Real-time System Research Articles

Monitoring of Water Quality using Machine Learning - A Review

Abstract: The incorporation of machine learning (ML) can improve the monitoring of water quality. It improves the sustainability and security of water resources by enabling forecasting and early detection of possible water contamination. A real-time system that collects information on numerous water parameters, including pH level, dissolved oxygen, turbidity, temperature, and conductivity, is made possible by the combination of IoT technology with ML algorithms. The system models complex links between water quality parameters and looks for variations from typical patterns using a mix of supervised and unsupervised learning and anomaly detection methods. Advantage of this method include cost-effectiveness, scalability, remote accessible, and real-time monitoring

RPCA-based thermoacoustic imaging for microwave ablation monitoring

Microwave ablation (MWA) is a potent cancer treatment tool, but its effectiveness can be hindered by the lack of visual feedback. This paper validates the feasibility of using microwave-induced thermoacoustic imaging (TAI) technique to monitor the MWA process. A feasibility analysis was conducted at the principle level and a high-performance real-time TAI system was introduced. To address the interference caused by MWA, a robust principal component analysis (RPCA)-based method for TAI was proposed. This method leverages the correlation between multiple signal frames to eliminate interference. RPCA’s effectiveness in TAI was demonstrated through three sets of different experiments. Experiments demonstrated that TAI can effectively monitors the MWA process. This work represents the first application of RPCA-related matrix decomposition methods in TAI, paving the way for the application of TAI in more complex clinical scenarios. By providing rapid and accurate visual feedback, this research advances MWA technology.

Pengamatan Cuaca Lokal secara Multi Node dengan Internet of Things dan Django Framework

Weather is one of the challenges that humans must experience in their activities. Like the MSMEs of sand crackers in Kediri Regency. This MSME uses sunlight as a means of drying products. What often becomes a problem is unpredictable weather conditions which reduce productivity and quality. Therefore, a real-time local weather observation system is needed to anticipate sudden weather changes. In this research, an IoT-based local weather condition measurement tool will be connected to a system built using the Django framework. This system and tools were tested for eight days. So it was concluded that the system was successfully built with data collection accuracy of 96.31%. Measurements are carried out every 5 minutes or a time frame of 5 minutes. In addition, this system supports observations in several places at once. This multiple node concept is used to detect local weather changes in the surrounding area. So it is not concentrated in the MSME area.

Real-Time Object Detection and Recognition with Computer Vision

Abstract: Object detection, a fundamental aspect of computer vision, is essential for identifying and localizing objects within images or video frames, leveraging advancements in deep learning, particularly convolutional neural networks (CNNs), to enhance precision and speed. Its applications span diverse domains, from autonomous vehicles and surveillance systems to augmented reality and human-computer interaction. Our project focuses on engineering a real-time object detection system, integrating deep learning and computer vision methodologies. Anchored on the robust Single Shot Multibox Detector (SSD) architecture and reinforced by the efficiency and accuracy of the MobileNetV3 backbone, our system utilizes a pre-trained SSD MobileNetV3 model and comprehensive annotations from the COCO dataset to adeptly detect and recognize a wide array of objects within live video streams or archived footage. It seamlessly processes video frames from various sources, annotating detected objects in real-time to provide instant visual feedback. Offering customizable confidence thresholds and support for multiple video sources, our project showcases the transformative potential of deep learning and computer vision, advancing realtime object detection across domains like surveillance and interactive systems. By pushing the boundaries of object detection technology, our project aims to enhance safety, efficiency, and user experiences in various applications, promising to redefine the landscape of computer vision with innovation and advancement.

Advanced method for Image detection using OpenCV

Abstract: In computer vision, object detection is an essential job with many real-world applications, such as robots, autonomous cars, and surveillance. Because of its great accuracy and speed, the YOLO (You Only Look Once) method is a well-liked realtime object recognition technique that has attracted a lot of attention. This technique is perfect for time-sensitive applications since it examines the full image at once and predicts bounding boxes and class probabilities for recognized items. YOLO has undergone many iterations, with YOLO v5 being the most recent and sophisticated version. It utilizes anchor boxes and a feature pyramid network (FPN) to increase the accuracy of object recognition. Our goal in this research is to apply YOLO v5 to realtime picture and object identification applications stage. The model will be trained using an appropriate dataset, and its performance will be assessed against a range of benchmarks and advanced object detection methods. The project's output will offer a reliable and effective real-time object detection system that will facilitate prompt decision-making in the identification of item types and their corresponding placements. It has useful uses in robotics, autonomous driving, and surveillance.

CPU 병렬 처리를 이용한 SPH 유체와 단일보드 컴퓨터의 실시간 상호작용 시스템 개발

CPU 병렬 처리를 이용한 SPH 유체와 단일보드 컴퓨터의 실시간 상호작용 시스템 개발

IONOLAB-Fusion: Fusion of Radio Occultation into Computerized Ionospheric Tomography

In this study, a 4-D, computerized ionospheric tomography algorithm, IONOLAB-Fusion, is developed to reconstruct electron density using both actual and virtual vertical and horizontal paths for all ionospheric states. The user-friendly algorithm only requires the coordinates of the region of interest and range with the desired spatio-temporal resolutions. The model ionosphere is formed using spherical voxels in a lexicographical order so that a 4-D ionosphere can be mapped to a 2-D matrix. The model matrix is formed automatically using a background ionospheric model with an optimized retrospective or near-real time manner. The singular value decomposition is applied to extract a subset of significant singular values and corresponding signal subspace basis vectors. The measurement vector is filled automatically with the optimized number of ground-based and space-based paths. The reconstruction is obtained in closed form in the least squares sense. When the performance of IONOLAB-Fusion across Europe was compared with ionosonde profiles, a 26.51% and 32.33% improvement was observed over the background ionospheric model for quiet and disturbed days, respectively. When compared with GIM-TEC, the agreement of IONOLAB-Fusion was 37.89% and 31.58% better than those achieved with the background model for quiet and disturbed days, respectively.

Salient Applications and Obstacles in IOT Edge Computing

Abstract: The Internet of Things (IoT) is a new technology that has emerged in recent years as a result of the exponential rise of linked gadgets. The IoT benefits from cloud computing. Applications to store the data and carry the calculations, that the enormous volume of data produced by these IoT devices may be managed and controlled. However, fulfilling the demands of numerous Internet of Things, real-time applications remains the main problem in cloud computing. On the other hand, Edge or Fog computing is a computing architecture that facilitates data management, processing, storing, and communication while providing a prompt response. By putting these functions closer to the end consumers, this is made possible. For many applications, edge and cloud computing are complementary technologies that work independently of one another. The overview of IoT and communication technologies and IoT protocols, as well as data transit in IoT. We look into cloud services for processing, storing, and analysing the data produced by Internet of Things devices.

Adaptive K values and training subsets selection for optimal K-NN performance on FPGA

This study introduces an Adaptive K-Nearest Neighbors methodology designed for FPGA platforms, offering substantial improvements over traditional K-Nearest Neighbors implementations. By integrating a dynamic classifier selection system, our approach enhances adaptability, enabling on-the-fly adjustments of K values and subsets of training data. This flexibility results in up to a 10.66% improvement in accuracy and significantly reduces latency, rendering our system up to 3.918 times more efficient than conventional K-Nearest Neighbors techniques. The methodology’s efficacy is validated through experiments across multiple datasets, demonstrating its potential in optimizing both classification accuracy and system efficiency. The adaptive approach’s ability to improve response times, along with its flexibility, positions it as an ideal solution for real-time applications and highlights the advantages of the adaptive K-Nearest Neighbors methodology in overcoming the constraints of hardware-accelerated machine learning.

SignEase - Sign Language Interpreter Model An Indian Sign Language Interpretation Model using Machine Learning and Computer Vision Technology

Abstract: This study introduces a real-time system designed to recognize hand poses and gestures from the Indian Sign Language (ISL) using grid-based (control points) features. The primary aim is to bridge communication barriers between the hearing and speech impaired individuals and the broader society.Existing solutions often struggle with either accuracy or realtime performance, whereas our system excels in both aspects. It can accurately identify hand gestures in Indian Sign Language. In addition to recognition capabilities, our system offers a ’Learning Portal’ for users to efficiently learn and practice ISL, ASL, etc., enhancing its accessibility and effectiveness. Notably, the system operates solely on smartphone camera input, eliminating the need for any external hardware like gloves or specialized sensors, thus ensuring user-friendliness. Key techniques employed include hand detection via MediaPipe, cvzone, etc modules, and grid-based feature extraction, which transforms hand poses into concise feature vectors. These features are then compared with a TensorFlow- provideddatabase for classification for accurate translation

Self-sampling with oral rinse to detect oropharyngeal Neisseria gonorrhoeae among men who have sex with men: results from an exploratory study in Belgium (the SSONG Study)

ObjectivesWe aimed to assess whether a self-collected oral rinse was non-inferior to clinician-collected oropharyngeal swabs to detect Neisseria gonorrhoeae (Ng) using culture and nucleic acid amplification tests (NAAT) among men...

Parallel illumination for depletion microscopy through acousto-optic spatial light modulation

Several types of super-resolution microscopy techniques, such as Stimulated Emission Depletion (STED), Reversible Saturable Optical Fluorescence Transitions (RESOLFT) or Switching Laser Mode (SLAM) microscopies, employ Laguerre-Gaussian beams (also called vortex or doughnut beams) to obtain fluorescence information within a sub-wavelength region of the specimen under observation, thus breaking the diffraction limit and producing images of greatly improved quality. However, in general, these techniques operate on a point-by-point basis, so scanning the sample in order to build a full, meaningful image, takes time. Parallelization of the illumination is the only way to make these microscopy techniques more suitable for real-time live cell imaging applications. Here, we demonstrate the parallel production of arbitrary arrays of Gaussian and Laguerre-Gaussian lasers foci suitable for super-resolution microscopy, together with the possibility to fast scan through the sample, by means of acousto-optic spatial light modulation, a technique that we have pioneered in the past in several other fields. Parallelized illumination with both Gaussian and doughnut beams will be then used to acquire super-resolution images.

Multi-resource allocation and care sequence assignment in patient management: a stochastic programming approach.

To mitigate outpatient care delivery inefficiencies induced by resource shortages and demand heterogeneity, this paper focuses on the problem of allocating and sequencing multiple medical resources so that patients scheduled for clinical care can experience efficient and coordinated care with minimum total waiting time. We leverage highly granular location data on people and medical resources collected via Real-Time Location System technologies to identify dominant patient care pathways. A novel two-stage Stochastic Mixed Integer Linear Programming model is proposed to determine the optimal patient sequence based on the available resources according to the care pathways that minimize patients' expected total waiting time. The model incorporates the uncertainty in care activity duration via sample average approximation.We employ a Monte Carlo Optimization procedure to determine the appropriate sample size to obtain solutions that provide a good trade-off between approximation accuracy and computational time. Compared to the conventional deterministic model, our proposed model would significantly reduce waiting time for patients in the clinic by 60%, on average, with acceptable computational resource requirements and time complexity. In summary, this paper proposes a computationally efficient formulation for the multi-resource allocation and care sequence assignment optimization problem under uncertainty. It uses continuous assignment decision variables without timestamp and position indices, enabling the data-driven solution of problems with real-time allocation adjustment in a dynamic outpatient environment with complex clinical coordination constraints.

A Geth-based real-time detection system for sandwich attacks in Ethereum

With the rapid development of the Ethereum ecosystem and the increasing applications of decentralized finance (DeFi), the security research of smart contracts and blockchain transactions has attracted more and more attention. In particular, front-running attacks on the Ethereum platform have become a major security concern. These attack strategies exploit the transparency and certainty of the blockchain, enabling attackers to gain unfair economic benefits by manipulating the transaction order. This study proposes a sandwich attack detection system integrated into the go-Ethereum client (Geth). This system, by analyzing transaction data streams, effectively detects and defends against front-running and sandwich attacks. It achieves real-time analysis of transactions within blocks, quickly and effectively identifying abnormal patterns and potential attack behaviors. The system has been optimized for performance, with an average processing time of 0.442 s per block and an accuracy rate of 83%. Response time for real-time detection new blocks is within 5 s, with the majority occurring between 1 and 2 s, which is considered acceptable. Research findings indicate that as a part of the go-Ethereum client, this detection system helps enhance the security of the Ethereum blockchain, contributing to the protection of DeFi users’ private funds and the safety of smart contracts. The primary contribution of this study lies in offering an efficient blockchain transaction monitoring system, capable of accurately detecting sandwich attack transactions within blocks while maintaining normal operation speeds as a full node.

Real-time Target Detection System in Scenic Landscape Based on Improved YOLOv4 Algorithm

Real-time Target Detection System in Scenic Landscape Based on Improved YOLOv4 Algorithm

Advanced risk management solutions for mitigating credit risk in financial operations

Advanced risk management solutions are essential for mitigating credit risk in financial operations, particularly in today's volatile economic environment. This Review explores the innovative approaches and technologies being utilized to enhance credit risk management and safeguard financial institutions against potential losses. Credit risk, the possibility that a borrower will default on their obligations, poses a significant threat to financial stability. Traditional methods of assessing and managing credit risk, such as credit scoring and historical data analysis, are no longer sufficient to address the complexities of modern financial markets. Advanced risk management solutions offer more robust and dynamic tools for identifying, assessing, and mitigating credit risk. One of the key advancements in this field is the integration of big data and machine learning algorithms. By analyzing vast amounts of data from diverse sources, financial institutions can gain deeper insights into borrower behavior, market trends, and economic indicators. Machine learning models can predict default probabilities with greater accuracy, allowing for proactive risk mitigation strategies. Additionally, real-time risk monitoring systems have become increasingly prevalent. These systems provide continuous oversight of credit portfolios, enabling financial institutions to detect early warning signs of potential defaults and take timely action. Advanced analytics and visualization tools facilitate the identification of emerging risks and the implementation of targeted interventions. Another crucial component of advanced risk management solutions is the use of stress testing and scenario analysis. These techniques simulate various economic conditions and assess the impact on credit portfolios, helping financial institutions prepare for adverse scenarios and develop contingency plans. Furthermore, blockchain technology is emerging as a promising tool for enhancing transparency and reducing fraud in credit transactions. By providing a secure and immutable record of credit histories and transactions, blockchain can improve trust and reliability in credit assessments. In conclusion, advanced risk management solutions are transforming the way financial institutions mitigate credit risk. By leveraging big data, machine learning, real-time monitoring, stress testing, and blockchain technology, financial institutions can achieve more accurate risk assessments and implement more effective risk mitigation strategies. These innovations not only enhance the stability and resilience of financial operations but also contribute to a more secure and trustworthy financial system.

Wireless End to End Image Transmission System using Li-Fi Technology

The first and most important objective of this project is to convey the image through the utilization of a light-emitting diode (LED). The innovative technique known as visible light communication (VLC) holds enormous promise for the implementation of high-speed, large-capacity, short-range wireless data transmission. It is gaining popularity on account of the growing use of solid-state lighting systems. Additionally, LED lights change frequency at a rate that is substantially faster than what the human eye is able to perceive. This is in addition to the fact that radio waves have a higher repetition rate than LED lights, which results in significantly greater speed than Wi-Fi. This work suggests a real-time image broadcast system prototype. Light-emitting diode (LED) lights are used in the prototype since they are widely available and reasonably priced. The scope of the work encompasses the possibility of making information and communication accessible through the utilization of LED bulbs in a manner that may be implemented in a variety of situations, such as homes, offices, organizations, and corporations. If the LED sources are positioned correctly and concentration effects are increased, it is feasible to obtain a real-time image with a maximum distance of two feet, according to the testing results. In addition to being made to last, the LI-FI (Light Fidelity) light source features a broad variety of digital settings that can be adjusted, and it is simple to operate as a result of its efficient design

A power-aware vision-based virtual sensor for real-time edge computing

Graphics processing units and tensor processing units coupled with tiny machine learning models deployed on edge devices are revolutionizing computer vision and real-time tracking systems. However, edge devices pose tight resource and power constraints. This paper proposes a real-time vision-based virtual sensors paradigm to provide power-aware multi-object tracking at the edge while preserving tracking accuracy and enhancing privacy. We thoroughly describe our proposed system architecture, focusing on the Dynamic Inference Power Manager (DIPM). Our proposed DIPM is based on an adaptive frame rate to provide energy savings. We implement and deploy the virtual sensor and the DIPM on the NVIDIA Jetson Nano edge platform to prove the effectiveness and efficiency of the proposed solution. The results of extensive experiments demonstrate that the proposed virtual sensor can achieve a reduction in energy consumption of about 36% in videos with relatively low dynamicity and about 21% in more dynamic video content while simultaneously maintaining tracking accuracy within a range of less than 1.2%.

Securing Systems using SIEM and FIM Tools

Today, computer networks are heavily documented security issues, making it impractical to manage them without Security Event Management (SIEM). A SIEM solution sets the controls everywhere, enhances information security, recording data from various devices and applications through agents or networks Protects data by aggregating and aggregating Provides filtering, normalization of redundant information it is proprietary, and they use context to analyze it. The SIEM solution provides threat detection and real-time system activity analysis, alerting operators in the event of an attack. Although there are high-quality SIEM solutions, success cannot be guaranteed. Instead, organizations should focus on a variety of use cases to effectively implement their SIEM solutions. Care must be taken with respect to the integrity of the operating system components. They are controlled to optimize system security. Attackers will always try to manipulate or alter these relevant resources to achieve their goals. System files are common targets for attackers. File integrity monitoring tools are often used to detect any malicious changes to these important files. In this project we developed a comprehensive security solution that combines a Security Information Event Management (SIEM) framework with a File Integrity Monitoring (FIM) tool to optimize the security posture of IT projects. Our SIEM project uses Azure Monitoring Agent to collect data from virtual machine and inject it into the Log Analytics Workspace. The FIM component is implemented by a Python script designed to scan multiple directories and files. The script initially stores the hashes of all monitored files in a baseline file named “baseline.txt” and creates backups of the original files. These backups are periodically updated, with old backups being deleted.

Enhancing image security via chaotic maps, Fibonacci, Tribonacci transformations, and DWT diffusion: a robust data encryption approach

In recent years, numerous image encryption schemes have been developed that demonstrate different levels of effectiveness in terms of robust security and real-time applications. While a few of them outperform in terms of robust security, others perform well for real-time applications where less processing time is required. Balancing these two aspects poses a challenge, aiming to achieve efficient encryption without compromising security. To address this challenge, the proposed research presents a robust data security approach for encrypting grayscale images, comprising five key phases. The first and second phases of the proposed encryption framework are dedicated to the generation of secret keys and the confusion stage, respectively. While the level-1, level-2, and level-2 diffusions are performed in phases 3, 4, and 5, respectively, The proposed approach begins with secret key generation using chaotic maps for the initial pixel scrambling in the plaintext image, followed by employing the Fibonacci Transformation (FT) for an additional layer of pixel shuffling. To enhance security, Tribonacci Transformation (TT) creates level-1 diffusion in the permuted image. Level-2 diffusion is introduced to further strengthen the diffusion within the plaintext image, which is achieved by decomposing the diffused image into eight-bit planes and implementing XOR operations with corresponding bit planes that are extracted from the key image. After that, the discrete wavelet transform (DWT) is employed to develop secondary keys. The DWT frequency sub-band (high-frequency sub-band) is substituted using the substitution box process. This creates further diffusion (level 3 diffusion) to make it difficult for an attacker to recover the plaintext image from an encrypted image. Several statistical tests, including mean square error analysis, histogram variance analysis, entropy assessment, peak signal-to-noise ratio evaluation, correlation analysis, key space evaluation, and key sensitivity analysis, demonstrate the effectiveness of the proposed work. The proposed encryption framework achieves significant statistical values, with entropy, correlation, energy, and histogram variance values standing at 7.999, 0.0001, 0.0156, and 6458, respectively. These results contribute to its robustness against cyberattacks. Moreover, the processing time of the proposed encryption framework is less than one second, which makes it more suitable for real-world applications. A detailed comparative analysis with the existing methods based on chaos, DWT, Tribonacci transformation (TT), and Fibonacci transformation (FT) reveals that the proposed encryption scheme outperforms the existing ones.