Real-time Response Research Articles

Modeling Mild Traumatic Brain Injury In-Vitro Using PHuman Choroid Plexus Endothelial Cells

Over 2.5 million Traumatic Brain Injuries (TBIs) occur each year due to falls, motor vehicle accidents, assaults, and sports (Brain Trauma Foundation, 2023). Short- and long-term consequences of TBI can include headache, cognitive impairment, seizures, hypoxia, and ischemia. Human TBI studies are diffcult due to the confounding variables of type and mechanism of injury, severity of injury, and length of time to present to emergency departments. While animal models exist, it is our goal to develop an in-vitro model of TBI using primary human brain cell cultures to examine cellular responses in real time. While the blood-brain barrier has been studied extensively post-TBI due to its role in ischemia and hypoxia, there is a dearth of research on the blood-CSF-barrier (BCSFB), the choroid plexus, and its response post-TBI. After culturing primary human choroid plexus endothelial cells (ScienCell Cat #1300) on a flexible membrane, we subjected them to mechanical strain using the FlexCell tension system and collected supernatant at 3-, 6-, 12-, 24-, 48-, 72-, and 96-hours post injury. The FlexCell tension bioreactor system uses positive and negative air pressure to apply mechanical elongation strain mimicking mild shearing injury. Using R&D cytokine arrays (R&D Systems, Cat# ARY005B), we measured 36 different cytokines, chemokines and acute phase proteins including C5a, GM-CSF, ICAM-1, IL-1, IL-6, TNFα, IFNγ, CCL5/RANTES, etc. We hypothesized that we would see a pro-inflammatory response (IL-1β, IL-6, TNFα) within 24 hours after one or two 12% mechanical strain injuries compared to the control of no strain, as seen in the literature. However, there were not significant increases in cytokine signaling until 24-48 hours post-injury, and in regulatory cytokines, such as CCL2, MIP1α/MIP1β, IL-2, IL-12, & IL-17, that lasted as long as 96-hours. This effect was more pronounced in the two strain verses one strain model and control, as expected. Interestingly, anti-inflammatory cytokine IL-10 was significantly increased in the one strain model, but not two strain model, 48 hours post-insult. As the choroid plexus is a niche for T cell stimulation in the central nervous system (Strominger et al., 2018), these results indicate a complex immunological response that seems to favor T-Cell response over monocytes/macrophages. These experiments were completed with the lowest mechanical strain of the FlexCell system and future experiments are warranted to determine if a stronger mechanical strain is needed to produce the pro-inflammatory response seen in the literature in mild to severe models of TBI. This project was funded by a Senior Research Grant from the Indiana Academy of Science and from a Faculty Research Development Grant from Marian University College of Osteopathic Medicine. This is the full abstract presented at the American Physiology Summit 2024 meeting and is only available in HTML format. There are no additional versions or additional content available for this abstract. Physiology was not involved in the peer review process.

Deep-Learning-Based Strong Ground Motion Signal Prediction in Real Time

Processing ground motion signals at early stages can be advantageous for issuing public warnings, deploying first-responder teams, and other time-sensitive measures. Multiple Deep Learning (DL) models are presented herein, which can predict triaxial ground motion accelerations upon processing the first-arriving 0.5 s of recorded acceleration measurements. Principal Component Analysis (PCA) and the K-means clustering algorithm were utilized to cluster 17,602 accelerograms into 3 clusters using their metadata. The accelerograms were divided into 1 million input–output pairs for training, 100,000 for validation, and 420,000 for testing. Several non-overlapping forecast horizons were explored (1, 10, 50, 100, and 200 points). Various architectures of Artificial Neural Networks (ANNs) were trained and tested, such as Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) networks, and CNN-LSTMs. The utilized training methodology applied different aspects of supervised and unsupervised learning. The LSTM model demonstrated superior performance in terms of short-term prediction. A prediction horizon of 10 timesteps in the future with a Root Mean Squared Error (RMSE) value of 8.43 × 10−6 g was achieved. In other words, the LSTM model exhibited a performance improvement of 95% compared to the baseline benchmark, i.e., ANN. It is worth noting that all the considered models exhibited acceptable real-time performance (0.01 s) when running in testing mode. The CNN model demonstrated the fastest computational performance among all models. It predicts ground accelerations under 0.5 ms on an Intel Core i9-10900X CPU (10 cores). The models allow for the implementation of real-time structural control responses via intelligent seismic protection systems (e.g., magneto-rheological (MR) dampers).

Enhancing Urban Resilience: Strategic Management and Action Plans for Cyclonic Events through Socially Constructed Risk Processes

Cities will face increasing challenges due to the impacts of global climate change, particularly in the form of cyclonic events, necessitating a deeper understanding and the establishment of effective response mechanisms at both institutional and citizen levels. In this research, we tested the efficiency of crowdsourcing in fostering participatory resilience and improving urban management. The main aim was to design novel and accurate proactive response strategies and mitigate the adverse effects of cyclonic wind events through volunteerism, citizen science, and urban science. To achieve this goal, as a case study, the municipality of Soledad, Colombia was used. This research employed a two-phase methodological approach: (i) initially evaluating the spatial distribution of emergency response resources, and (ii) developing a geo-referenced survey to map, systematize, and categorize data and outcomes. A total of three hundred and seventy-eight residents across five neighborhoods in Soledad, which have experienced a high frequency of atmospheric wind phenomena over the past two decades, were surveyed. The results indicate that the crowdsourcing mechanism effectively enhanced the empirical understanding of atmospheric wind events in Soledad, facilitating the establishment of a geo-referenced volunteer network for real-time responses. Additionally, this study shed light on previously undocumented challenges, in terms of reducing the number of people affected, and the actions that would lead to improved urban development to reduce the impacts of cyclonic events, emphasizing the significance of citizen science in the social construction of risk and disaster risk reduction (DDR) efforts.

Intestinal ultrasound: Is it time to join our IBD units? How do we do it?

Abstract The objective in the treatment of inflammatory bowel disease is to achieve early control of the disease with the intention of obtaining mucosal and even transmural healing. To do this, it is necessary to have monitoring techniques that allow us to closely monitor the evolution of the disease. Intestinal ultrasound is a good alternative to more invasive imaging techniques, with similar precision. It is quickly and easily available, provides real-time response and allows early clinical decision-making, being able to modify the therapeutic and monitoring strategy of patients. The incorporation of ultrasound in IBD units allows us to save time and resources for the benefit of the patient themselves.

Advancements in Intelligent Video Surveillance for Public Safety: A Comprehensive Review

Abstract: Intelligent video surveillance systems have emerged as invaluable tools for ensuring public safety in a variety of settings, from essential infrastructure to urban environments. These systems, which are driven by state-of-the-art technology like computer vision, machine learning, and artificial intelligence, provide unmatched real-time threat detection, analysis, and response capabilities. This study provides an in-depth analysis of the most recent developments in intelligent video surveillance for public safety, covering key technology, useful uses, enduring difficulties, and potential directions. This paper aims to provide a thorough knowledge of the significant implications and emerging opportunities of intelligent video surveillance in protecting public places from potential dangers through an examination of recent research insights and industry advancements. This article seeks to offer a guide for researchers, practitioners, policymakers, and stakeholders navigating the ever-changing field of intelligent video surveillance for public safety by exploring the evolving trends, emerging technologies, and practical applications.

A Deep Learning Approach for Real-Time Sign Language Detection and Response through Avatar Model

Abstract: This paper focuses on the evolution of a real-time sign language detection model using computer vision, machine learning, and deep learning. Its goal is to narrow the poor communication for the speaking and hearing-impaired community by using recurrent neural networks and long short-term memory models. The proposed system utilizes a dataset comprising sign language gestures captured in various contexts and by different signers. Preprocessing techniques are applied to draw out fitting features from the video frames, including hand movements, facial expressions, and body postures. The LSTM neural network architecture is chosen to grab temporal dependencies in sequential data, making it suitable for the robust nature of sign language. The training process involves optimizing the LSTM network on the labeled dataset, incorporating techniques such as transfer learning and data augmentation to enhance model generalization. The resulting model is capable of recognizing a divergent set of sign language actions in real-time

Tensor Flow-powered Spam Email Filtering: An Evaluation of Performance and Robustness

Spam emails continue to pose significant challenges in email communication, requiring robust and adaptive filtering mechanisms to safeguard users and organizations. Leveraging the capabilities of machine learning and deep learning, this paper presents an evaluation of a spam email filtering system powered by Tensor Flow. The system's architecture is designed to utilize deep neural networks for feature extraction and classification, enabling flexibility and scalability in handling diverse spam tactics. We assess the system's performance in accurately distinguishing between spam and legitimate emails, evaluating metrics such as precision, recall, and F1-score. Additionally, we analyze the system's resilience against adversarial attacks and its ability to adapt to evolving spam techniques. Comparative analysis with traditional spam filtering techniques highlights the superiority of deep learning-based approaches. Practical considerations such as computational efficiency and scalability are also addressed, ensuring real-time responsiveness in processing vast volumes of emails. Through comprehensive experimentation and benchmarking, this paper contributes to the advancement of spam email filtering, guiding the development of more effective and efficient solutions for enhancing email security and user experience.

Research on Optimization of Intelligent Driving Vehicle Path Tracking Control Strategy Based on Backpropagation Neural Network

To enhance path tracking precision in intelligent vehicles, this study proposes a lateral–longitudinal control strategy optimized with a Backpropagation (BP) neural network. The strategy employs the BP neural network to dynamically adjust prediction and control time-domain parameters within an established Model Predictive Control (MPC) framework, effectively computing real-time front-wheel steering angles for lateral control. Simultaneously, it integrates an incremental Proportional–Integral–Derivative (PID) approach with a meticulously designed acceleration–deceleration strategy for accurate and stable longitudinal speed tracking. The strategy’s efficiency and superior performance are validated through a comprehensive CarSim(2020)/Simulink(2020b) simulation, demonstrating that the proposed controller adeptly modulates control parameters to adapt to various road adhesion coefficients and vehicle speeds. This adaptability significantly improves tracking and driving dynamics, thereby enhancing accuracy, safety, stability, and real-time responsiveness in the intelligent vehicle tracking control system.

Pre-Disaster Optimal Operation Strategy for Hydrogen-Fuel-Based Isolated Power System with Disaster Uncertainties

The increasing occurrence of severe weather phenomena presents substantial difficulties for electricity distribution systems. This study investigates the integration of hydrogen production plants (HPPs) into power distribution networks to bolster resilience against the increasing frequency of extreme weather events. It highlights the innovative use of hydrogen, generated from renewable sources, as an energy storage medium to ensure a stable power supply during disruptions. By employing stochastic optimization, the study aims to effectively manage hydrogen production and utilization, considering uncertainties in disaster scenarios and energy demands. It addresses critical research gaps, such as the lack of focus on pre-disaster preventive scheduling using hydrogen, the under-explored application of stochastic optimization in such contexts, and the predominance of real-time response strategies over pre-emptive measures. This approach significantly advances current understanding by proposing novel strategies that leverage hydrogen production and sophisticated optimization to enhance the resilience of power networks against extreme weather events. In some scenarios, using our method can reduce the cost of pre-disaster prevention by approximately 15.68% while ensuring that the disaster recovery effect remains unchanged.

Real-time, ultra-sensitive and label-free detection of OTA based on DNA aptamer functionalized carbon nanotube field-effect transistor

Ochratoxin A (OTA), widely recognized as a mycotoxin contaminant across various food products, poses significant health risks attributed to its nephrohepatotoxic and carcinogenic effects. Consequently, detecting OTA is crucial for ensuring food safety and preventing mycotoxicosis. In our study, we employed a carbon nanotube field-effect transistor (CNT FET) functionalized with DNA aptamers for targeted OTA detection. The sensor achieved a remarkably low detection threshold of 0.2 femtomolars (fM) in phosphate-buffered saline (PBS), enabling real-time detection of OTA over a broad concentration spectrum spanning from 8 fM to 80 pM. This research confirmed the sensor’s superior selectivity by effectively distinguishing OTA from non-target fungal toxins and showcased its rapid analysis capabilities across diverse complex matrices. Utilizing homogenized liquids from ten representative food samples for analysis, the sensor delivered real-time responses within 100 s, accurately identifying varying OTA concentrations down to 80 fM. In conclusion, this biosensor provides a label-free, highly sensitive, and rapid detection method for OTA, introducing novel solutions for effective mycotoxin surveillance in food safety. This biosensor also paves the way for the creation of a multiplex platform for concurrent monitoring of multiple fungal toxins.

Design and Evaluation of CPU-, GPU-, and FPGA-Based Deployment of a CNN for Motor Imagery Classification in Brain-Computer Interfaces

Brain–computer interfaces (BCIs) have gained popularity in recent years. Among noninvasive BCIs, EEG-based systems stand out as the primary approach, utilizing the motor imagery (MI) paradigm to discern movement intentions. Initially, BCIs were predominantly focused on nonembedded systems. However, there is now a growing momentum towards shifting computation to the edge, offering advantages such as enhanced privacy, reduced transmission bandwidth, and real-time responsiveness. Despite this trend, achieving the desired target remains a work in progress. To illustrate the feasibility of this shift and quantify the potential benefits, this paper presents a comparison of deploying a CNN for MI classification across different computing platforms, namely, CPU-, embedded GPU-, and FPGA-based. For our case study, we utilized data from 29 participants included in a dataset acquired using an EEG cap for training the models. The FPGA solution emerged as the most efficient in terms of the power consumption–inference time product. Specifically, it delivers an impressive reduction of up to 89% in power consumption compared to the CPU and 71% compared to the GPU and up to a 98% reduction in memory footprint for model inference, albeit at the cost of a 39% increase in inference time compared to the GPU. Both the embedded GPU and FPGA outperform the CPU in terms of inference time.

Collaborative Optimization of Dynamic Lane Assignment and Signal Timing for Incident-Affected Intersections

Traffic accidents can lead to rapid changes in the traffic supply and demand at urban intersections, thus causing a severe traffic supply/demand imbalance during specific periods. Responding to accidents requires dynamic and accurate adjustments to optimize intersection resources collaboratively and enhance the real-time reliability and stability of traffic flows during such accidents. Currently, research on traffic incidents rarely considers real-time data-based collaborative optimization theories. Therefore, this study, supported by real-time incident detection technology and accident data, first considers the location and intensity of traffic incidents to update dynamically the changes in intersection traffic demand and supply. Subsequently, a dynamically collaborative optimization method is proposed based on lane assignment and signal timings to minimize the sum of variances of the degree of saturation of various approach lanes. Finally, various traffic demand scenarios are set, and the effectiveness of the proposed model is validated based on numerical and sensitivity analyses. The results demonstrate that compared with signal-only optimization and the highway capacity methods (HCM), the collaborative optimization method presented in this study reduces the average vehicular delay percentages by 8.54% and 16.47%, respectively. Sensitivity analysis indicates that, under various detour rates and detour modes, collaborative optimization methods have effectively mitigated the average vehicular delay at upstream intersections to varying degrees. In the context of real-time accident response, collaborative optimization methods demonstrate a capacity to promptly address the urgency of incidents occurring and maintain a sustained reduction in overall delay levels following detours.

Advancing Chatbot Conversations: A Review of Knowledge Update Approaches

Conversational systems like chatbots have emerged as powerful tools for automating interactive tasks traditionally confined to human involvement. Fundamental to chatbot functionality is their knowledge base, the foundation of their reasoning processes. A pivotal challenge resides in chatbots' innate incapacity to seamlessly integrate changes within their knowledge base, thereby hindering their ability to provide real-time responses. The increasing literature attention dedicated to effective knowledge base updates, which we term content update, underscores the significance of this topic. This work provides an overview of content update methodologies in the context of conversational agents. We delve into the state-of-the-art approaches for natural language understanding, such as language models and alike, which are essential for turning data into knowledge. Additionally, we discuss turning point strategies and primary resources, such as deep learning, which are crucial for supporting language models. As our principal contribution, we review and discuss the core techniques underpinning information extraction as well as knowledge base representation and update in the context of conversational agents.

Organized leader election consensus protocol and a supportive blockchain model for ambient assisted living

Blockchain enhances the development of other technologies and systems by providing more transparency, sharing, decentralization, security, and privacy. Blockchain has many applications that enable integration and application in many areas, such as the field of ambient assisted living (AAL). However, blockchain includes many processes for data proposing, validating, and approving, which result in high latency. Such latency negatively influences AAL systems, which require real-time responses in many cases. In addition, blockchain processes are processed based on consensus. This challenges specialized decisions that should be taken only by specialized members within the blockchain network. Therefore, this work introduces an organized leader election consensus protocol with a blockchain model that is applicable for AAL. The proposed protocol and model are able to solve the issue of latency as well as consider specialized decisions. Solving the issue of latency enables AAL to perform real-time processes in the needed cases. While considering the matter of specialization gives more credibility to the blockchain’s decisions, which is necessary for AAL. Indeed, it classifies the blocks into special-sensitive, time-sensitive, and non-sensitive classes, where each class has a suitable procedure. In addition, to manage the organized leader election consensus protocol, we manage the blockchain feature and rewarding strategy. This enhances the miners’ participation in a way that supports blockchain and AAL simultaneously. The experimental results show that our model reduces the execution time by about 51% in comparison to the original blockchain model.

A Fluorescent Probe for Hg2+ Specific Recognition Based on Xanthene and its Application in Food Detection and Cell Imaging.

The mercury-loving unit aminothiourea was introduced into the xanthene fluorophore to synthesized the probe molecule NXH. NXH has a specific response to Hg2+, and with the addition of (0 ~ 50 µM) Hg2+, the fluorescence intensity of the probe solution was quenched from 2352 a.u. to about 308 a.u. NXH exhibited excellent detection performance of high sensitivity (LOD = 96.3 nM), real-time response (105s), wide pH range (2.1 ~ 9.3), and strong anti-interference ability for Hg2+. At the same time, NXH has wide range of applications for Hg2+ detection, which can fluorescence imaging of Hg2+ in Hela cells and tea samples, and can also be made into Hg2+ detection test paper.

AI Gym Buddy Using Mediapipe

The AI Gym Trainer is a system that provides multiple features designed to provide personalized fitness coaching and nutrition tracking. Imposing the advanced pose estimation capabilities of Mediapipe, the system provides real-time responses to exercise performance, focusing on posture, alignment, and technique.This feature is helpful because users will receive accurate guidance in workout sessions, which in turn enhances effectiveness while minimizing the risk of injury. Furthermore, the AI Gym Trainer is implemented using machine learning algorithms, which makes it capable of providing tailor workout routines to individual preferences and abilities, encouraging a personalized training experience. Through a user- friendly interface accessible through a desktop or web application, users can seamlessly interact with the system, track their progress, and receive personalized recommendations. Additionally, the system has a feature of a Flask-based food tracking feature which enhances the capabilities, allowing users to monitor their calorie intake and receive nutritional analysis. This comprehensive approach addresses both physical activity and dietary habits, and provides users with a holistic platform for managing their fitness goals. Evaluation through rigorous testing and user trials demonstrates the effectiveness and potential impact of the AI Gym Trainer in promoting overall health and well-being. With its combination of cutting-edge technology and user-centric design, the AI Gym Trainer represents a significant advancement in personalized fitness coaching and nutrition tracking, catering to the diverse needs of individuals striving to achieve their fitness goals.

Smart Farming Robot for Detecting Environmental Conditions in a Green House

At a high level, the Smart Farming Robot for detecting environmental conditions in a greenhouse embodies a pioneering solution merging robotics and agricultural technology. This innovative system integrates advanced sensors to meticulously monitor vital parameters within the greenhouse environment, including temperature, humidity, soil moisture, light intensity, and air quality. Through seamless data collection and analysis facilitated by Raspberry Pi microcontroller technology, the robot autonomously navigates the greenhouse, continuously assessing conditions crucial for optimal plant growth. At an intermediate level, the system orchestrates a symphony of sensor data acquisition, processing algorithms, and navigational control mechanisms, all orchestrated to ensure real-time detection and response to deviations from ideal environmental conditions. Delving deeper, the system architecture encompasses intricacies of sensor interfacing, data processing, and algorithmic decision-making, harmonizing to deliver actionable insights for precision agriculture practices. Keywords- Raspberry Pico

A computational framework based on the dynamic pipeline approach

Stream processing has inspired new computational approaches to facilitate effectiveness and efficiency. One such approach is the dynamic pipeline, which serves as a powerful computational model for stream processing. It is particularly well suited for solving problems that require incremental generation of results, making it an approach for scenarios where real-time analysis and responsiveness are critical. This paper aims to address a family of problems using the Dynamic Pipeline approach, and as a first step, we provide a comprehensive characterization of this problem family. In addition, we present the definition of a Dynamic Pipeline framework. To demonstrate the practicality of this framework, we present a proof of concept through its implementation and perform an empirical performance study. To this end, we focus on solving the problem of enumerating or listing the weakly connected components of a graph within the proposed framework. We provide two implementations of this algorithm to demonstrate the computational power and continuous behavior of the Dynamic Pipeline framework. The first implementation serves as a baseline for our experiments, representing an ad hoc solution based on the Dynamic Pipeline approach. In contrast, the second implementation is built on top of the developed framework. The observed results strongly support the suitability and effectiveness of the Dynamic Pipeline framework for implementing graph stream processing problems, especially those where continuous and real-time result generation is essential.

Advanced Vehicle Locking System Using Facial Recognition

Access control systems are crucial for vehicle security. This study presents an innovative method employing a Raspberry Pi-based system integrated with face-api.js, along with dlib libraries, to establish a secure vehicle access control system. Facial recognition algorithms are utilized for user authentication, adding an extra level of security. Any unauthorized access prompts an alert to the administrator, improving real-time monitoring and response capabilities.

Microflow sensing and control using an in-channel birefringent biomembrane.

This study describes the function, optimization, and demonstration of a new class of passive, low-cost microfluidic flow meters based on birefringent chitosan biomembranes analyzed by polarized microscopy. We subjected the membrane to dynamic flow conditions while monitoring the real-time response of its optical properties. We obtained figures of merit, including the linear response operating range (0 to 65 μL min-1), minimum response time (250 ms), sensitivity (2.03% × 10-3 μL-1 min), and minimum sensor longevity (1 week). In addition, possible sources of interference were identified. Finally, we demonstrate the membrane as a low-cost flow rate measurement device for the close loop control of a commercial pressure-driven pump. Preliminary experiments using a basic PID controller with the membrane-based flow rate measurement device showed that stable control could be achieved and the system could reach steady-state behavior in less than 15 seconds. Analysis of fundamental limits to sensor response time indicate the potential for faster steady-state behaviour.