Real-Time Ensemble Model for Stroke, Drowsy, and Distracted Driver Detection Using Transfer Learning Models
Road safety remains a global concern, with driver-related factors like distraction, drowsiness, and medical conditions such as stroke being leading causes of accidents. In this paper, we propose a real-time ensemble learning framework that leverages transfer learning for the detection of stroke, drowsiness, and distracted driving. Our model integrates multiple Convolutional Neural Networks (CNNs) fine-tuned for each specific task, and employs a stacking method to combine the predictions of these models using a meta-classifier. Notably, the model is optimized to enhance stroke detection, minimizing false negatives— an essential aspect for timely medical intervention. Experimental evaluations on diverse datasets demonstrate the efficacy of our approach, achieving an overall accuracy of 92.5%. The results emphasize the model’s potential for real-time driver monitoring, offering critical safety features that could reduce accidents and save lives.
Revolutionizing Potato Agriculture: Harnessing Machine Learning Techniques for Disease Detection and Management
Aim: The aim of this study is to make a disease-predicting model trained on data from weather stations and API using machine learning that gives the farmer the ability to predict crop diseases before they set in, allowing them to take timely preventative measures and reduce wastage. Materials and Methods: In this study the Internet of Things (IoT) sensors throughout agricultural fields of potato crops in Jafferabad, Depalpur Punjab. The sensors collect real-time data on environmental conditions, such as precipitation, air temperature, relative humidity, wind speed, and direction, Dew Point, VPD, and the Delta T values, to identify subtle disease indicators and patterns within the environmental data. Our novel machine-learning program makes use of the data collected by the weather station and analyses them. Results: Using the data, one predictive statistical method using Python 3.8.0 was created which uses the data from the weather station which can predict diseases before they set in.
TEST & SAVE
Electricity has become an essential part of modern life, powering homes, businesses, and industries. However, the misuse of electricity or malfunctioning electrical systems can lead to hazardous situations such as electrical fires, shocks, and significant energy wastage. This project focuses on creating a Comprehensive Electrical Security System to protect users and properties from the risks associated with electricity. The system is designed to prevent electrical malfunctions, ensure safety in various scenarios, and monitor energy consumption effectively. It integrates a variety of sensors and safety mechanisms to detect dangers and take preemptive action
Using Focused Ultrasound and Pulsed Ultrasound as a Solution to Viral Infection
Viruses Both enveloped and non-enveloped viruses conceal their membrane-penetrating peptide, usually within a glycoprotein of the virion membrane, inside the coat, or within the virion lumen. Cellular signals expose membrane-penetrating peptides that influence the virus during its entry. Instances of cellular signals regulating virus entry include receptors, enzymes, and substances like proteases, metal ions, and reducing agents. Recently, motor proteins or virus maturation have been seen to regulate virus entry through mechanical processes.
Let There Be (Optimal) Light
On average, the agricultural sector uses 70% of water withdrawals worldwide to produce crops1 and contributes to the eutrophication of lakes by using nutrients that are leached from the soils into lakes and reservoirs2. Vertical farming has great potential to remedy some of these issues. By growing plants vertically in controlled environments with artificial light and reusing the water, vertical farms use op to 99% less water3 and can produce up to 10 times the yield per square meter4 compared to traditional greenhouses. This improved efficiency comes at a cost; on average, vertical farms use more than 600% more energy per kilogramme of crop compared to traditional greenhouses5. 55% of this energy use is due to the use of artificial lighting6. Even though a lot of research is conducted on yield optimisation of crops in vertical farming, few research articles focus on the growth efficiency of crops to reduce the energy use in vertical farms. Only a few previous studies have tested photoperiods under 10 h·d-1. This study focuses on reducing the energy costs of light use in vertical farms by finding the photoperiod with highest energy use efficiency for the leafy vegetable arugula (eruca sativa). Energy use efficiency is defined as fresh mass per unit of electricity input (measured in kWh). In this study, arugula plants were exposed to LED growth light, with photoperiods ranging from 0 h·d-1 to 24 h·d-1 (0 h·d-1, 4 h·d-1, 7 h·d-1, 9 h·d-1, 12 h·d-1, 14 h·d-1, 16 h·d-1 and 24 h·d-1) and a PPFD of 800 μmol·m-2·s-1. The photoperiod 7 h·d-1 had the highest energy use efficiency of all photoperiods and, if used in vertical farms, this could account for approximately a 10 percent decrease in energy per kilogramme used in vertical farms (a 4 kWh decrease), with the planting density of 1400 plants per m2. This could amount to a yearly energy saving of 4,000,000 kWh per vertical farm (based on the yearly harvest of the vertical farm Nordic Harvest). This could help make vertical farming a more sustainable plant production for the future and in turn, help farming protect our water resources instead of consuming and polluting.
MEDTEC - Artificial Intelligence Software for medical diagnosis optimization and analysis
In Brazil, approximately sixty million people suffer from or acquire some type of disease daily. However, the average time for blood count diagnoses, used to identify many of these diseases, remains very lengthy. This can lead to the worsening of conditions and delays in care, as well as a decrease in the patients’ quality of life. Moreover, in some cases, the waiting period can result in irreversible situations and even the death of the affected individuals. In this landscape, technological tools such as artificial intelligence software can help reduce the time taken for diagnostic reporting. In light of this, the project involves developing software to assist in the analysis of blood counts and optimize medical diagnoses. For this purpose, the methodology was divided into three stages. In the first, titled ”Medical Standardization”, a survey of the standard variables related to diseases that can be identified with the help of blood counts was conducted. Among the findings, diabetes, anemia, leukemia, dengue, polycythemia, tuberculosis, leprosy, meningitis, chlamydia, schistosomiasis, spotted fever, and malaria were the main diseases detected. Furthermore, hemoglobin, leukocytes, platelets, glucose, cholesterol, ions, and hormones were the key findings concerning the primary blood indicative factors for the mentioned diseases. In the second phase, the theoretical and practical foundations of the software were developed, based on artificial neural networks. In Python, regression models were also crafted to check the feasibility of the analyses. Finally, the last stage consisted of testing with real datasets, based on 1,227 anonymized blood counts. Among the artificial intelligence algorithm models tested, Support Vector (0.02) and Multiple Linear (0.61) had the lowest performances, while Polynomial (0.97), Random Forest (1.0), and Decision Tree (1.0) showed the best results. Given that the Random Forest and Decision Tree regression models achieved an accuracy of 1.0, while the Polynomial model scored 0.97, Support Vector 0.02, and Multiple Linear Regression 0.61, it is concluded that the blood count analysis system, with Python tools like regression, proved to be highly efficient. The closer the R² value is to 1.0, the better the programming fits the model, ensuring accurate analyses. Aside from that, in order to expand the number of analysis possible to do be done we decided to use a second tool called ”classification”, with which we made a bigger dataset to be used as a model to identify blood related diseases and the behavior of complex and diverse diseases. With that in mind, we performed a second evaluation of the models by doing an accuracy test, scored 87 percentage points and with a confusion matrix. With those results, we verified that the high performance of the tests indicates that Artificial Intelligence can be avaunt-guard to the elaboration of more efficient medical diagnosis, improving people’s lives quality and, overall, lowering the number of deaths in our country.
Synthesis of Nanocomposite Nanocellulose From Durio zibethinus L. and TiO2 NPs as Potential Food Packaging Antibacterial (E. coli Wild Type and Resistance)
According to the 印尼n Association of Olefin Aromatic and Plastic Industries/INAPLAS, 2019 national plastic consumption still relies on plastic packaging at 65% and surprisingly, around 60% of plastic waste is absorbed by the food and beverage industry. The waste has been widely sought to be environmentally friendly, one of which is by developing biodegradable packaging. The purpose of this research is to make durian peel cellulose nanocomposites impregnated with TiO2 NPs, to form antibacterial properties against E. coli wild type and resistance. In this research, there are research methods consisting of nanocomposite synthesis, PSA test, FTIR, physical characteristics test and resistance test. The results analyzed that the nanocomposite nanocellulose-TiO2 NPs was successfully made using a 1:1 ratio and had a particle size of 458.7 nm based on the PSA test, which is classified as a nano size. The success of nanocomposite synthesis was proven by the results of FTIR analysis, which showed the formation of 698.65cm-1 and 1633.99cm-1 spectra, indicating the peak of TiO2 NPs and O-H functional groups on TiO2 NPs, as well as 1028.98cm-1 and 1158.42cm-1 showing C-O and C-O-C bonds in cellulose. The antibacterial test performed showed no significant activity in disc diffusion and well diffusion tests against E. coli wild type and resistance. This is potentially caused by inhomogeneous particle size variation. Physical characteristics test showed that the tensile strength test (0.075 > 0.0125 MPa) Durio Nano-Pack is superior to styrofoam, but the compressive strength test (0.125 > 0.875 MPa) shows the opposite. In this study, nanocomposite has a potential innovation that provides good mechanical properties and has a dual function mechanically as bio-based food packaging and chemically as antibacterial. Further research is needed to improve the particle size homogeneity of nanocomposites, modify the impregnation method, so that it has the potential to develop multifunctional materials that excel in various applications.