Load Forecasting using Machine Learning Model Rupesh, K C; Renushree, G; Deepika, S ...
2024 International Conference on Smart Systems for applications in Electrical Sciences (ICSSES),
2024-May-3
Conference Proceeding
This paper presents a comprehensive system for load forecasting, a critical component in energy management. The system employs advanced machine learning techniques, specifically the Long Short-Term ...Memory (LSTM) model, to provide accurate and tailored load forecasts. The paper follows a streamlined flow, integrating data collection, pre-processing, model training, and user interaction. The system's architecture involves a react front-end for user interaction and a flask backend for seamless communication with the machine learning model. Visual representations, such as line graphs, enhance the understanding of load patterns, and interpolation/extrapolation techniques contribute to the system's forecasting accuracy. Experiments were involved using XGBoost model. Compared to XGBoost model and LSTM has better accuacy.
Detecting suspicious activities in public places with higher people gathering and interaction has turned out to be an act with growing interest due to the increasing number of crime scenes and ...causalities happening in these days. Surveying and tracking of human activities are increasingly difficult owing to the random nature of human movements and actions. The reliability is greatly affected due to this randomness. Also a human operator cannot continuously monitor multiple screens efficiently in a consequent manner so an automated surveillance system deployment becomes a necessity. Currently, tracking individuals may be done remotely, and the analysis of the recorded images can be automated using object detection models, with the help of high resolution cameras and the development of machine learning techniques. This proposed system aims in identifying threats that are probable to occur in a public gathering or space which may be an explosion, accident or possession of armoury, etc. This proposed model takes advantage of the information from the image data to learn complex patterns and develop pattern recognition technique to identify the anomalies using high resolution camera and alert the monitoring authority in order to take the necessary actions. This proposed work compares various object detection techniques of machine learning algorithms and suggests the best model based on its performance metrics.
Predictive Maintenance of Machine Tools Thenmozhi, M.; A, Kavya; M, Vishnu ...
2024 International Conference on Science Technology Engineering and Management (ICSTEM),
2024-April-26
Conference Proceeding
The study takes an empirical approach by testing the proposed predictive maintenance system in a real industrial scenario. To begin, data is collected from diverse sources within the industrial ...ecosystem, which includes information gathered through system, which combines data acquired from sensors, devices with PLCs (programmable logic controllers), and different communication protocols. This rich and diverse dataset is then processed and made accessible through a Data Analysis Tool. One of the key strengths of this approach is its reliance on Machine Learning, specifically the logistic regression and support vector machine. It is well-suited for predictive maintenance because of its ability to handle complex datasets and relationships among different variables. The paper details the process of applying the logistic regression and support vector machine approach to the collected data, which allows for the prediction of various machine states. This is crucial in foreseeing potential issues before they escalate into significant failures, enabling timely maintenance interventions. Moreover, the research extends its assessment by comparing the outcomes of the Machine Learning approach to results obtained using simulation tools, thus providing a comprehensive an assessment of the system for predictive maintenance.
This project, "Enhancing Trust in Currency Transactions: Currency Note Authentication with Transfer Learning," employs transfer learning in machine learning to improve the accuracy and efficiency of ...authenticating physical currency notes. By leveraging pre-trained deep learning models, the system distinguishes genuine from counterfeit notes, bolstering trust in currency transactions. The research includes developing a transfer learning framework, creating datasets, and evaluating the system's effectiveness against counterfeit scenarios. This work contributes to enhancing the security of currency transactions in our digital financial landscape.
The role of hydrolytic enzymes (proteases and chitinase) and oxidative stress in the autolysis and morphology of Blakeslea trispora during β-carotene production from a chemically defined medium in ...shake flask culture was investigated. The process of cellular autolysis was studied by measuring the changes in biomass dry weight, pH, concentration of β-carotene, specific activity of the hydrolytic enzymes and micromorphology of the fungus using a computerized image analysis system. In addition, the phenomenon of autolysis was associated with high concentrations of reactive oxygen species (ROS). The accumulation of ROS produced during fermentation causes oxidative stress in B. trispora. Oxidative stress was examined in terms of the activities of two key defensive enzymes: catalase (CAT) and superoxide dismutase (SOD). The profile of the specific activities of the above enzymes appeared to correlate with the oxidative stress of the fungus. The high activities of CAT and SOD showed that B. trispora is found under oxidative stress during β-carotene production. The culture began to show signs of autolysis nearly in the growth phase and autolysis increased significantly during the production phase. The morphological differentiation of the fungus was a result of the degradation of the cell membrane by hydrolytic enzymes and oxidative stress. Increased β-carotene production is correlated with intense autolysis of clumps, which has as a consequence the increase of the freely dispersed mycelia.
Full text
Available for:
CEKLJ, DOBA, EMUNI, FZAB, GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UILJ, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ
In this paper we study the steady state deflection and reverse snapping phenomenon of a spinning non-flat disk. Both the initial and the deformed shapes of the disk are allowed to have axisymmetrical ...and unsymmetrical components. For the analysis of a rotating axisymmetrical disk, we conclude that there is no need to include the unsymmetrical assumed modes in the solution because all the unsymmetrical steady state deformations are unstable. In addition, the stability of the axisymmetrical positions will not be affected by the inclusion of the unsymmetrical assumed modes. In the case when the initial shape of the disk contains a dominant axisymmetrical component and a smaller unsymmetrical component, attention is focused on the effect of this unsymmetrical component on the overall deformation and stability of the spinning disk. It is found that the unsymmetrical component with one nodal diameter tends to slightly defer the occurrence of the reverse snapping phenomenon. On the other hand, all other unsymmetrical components with more than one nodal diameter tend to reduce dramatically the reverse snapping speed. Experiment is conducted on a non-flat brass disk containing an axisymmetrical component and an unsymmetrical component with two nodal diameters. The experimental measurement confirms the theoretical prediction.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
In the Internet of Things (IoT) scenario, the hardware resources in the edge computing paradigm are limited, so the applications in the cloud computing paradigm are not suitable for edge computing. ...New system architecture and key technologies are needed for application implement and deployment in edge computing. Based on the hardware performance constraints and scene functional requirements under edge computing, this paper designs and develops a microservice system for edge computing. So it introduces the design of microservice system architecture for edge computing. And it analyzes the key technologies of the system. It selects the PostgreSQL database to achieve data storage, the Flask framework to build back-end services, and the Vue.js framework to build front-end services. Meanwhile, docker containers are used for system deployment and testing. The test results prove that the system has perfect functions and stable operation, which is very suitable for edge devices with limited resources. According to the start-up time and resource consumption of the project, the distributed deployment of applications has better performance than the unified deployment.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Abstract For various reasons, many people suspected of driving under the influence of alcohol (DUIA) are not apprehended sitting behind the wheel, but some time after the driving. This gives them the ...opportunity to claim they drank alcohol after the time of driving or after they were involved in a road-traffic crash. Alleged post-offence drinking is not easy for the prosecution to disprove, which often means that the DUIA charge is dropped or the person is acquitted if the case goes to trial. The routine practice of sampling and measuring the concentration of alcohol in blood (BAC) and urine (UAC) and calculating urine/blood ratios (UAC/BAC) and the changes in UAC between two successive voids furnishes useful information to support or challenge alleged drinking after driving. We present here a retrospective case series of DUIA offenders ( N = 40) in half of which there was supporting evidence of an after-drink (eye witness or police reports) and in the other half no such evidence existed apart from the suspect's admission. When there was supporting evidence of an after-drink, the UAC/BAC ratio for the first void was close to or less than unity (mean 1.04, median 1.08, range 0.54–1.21) and the UAC increased by 0.21 g/L (range 0.02–0.57) between the two voids. Without any supporting evidence of post-offence drinking the mean UAC/BAC ratio was 1.46 (range 1.35–1.93) for the first void, verifying that absorption and distribution of alcohol in all body fluids and tissues was complete. In these cases, the UAC between successive voids decreased by 0.25 g/L on average (range 0.10–0.49), indicating the post-absorptive phase of the BAC curve. Long experience from investigating claims of post-offence drinking leads us to conclude that in the vast majority of cases this lacks any substance and is simply a last resort by DUIA offenders to evade justice. Unless supporting evidence exists (eye witness, police reports, etc.) of post-offence drinking the courts are encouraged to ignore this defence argument.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
RésuméLe modèle collaboratif a été testé dans le cadre de l’amélioration de la qualité des services de vaccination et de surveillance des maladies cibles dans la commune de Pèrèrè, au Bénin. Elle a ...pour objectif de mesurer l’impact de ce type d’approche sur l’amélioration des couvertures vaccinales et la détection des cas suspects de paralysie flasque aiguë. Après la mise en place du modèle collaboratif, les données relatives aux couvertures vaccinales et à la détection des cas de paralysies flasques aiguës ont été recueillies au moyen des rapports d’activités mensuels des formations sanitaires et analysées sur une période de deux ans. Les couvertures vaccinales ont progressé entre 2004 et 2005 et six cas suspects de paralysie flasque aiguë ont été notifiés en 2004 contre 1 cas en 2003. La mise en place du modèle collaboratif a eu un impact positif sur l’amélioration de la performance du programme de vaccination, la notification des cas et sur le renforcement du partenariat entre les structures sanitaires et les communautés.
The rapid advancement of the integration between sport science and computer technology has given rise to a new web-based application with focus on sports analysis. The design and development process ...of this web application is presented in this paper, focusing on the workflow and processes involved using Python Flask framework, video processing, video manifest structure, database structure with MongoDB, machine learning back-end with Keypoint RCNN, and the front-end intuitive data visualisation interface. Insights of athletes performance are gained through the integration of frame accurate video play-back, human pose estimation, concise biomechanical reporting, and consistency measurements. Despite its primary emphasis on archery, the fundamental workings can be applied to a broader sporting implementations. Preliminary field tests with a sports centre indicate a positive reception from users, noting its efficiency and depth of analysis. This paper highlights the capacity of integrating computational tools with sport science to provide objective insights to optimise training and performance evaluation.