Pub Date : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10201200
Muhammad E V, Neethu Suman, Bobby Mathew C
A nurse call system is a valuable tool for improving patient care and optimizing hospital staff utilization. By providing efficient and attentive care, patients are more likely to feel comfortable and recover more quickly. Nurse call systems come in two main types: wired and wireless. While wired systems offer many advantages, they can be difficult to install, particularly in established hospitals. Therefore, we will focus on wireless nurse call systems in this paper because they are easy to install, portable, and flexible. However, wireless nurse call systems have some limitations, including battery life and coverage range. To address these issues, we propose a solution that utilizes LORA connectivity. This technology uses less power and has a longer range, eliminating the need for additional repeaters. Our proposed system uses push buttons at the patient station to communicate with an Arduino Nano, which transmits patient information via a LORA SX 1278 transceiver to the nurse station. The LORA transceiver at the nurse station receives the signal and sends it to the Arduino Nano, which controls four 8x8 led matrix displays through a MAX7219 IC. Based on our research, we conclude that incorporating LORA technology into wireless nurse call systems can make them more battery-efficient and offer longer range coverage. This solution can greatly improve patient care and help hospitals optimize their staff utilization.
{"title":"A Low Power, Long Range, Portable Wireless Nurse Call System","authors":"Muhammad E V, Neethu Suman, Bobby Mathew C","doi":"10.1109/ACCESS57397.2023.10201200","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10201200","url":null,"abstract":"A nurse call system is a valuable tool for improving patient care and optimizing hospital staff utilization. By providing efficient and attentive care, patients are more likely to feel comfortable and recover more quickly. Nurse call systems come in two main types: wired and wireless. While wired systems offer many advantages, they can be difficult to install, particularly in established hospitals. Therefore, we will focus on wireless nurse call systems in this paper because they are easy to install, portable, and flexible. However, wireless nurse call systems have some limitations, including battery life and coverage range. To address these issues, we propose a solution that utilizes LORA connectivity. This technology uses less power and has a longer range, eliminating the need for additional repeaters. Our proposed system uses push buttons at the patient station to communicate with an Arduino Nano, which transmits patient information via a LORA SX 1278 transceiver to the nurse station. The LORA transceiver at the nurse station receives the signal and sends it to the Arduino Nano, which controls four 8x8 led matrix displays through a MAX7219 IC. Based on our research, we conclude that incorporating LORA technology into wireless nurse call systems can make them more battery-efficient and offer longer range coverage. This solution can greatly improve patient care and help hospitals optimize their staff utilization.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114725514","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10199359
Indhu Kk, Abhilash Ap, Anilkumar R, Aanandan Ck
This paper proposes a simple triangle-shaped electromagnetic wave polarization rotation reflective surface (PRRS) for radar cross section (RCS) reduction of patch antenna over a wide band. It is possible to achieve a decrease in RCS in the frequency region of 13.2-17.9 GHz by placing the PRRS circling the patch antenna in directions that are orthogonal to one another. The simulation results indicate that the intended PRRS dramatically reduces the antenna RCS. The polarization rotation property of the proposed structure is verified experimentally. The suggested polarization converter has a very simple geometry in comparison to the existing designs.
{"title":"A Simple Low Profile Polarization Rotation Reflective Surface for RCS Reduction of Patch Antenna","authors":"Indhu Kk, Abhilash Ap, Anilkumar R, Aanandan Ck","doi":"10.1109/ACCESS57397.2023.10199359","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10199359","url":null,"abstract":"This paper proposes a simple triangle-shaped electromagnetic wave polarization rotation reflective surface (PRRS) for radar cross section (RCS) reduction of patch antenna over a wide band. It is possible to achieve a decrease in RCS in the frequency region of 13.2-17.9 GHz by placing the PRRS circling the patch antenna in directions that are orthogonal to one another. The simulation results indicate that the intended PRRS dramatically reduces the antenna RCS. The polarization rotation property of the proposed structure is verified experimentally. The suggested polarization converter has a very simple geometry in comparison to the existing designs.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116885527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10200511
Sudhakar Majjari, K. R. Anne, Joseph George
Internet of Things (IoT) trends show rising data processing computational needs. Sensor data is uploaded to backend cloud nodes before data analyses at the network edge. IoT devices are usually resource-constrained and unable to execute operations quickly and accurately. Cloud servers are impractical and increase communication overhead. Cloud platforms offer machine learning services with pretrained models to understand IoT data. To use the cloud service, personal data must be transferred, and network problems may impede timely analysis results. Data and analysis are shifting to edge platforms to solve these concerns. Most edge devices can't analyze and train a lot of data. Edge-enabled systems provide efficient compute and control at the network edge to reduce scalability and latency. IoT applications provide large heterogeneous data, which makes edge computing difficult. To solve this issue, Deep Reinforcement Learning (DRL) based data analytics framework for Edge based IoT devices to enable devices to execute tasks jointly, leveraging proximity and resource complementarity. It supports parallel data input and strengthen the comprehensive communication overhead handling through data scheduling optimization. The simulation results conveys that the proposed approach uses DRL to optimize execution accuracy and time without requiring a priori IoT node information. Moreover, the average delay time, percentage of failure and cost of rewards are computed in which being compared with the existing scheduling methods includes Proximal Policy Optimization technique (PPO), and Deep Deterministic Policy Gradient technique (DDPG).
{"title":"Deep Reinforcement Learning (DRL) based data analytics framework for Edge based IoT devices latency and resource optimization","authors":"Sudhakar Majjari, K. R. Anne, Joseph George","doi":"10.1109/ACCESS57397.2023.10200511","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10200511","url":null,"abstract":"Internet of Things (IoT) trends show rising data processing computational needs. Sensor data is uploaded to backend cloud nodes before data analyses at the network edge. IoT devices are usually resource-constrained and unable to execute operations quickly and accurately. Cloud servers are impractical and increase communication overhead. Cloud platforms offer machine learning services with pretrained models to understand IoT data. To use the cloud service, personal data must be transferred, and network problems may impede timely analysis results. Data and analysis are shifting to edge platforms to solve these concerns. Most edge devices can't analyze and train a lot of data. Edge-enabled systems provide efficient compute and control at the network edge to reduce scalability and latency. IoT applications provide large heterogeneous data, which makes edge computing difficult. To solve this issue, Deep Reinforcement Learning (DRL) based data analytics framework for Edge based IoT devices to enable devices to execute tasks jointly, leveraging proximity and resource complementarity. It supports parallel data input and strengthen the comprehensive communication overhead handling through data scheduling optimization. The simulation results conveys that the proposed approach uses DRL to optimize execution accuracy and time without requiring a priori IoT node information. Moreover, the average delay time, percentage of failure and cost of rewards are computed in which being compared with the existing scheduling methods includes Proximal Policy Optimization technique (PPO), and Deep Deterministic Policy Gradient technique (DDPG).","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129442426","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10199700
K. Singh, Prabh Deep Singh, Ankit Bansal, Gaganpreet Kaur, Vikas Khullar, V. Tripathi
The telecommunications business is one of the key industries with a higher risk of revenue loss owing to client turnover and environmental impact. Thus, efficient and effective churn management includes targeted marketing campaigns, special promotions, or other incentives to keep the customer engaged in technological progress. There are a lot of machine learning algorithms available now, but very few of them can effectively take into account the asymmetrical structure of the telecommunications dataset. The efficiency of machine learning algorithms may also vary depending on how closely they approximate the real-world telecommunications data rather than the publicly available dataset. As a result, the researchers used various predictive models, including XGBoost, for this dataset. The accuracy achieved on the native dataset is 82.80%. Results show the effectiveness of the predictive model with great technological capabilities.
{"title":"Exploratory Data Analysis and Customer Churn Prediction for the Telecommunication Industry","authors":"K. Singh, Prabh Deep Singh, Ankit Bansal, Gaganpreet Kaur, Vikas Khullar, V. Tripathi","doi":"10.1109/ACCESS57397.2023.10199700","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10199700","url":null,"abstract":"The telecommunications business is one of the key industries with a higher risk of revenue loss owing to client turnover and environmental impact. Thus, efficient and effective churn management includes targeted marketing campaigns, special promotions, or other incentives to keep the customer engaged in technological progress. There are a lot of machine learning algorithms available now, but very few of them can effectively take into account the asymmetrical structure of the telecommunications dataset. The efficiency of machine learning algorithms may also vary depending on how closely they approximate the real-world telecommunications data rather than the publicly available dataset. As a result, the researchers used various predictive models, including XGBoost, for this dataset. The accuracy achieved on the native dataset is 82.80%. Results show the effectiveness of the predictive model with great technological capabilities.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129596230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10200907
Kamal Saluja, S. Gupta, Vikas Solanki, Sanjoy Kumar Debnath, Ankit Bansal
The term "robot" refers to an electromechanical device that, as a result of its incorporation of electronic and computer programming, may carry out tasks either independently or in conjunction with a human operator [1]. Robots can be designed to perform functions in any order that the programmer specifies. Robots have found uses in a broad variety of disciplines, including those connected to the military, healthcare, and industry, among a number of other fields. Robots can be programmed to perform in either a mobile or stationary manner, and the choice of which mode to use is often dictated by the tasks that are intended to be carried out by the robots. It is extremely essential for a mobile robot to be able to traverse its environment in order for the robot to be capable of efficiently completing tasks, avoiding obstacles, and participating in other activities. This capability for navigation, which is dependent on sensors to supply environmental data as feedback signals, can be operator-independent or autonomous if "intelligence" is built into the computer code. Sensors are required to provide environmental data as feedback signals. Sensors are required to provide environmental data as return signals. This learning opportunity can be further used in affordable energy, agriculture, environmentally sound technologies, etc.
{"title":"An EEG-Based Brain-Computer Interface for Guiding Mobile Robots","authors":"Kamal Saluja, S. Gupta, Vikas Solanki, Sanjoy Kumar Debnath, Ankit Bansal","doi":"10.1109/ACCESS57397.2023.10200907","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10200907","url":null,"abstract":"The term \"robot\" refers to an electromechanical device that, as a result of its incorporation of electronic and computer programming, may carry out tasks either independently or in conjunction with a human operator [1]. Robots can be designed to perform functions in any order that the programmer specifies. Robots have found uses in a broad variety of disciplines, including those connected to the military, healthcare, and industry, among a number of other fields. Robots can be programmed to perform in either a mobile or stationary manner, and the choice of which mode to use is often dictated by the tasks that are intended to be carried out by the robots. It is extremely essential for a mobile robot to be able to traverse its environment in order for the robot to be capable of efficiently completing tasks, avoiding obstacles, and participating in other activities. This capability for navigation, which is dependent on sensors to supply environmental data as feedback signals, can be operator-independent or autonomous if \"intelligence\" is built into the computer code. Sensors are required to provide environmental data as feedback signals. Sensors are required to provide environmental data as return signals. This learning opportunity can be further used in affordable energy, agriculture, environmentally sound technologies, etc.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125258462","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10199887
Joseph George, A. K. Rao, Bipin P R, Majjari Sudhakar
Nowadays, skin diseases are among the most common health issues faced by people. Skin cancer (SC) is one of these diseases, and its detection relies on skin biopsy results and the expertise of doctors. However, this process is time-consuming and has poor accuracy. Detecting SC at an early stage is challenging, as it can quickly spread throughout the body, leading to higher mortality rates. Early detection of SC is crucial for successful treatment. The critical task in achieving accurate SC classification lies in identifying and classifying SC based on various features such as shape, size, color, symmetry, etc., which are also present in many other skin diseases. Selecting relevant features from a SC dataset image poses a significant challenge. Therefore, an automated SC detection and classification framework is required to improve diagnostic accuracy and address the shortage of human experts. In this paper, we implement a modified depth-wise Convolutional Neural Network (D-CNN) and compare its performance with other CNN frameworks, namely Deep Belief Network (DBN) and CNN-based cascaded ensemble network. We evaluate the effectiveness of SC identification using depth-wise CNN technique by employing performance metrics such as precision, recall, accuracy, sensitivity, specificity, and F-measure. The proposed technique not only improves classification accuracy but also reduces computational complexities and time consumption.
{"title":"Skin Cancer Classification from Skin Lesion Images Using Modified Depthwise Convolution Neural Network","authors":"Joseph George, A. K. Rao, Bipin P R, Majjari Sudhakar","doi":"10.1109/ACCESS57397.2023.10199887","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10199887","url":null,"abstract":"Nowadays, skin diseases are among the most common health issues faced by people. Skin cancer (SC) is one of these diseases, and its detection relies on skin biopsy results and the expertise of doctors. However, this process is time-consuming and has poor accuracy. Detecting SC at an early stage is challenging, as it can quickly spread throughout the body, leading to higher mortality rates. Early detection of SC is crucial for successful treatment. The critical task in achieving accurate SC classification lies in identifying and classifying SC based on various features such as shape, size, color, symmetry, etc., which are also present in many other skin diseases. Selecting relevant features from a SC dataset image poses a significant challenge. Therefore, an automated SC detection and classification framework is required to improve diagnostic accuracy and address the shortage of human experts. In this paper, we implement a modified depth-wise Convolutional Neural Network (D-CNN) and compare its performance with other CNN frameworks, namely Deep Belief Network (DBN) and CNN-based cascaded ensemble network. We evaluate the effectiveness of SC identification using depth-wise CNN technique by employing performance metrics such as precision, recall, accuracy, sensitivity, specificity, and F-measure. The proposed technique not only improves classification accuracy but also reduces computational complexities and time consumption.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128631451","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10199873
Gutti Venkata Ranga Priyanka, A. T, Niktha Malladi
One of the most well-known online communities for question and answer exchanges is the Quora platform, with millions of users asking and answering questions on a wide range of topics. However, a major issue faced by the Quora community is the high quantity of questions that are duplicates that are posted on the platform. These duplicate questions not only clutter the platform but also affect the quality of content, making it difficult for users to find relevant information. Hence, there is a need to automatically identify and remove duplicate question pairs in the Quora community. Duplicate question pair detection is a a difficult issue because of the considerable fluctuation and complexity of natural language. Traditional rule-based approaches are often insufficient for capturing the nuanced meaning and context of questions. Therefore, machine learning-based methods have gained popularity in recent years for detecting duplicate question pairs. This paper proposes a framework for detecting duplicate question pairs on the Quora platform using Siamese Neural Network, BERT, MaLSTM, and BiLSTM models. Each model's effectiveness is evaluated using a variety of evaluation criteria, including accuracy, precision, recall, and F1-score, on a dataset of Quora question pairs. The experimental outcomes demonstrate that the proposed framework detects duplicate question pairs with high accuracy. with the BERT model outperforming the other models in terms of overall performance. This suggests that pretrained transformer networks can effectively capture the semantic meaning of questions and enhance the performance of duplicate question pair detection
{"title":"Duplicate Quora Questions Pair Detection using Siamese Bert and Ma-LSTM","authors":"Gutti Venkata Ranga Priyanka, A. T, Niktha Malladi","doi":"10.1109/ACCESS57397.2023.10199873","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10199873","url":null,"abstract":"One of the most well-known online communities for question and answer exchanges is the Quora platform, with millions of users asking and answering questions on a wide range of topics. However, a major issue faced by the Quora community is the high quantity of questions that are duplicates that are posted on the platform. These duplicate questions not only clutter the platform but also affect the quality of content, making it difficult for users to find relevant information. Hence, there is a need to automatically identify and remove duplicate question pairs in the Quora community. Duplicate question pair detection is a a difficult issue because of the considerable fluctuation and complexity of natural language. Traditional rule-based approaches are often insufficient for capturing the nuanced meaning and context of questions. Therefore, machine learning-based methods have gained popularity in recent years for detecting duplicate question pairs. This paper proposes a framework for detecting duplicate question pairs on the Quora platform using Siamese Neural Network, BERT, MaLSTM, and BiLSTM models. Each model's effectiveness is evaluated using a variety of evaluation criteria, including accuracy, precision, recall, and F1-score, on a dataset of Quora question pairs. The experimental outcomes demonstrate that the proposed framework detects duplicate question pairs with high accuracy. with the BERT model outperforming the other models in terms of overall performance. This suggests that pretrained transformer networks can effectively capture the semantic meaning of questions and enhance the performance of duplicate question pair detection","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121316090","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10200132
Athul Parameswaran, R. O
This paper describes the design of a low frequency dual band metamaterial absorber. The unit cell of the proposed absorber contains 3 hexagonal split ring resonators with four wave trappers encircled in a circular ring resonator. The modelling and simulation of the unit cell with a dimension of 32mm X 32mm are carried out in ANSYS HFSS. For enhancing the absorption capability, complete metal backing is provided for the proposed structure. On simulation, perfect absorption is achieved at 2.4 GHz (ISM band) and 5.3 GHz (satellite band) frequencies. The metamaterial element is modelled on FR4_epoxy substrate with a dielectric constant of 4.4 and loss tangent of 0.02. The metamaterial properties of the proposed structure are investigated using S- parameter retrieval method and found to have perfect double negative behavior at 2.4GHz.
{"title":"Dual Band Metamaterial Absorber For S And C Band Applications","authors":"Athul Parameswaran, R. O","doi":"10.1109/ACCESS57397.2023.10200132","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10200132","url":null,"abstract":"This paper describes the design of a low frequency dual band metamaterial absorber. The unit cell of the proposed absorber contains 3 hexagonal split ring resonators with four wave trappers encircled in a circular ring resonator. The modelling and simulation of the unit cell with a dimension of 32mm X 32mm are carried out in ANSYS HFSS. For enhancing the absorption capability, complete metal backing is provided for the proposed structure. On simulation, perfect absorption is achieved at 2.4 GHz (ISM band) and 5.3 GHz (satellite band) frequencies. The metamaterial element is modelled on FR4_epoxy substrate with a dielectric constant of 4.4 and loss tangent of 0.02. The metamaterial properties of the proposed structure are investigated using S- parameter retrieval method and found to have perfect double negative behavior at 2.4GHz.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116728837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10201003
Pooja Sidharthan, D. S. kumar
Energy is the fundamental part of life and there is great demand of using renewable energy sources. Energy can be harvested from human body movements using piezoelectric transducers. The energy wasted during walking and exercising can be converted into useful energy is considered in this paper. The proposed system consists of the piezoelectric transducers on which the muscle force is applied. The AC signal from piezoelectric transducers is converted to DC using bridge rectifier. Then the DC signal is boosted by a DC-DC boost converter and the energy is stored in a supercapacitor. Due to the fast discharging rate of supercapacitor, it is thereby discharged to a rechargeable battery. This can power up the Arduino and thereby the electromyography sensor which analyses the muscle activity. A mathematical model can be used determine the work-done by lifting some known weights and comparing with electromyographic value. Series-parallel combination of piezoelectric transducers provides more voltage and current. Amplitude variations while lifting different known weights are analyzed using electromyography sensors. Deviation of conceptual work-done and measured value is analyzed.
{"title":"Energy Harvesting based Electromyography Analysis for Muscle Activity","authors":"Pooja Sidharthan, D. S. kumar","doi":"10.1109/ACCESS57397.2023.10201003","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10201003","url":null,"abstract":"Energy is the fundamental part of life and there is great demand of using renewable energy sources. Energy can be harvested from human body movements using piezoelectric transducers. The energy wasted during walking and exercising can be converted into useful energy is considered in this paper. The proposed system consists of the piezoelectric transducers on which the muscle force is applied. The AC signal from piezoelectric transducers is converted to DC using bridge rectifier. Then the DC signal is boosted by a DC-DC boost converter and the energy is stored in a supercapacitor. Due to the fast discharging rate of supercapacitor, it is thereby discharged to a rechargeable battery. This can power up the Arduino and thereby the electromyography sensor which analyses the muscle activity. A mathematical model can be used determine the work-done by lifting some known weights and comparing with electromyographic value. Series-parallel combination of piezoelectric transducers provides more voltage and current. Amplitude variations while lifting different known weights are analyzed using electromyography sensors. Deviation of conceptual work-done and measured value is analyzed.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121488625","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-05-18DOI: 10.1109/ACCESS57397.2023.10199916
Shiv Kumar, Vikas K. Garg, Ankit Bansal, K. Singh
Automation is part of life these days. Every gadget in our routine lives is part of artificial intelligence these days. Vehicles are also part of this update these days. Almost all the automations around us that concern vehicles are useful. From the auto-engine-check system to the automatic cleaning of the wind screen and the auto-door-lock system to the anti-lock-braking system and the auto-air-bag system, all are useful and are part of vehicle safety these days. Furthermore, the auto-dip system is important in vehicle automation. Nearly 50% of accidents these days are due to bad driving at night. Dipping headlights play a vital role in visibility at night. Several papers have been published in response to this concern about the course of scarcity. Some are widely used in the market, but they have limitations, such as not being able to provide legally required removal or working in every climate. The framework is required and won't influence the exhibition of vehicles. This paper proposes an innovative system of auto-dipping using LiDAR that is accurate and will work in every atmospheric condition. Moreover, the auto-dipping system that is proposed is handy and innumerable in terms of weight.
{"title":"A Novel Approach To Auto Dipping System Of Vehicles Based On LiDAR","authors":"Shiv Kumar, Vikas K. Garg, Ankit Bansal, K. Singh","doi":"10.1109/ACCESS57397.2023.10199916","DOIUrl":"https://doi.org/10.1109/ACCESS57397.2023.10199916","url":null,"abstract":"Automation is part of life these days. Every gadget in our routine lives is part of artificial intelligence these days. Vehicles are also part of this update these days. Almost all the automations around us that concern vehicles are useful. From the auto-engine-check system to the automatic cleaning of the wind screen and the auto-door-lock system to the anti-lock-braking system and the auto-air-bag system, all are useful and are part of vehicle safety these days. Furthermore, the auto-dip system is important in vehicle automation. Nearly 50% of accidents these days are due to bad driving at night. Dipping headlights play a vital role in visibility at night. Several papers have been published in response to this concern about the course of scarcity. Some are widely used in the market, but they have limitations, such as not being able to provide legally required removal or working in every climate. The framework is required and won't influence the exhibition of vehicles. This paper proposes an innovative system of auto-dipping using LiDAR that is accurate and will work in every atmospheric condition. Moreover, the auto-dipping system that is proposed is handy and innumerable in terms of weight.","PeriodicalId":345351,"journal":{"name":"2023 3rd International Conference on Advances in Computing, Communication, Embedded and Secure Systems (ACCESS)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129321668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：