Performance Of Detection System Research Articles

Comparative Evaluation of YOLO Models on an African Road Obstacles Dataset for Real-Time Obstacle Detection

Public datasets are used to train road obstacle detection models, but they lack diverse and rare object classes found on African roads, negatively impacting the performance of models trained on them. Although attempts have been made to create custom datasets to train road obstacle detection models, they lack the unique challenges posed by African wildlife and livestock commonly encountered on African roads. This leads to poor performance of road obstacle detection systems in the African context. This study presents a custom dataset with rare African object classes and compares the performance of three YOLO models on it using mean Average Precision (mAP). The images were collected from multiple sources to ensure a wide range of scenarios. Offline data augmentation was applied to increase dataset diversity and simulate real-world road scenarios. The models were trained and evaluated, with YOLOv5 demonstrating superiority over the other two models, with an object detection accuracy of 94.68% mAP at an Intersection over Union (IoU) threshold of 0.5 with data augmentation. Offline data augmentation significantly improved all models' object detection accuracy, especially for YOLOv3. The results reveal the effectiveness of the custom dataset and highlight the importance of data augmentation in improving object detection.

Towards Transparent AI in Medicine: ECG-Based Arrhythmia Detection with Explainable Deep Learning

Cardiovascular diseases are the leading cause of death globally, highlighting the need for accurate diagnostic tools. To address this issue, we introduce a novel approach for arrhythmia detection based on electrocardiogram (ECG) that incorporates explainable artificial intelligence through three key methods. First, we developed an enhanced R peak detection method that integrates domain-specific knowledge into the ECG, improving peak identification accuracy by accounting for the characteristic features of R peaks. Second, we proposed an arrhythmia classification method utilizing a modified convolutional neural network (CNN) architecture with additional convolutional and batch normalization layers. This model processes a triad of cardio cycles—the preceding, current, and following cycles—to capture temporal dependencies and hidden features related to arrhythmias. Third, we implemented an interpretation method that explains CNN’s decisions using clinically relevant features, making the results understandable to clinicians. Using the MIT-BIH database, our approach achieved an accuracy of 99.43%, with F1-scores approaching 100% for major arrhythmia classes. The integration of these methods enhances both the performance and transparency of arrhythmia detection systems.

Enhancing malware detection through self-union feature selection using gray wolf optimizer

This research explores the impact of malware on the digital world and presents an innovative system to detect and classify malware instances. The suggested system combines a random forest (RF) classifier and gray wolf optimizer (GWO) to identify and detect malware effectively. Therefore, the suggested system is called RFGWO-Mal. The RFGWO-Mal system employs the GWO for feature selection in binary and multiclass classification scenarios. Then, the RFGWO-Mal system uses a novel self-union feature selection approach, combining features from different subsets of binary and multiclass classification extracted using the GWO optimizer. The RF classifier is then applied for classifying malware and benign data. The comprehensive Obfuscated-MalMem2022 dataset was utilized to evaluate the suggested RFGWO-Mal system, which has been implanted using Python. The suggested RFGWO-Mal system achieves significantly improved results using the novel self-union feature selection approach. Specifically, the RFGWO-Mal system achieves an outstanding accuracy of 99.95% in binary classification and maintains a high accuracy of 86.57% with multiclass classification. The findings underscore the achievement of a self-union feature selection approach in enhancing the performance of malware detection systems, providing a valuable contribution to cybersecurity.

A novel boundary adaptive oversampling approach for intrusion detection

Managing unbalanced datasets is a significant challenge in intrusion detection, since uncommon assaults are often obscured by the bulk of regular network traffic. In order to mitigate the effects of class imbalance and improve intrusion detection system (IDS) performance, it is necessary to use a variety of imbalanced learning algorithms. Methods of data augmentation such as adaptive synthetic sampling (ADASYN) and synthetic minority oversampling technique (SMOTE) are useful in addressing class imbalance. This paper introduces a novel technique to data resampling where decision tree-generated decision boundaries are used to conduct ADASYN on complicated and unusual samples. When this method’s efficacy was evaluated using the standard NSL-KDD dataset, the accuracy of the unusual class u2r was increased to 42% and, for r2l it was improved to 83%, respectively. The UNSW-NB 15 dataset has been used for further validation of the method, and its statistical significance has been asserted by comparing the suggested method to other oversampling techniques.

Electrochemical Determination of 17‐α‐Ethinylestradiol on a Graphene Quantum Dots and Carbon‐Black‐Modified Glassy Carbon Electrode

A simple and inexpensive electrochemical sensor based on a glassy carbon electrode (GCE) modified with graphene quantum dots and carbon black nanoparticles (dihydrogen phosphate polyelectrolyte) is applied to determination of the emerging contaminant the estrogen 17‐α‐ethinylestradiol (EE2). The combination of this nanocomposite with the GCE has not yet been explored as an electrochemical sensor. Combined, these materials create a synergy that enhances the overall performance of the oxidative detection system, resulting in a more efficient and accurate detection. The analytical curve presents a linear dynamic range from 0.998 to 10.0 µmol L−1, with a detection limit of 0.998 µmol L−1. Addition and recovery studies are carried out on a lake water sample, showing a recovery of 92.3%. The accuracy of the developed method is also evaluated by determining EE2 in pharmaceutical formulation samples. The obtained results are in statistical agreement with those obtained using high‐performance liquid chromatography–diode array detector at a confidence level of 95%. Therefore, the electrochemical sensor developed presents a fast construction procedure and the electroanalytical method for EE2 determination proves to be precise and accurate, with low consumption of reagents and a low relative cost.

Network Security Intrusion Detection Methods Combining Optimization Algorithms and Neural Networks

Cyber-attacks are becoming increasingly common and sophisticated, and the security of net-works is a pressing concern for companies everywhere. To spot and stop attempts to access network resources without authorization, intrusion. There is, however, a problem that many traditional IDS methods can generate a lot of false alarms. This means that it misidentifies safe activity as a threat and is not readily accepted by security teams for which real issues. Scalability and resistance to evolving threats a hybrid approach of a neural network combined with an adaptive algorithm was used in this paper focuses on improvement the performance and accuracy of the intrusion detection system proposed by us. Combining genetic algorithms and particle swarm optimization with neural networks using a framework optimized for comprehensive performance is present in this tutorial. More to the point, parameters and training procedures for Deep learning models in intrusion detection tasks. The objective of this research paper model is to make a false alarm the rate should be decreased, search accuracy increased and in real-time network environments, the system should adapt easily. Experimental results show that the combination of optimization algorithms and neural networks outperforms traditional IDS methods.

Hybrid bagging and boosting with SHAP based feature selection for enhanced predictive modeling in intrusion detection systems

The novelty and growing sophistication of cyber threats mean that high accuracy and interpretable machine learning models are needed more than ever before for Intrusion Detection and Prevention Systems. This study aims to solve this challenge by applying Explainable AI techniques, including Shapley Additive explanations feature selection, to improve model performance, robustness, and transparency. The method systematically employs different classifiers and proposes a new hybrid method called Hybrid Bagging-Boosting and Boosting on Residuals. Then, performance is taken in four steps: the multistep evaluation of hybrid ensemble learning methods for binary classification and fine-tuning of performance; feature selection using Shapley Additive explanations values retraining the hybrid model for better performance and reducing overfitting; the generalization of the proposed model for multiclass classification; and the evaluation using standard information metrics such as accuracy, precision, recall, and F1-score. Key results indicate that the proposed methods outperform state-of-the-art algorithms, achieving a peak accuracy of 98.47% and an F1 score of 96.19%. These improvements stem from advanced feature selection and resampling techniques, enhancing model accuracy and balancing precision and recall. Integrating Shapley Additive explanations-based feature selection with hybrid ensemble methods significantly boosts the predictive and explanatory power of Intrusion Detection and Prevention Systems, addressing common pitfalls in traditional cybersecurity models. This study paves the way for further research on statistical innovations to enhance Intrusion Detection and Prevention Systems performance.

Optimization of Imaging Reconnaissance Systems Using Super-Resolution: Efficiency Analysis in Interference Conditions.

Image reconnaissance systems are critical in modern applications, where the ability to accurately detect and identify objects is crucial. However, distortions in real-world operational conditions, such as motion blur, noise, and compression artifacts, often degrade image quality, affecting the performance of detection systems. This study analyzed the impact of super-resolution (SR) technology, in particular, the Real-ESRGAN model, on the performance of a detection model under disturbed conditions. The methodology involved training and evaluating the Faster R-CNN detection model with original and modified data sets. The results showed that SR significantly improved detection precision and mAP in most interference scenarios. These findings underscore SR's potential to improve imaging systems while identifying key areas for future development and further research.

Deep Reinforcement Learning-Based Adversarial Attack and Defense in Industrial Control Systems

Adversarial attacks targeting industrial control systems, such as the Maroochy wastewater system attack and the Stuxnet worm attack, have caused significant damage to related facilities. To enhance the security of industrial control systems, recent research has focused on not only improving the accuracy of intrusion detection systems but also developing techniques to generate adversarial attacks for evaluating the performance of these intrusion detection systems. In this paper, we propose a deep reinforcement learning-based adversarial attack framework designed to perform man-in-the-middle attacks on industrial control systems. Unlike existing adversarial attack methods, our proposed adversarial attack scheme learns to evade detection by the intrusion detection system based on both the impact on the target and the detection results from previous attacks. For performance evaluation, we utilized a dataset collected from the secure water treatment (SWaT) testbed. The simulation results demonstrated that our adversarial attack scheme successfully executed man-in-the-middle attacks while evading detection by the rule-based intrusion detection system, which was defined based on the analysis of the SWaT dataset.

Building robust malware detection through conditional Generative Adversarial Network-based data augmentation

Malware detection is essential in cybersecurity, yet its accuracy is often compromised by class imbalance and limited labeled data. This study leverages conditional Generative Adversarial Networks (cGANs) to generate synthetic malware samples, addressing these challenges by augmenting the minority class. The cGAN model generates realistic malware samples conditioned on class labels, balancing the dataset without altering the benign class. Applied to the CICMalDroid2020 dataset, the augmented data is used to train a LightGBM model, leading to improved detection accuracy, particularly for underrepresented malware classes. The results demonstrate the efficacy of cGANs as a robust data augmentation tool, enhancing the performance and reliability of machine learning-based malware detection systems.

Mid-infrared quasi-distributed carbon monoxide gas sensing based on QEPAS and hollow waveguide

In this paper, a mid-infrared quasi-distributed carbon monoxide (CO) gas sensing based on quartz-enhanced photoacoustic spectroscopy (QEPAS) and hollow waveguide (HWG) was proposed for the first time. Three micropores with a diameter of 200 μm were developed at three different locations of a HWG with a length of 30 cm. Three customized low-frequency quartz tuning forks (QTFs) with a resonant frequency of 8.7 kHz were used to detect the photoacoustic signals generated at the micropores to achieve quasi-distributed measurements of CO, which provides a new idea for monitoring the leakage of gas pipelines and so on. In order to improve the performance of the gas detection system, the strongest absorption line with CO located at 2179.77 cm−1 (4.58 µm) was selected as the target absorption line, and a quantum cascade laser (QCL) was used as the excitation source to achieve the detection of CO in the mid infrared spectral region. The experimental results show that all three QTFs have excellent concentration linear response to CO, and the minimum detection limit (MDL) of the three QTFs to CO were 2.40 ppm, 2.59 ppm, and 2.34 ppm, respectively. Finally, the experiment tested the response ability of three QTFs to different concentrations of CO at the same time. The results showed that for micropores with different concentrations, all three QTFs can detect their corresponding concentrations, which proves that the sensor can achieve quasi-distributed measurement.

MSDFEN: Multi-scale dynamic feature extraction network for pathological voice detection

With the rapid development of deep learning methods, their application in pathological voice detection has become increasingly extensive, yielding promising results. However, most deep learning methods used in pathological voice detection employ network architectures where all constituent modules are static, performing the same operations on all inputs. This significantly limits the model’s adaptive capacity and generalization ability and restricts further improvement in model performance. To address this issue, this paper proposes a novel pathological voice detection system called the Multi-Scale Dynamic Feature Extraction Network (MSDFEN), designed to enhance the performance and adaptive capability of pathological voice detection systems. In the MSDFEN model, sinc filter banks combined with a channel attention mechanism were employed for the preprocessing of vocal signals, effectively capturing the high-frequency transitions characteristic of pathological voices. Furthermore, dynamic blocks, consisting of multiple dynamic components, were designed and integrated into a multi-scale convolutional neural network, significantly enhancing the network’s dynamic performance and enriching the features obtained through multi-scale fusion. Comparative experiments and ablation studies were conducted using three internationally recognized pathological voice detection databases: MEEI, SVD, and HUPA. the proposed model achieved recognition accuracies of 0.9883, 0.7424, and 0.8409 in these databases, and other parameters also yielded satisfactory results. Experimental results indicate that the proposed method exhibits excellent adaptive and generalization capabilities in pathological voice detection.

Fall Detection in Q-eBall: Enhancing Gameplay Through Sensor-Based Solutions

The field of physically interactive electronic games is rapidly evolving, driven by the fact that it combines the benefits of physical activities and the attractiveness of electronic games, as well as advancements in sensor technologies. In this paper, a new game was introduced, which is a special version of Bubble Soccer, which we named Q-eBall. It creates a dynamic and engaging experience by combining simulation and physical interactions. Q-eBall is equipped with a fall detection system, which uses an embedded electronic circuit integrated with an accelerometer, a gyroscopic, and a pressure sensor. An evaluation of the performance of the fall detection system in Q-eBall is presented, exploring its technical details and showing its performance. The system captures the data of players’ movement in real-time and transmits it to the game controller, which can accurately identify when a player falls. The automated fall detection process enables the game to take the required actions, such as transferring possession of the visual ball or applying fouls, without the need for manual intervention. Offline experiments were conducted to assess the performance of four machine learning models, which were K-Nearest Neighbors (KNNs), Support Vector Machine (SVM), Random Forest (RF), and Long Short-Term Memory (LSTM), for falls detection. The results showed that the inclusion of pressure sensor data significantly improved the performance of all models, with the SVM and LSTM models reaching 100% on all metrics (accuracy, precision, recall, and F1-score). To validate the offline results, a real-time experiment was performed using the pre-trained SVM model, which successfully recorded all 150 falls without any false positives or false negatives. These findings prove the reliability and effectiveness of the Q-eBall fall detection system in real time.

Hyperparameter Tuning of EfficientNet Method for Optimization of Malaria Detection System Based on Red Blood Cell Image

Nowadays, malaria has become an infectious disease with a high mortality rate. One way to detect malaria is through microscopic examination of blood preparations, which is done by experts and often takes a long time. With the development of deep learning technology, the observation of blood cell images infected with malaria can be more easily done. Therefore, this study proposes a red blood cell image-based malaria detection system using the EfficientNet method with hyperparameter tuning. There are three parameters which are learning rate, activation function, and optimiser. The learning rate used is 0.01 and 0.001, while the activation functions used are ReLU and Tanh. In addition, the optimisers used include Adam, SGD, and RMSProp. In the implementation, the cell image dataset from the NIH repository was pre-processed such as resizing, rotating, filtering, and data augmentation. Then the data is trained and tested on several EfficientNet models (B0, B1, B3, B5, and B7) and their performance values are compared. Based on the test results, EfficientNet-B5 and B7 models showed the best performance compared to other EfficientNet models. The most optimal system test results are when the EfficientNet B5 model is used with a learning rate of 0.001, ReLU activation function, and Adam optimiser, with values of 97.69% (accuracy), 98.36% (precision), and 97.03% (recall). This research has proven that proper model selection and hyperparameter tuning can maximise the performance of cell image-based malaria detection system. The development of this EfficientNet-based diagnostic method is more sensitive and specific in malaria detection using RBCs.

Differential Analysis of Emergency Vehicle Detection in Urban Traffic : A Systematic Review

The differential analysis of emergency vehicle detection in urban traffic is crucial for improving response times and reducing traffic-related delays during emergencies. This systematic review aims to analyze various methods and technologies, such as acoustic, visual, and sensor-based systems, used for detecting emergency vehicles in complex urban environments. The motivation behind this study is the growing need for more efficient traffic management systems that prioritize emergency vehicles, minimizing delays caused by congestion. However, limitations include the inconsistent performance of detection systems in varying weather, lighting, and noise conditions, as well as integration challenges with existing infrastructure. The objective is to evaluate current detection methods, identify their limitations, and propose potential improvements to enhance the accuracy and reliability of emergency vehicle detection in urban traffic systems.

Performance verification of Siemens Atellica DL IM1600 automatic immune analyzer detection system: A-TPO and A-TG.

To study the performance of the Siemens Atellica DL IM1600 automatic immune analyzer detection system for thyroid peroxidase antibodies (A-TPO) and anti-thyroglobulin antibodies (A-TG). Perform performance verification based on CNAS and CLSI related documents, including precision, accuracy, reference interval, and linearity. In precision validation, intra-batch imprecision coefficient of variation values of A-TG and A-TPO were 3.60%, 5.40%, and 3.20%, 2.20%, inter-batch imprecision coefficient of variation values were 5.40%, 4.40%, and 5.00%, 2.50%, all within the specified range. In the accuracy verification, the A-TG comparison values were -10.94%, -1.49%, -1.14%, -7.78%, -3.28%, and the A-TPO values were 21.20%, 6.42%, 14.63%, 12.40%, and 6.55%, The absolute values were all lower than the comparison requirements. The reference interval verifies that the A-TG and A-TPO test results of health patients were within the normal reference interval of 0 to 60 U/mL. In the linear range validation, A-TG linear regression y = 1.0145x - 10.093, correlation coefficient R2 = 0.9963 > 0.95, A-TPO linear regression y = 0.9985x - 18.172, correlation coefficient R2 = 0.9954 > 0.95, indicating linear linearity. The performance verification of Siemens Atellica DL IM1600 automatic immune analyzer detection system for A-TPO and A-TG was satisfactory, suitable for clinical application.

Performance of free-space optical coherent detection systems under imprecise channels with nonzero boresight pointing errors

Performance of free-space optical coherent detection systems under imprecise channels with nonzero boresight pointing errors

In situ monitoring of defects in steel structures using a robot‐assisted ultrasonic inspection technique

AbstractIncidents in extreme environments can bring unprecedented consequences that would endanger the lives of many humans. Real‐time and early detection of cracks and defects in the steel used for the construction of industrial sites can bring many benefits to remote operators and site managers. Although different methods and systems have been proposed in the past, they are not suitable for real‐time fault detection or long‐term operation in harsh environments. Therefore, this paper proposes a low‐power robotic platform with a magnetic actuator mechanism which is capable of wireless inspection of steel structures using the ultrasonic method. The proposed magnetic motion uses the inertia force generated by the piston vibration and the difference in frictional force during movement. The paper evaluates the performance of the steel structure defect detection system from four different perspectives: sensing principle, wireless communication network, driving part, and power supply.

Development of a silicon carbide radiation detection system and experimentation of the system performance

Silicon carbide (SiC) detectors have excellent radiation detection capabilities for various radiation particles, including high energy resolution, fast response times, and good radiation resistance. A SiC radiation detection system was developed to measure the neutron fluence rate and the γ-ray dose rate in high intensity radiation fields. The system was composed of two SiC detectors, a temperature monitor, two preamplifiers for each SiC detector, a data acquisition unit with two signal channels, three pairs of communication devices, and an application software to analyze and visualize the measurement data. The two SiC detectors were fabricated based on two kinds of 4H-SiC diodes and used to respectively respond to neutrons and γ-rays. Repeated experiments showed that the two SiC detectors of the system can respond to α-particles, neutrons, and γ-rays. To verify the performance of the SiC detection system, including the response linearity of the neutron fluence rate, the measurement range of the γ-ray dose rate, and the radiation resistance of the SiC radiation detectors, the system was tested in multiple neutron and γ-ray fields. The tests results show the system can measure the neutron fluence rate from 5.64 × 10 2 cm−2 s−1 to 1.03 × 10 5 cm−2 s−1 with excellent linearity response, and the γ-ray dose rate from 0.005 Gy/h to 20 Gy/h. Furthermore, the SiC detectors demonstrated good radiation resistance. The neutron and γ-ray radiation field can still be measured stably by the system after exposure to neutron fluence of 1.07 × 10 14 cm−2 and γ-ray dose of 3.52 × 10 4 Gy. This work is the preliminary research to continue the exploration how to measure the n/γ hybrid fields accurately using SiC detectors considering the different energy of neutrons.

Scintillation light in SBND: simulation, reconstruction, and expected performance of the photon detection system

SBND is the near detector of the Short-Baseline Neutrino program at Fermilab. Its location near to the Booster Neutrino Beam source and relatively large mass will allow the study of neutrino interactions on argon with unprecedented statistics. This paper describes the expected performance of the SBND photon detection system, using a simulated sample of beam neutrinos and cosmogenic particles. Its design is a dual readout concept combining a system of 120 photomultiplier tubes, used for triggering, with a system of 192 X-ARAPUCA devices, located behind the anode wire planes. Furthermore, covering the cathode plane with highly-reflective panels coated with a wavelength-shifting compound recovers part of the light emitted towards the cathode, where no optical detectors exist. We show how this new design provides a high light yield and a more uniform detection efficiency, an excellent timing resolution and an independent 3D-position reconstruction using only the scintillation light. Finally, the whole reconstruction chain is applied to recover the temporal structure of the beam spill, which is resolved with a resolution on the order of nanoseconds.