Detection Accuracy Rate Research Articles

Machine learning-driven intelligent water quality assessment for enhanced drinking safety and real-time consumer awareness

ABSTRACT As to the sphere of smart water management and managing water Internet of Things (IoT) systems, water condition safety for drinking is very important. The proposed methodology, known as the Smart Water Consumption Monitoring System (SWCMS), is based on the WaterNet dataset acquired from a standard data repository for training the selected machine learning (ML) models. For water quality parameters such as temperature, turbidity, pH, and some chemical concentrations, the system uses real-time sensors. At the testing phase, information received from the sensors is time-stamped, and with the utilization of applicable ML approaches, potential challenges; assessment of water quality is processed. This encompasses the employment of advanced instruments for the detection of water quality with concentration on pH and other chemical values through a detection accuracy rate of over 95% on any other signs of abnormalities. This processed information is further availed with the timestamps to the consumers' mobile phones through a user interface application for real-time awareness and timely response. With the aid of timely information about their drinking water, the SWCMS increases the water safety parameter by 90% and the overall consumer awareness by 92.5%, thereby creating an effective health parameter among the public.

A pilot study on diabetes detection using handheld fundus camera and mobile app development

BackgroundDiabetes, affecting more than 500 million individuals worldwide, is the most widespread non-communicable disease, globally. The early identification and effective management of diabetes are crucial for controlling its spread. Currently, the HbA1c test is the gold standard for the detection of diabetes with high confidence. But this is an invasive, expensive pathology test. Therefore, alternative non-invasive and inexpensive methods have been proposed in the literature for the early detection of diabetes.MethodsIn this pilot study, we used a handheld fundus camera that simplifies the accessibility issue for doctors and patients in underprivileged communities, remote areas, enabling a quick and reasonably accurate diabetes diagnosis process. We invited participants from the community to share their demographic information, history of diabetes, and captured their retinal fundus images using the oDocs Nun IR handheld non-mydriatic fundus camera in a non-invasive manner (no dilation is required). Subsequently, we developed a deep learning model for early diagnosis of diabetes based on fundus image only. Moreover, we created an Android-based mobile application, DMPred, which utilizes the fundus images to predict the onset of diabetes.ResultsThe proposed model achieved an 86.4% accuracy rate in diabetes detection showing that handheld cameras can be effective and provide comparable results like tabletop cameras in the early diagnosis of diabetes. We also provide a comprehensive guideline, including necessary steps for transforming deep learning models into Android-based mobile applications for tech transfer.ConclusionsTo the best of our knowledge, this article is the first demonstration of diabetes diagnosis using handheld fundus camera and mobile app. We believe that this pilot study and the proposed tech solution will support the larger community with limited clinical facilities and enhance the accessibility of technology for diabetes detection.

Pengembangan Sistem untuk Deteksi dan Identifikasi Lokasi Kecelakaan pada Lansia sebagai Bentuk Peningkatan Keselamatan berbasis Internet of Things (IoT)

fainting, which can be fatal to their health and quality of life. The elderly population in Indonesia continues to increase, creating an urgent need for technological solutions to effectively monitor their health conditions. This study aims to design and develop an Internet of Things (IoT)-based accident detection and identification system for the elderly. The system utilizes several sensors, including an accelerometer, pulse sensor, and GPS, to monitor the physical conditions of the elderly and track their location in real-time. The research method employed is the Research and Development (R&D) method. Testing was conducted on a non-elderly subject by simulating falls with several scenarios, repeated multiple times. When the sensors detect an accident, the system automatically sends notifications to the user’s or the elderly family’s smartphone, enabling quick actions that can prevent further impacts. The results showed that the system achieved a detection accuracy rate of 91% in identifying falls and weak pulse conditions out of 30 test trials

Implementasi Internet of Things (IoT) Untuk Sistem Pemantauan Kebakaran Dini Dengan Notifikasi Telegram dan Alarm

Fire is a serious threat that can cause major losses, both material and non-material. This research aims to develop an Internet of Things (IoT) based fire monitoring system at the Tangen District Office to detect fires early. This system uses smoke, temperature and fire sensors integrated with a NodeMCU microcontroller to process data in real-time. Data from sensors is analyzed to detect signs of fire, and notifications are sent instantly via the Telegram application and accompanied by alarm activation. Tests show that the system has a detection accuracy rate of up to 95% in detecting various types of fire media, such as wood, paper and plastic, with an effective sensor distance of up to 20 cm. This system is able to reduce response time by up to 70% compared to conventional methods, increasing the readiness of officers in handling fires. It is hoped that the results of this research can minimize the risk and impact of fire, as well as significantly increase building safety

AI-Driven Open Source Intelligence in Cyber Defense: A Double-edged Sword for National Security

This study explores the dual implications of Artificial Intelligence (AI)-driven Open Source Intelligence (OSINT) in enhancing cyber defense capabilities. Using publicly available datasets, including IBM X-Force breach metrics, MITRE ATT&CK adversarial tactics, GDPR privacy violations, AI-driven phishing incidents, and case-specific data from the Colonial Pipeline ransomware attack and Russia-Ukraine conflict, the research employs multivariate regression, logistic regression, and K-Means clustering. The findings indicate that AI investments improve detection time (-0.68), accuracy (+2.09), and resolution rates (+1.55) with statistical significance (p < 0.001). However, risks associated with algorithmic opacity, weak regulatory frameworks, and reactive AI systems pose ethical and operational challenges. Clustering reveals variability in AI applications, with optimized systems achieving 95.2% detection rates and 5.5-hour response times. Recommendations include investing in scalable tools, strengthening regulations, fostering public-private collaborations, and enhancing reactive AI oversight. The results highlight AI’s transformative potential in cyber defense while emphasizing the need for ethical and regulatory alignment. Future directions include testing these models in diverse operational environments to validate effectiveness and exploring hybrid AI approaches to balance proactive and reactive capabilities, ensuring robust and adaptive defense mechanisms.

Smart Agricultural Pest Detection Using I-YOLOv10-SC: An Improved Object Detection Framework

Aiming at the problems of insufficient detection accuracy and high false detection rates of traditional pest detection models in the face of small targets and incomplete targets, this study proposes an improved target detection network, I-YOLOv10-SC. The network leverages Space-to-Depth Convolution to enhance its capability in detecting small insect targets. The Convolutional Block Attention Module is employed to improve feature representation and attention focus. Additionally, Shape Weights and Scale Adjustment Factors are introduced to optimize the loss function. The experimental results show that compared with the original YOLOv10, the model generated by the improved algorithm improves the accuracy by 5.88 percentage points, the recall rate by 6.67 percentage points, the balance score by 6.27 percentage points, the mAP value by 4.26 percentage points, the bounding box loss by 18.75%, the classification loss by 27.27%, and the feature point loss by 8%. The model oscillation has also been significantly improved. The enhanced I-YOLOv10-SC network effectively addresses the challenges of detecting small and incomplete insect targets in tea plantations, offering high precision and recall rates, thus providing a solid technical foundation for intelligent pest monitoring and precise prevention in smart tea gardens.

A New Approach to COVID-19 Detection Using Alexnet From Chest CT Images

Background: At the beginning of 2020, the pneumonia-like COVID-19 virus spread rapidly worldwide. With the emergence of this dangerous virus, work, and daily life have become very difficult. To control this virus, all the centers are closed and quarantined by the government and the countries of the world. Every day, many people from all over the world die due to COVID-19. Many efforts are being made in all fields to diagnose and treat people infected with this virus. For this reason, many researchers started working on identifying this virus and its types. The Scientifics, in computer science, did not sit idle either. Method: In some studies, different image processing methods and algorithms have been used to extract the edge features of the Computed Tomography (CT) images of the lung. In this clinical-computerized study, lung CT images of non-infected and infected people from different hospitals in Lorestan province were used. This collection has 90 stereotypes of images in jpg format of CT scans of people's lungs, each file has more than 200 images from different angles of lung imaging. The preprocessing methods were the first step of the research. In the second phase, edge detection was applied to the dataset to get the highest accuracy rate. Consequently, a classification Convolutional Neural Network (CNN)-AlexNet architecture was used to reach the final aim. Results: The results show that the average accuracy rate of image edge extraction with a threshold value of 0.1 is 93% and the accuracy rate of AlexNet architecture classification is 100%. The proposed method helps physicians to improve disease diagnosis from lung CT images to achieve a more accurate detection rate. Conclusion: This study shows that the CNN-AlexNet architecture effectively increases the diagnosis accuracy rate than the other methods. It is suggested that educational programs for researchers in the field of disease detection from radiology images be provided and that the effectiveness of different types of deep learning methods be compared in future studies.

CoralMatrix: A Scalable and Robust Secure Framework for Enhancing IoT Cybersecurity

In the current age of digital transformation, the Internet of Things (IoT) has revolutionized everyday objects, and IoT gateways play a critical role in managing the data flow within these networks. However, the dynamic and extensive nature of IoT networks presents significant cybersecurity challenges that necessitate the development of adaptive security systems to protect against evolving threats. This paper proposes the CoralMatrix Security framework, a novel approach to IoT cybersecurity that employs advanced machine learning algorithms. This framework incorporates the AdaptiNet Intelligence Model, which integrates deep learning and reinforcement learning for effective real-time threat detection and response. To comprehensively evaluate the performance of the framework, this study utilized the N-BaIoT dataset, facilitating a quantitative analysis that provided valuable insights into the model's capabilities. The results of the analysis demonstrate the robustness of the CoralMatrix Security framework across various dimensions of IoT cybersecurity. Notably, the framework achieved a high detection accuracy rate of approximately 83.33%, highlighting its effectiveness in identifying and responding to cybersecurity threats in real-time. Additionally, the research examined the framework's scalability, adaptability, resource efficiency, and robustness against diverse cyber-attack types, all of which were quantitatively assessed to provide a comprehensive understanding of its capabilities. This study suggests future work to optimize the framework for larger IoT networks and adapt continuously to emerging threats, aiming to expand its application across diverse IoT scenarios. With its proposed algorithms, the CoralMatrix Security framework has emerged as a promising, efficient, effective, and scalable solution for the dynamic challenges of IoT Cyber Security.

GGSYOLOv5: Flame recognition method in complex scenes based on deep learning.

The continuous development of the field of artificial intelligence, not only makes people's lives more convenient but also plays a role in the supervision and protection of people's lives and property safety. News of the fire is not uncommon, and fire has become the biggest hidden danger threatening the safety of public life and property. In this paper, a deep learning-based flame recognition method for complex scenes, GGSYOLOv5, is proposed. Firstly, a global attention mechanism (GAM) was added to the CSP1 module in the backbone part of the YOLOv5 network, and then a parameterless attention mechanism was added to the feature fusion part. Finally, packet random convolution (GSConv) was used to replace the original convolution at the output end. A large number of experiments show that the detection accuracy rate is 4.46% higher than the original algorithm, and the FPS is as high as 64.3, which can meet the real-time requirements. Moreover, the algorithm is deployed in the Jetson Nano embedded development board to build the flame detection system.

Optimizing accuracy rate of Detection of COVID-19: A Machine Learning approach

COVID-19, one of the most highly transmissible diseases in the twenty-first century, has had a profound impact on global lifestyles. Recently, the medical industry has increasingly relied on machine learning, which shows promise in anticipating the presence of COVID-19. By using machine learning techniques, test result turnaround time can be accelerated, and medical personnel can promptly attend to patients' needs. These algorithms analyze various attributes to classify COVID patients and predict their likelihood of contracting the disease. This study aims to utilize X-ray images processed by machine learning algorithms to predict the occurrence of COVID-19 and enhance its detection rate. The paper outlines two strategies employing machine learning techniques: one for predicting the likelihood of infection and the other for identifying positive cases. Different machine learning algorithms, such as decision trees, logistic regression, support vector machines, naive Bayes, and artificial neural networks, were employed. The simulation results reveal that the artificial neural networks model outperforms other methods in terms of accuracy rate.

Accurate localization of indoor high similarity scenes using visual slam combined with loop closure detection algorithm.

Accurate localization is a critical technology for the application of intelligent robots and automation systems in complex indoor environments. Traditional visual SLAM (Simultaneous Localization and Mapping) techniques often face challenges with localization accuracy in high similarity scenes. To address this issue, this paper proposes an improved visual SLAM loop closure detection algorithm that integrates deep learning techniques. Using the TUM f3 loh, Lip6 Indoor, and Bicocca Indoor datasets as experimental bases, a detailed comparison of the proposed algorithm against other methods was conducted across various evaluation metrics. The experimental results show that the proposed loop closure detection algorithm significantly outperforms traditional methods in terms of localization accuracy in high similarity scenes. Specifically, the detection accuracy rates for the TUM f3 loh, Lip6 Indoor, and Bicocca Indoor datasets were 66.67%, 72.72%, and 80.00%, respectively, representing an approximate 18% improvement over the average accuracy of ORB-SLAM2. Additionally, the proposed method demonstrated excellent performance in trajectory error, with a root mean square error (RMSE) of just 0.0816m on the Bicocca Indoor dataset, significantly lower than the 0.1341m RMSE of ORB-SLAM2. Furthermore, improvements in feature extraction and matching mechanisms greatly reduced the occurrence of mismatches, enhancing the system's adaptability for more accurate localization and navigation in complex indoor environments. The proposed method effectively enhances localization accuracy and system practicality in visually similar indoor environments, offering a new direction for the development of visual SLAM technology and holding significant application potential in intelligent robots and indoor navigation systems.

Blending-Based Ensemble Learning Low-Voltage Station Area Theft Detection

In order to improve the efficiency of electricity theft detection, the power theft detection area and users should be better integrated, we proposed a Blending ensemble learning electricity theft detection model based on the Base Learner Selection Strategy (BLSS). Firstly, the adaptive synthetic (ADASYN) sampling method is used to process the unbalanced power consumption data, and the sample distribution of training data is balanced. Secondly, the BLSS selection method is used to screen the optimal base learner combination and construct the Blending ensemble learning model. Then, based on the historical data, the model makes a short-term prediction of the power consumption of the station area the next day, and focuses on the verification of the suspected energy-stealing station area where the Root Mean Square Percentage Error (RSPE) exceeds the threshold, so as to lock in the potential energy stealing users. Finally, through the comparison and verification of real examples, the search scope for electricity theft inspections was reduced by 79.17%, greatly improving the detection efficiency of the power supply company. At the same time, the model’s electricity theft detection and recognition accuracy rate can be as high as 97.50%. The Blending ensemble learning electricity stealing detection model based on the BLSS base learner selection method has strong electricity stealing detection and recognition ability.

LSTM-Enabled Big Data Security Framework Integrating Kerberos Authentication on AWS for Robust Cloud Protection

In today’s digital era, safeguarding cloud environments has become paramount due to the increasing complexity and volume of cyber threats. This research presents an innovative LSTM-enabled Big Data Security Framework that integrates the Kerberos Authentication Protocol on the Amazon Web Services (AWS) cloud platform. The proposed framework leverages the scalability and processing capabilities of Hadoop to manage and analyze large-scale data while ensuring robust security through Kerberos. The Long Short-Term Memory (LSTM) model is deployed to predict and detect anomalies in authentication requests, enhancing the framework's ability to mitigate unauthorized access. By combining LSTM’s predictive analytics with Kerberos’s ticket-based authentication, the framework ensures a multi-layered security architecture capable of identifying threats in real-time. Hadoop’s distributed computing environment further enables efficient processing of security logs and user behavior data, making it ideal for large-scale enterprise applications. A comprehensive evaluation of the framework demonstrates its efficacy in reducing false positives and achieving a high detection accuracy rate for potential threats. Key metrics, including precision, recall, and F1 score, validate the robustness of the approach. Additionally, the framework showcases superior scalability and adaptability to dynamic workloads in the AWS environment, ensuring consistent performance under varying data loads. This research contributes to the advancement of secure cloud computing by bridging the gap between traditional authentication methods and machine learning-driven threat detection. The integration of Kerberos with Big Data analytics and LSTM-based models establishes a foundation for future work in securing large-scale cloud ecosystems.

Artificial-Weld-Crack Detection Network, YOLOv6-NW, Based on Target Recognition Technology.

Aiming at the problems of scarce datasets and the low identification accuracy faced in the field of weld-crack detection, this paper proposes an artificial-weld-crack preparation method based on the doping of dissimilar metal particles to augment the number of samples of weld-crack defects. Meanwhile, data augmentation methods such as random cropping, scaling and Mosaic are combined to further enhance the richness of the samples, so as to provide strong data support for the proposed weld-crack-defect detection model. Given the limitations of storage and computational resources in industrial application scenarios, this paper designs the lightweight detection network YOLOv6-NW. It is achieved by optimizing the YOLOv6-N model for width and depth compression to efficiently identify and locate weld-crack defects. The experimental results demonstrate that YOLOv6-NW significantly outperforms YOLOv5 in terms of both model detection performance and model size. Compared to YOLOv6-N, the number of model parameters in YOLOv6-NW is only 16% of that in YOLOv6-N, yet its model detection accuracy and recall rate remain on a comparable level with YOLOv6-N. Additionally, the precision of crack detection by YOLOv6-NW under low-resolution or low-illumination conditions remains above 0.9.

Artificial intelligence for dental implant classification and peri-implant pathology identification in 2D radiographs: A systematic review.

This systematic review aimed to summarize and evaluate the available information regarding the performance of artificial intelligence on dental implant classification and peri-implant pathology identification in 2D radiographs. Electronic databases (Medline, Embase, and Cochrane) were searched up to September 2024 for relevant observational studies and both randomized and controlled clinical trials. The search was limited to studies published in English from the last 7 years. Two reviewers independently conducted both study selection and data extraction. Risk of bias assessment was also performed individually by both operators using the Quality Assessment Diagnostic Tool (QUADAS-2). Of the 1,465 records identified, 29 references were selected to perform qualitative analysis. The study characteristics were tabulated in a self-designed table. QUADAS-2 tool identified 10 and 15 studies to respectively have a high and an unclear risk of bias, while only four were categorized as low risk of bias. Overall, accuracy rates for dental implant classification ranged from 67 % to 99 %. Peri-implant pathology identification showed results with accuracy detection rates over 78,6 %. While AI-based models, particularly convolutional neural networks, have shown high accuracy in dental implant classification and peri-implant pathology detection, several limitations must be addressed before widespread clinical application. More advanced AI techniques, such as Federated Learning should be explored to improve the generalizability and efficiency of these models in clinical practice. AI-based models offer can and clinicians to accurately classify unknown dental implants and enable early detection of peri-implantitis, improving patient outcomes and streamline treatment planning.

A Composite Pulse Excitation Technique for Air-Coupled Ultrasonic Detection of Defects in Wood.

To overcome the problems of the low signal-to-noise ratio and poor performance of wood ultrasonic images caused by ring-down vibrations during the ultrasonic quality detection of wood, a composite pulse excitation technique using a wood air-coupled ultrasonic detection system is proposed. Through a mathematical analysis of the output of the ultrasonic transducer, the conditions necessary for implementing composite pulse excitation were analyzed and established, and its feasibility was verified through COMSOL simulations. Firstly, wood samples with knot and pit defects were used as experimental samples. We refined the parameters for the composite pulse excitation technique by conducting A-scan measurements on both defective and non-defective areas of the samples. Moreover, two stepper motors were employed to control the path for C-scan imaging to detect wood defects. The experiment results showed that the composite pulse excitation technique significantly enhanced the precision of nondestructive ultrasonic testing for wood defects compared to the traditional single-pulse excitation method. This technique successfully achieved precise detection and location of pit defects, with a detection accuracy rate of 90% for knot defects.

Real-time Mask Detection with YOLOv3 and Ensemble Residual Networks

The proposed system introduced an advanced face mask detections framework leveraging Adaptively YOLOv3 with Hybrid Atrous Convolution-depend Face Detector, optimized through an Ensembles residual Learning Network. This approach aims to enhance the accuracy level and efficacy of face mask detection in real-time situation. By integrating of the adaptive capability of YOLOv3 on the spatial benefits of atrous convolution defined, the system effectively captured varying of facial features and masks placements. The ensemble residual learning further refined detection by amalgamating of multiple learning models, by reducing false positives values and negatives. This hybrid model is meticulous optimized to maintaining of higher detection precision rate and recall, for ensuring robust performance even over diverse and complex conditions. The system’s efficacy will underscored by reduces the inference time and enhanced processing throughput rate, by making it highly suitable for large-scale deployment on public safety applications. By rigorously testing phase, the proposed system demonstrated significant improvements in detection accuracy rate, inference speed, and overall reliability, positioning it will be a pivotal tool in enforcing healthy safety protocols on various public and private settings.

Detection of Defects in Warp Knitted Fabrics Based on Local Feature Scale Adaptive Comparison

In order to improve the accuracy and detection effect of fabric defect detection, a fabric defect detection method based on local similarity comparison is proposed in this paper. This method first takes each pixel in the image as the central pixel, selects a specific window as the region size, and then uses the similarity between the central region and the surrounding neighborhood to find the neighborhood most similar to the central region to complete the estimation of the central pixel. Finally, the target image is obtained by the principle of background difference, so as to detect fabric defects. The results show that this method is superior to the traditional detection method, which can not only detect the defect image under the complex background, but also have good detection results for the fabric defect image under the influence of different organization and lighting factors. The detection accuracy rate under factory conditions can reach 98.45%, which has a high applicability and detection rate, and also demonstrates certain anti-interference performance.

A fuzzy based chicken swarm optimization algorithm for efficient fault node detection in Wireless Sensor Networks

Wireless Sensor Networks (WSN) are built with miniature sensor nodes (SN), which are deployed into the geographical location being sensed to monitor environmental conditions, which transfer the sensed physical information to the base station for further processing. The sensor nodes frequently experience node failure as a result of their hostile deployment and resource limitations. In WSN, node failure can cause a number of issues, namely Wireless Sensor Networks topology changes, broken communications links, disconnected portions of the network, and data transmission errors. An important concern of WSN is the detecting, diagnosing and recovering of sensor node failures. In the course of this effort, an effective strategy for sensor node failure detection algorithm using the Poisson Hidden Markov Model (PHMM) and the Fuzzy-based Chicken Swarm Optimization (F-CSO) is proposed for efficient detection of sensor node faults in the WSN. The proposed work offers optimal false alarm, false positive, energy consumption, detection accuracy, network lifetime, and least delay rates. Moreover, the F-CSO provides improved localization to locate the defective sensor nodes that are present in the WSN. The proposed work is implemented in the NS2 simulator with realistic simulation parameters, and the simulation results demonstrate that the proposed work is more effective in terms of 89.5% fault detection accuracy, 19.53% throughput, 8.43% energy consumption with minimum delay and less false positive rate when it is compared with other existing state-of-art systems.

An algorithm for lane detection based on RIME optimization and optimal threshold

In order to address the challenges of low lane line detection rates caused by complex road conditions,we propose a novel algorithm that integrates frost and ice optimisation with optimal thresholding. A pre-processing model based on Retinex theory is used to reduce noise and preserve grey scale detail. The optimal OTSU threshold is determined for segmentation, which is enhanced by tent mapping. To further enhance the precision of the detection process, the binarized image is transformed into a bird’s-eye view, and the lane line pixel features are identified through the use of an adaptive sliding window. Ultimately, the RANSAC algorithm is utilized in conjunction with a parabolic model for lane line fitting. The experimental results demonstrate that, in comparison to similar image segmentation algorithms, the proposed method exhibits a notable advantage in terms of threshold calculation error and computational efficiency. Moreover, in comparison to analogous line detection algorithms, the detection accuracy rate reaches 93.87%, effectively reducing the impact of interference factors and demonstrating remarkable robustness that surpasses the traditional Hough Transform, which has an accuracy of 43.2%, and sliding window and Hough transform, with an accuracy of 89.16%. The code of our research work is publicly available at: https://github.com/zx2000430/rime.