaction lifecycle for this mechanism. We use Hyperledger Fabric and FISCO BCOS blockchain to design and implement this solution, and verify the feasibility of this cross-chain interaction mechanism. The experimental results show that the mechanism can achieve a stable data cross-chain read throughput of 2,000 transactions per second (TPS), which can meet the requirements of secure and efficient cross-chain communication and interaction among heterogeneous blockchains in the ITS, and has high application value.

FloodIntel: Advancing flood disaster forecasting through comprehensive intelligent system approach

<p><strong>Background:</strong> Every year, floods are the most devastating natural disaster that hits Malaysia, causing damage to people’s livelihoods, destroying property and infrastructure, and taking lives. Flood disasters are becoming more frequent and severe, necessitating the development of sophisticated forecasting and early warning systems to mitigate their effects. This study presents the design and implementation of a sophisticated flood forecasting and early warning system, utilizing intelligent technologies to enable timely prediction and proactive measures in high-risk areas.<strong> Methods:</strong> The proposed system incorporates Internet of Things (IoT) technology to collect real-time data on the river’s water level. The collected data are analyzed using an association rule technique to generate accurate forecasts of prospective flood occurrences. By using this intelligent flood disaster prediction system, users and authorities can receive early warnings and make informed decisions regarding evacuation, resource allocation, and infrastructure reinforcement. The system’s capability to provide early flood forecasts in high-risk areas can substantially enhance flood preparedness and response and save more life. <strong>Results:</strong> The findings of the study highlight the potential of the system to improve flood risk management strategies and reduce flood-related devastation and human suffering in vulnerable regions.<strong> Conclusions:</strong> In conclusion, it is important to implement IoT and AI technologies to improve flood prediction systems and reduce the negative effects of flood disasters.</p>

Real-Time IoT-Based Connected Vehicle Infrastructure for Intelligent Transportation Safety

The transportation sector faces severe consequences due to the incrementing population influx yielding congestions, fatalities and haphazard traffic scenarios. Advanced Driver Assistance Systems (ADAS) assists highly in such scenarios by eradicating probable accidents and ensures traffic safety. This paper presents intelligent transportation systems (ITS) approach through the connected vehicle technology infrastructure. YOLO v4 (You Only Look Once) inspired real-time computer vision capable of detecting vehicles, pedestrians and animals at high efficiency (0.9777 mean average precision) is deployed on the GPU (Graphics Processing Unit) which offered higher frame rate of detection (74.26 fps). The locations of animals and potholes were mapped through consistent survey and mobile app which relayed the detected locations to the cloud server forming a geospatial database. Clustered locations from the geospatial database on dense transportation network were utilized for constructing animal and pothole hotspot zones. A basic level of display warning was triggered when the vehicle approached animal and pothole areas. Furthermore, advanced alert comprising of display and sound alert was trigger when the vehicle approached hotspot zones. This was implemented using real-time Internet of things (IoT) and cloud infrastructure applications for continuous vehicle’s location monitoring and triggering as per the hotspot geo-locations. The proposed system ensured traffic safety and assisted in avoiding probable crashes and accidents that generally led to congestions and fatalities.

A hybrid location‐dependent ultra convolutional neural network‐based vehicle number plate recognition approach for intelligent transportation systems

SummaryIn today's world, identifying the owner and proprietor of a vehicle that violates driving rules or does any unintentional work on the street is a challenging task. Inspection of each driver's license number takes a long time for a highway police officer. To overcome this, many researchers have introduced an automated number plate recognition approach which is usually a computer vision‐based technique to identify the vehicle's registration plate. However, the existing recognition approaches are lagged to extract the influential features which degrade the detection accuracy and increase the misclassification errors. In this article, a novel automated number plate recognition methodology has been proposed to identify the number plates accurately with minimal error rates. Primary, a new pretrained location‐dependent ultra convolutional neural network (LUCNN) is employed to learn the influential features from the input images. These obtained features are then fed into hybrid single‐shot fully convolutional detectors with a support vector machine (SSVM) classifier to separate the vehicle's city, model, and number from the registration location. At varied automobile distances, the proposed LUCNN + SSVM model is able to retrieve the number plate regions in the picture acquired from its back end. The performance results manifest that the proposed LUCNN + SSVM model attains a better accuracy of 98.75% and a lesser error range of 1.25% than the existing recognition models.

Pathogen-Based Classification of Plant Diseases: A Deep Transfer Learning Approach for Intelligent Support Systems

Pathogen-Based Classification of Plant Diseases: A Deep Transfer Learning Approach for Intelligent Support Systems

Toward an Appropriate Approach for Intelligent Intrusion and Detection Systems

Now a days, the company’s information security become among a main priority. Indeed, the more the attack force on the network develops, the more it is necessary to develop the security and the network surveillance. The data is to be exchanged between the internal company network and the outside one such as Internet. It is therefore necessary to be protected against malicious intrusions into the company's network, but also to monitor the traffic inside the network in order to prevent possible internal attacks. Currently, security and reliability have become the major concerns of an individual or organization. A rule-based intrusion detection system (IDS) called Snort is an open-source software used as a network protection tool that can only detect recognized attacks. In order to detect advanced network attacks and detect fraudulent network traffic, this research paper proposes an advanced and more intelligent approach by applying machine learning. To find the best algorithm to use with Snort to improve its detection, the support vector machine (SVM) was chosen based on its accuracy. The proposed system has produced efficient detection rates versus other proposed approaches in the security intrusions detection field.

Requirements Conflict Detection and Resolution in AREM Using Intelligence System Approach

Requirements engineering (RE) is the process of defining user requirements that are used as the main reference in the system development process. The quality of the RE results is measured based on the consistency and completeness of the requirements. The collection of requirements from multiple stakeholders can cause requirements conflict and have an impact on the inconsistency and incompleteness of the resulting requirements model. In this study, a method for automatic conflict detection and resolution in the Automatic Requirements Engineering Model (AREM) was developed. AREM is a model that automates the process of elicitation, analysis, validation, and requirements specification. The requirement conflict detection method was developed using an intelligent agent approach combined with a Weighted Product approach. Meanwhile, Conflict resolution is made automatically using a rule-based model and clustering method. Testing the ability of the method to detect and resolve conflicting requirements was carried out through five data sets of requirements from five system development projects. Based on the test results, it is known that the system is able to produce a set of objects that have conflicts in the data requirements. For conflict resolution, experiments were conducted with five conflict resolution scenarios. The experimental results show that the method is able to resolve conflicts by producing the highest completeness value, but the results of conflict resolution also produce a number of soft goals. The success of the method in detecting and resolving conflicts in the model is able to overcome the problem of inconsistencies and incompleteness in the requirements model.

Laser Lift‐Off Technologies for Ultra‐Thin Emerging Electronics: Mechanisms, Applications, and Progress

AbstractDue to the advantages of non‐contact processing, high efficiency, high precision, and superior controllability, laser lift‐off (LLO) technologies exhibit excellent material applicability and process compatibility in the lift‐off of ultra‐thin electronic devices. This brings new opportunities for large‐scale manufacturing of emerging electronics that meet ultra‐thin, fragile, and poor high‐temperature resistance. However, this opportunity also comes with formidable challenges from the complex mechanisms of laser‐matter interactions, which hinder comprehensive exploration and fundamental understanding. By elaborating the laser‐material interactions, the photothermal effect, “cold” processing, shockwave effect, and cavitation effect in LLO process from multiple perspectives, this review is devoted to discussing the latest progress and sustainable application of LLO technologies in emerging electronics that are developing toward ultra‐thin, miniaturization, and integration, such as wafer level packaging, displays, energy harvesters, sensors, and memories. Finally, starting from the fundamental principles of material design, light field regulation, and intelligent control system, the challenges and new approaches faced by LLO technologies are explored and fully integrated with future innovative manufacturing concepts and device structures.

Towards smart government for sustainable fisheries and marine development: An intelligent web-based support system approach in small islands

Indonesia is one of the few archipelagic countries with an abundance of marine resources in the world. However, these characteristics provide different kinds of challenges for remote small island regions in the country, in particular for sustainable development of marine and fisheries. Southeast Maluku Regency also falls into that category. Located in the eastern part of Indonesia, with high biodiversity as it is included in the coral triangle area and flanked by two of the world's largest fisheries, namely the Arafura Sea and the Banda Sea, the region’s marine and fishing sectors still underperform due to the lack of consistency in developing plans. This is due to the limited use of empirical information on the socio-economy, marine characteristics, and empirical potential of the region. This study aimed to build a web-based Intelligent Decision Support System (DSS) for sustainable fisheries and marine development of Southeast Maluku regency and use the system as the basis for evaluation of current and previous region’s marine and fisheries plans. The system provides all the basic to useful calculated information-based GIS (Geographical Information System) in an effort to help local governments better plan and develop the marine and fishing sectors.

Intelligent Braking System Using Electromagnetic Actuators

Abstract: Accident prevention has been one of the leading areas of research today. Our paper is designed to prevent accidents due to loss of control, drunken driving, and rash driving, using circuitry aided by a microcontroller kit. In our work, braking distance and the distance of the obstacle are taken into consideration along with the speed of the vehicle. The sensor helps in finding the speed of movement of the vehicle and the ultrasonic sensor senses the distance of the object in front. These sensors provide real- time inputs to the microcontroller program. Using sensor the system will sense the speed of the vehicle and with the microcontroller, it will calculate the distance required to bring the vehicle to a complete stop for that speed. Breaking motors is incorporated to activate the brakes thereby achieving automatic breaking procedures. The system helps in conjunction with the driver judgment if the driver doesn’t sense the obstacle and applies the brake at the right time then the microcontroller initiates braking motor to apply the brakes automatically. Our future work deals with incorporating real time brake shoe wear system to provide enhanced feature for the intelligent braking system.  By looking at safety in terms of avoiding accidents in the first place.  And then protecting occupants when a crash is unavoidable.  We can prevent more accidents, save more lives, and reduce insurance and medical costs to society. Intelligent Braking System approach represents a significant shift from the traditional approach to safety, but it is fundamental to achieving the substantial benefit

Suspended Sediment Load Simulation during Flood Events Using Intelligent Systems: A Case Study on Semiarid Regions of Mediterranean Basin

Sediment transport in rivers is a nonlinear natural phenomenon, which can harm the environment and hydraulic structures and is one of the main reasons for the dams’ siltation. In this paper, the following artificial intelligence approaches were used to simulate the suspended sediment load (SSL) during periods of flood events in the northeastern Algerian river basins: artificial neural network combined with particle swarm optimization (ANN-PSO), adaptive neuro-fuzzy inference system combined with particle swarm optimization (ANFIS-PSO), random forest (RF), and long short-term memory (LSTM). The comparison of the prediction accuracies of such different intelligent system approaches revealed that ANN-PSO, RF, and LSTM satisfactorily simulated the nonlinear process of SSL. Carefully comparing the results, the ANN-PSO model showed a slight superiority over the RF and LSTM models, with RMSE = 67.2990 kg/s in the Chemourah basin and RMSE = 55.8737 kg/s in the Gareat el tarf basin.

Adaptive Athlete Training Plan Generation: An intelligent control systems approach

ObjectivesThe planning and control of team sport training activities is an extremely important aspect of athletic development and team performance. This research introduces a novel system which leverages techniques from the fields of control system theory and artificial intelligence to construct optimal future training plans when unexpected disturbances and deviations from a training plan goal occur. DesignSimulation-based experimental design. MethodsThe adaptation of training load prescriptions was formulated as an optimal control problem where we seek to minimize the difference between a desired training plan goal and an observed training outcome. To determine the most suitable approach to optimize future training loads the performance of an artificial intelligence-based feedback controller was compared to random and proportional controllers. Computational simulations (N = 1800) were conducted using a non-linear training plan spanning 60 days over a 12-week period, and the control strategies were assessed on their ability to adapt future training loads when disturbances and deviations from an optimal planning policy have occurred. Statistical analysis was conducted to determine if significant differences existed between the three control strategies. ResultsThe results of a repeated measures analysis of variance demonstrated that an intelligent feedback controller significantly outperforms the random (p < .001, ES = 7.41, very large) and proportional control (p < .001, ES = 7.41, very large) strategies at reducing the deviations from a training plan goal. ConclusionsThis system can be used to support the decision making of practitioners across several areas considered important for the effective planning and adaption of athletic training.

Intelligent decision support system approach for predicting the performance of students based on three-level machine learning technique

Abstract In this research work, a user-friendly decision support framework is developed to analyze the behavior of Pakistani students in academics. The purpose of this article is to analyze the performance of the Pakistani students using an intelligent decision support system (DSS) based on the three-level machine learning (ML) technique. The neural network used a three-level classifier approach for the prediction of Pakistani student achievement. A self-recorded dataset of 1,011 respondents of graduate students of English and Physics courses are used. The ten interviews along with ten questions were conducted to determine the perception of the individual student. The chi-squared ( χ ) \left(\chi ) test was applied to test statistical significancy of the questionnaire. The statistical calculations and computation of data were performed by using the statistical package of IBMM SPSS version 21.0. The seven different algorithms were tested to improve the data classification. The Java-based environment was used for the development of numerous prediction classifiers. C4.5 algorithm shows the finest accuracy, whereas Naïve Bayes (NB) algorithm shows the least. The results depict that the classifier’s efficiency was improved by using a three-level proposed scheme from 83.2% to 88.8%. This prediction has shown remarkable results when compared with the individual level classifier technique of ML. This improvement in the accuracy of DSSs is used to identify more efficiently the gray areas in the education stratum of Pakistan. This will pave a path for making policies in the higher education system of Pakistan. The presented framework can be deployed on different platforms under numerous operating systems.

A Greedy Scheduling Approach for Peripheral Mobile Intelligent Systems

Smart, pervasive devices have recently experienced accelerated technological development in the fields of hardware, software, and wireless connections. The promotion of various kinds of collaborative mobile computing requires an upgrade in network connectivity with wireless technologies, as well as enhanced peer-to-peer communication. Mobile computing also requires appropriate scheduling methods to speed up the implementation and processing of various computing applications by better managing network resources. Scheduling techniques are relevant to the modern architectural models that support the IoT paradigm, particularly smart collaborative mobile computing architectures at the network periphery. In this regard, load-balancing techniques have also become necessary to exploit all the available capabilities and thus the speed of implementation. However, since the problem of scheduling and load-balancing, which we addressed in this study, is known to be NP-hard, the heuristic approach is well justified. We thus designed and validated a greedy scheduling and load-balancing algorithm to improve the utilization of resources. We conducted a comparison study with the longest cloudlet fact processing (LCFP), shortest cloudlet fact processing (SCFP), and Min-Min heuristic algorithms. The choice of those three algorithms is based on the efficiency and simplicity of their mechanisms, as reported in the literature, for allocating tasks to devices. The simulation we conducted showed the superiority of our approach over those algorithms with respect to the overall completion time criterion.

A Prescriptive Intelligent System for an Industrial Wastewater Treatment Process: Analyzing pH as a First Approach

An important issue today for industries is optimizing their processes. Therefore, it is necessary to make the right decisions to carry out these activities, such as increasing the profit of businesses, improving the commercial strategies, and analyzing the industrial processes performance to produce better goods and services. This work proposes an intelligent system approach to prescribe actions and reduce the chemical oxygen demand (COD) in an equalizer tank of a wastewater treatment plant (WWTP) using machine learning models and genetic algorithms. There are three main objectives of this data-driven decision-making proposal. The first is to characterize and adapt a proper prediction model for the decision-making scheme. The second is to develop a prescriptive intelligent system based on expert’s rules and the selected prediction model’s outcomes. The last is to evaluate the system performance. As a novelty, this research proposes the use of long short-term memory (LSTM) artificial neural networks (ANN) with genetic algorithms (GA) for optimization in the WWTP area.

A Time-Aware Hybrid Approach for Intelligent Recommendation Systems for Individual and Group Users

Although personal and group recommendation systems have been quickly developed recently, challenges and limitations still exist. In particular, users constantly explore new items and change their preferences throughout time, which causes difficulties in building accurate user profiles and providing precise recommendation outcomes. In this context, this study addresses the time awareness of the user preferences and proposes a hybrid recommendation approach for both individual and group recommendations to better meet the user preference changes and thus improve the recommendation performance. The experimental results show that the proposed approach outperforms several baseline algorithms in terms of precision, recall, novelty, and diversity, in both personal and group recommendations. Moreover, it is clear that the recommendation performance can be largely improved by capturing the user preference changes in the study. These findings are beneficial for increasing the understanding of the user dynamic preference changes in building more precise user profiles and expanding the knowledge of developing more effective and efficient recommendation systems.

Pre‐fall prognostics, prevention and management of frailty in geriatrics: A personalized intelligent system approach (ALL‐FrAAgile)

AbstractContextFrailty is a clinical state in which there is an increase in an individual’s vulnerability for developing an increased dependency and/or mortality when exposed to a stressor”. Frailty can occur in 15% of adults aged 65 years and over as the result of a variety of medical and socio‐demographic conditions such as living alone, depression, polypharmacy, malnutrition or sedentary lifestyle, etc. Even small stressors may increase the risk of developing significant health complications such as falls, dependency and hospitalizations. Nevertheless this state can be reversed through personalized intervention. So screening, evaluation and management are highly important.ObjectivesFrailty detection and prevention.MethodsThe FrAAgile is an ICT based personalized Ambient Assisted Living (ALL) intelligent system aimed at pre‐fall prognostics, identification, prevention and management of physical and mental frailty and multimorbidity and transition to robust health status. A personalized intelligent role‐based service is offered to access and improve the physical and the mental state of the individual through physical and cognition‐enhancing games based exercises. Intelligent system applications accessing the individual’s behavior, cognition, mood, agility, onset/lack of outside activities, balance, gate etc. to define a personalized role for that particular person to improve his/her physical and mental condition avoiding fall incidents due to frailty. This approach can be implemented and offered as a service directly to an individual user or to his/her informal and formal caregivers.ResultsDuring the CO‐creation phase, more than ninety End‐Users in Cyprus, Spain, Switzerland and Romania sites are identified and started to be recruited since Jan 2020. The ICT architecture of the project has been defined, considering required hardware, web‐connection, cloud database, data collection modules, video, and game applications and libraries.ConclusionThe mild cognitive impairment individuals (MCI) would be accompanied across three phases of pre‐trial pilot lab‐testing, adaptation, and optimization, which leads finally to field trails. The main focus of the role‐based intervention aims to prevent clinical frailty and falls incidence through augmenting physical and mental health condition considering a holistic personalized view of the individual lifestyle and condition (EU AAL‐frAAgiLe project, Active Assisted Living, Ageing Well in the Digital World, aal‐2018‐5‐152‐CP).