Intelligence-based System Research Articles

Artificial intelligence-based system frequency response modeling considering contribution of inverter-based resources

Artificial intelligence-based system frequency response modeling considering contribution of inverter-based resources

Analysis of features of electric energy quality management and voltage regulation in housing and communal services

Subject of research: methods of improving the quality of electric energy in electric networks used for power supply mainly to municipal consumers in urban areas. The purpose of the study is to determine the most relevant methods for improving the quality of electric energy of municipal consumers, their advantages and disadvantages, as well as determining the direction of modernization. Methods and objects of research: the object of research in this material is the housing and communal complex in urban areas, in particular the electric grid complex. The work is based on such scientific research methods as analysis, synthesis, modeling and generalization. The main results of the study: the analysis of the features of electric energy quality management and voltage regulation in modern conditions. The importance and necessity of using modern intelligent systems to improve reliability, energy efficiency and quality of electric energy i s highlighted. The key prerequisites for the introduction of smart systems for monitoring the state of the electrical network are formulated. The tasks, the solution of which is necessary for the modernization of the complex, have been identified. A proposal has been made to use artificial intelligence-based systems as the main tool for modernization.

Development of an automated artificial intelligence-based system for urogenital schistosomiasis diagnosis using digital image analysis techniques and a robotized microscope.

Urogenital schistosomiasis is considered a Neglected Tropical Disease (NTD) by the World Health Organization (WHO). It is estimated to affect 150 million people worldwide, with a high relevance in resource-poor settings of the African continent. The gold-standard diagnosis is still direct observation of Schistosoma haematobium eggs in urine samples by optical microscopy. Novel diagnostic techniques based on digital image analysis by Artificial Intelligence (AI) tools are a suitable alternative for schistosomiasis diagnosis. Digital images of 24 urine sediment samples were acquired in non-endemic settings. S. haematobium eggs were manually labeled in digital images by laboratory professionals and used for training YOLOv5 and YOLOv8 models, which would achieve automatic detection and localization of the eggs. Urine sediment images were also employed to perform binary classification of images to detect erythrocytes/leukocytes with the MobileNetv3Large, EfficientNetv2, and NasNetLarge models. A robotized microscope system was employed to automatically move the slide through the X-Y axis and to auto-focus the sample. A total number of 1189 labels were annotated in 1017 digital images from urine sediment samples. YOLOv5x training demonstrated a 99.3% precision, 99.4% recall, 99.3% F-score, and 99.4% mAP0.5 for S. haematobium detection. NasNetLarge has an 85.6% accuracy for erythrocyte/leukocyte detection with the test dataset. Convolutional neural network training and comparison demonstrated that YOLOv5x for the detection of eggs and NasNetLarge for the binary image classification to detect erythrocytes/leukocytes were the best options for our digital image database. The development of low-cost novel diagnostic techniques based on the detection and identification of S. haematobium eggs in urine by AI tools would be a suitable alternative to conventional microscopy in non-endemic settings. This technical proof-of-principle study allows laying the basis for improving the system, and optimizing its implementation in the laboratories.

A New Artificial Intelligence-Based System for Optimal Electricity Arbitrage of a Second-Life Battery Station in Day-Ahead Markets

Electric vehicles (EVs) are widely regarded as a crucial tool for carbon reduction due to the gradual increase in their numbers. However, these vehicles are equipped with batteries that have a limited lifespan. It is commonly stated that when the battery capacity falls below 70%, it needs to be replaced, and these discarded batteries are typically sent for recycling. Nevertheless, there is an opportunity to repurpose these worn-out batteries for a second life in electric power systems. This study focuses on the arbitrage situation of a second-life battery (SLB) facility in day-ahead electricity markets. This approach not only contributes to balancing supply and demand in the electric power system but also allows the battery facility to achieve significant gains. We propose an artificial intelligence system that integrates optimized deep learning algorithms for market price predictions with a mixed-integer linear programming (MILP) model for market participation and arbitrage decisions. Our system predicts prices for the next 24 h using Neural Hierarchical Interpolation for Time Series (N-HiTS) and decides when to enter the market using the MILP model and incorporating the predicted data and the statuses of the batteries. We compare the accuracy of our trained deep learning model with other deep learning models such as recurrent neural networks (RNNs), Long Short-Term Memory (LSTM), and Neural Basis Expansion Analysis for Interpretable Time-Series Forecasting (N-BEATS). We test the efficiency of the proposed system using real-world Turkish day-ahead market data. According to the results obtained, this study concludes that substantial gains can be achieved with the predicted prices and the optimal operating model. A facility with a total battery energy capacity of 5.133 MWh can generate a profit of USD 539 in one day, showcasing the potential of our study. Our new system’s approach provides proof of concept of new research opportunities for the participation of SLB facilities in day-ahead markets.

A Review of Expert Systems Integration in Signal Plan Optimisation

In urban networks, periodic peak traffic congestion often occurs during the day, namely in the morning and afternoon hours. Due to spatial constraints and the inability to increase capacity through physical road expansion, modern traffic management increasingly relies on Intelligent Transport Systems (ITS) solutions. One such solution is the integration of automatic licence plate recognition, an expert system and microsimulation tools aimed at optimising the network performance of signalised intersections within a network. Based on real-time and historical data on individual vehicle trajectories, the system predicts the route of each vehicle through the observed segment of the traffic network, determines the network load and proposes optimal signal plans. This paper provides an overview of conducted research related to the optimisation of signal plans utilising expert systems. Mathematical models for capacity and load determination, as well as computational intelligence-based systems used for signalised intersection management strategies, are described. Finally, the paper proposes a basic framework and guidelines related to the suggested system, highlighting open questions and potential challenges in its development.

Similarity-driven adversarial testing of neural networks

Although Convolutional Neural Networks (CNNs) are among the most important algorithms of computer vision and the artificial intelligence-based systems, they are vulnerable to adversarial attacks. Such attacks can cause dangerous consequences in real-life deployments. Consequently, testing of the artificial intelligence-based systems from their perspective is crucial to reliably support human prediction and decision-making through computation techniques under varying conditions. While proposing new effective attacks is important for neural network testing, it is also crucial to design effective strategies that can be used to choose target labels for these attacks. That is why, in this paper we propose a novel similarity-driven adversarial testing methodology for target label choosing. Our motivation is that CNNs, similarly to humans, tend to make mistakes mostly among categories they perceive similar. Thus, the effort to make models predict a particular class is not equal for all classes. Motivated by this, we propose to use the most and least similar labels to the ground truth according to different similarity measures to choose the target label for an adversarial attack. They can be treated as best- and worst-case scenarios in practical and transparent testing methodologies. As similarity is one of the key components of human cognition and categorization, the approach presents a shift towards a more human-centered security testing of deep neural networks. The obtained numerical results show the superiority of the proposed methods to the existing strategies in the targeted and the non-targeted testing setups.

Classification of Garlic Varieties with Fluorescent Spectroscopy Using Machine Learning

Machine learning techniques can produce fast, accurate and objective results in the analysis of agricultural products. These artificial intelligence-based systems are frequently encountered in studies on agriculture in the literature. This study reveals the usability of machine learning algorithms in classification of garlic cultivars using fluorescent spectroscopic data. For this, six types of garlic were used: Razgradski-11, Razgradski-12, Razgradski-115, Plovdivski-120, Yambolski-99 and Topolovgradski. In the first stage, the parsing analysis made from the fluorescent spectroscopic data of the garlics was carried out with seven different machine learning. The classification results of these seven types of machine learning algorithms were obtained. In the second stage, the classification results were obtained by adjusting the hyperparameters of each Machine Learning (ML) algorithm in order to control the improvability of the classification accuracy rates. Finally, performance metrics such as Specificity, precision, MCC, F1-Score of the classification processes obtained in the two stages were compared. In general, it was observed that the classification performances increased with the hyperparameter adjustment performed in the second stage. In this study, classification results with ML showed that fluorescent spectroscopy data of garlic strongly represented garlic species and provided high performance classification accuracy of 99.93% with Neural Network (NN), one of the machine learning methods using these data.

Applications of Artificial Intelligence-Based Systems in the Management of Esophageal Varices.

Esophageal varices, dilated submucosal veins in the lower esophagus, are commonly associated with portal hypertension, particularly due to liver cirrhosis. The high morbidity and mortality linked to variceal hemorrhage underscore the need for accurate diagnosis and effective management. The traditional method of assessing esophageal varices is esophagogastroduodenoscopy (EGD), which, despite its diagnostic and therapeutic capabilities, presents limitations such as interobserver variability and invasiveness. This review aims to explore the role of artificial intelligence (AI) in enhancing the management of esophageal varices, focusing on its applications in diagnosis, risk stratification, and treatment optimization. This systematic review focuses on the capabilities of AI algorithms to analyze clinical scores, laboratory data, endoscopic images, and imaging modalities like CT scans. AI-based systems, particularly machine learning (ML) and deep learning (DL) algorithms, have demonstrated the ability to improve risk stratification and diagnosis of esophageal varices, analyzing vast amounts of data, identifying patterns, and providing individualized recommendations. However, despite these advancements, clinical scores based on laboratory data still show low specificity for esophageal varices, often requiring confirmatory endoscopic or imaging studies. AI integration in managing esophageal varices offers significant potential for advancing diagnosis, risk assessment, and treatment strategies. While promising, AI systems should complement rather than replace traditional methods, ensuring comprehensive patient evaluation. Further research is needed to refine these technologies and validate their efficacy in clinical practice.

AI-Enabled Traffic Light Control System: An Efficient Model to Manage the Traffic at Intersections using Computer Vision

Traffic congestion is a significant issue with studies indicating it costs cities billions annually and averages 54 hours of wasted time per traveler each year. This situation necessitates the implementation of efficient traffic management systems, especially at intersections. In response to this challenge, our work introduces an artificial intelligence-based system designed to analyze and predict traffic flow using machine learning algorithms and deep learning methods in conjunction with traffic cameras. The model comprises two main components: real-time data collection and predictive modeling. It employs object detection to identify and classify vehicles and adjusts traffic signal timings based on the necessary passage time and predetermined constraints. Additionally, data accumulated during operation facilitates the development of a predictive model for traffic flow over time, allowing for proactive traffic management. Evaluations are done to showcase the accuracy of the model and corresponding simulation and physical implementation further approved the applicability of our approach. Finally, this work aims to enhance urban transportation efficiently, reduce commuting stress, and improve the quality of life for city residents

Diagnostic Accuracy of Artificial Intelligence-Based Systems for Detecting Diabetic Retinopathy: A Systematic Review

Diabetic retinopathy (DR) represents a leading cause of blindness worldwide, early detection is critical to prevent vision loss. However, traditional screening methods, which rely on human experts, prove to be costly and time-consuming. The systematic review aims to assess the validity of artificial intelligence (AI) as a screening tool for detecting DR among diabetic patients. A systematic literature search was performed of the following databases: PubMed, Scopus, CINAHL, and Web of Science. The last date of our search was January 31, 2024. We included all observational studies, including cohort, case–control and cross-sectional studies and evaluated their quality using the Joanna Briggs Institute tool. We included diagnostic test accuracy studies evaluating the use of AI algorithms for DR screening in patients with diabetes. Studies were excluded if they exclusively assessed diagnostic accuracy for DR that did not use AI algorithms as a diagnostic tool and studies with incomplete or inaccessible data. Thirteen studies with sample sizes ranging from 69 to 1378 participants, reported good sensitivity of AI for detecting visually threatening DR (VTDR). The lowest sensitivity was 89.2%, and the highest was 100%. In terms of specificity, Any DR exhibited higher specificity compared to RDR and VTDR, ranging from 80.2% to 100%. The sensitivity and specificity of the Artificial Intelligence (AI)-based tools available for DR screening was considered acceptable, especially in detecting VTDR and Any DR, was regarded as good. These results implied the potential usefulness of these tools for DR screening in settings with limited resources. However, further high-quality comparative studies were deemed necessary to evaluate their effectiveness in real-world clinical settings.

Detecting COVID-19 from chest X-ray images using machine learning and deep convolutional neural networks

<p>The world was affected by a novel coronavirus in December 2019 that changed human life. Several types of research have been done, substantial scientific advances have been made, and millions of dollars have been spent on bringing scholars and scientists to one platform to end this critical pandemic. Ascertaining COVID-19 diagnoses in the initial stage of the pandemic was critical, specifically for patients with no manifestations. In this case, artificial intelligence-based systems were proposed to identify the virus at an earlier phase. Thus, the present study suggests a machine vision scheme to identify COVID-19 from chest X-ray images. Three machine learning approaches, such as logistic regression (LR), decision tree (DT), and random forest (RF), were implemented with more than 95% accuracy. The deep convolutional neural network (CNN) architecture was also proposed and implemented with a 99.99% detection rate. Therefore, the present work can effectively detect COVID-19 cases in the early stages.</p>

In silico docking and molecular dynamics for the discovery of inhibitors of enteric methane production in ruminants: a review.

The increase in methane emissions, a major greenhouse gas, threatens human well-being and global ecosystems due to its contribution to global warming. Livestock, particularly ruminants, have been a major research topic in recent decades due to their methane production. Therefore, the objective of the current review was to comprehensively discuss the in silico techniques used to mitigate methane production from ruminants. The review covers the principles of in silico docking and molecular dynamics, which can be used to develop methanogenesis inhibitors. It also discusses specific methanogen enzymes as potential targets for inhibitor development. Furthermore, in silico-based methanogenesis inhibitor development studies have been reviewed with the authors' opinions. The further use of in silico-based research techniques, including artificial intelligence-based systems, is encouraged to help reduce methane production from livestock more efficiently and cost-effectively.

Auto-Optimized Electro-Flow Reactor Platform for the in-situ Reduction of P(V) Oxide to P(III) and Their Application.

Trivalent phosphine catalysis is mostly utilized to activate the carbon-carbon multiple bonds to form carbanion intermediate species and is highly sensitive to certain variables. Random manual multi-variables are critical for understanding the batch disabled regeneration of trivalent phosphine chemistry. We need the artificial intelligence-based system which can change the variable based on previously conducted failed experiment. Herein, we report an auto-optimized electro-micro-flow reactor platform for the in-situ reduction of stable P(V) oxide to sensitive P(III) and further utilized the method for Corey-Fuchs reaction.

Multi-timescale neural dynamics for multisensory integration.

Carrying out any everyday task, be it driving in traffic, conversing with friends or playing basketball, requires rapid selection, integration and segregation of stimuli from different sensory modalities. At present, even the most advanced artificial intelligence-based systems are unable to replicate the multisensory processes that the human brain routinely performs, but how neural circuits in the brain carry out these processes is still not well understood. In this Perspective, we discuss recent findings that shed fresh light on the oscillatory neural mechanisms thatmediate multisensory integration (MI), including power modulations, phase resetting, phase-amplitude coupling and dynamic functional connectivity. We then consider studies that also suggest multi-timescale dynamics in intrinsic ongoing neural activity and during stimulus-driven bottom-up and cognitive top-down neural network processing in the context of MI. We propose a new concept of MI that emphasizes the critical role of neural dynamics at multiple timescales within and across brain networks, enabling the simultaneous integration, segregation, hierarchical structuring and selection of information in different time windows. To highlight predictions from our multi-timescale concept of MI, real-world scenarios in which multi-timescale processes may coordinate MI in a flexible and adaptive manner are considered.

Balancing accuracy and efficiency: A lightweight deep learning model for COVID 19 detection

The novel coronavirus disease in human was detected in Wuhan, China and spread rapidly across countries each time mutating itself as a new variant. It has impacted not only the patients but also medical infrastructure a lot. Several artificial intelligence-based systems for detection of covid-19 in chest images have been proposed. This study aims to develop a deep learning-based approach that efficiently detect Covid-19 using chest Computed Tomography (CT) images. In this work, we propose an efficient and lightweight deep-learning architecture based on the concept of a densely connected network for Covid-19 detection. The proposed architecture is designed by stacking dense modules in which each layer is directly connected to the other layers, with very fewer number of neurons at each layer. The dense connection is used to improve the learning capability of the proposed model and the fewer number of neurons make network computationally efficient. CT images for covid-19 detection are effectively used for the detection of Covid-19 patients. We train and test our model on SARS-CoV-2 CT-scan datasets. The experimental results are evaluated on accuracy, sensitivity and F1 score. The Adam optimizer with binary cross entropy loss function gives 97.2% accuracy with 0.98 sensitivity, 0.97 precision and 0.97 F1 score. The model achieves maximum accuracy of 88% at precision 0.97%, specificity 0.82 and F1 score 0.89 with Covid-CT dataset. The proposed model is compared with other state-of-the-art methods. The results of the proposed methods and its comparison shows acceptable level of performance on chest CT images.

Artificial Intelligence-Based System for Retinal Disease Diagnosis

Artificial Intelligence-Based System for Retinal Disease Diagnosis

Pixel-wise segmentation of cells in digitized Pap smear images

A simple and cheap way to recognize cervical cancer is using light microscopic analysis of Pap smear images. Training artificial intelligence-based systems becomes possible in this domain, e.g., to follow the European recommendation to screen negative smears to reduce false negative cases. The first step for such a process is segmenting the cells. A large and manually segmented dataset is required for this task, which can be used to train deep learning-based solutions. We describe a corresponding dataset with accurate manual segmentations for the enclosed cells. Altogether, the APACS23 (Annotated PAp smear images for Cell Segmentation 2023) dataset contains about 37 000 manually segmented cells and is separated into dedicated training and test parts, which could be used for an official benchmark of scientific investigations or a grand challenge.

Utilization of artificial intelligence in minimally invasive right adrenalectomy: recognition of anatomical landmarks with deep learning

Background The primary surgical approach for removing adrenal masses is minimally invasive adrenalectomy. Recognition of anatomical landmarks during surgery is critical for minimizing complications. Artificial intelligence-based tools can be utilized to create real-time navigation systems during laparoscopic and robotic right adrenalectomy. In this study, we aimed to develop deep learning models that can identify critical anatomical structures during minimally invasive right adrenalectomy. Methods In this experimental feasibility study, intraoperative videos of 20 patients who underwent minimally invasive right adrenalectomy in a tertiary care center between 2011 and 2023 were analyzed and used to develop an artificial intelligence-based anatomical landmark recognition system. Semantic segmentation of the liver, the inferior vena cava (IVC), and the right adrenal gland were performed. Fifty random images per patient during the dissection phase were extracted from videos. The experiments on the annotated images were performed on two state-of-the-art segmentation models named SwinUNETR and MedNeXt, which are transformer and convolutional neural network (CNN)-based segmentation architectures, respectively. Two loss function combinations, Dice-Cross Entropy and Dice-Focal Loss were experimented with for both of the models. The dataset was split into training and validation subsets with an 80:20 distribution on a patient basis in a 5-fold cross-validation approach. To introduce a sample variability to the dataset, strong-augmentation techniques were performed using intensity modifications and perspective transformations to represent different surgery environment scenarios. The models were evaluated by Dice Similarity Coefficient (DSC) and Intersection over Union (IoU) which are widely used segmentation metrics. For pixelwise classification performance, accuracy, sensitivity and specificity metrics were calculated on the validation subset. Results Out of 20 videos, 1000 images were extracted, and the anatomical landmarks (liver, IVC, and right adrenal gland) were annotated. Randomly distributed 800 images and 200 images were selected for the training and validation subsets, respectively. Our benchmark results show that the utilization of Dice-Cross Entropy Loss with the transformer-based SwinUNETR model achieved 78.37%, whereas the CNN-based MedNeXt model reached a 77.09% mDSC score. Conversely, MedNeXt reaches a higher mIoU score of 63.71% than SwinUNETR by 62.10% on a three-region prediction task. Conclusion Artificial intelligence-based systems can predict anatomical landmarks with high performance in minimally invasive right adrenalectomy. Such tools can later be used to create real-time navigation systems during surgery in the near future.

Smart Monitoring System Pada Pembudidayaan Jamur Tiram Menggunakan Metode Fuzzy Logic

Mushrooms, which are known as food commodities, when cultivated require temperatures between 22-28°C and humidity of 60-80%. Controlling these two factors is very crucial, especially when weather fluctuations occur throughout the day. As a solution, an artificial intelligence-based system was introduced to regulate temperature and humidity. The "fuzzy control" technique in artificial intelligence is an option because of its flexibility and convenience without involving complex mathematical calculations. The Fuzzy Mamdani method is one approach to "fuzzy control" which allows automatic control of temperature and humidity in mushroom cultivation areas. To apply this method, sensors are needed that can provide data to the fuzzy system. This fuzzy system works in four steps: fuzzification, rule determination, inference, and defuzzification. Based on the results of comparative tests with MATLAB software, there is a correctness level of around 26% in the measurement results.

An ethical assessment of professional opinions on concerns, chances, and limitations of the implementation of an artificial intelligence-based technology into the geriatric patient treatment and continuity of care

With the introduction of an artificial intelligence-based dashboard into the clinic, the project SURGE-Ahead responds to the importance of improving perioperative geriatric patient treatment and continuity of care. The use of artificial intelligence to process and analyze data automatically, aims at an evidence-based evaluation of the patient’s health condition and recommending treatment options. However, its development and introduction raise ethical questions. To ascertain professional perspectives on the clinical use of the dashboard, we have conducted 19 semi-structured qualitative interviews with head physicians, computer scientists, jurists, and ethicists. The application of a qualitative content analysis and thematic analysis enabled the detection of main ethical concerns, chances, and limitations. These ethical considerations were categorized: changes of the patient-physician relationship and the current social reality are expected, causing de-skilling and an active participation of the artificial intelligence. The interviewees anticipated a redistribution of human resources, time, knowledge, and experiences as well as expenses and financing. Concerns of privacy, accuracy, transparency, and explainability were stated, and an insufficient data basis, an intensifying of existing inequalities and systematic discrimination considering a fair access emphasized. Concluding, the patient-physician relationship, social reality, redistribution of resources, fair access, as well as data-related aspects of the artificial intelligence-based system could conflict with the ethical principles of autonomy, non-maleficence, beneficence, and social justice. To respond to these ethical concerns, a responsible use of the dashboard and a critical verification of therapy suggestions is mandatory, and the application limited by questions at the end of life and taking life-changing decisions.