Pub Date : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170536
Sundaresan Sabapathy, Aswini Krishnan, Nishanth Nedoumarane, Surendar Maruthu, D. Jayakody
The exponential growth of wireless data services driven by mobile internet and connected devices has triggered the thriving of beyond fifth-generation (B5G) cellular networks. The integration of simultaneous wireless information and power transfer (SWIPT), non-orthogonal multiple access (NOMA), with multiple antenna system is a potential solution to improve spectral efficiency (SE) and energy efficiency (EE). Moreover, it paves the way for ultra-reliable and low-latency communication (URLLC) and massive machine-type communication (mMTC) scenarios. This paper explores an optimal solution for power allocation (PA) and power splitting (PS) control for EE maximization in SWIPT-based multiple input multiple outputs (MIMO) NOMA system. The significant aim is to maximize the EE of the system, maintaining equal fairness among the users in the cluster while satisfying the quality-of-service (QoS) requirements. The optimal solution to fulfill the trade-off between data decoded and energy harvested (EH) at the receiver is achieved through a deep learning (DL) model, viz., deep belief network (DBN). The dataset consisting of 3500 samples is created by varying the power levels from 20 dBm to 40 dBm, and also varying the distance of the users from the base station (BS). The PA and PS efficiency of 94.09 and 91.36 percent respectively, is achieved with DBN which aids for energy and SE in SWIPT MIMO NOMA system for 5GB.
由移动互联网和连接设备驱动的无线数据服务的指数级增长引发了第五代(B5G)以上蜂窝网络的蓬勃发展。同时无线信息与功率传输(SWIPT)、非正交多址(NOMA)与多天线系统的集成是提高频谱效率(SE)和能量效率(EE)的一种潜在解决方案。此外，它还为超可靠和低延迟通信(URLLC)和大规模机器类型通信(mMTC)场景铺平了道路。本文探讨了基于swipt的多输入多输出(MIMO) NOMA系统中功率分配(PA)和功率分割(PS)控制的最佳解决方案，以实现EE的最大化。重要的目标是最大化系统的EE，在满足服务质量(QoS)要求的同时保持集群中用户之间的公平。通过深度学习(DL)模型，即深度信念网络(DBN)，实现了在接收端解码数据和能量收集(EH)之间权衡的最佳解决方案。该数据集由3500个样本组成，通过改变功率水平从20 dBm到40 dBm，并改变用户到基站的距离(BS)来创建。在5GB的SWIPT MIMO NOMA系统中，DBN的PA效率和PS效率分别为94.9%和91.36%。
{"title":"Deep Learning based Simultaneous Wireless Information and Power Transfer Enabled Massive MIMO NOMA for Beyond 5G","authors":"Sundaresan Sabapathy, Aswini Krishnan, Nishanth Nedoumarane, Surendar Maruthu, D. Jayakody","doi":"10.1109/IConSCEPT57958.2023.10170536","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170536","url":null,"abstract":"The exponential growth of wireless data services driven by mobile internet and connected devices has triggered the thriving of beyond fifth-generation (B5G) cellular networks. The integration of simultaneous wireless information and power transfer (SWIPT), non-orthogonal multiple access (NOMA), with multiple antenna system is a potential solution to improve spectral efficiency (SE) and energy efficiency (EE). Moreover, it paves the way for ultra-reliable and low-latency communication (URLLC) and massive machine-type communication (mMTC) scenarios. This paper explores an optimal solution for power allocation (PA) and power splitting (PS) control for EE maximization in SWIPT-based multiple input multiple outputs (MIMO) NOMA system. The significant aim is to maximize the EE of the system, maintaining equal fairness among the users in the cluster while satisfying the quality-of-service (QoS) requirements. The optimal solution to fulfill the trade-off between data decoded and energy harvested (EH) at the receiver is achieved through a deep learning (DL) model, viz., deep belief network (DBN). The dataset consisting of 3500 samples is created by varying the power levels from 20 dBm to 40 dBm, and also varying the distance of the users from the base station (BS). The PA and PS efficiency of 94.09 and 91.36 percent respectively, is achieved with DBN which aids for energy and SE in SWIPT MIMO NOMA system for 5GB.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114910364","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170307
Archana Saini, Kalpna Guleria, Shagun Sharma
With the evolvement in technology and social media, the prevalence of fake news is rapidly increasing. It has become a new research field that is gaining popularity and requires attention. However, due to a scarcity of resources such as insufficient and invalid datasets along with analysis techniques, there are various challenges such as the flourishment of fake news, that are faced. It has a considerable influence on everyday lives, as well as in almost every single field, especially politics, and education. Hence, this condition requires attention to detect fake news for reducing distrust in the government systems. This article introduces a solution to fake news detection by implementing a model using various classification techniques. This work has been implemented with Decision Tree, Random Forest, Logistic Regression, and Passive Aggressive Classifier for identifying fake news. However, the outcome of the passive-aggressive classifier has resulted in the highest accuracy of 93.05%. Furthermore, this work can help in the real-time identification of fake news leading to maintaining people’s trust on social media and government systems.
{"title":"An Automatic Fake News Identification System using Machine Learning Techniques","authors":"Archana Saini, Kalpna Guleria, Shagun Sharma","doi":"10.1109/IConSCEPT57958.2023.10170307","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170307","url":null,"abstract":"With the evolvement in technology and social media, the prevalence of fake news is rapidly increasing. It has become a new research field that is gaining popularity and requires attention. However, due to a scarcity of resources such as insufficient and invalid datasets along with analysis techniques, there are various challenges such as the flourishment of fake news, that are faced. It has a considerable influence on everyday lives, as well as in almost every single field, especially politics, and education. Hence, this condition requires attention to detect fake news for reducing distrust in the government systems. This article introduces a solution to fake news detection by implementing a model using various classification techniques. This work has been implemented with Decision Tree, Random Forest, Logistic Regression, and Passive Aggressive Classifier for identifying fake news. However, the outcome of the passive-aggressive classifier has resulted in the highest accuracy of 93.05%. Furthermore, this work can help in the real-time identification of fake news leading to maintaining people’s trust on social media and government systems.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128197275","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170157
P. V. Yeswanth, Raavi Raviteja, S. Deivalakshmi
A prevalent and serious illness that affects people all over the globe is tuberculosis. A successful diagnosis of tuberculosis is essential for better survival rates and a successful course of treatment. Different techniques for detecting tuberculosis have been developed recently as a result of advancements in medical technology. These techniques have greatly increased the reliability and precision of tuberculosis detection. Finding tuberculosis at an early state, in which it is most treatable, is still a challenge. In order to improve the resolution of X-ray chest images for the early detection of tuberculosis, study is currently being done in this area. The Sovereign Critique Network (SCN) model is suggested in this article as a means of generating super resolution images from low-resolution X-ray images. The suggested SCN model is evaluated on the Tuberculosis (TB) Chest X-ray database for super resolution factors of 2, 4, and 6 separately with PSNR values of 31.85, 33.79, and 35.93 and SSIM values of 0.84, 0.91, and 0.96 for super resolution factors 2, 4, and 6, respectively. The proposed model shows promising results than any of the existing models.
{"title":"Sovereign Critique Network (SCN) Based Super-Resolution for chest X-rays images","authors":"P. V. Yeswanth, Raavi Raviteja, S. Deivalakshmi","doi":"10.1109/IConSCEPT57958.2023.10170157","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170157","url":null,"abstract":"A prevalent and serious illness that affects people all over the globe is tuberculosis. A successful diagnosis of tuberculosis is essential for better survival rates and a successful course of treatment. Different techniques for detecting tuberculosis have been developed recently as a result of advancements in medical technology. These techniques have greatly increased the reliability and precision of tuberculosis detection. Finding tuberculosis at an early state, in which it is most treatable, is still a challenge. In order to improve the resolution of X-ray chest images for the early detection of tuberculosis, study is currently being done in this area. The Sovereign Critique Network (SCN) model is suggested in this article as a means of generating super resolution images from low-resolution X-ray images. The suggested SCN model is evaluated on the Tuberculosis (TB) Chest X-ray database for super resolution factors of 2, 4, and 6 separately with PSNR values of 31.85, 33.79, and 35.93 and SSIM values of 0.84, 0.91, and 0.96 for super resolution factors 2, 4, and 6, respectively. The proposed model shows promising results than any of the existing models.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"297 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123464237","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}
Alzheimer’s disease (AD) is a progressive neurological ailment causing damage to brain cells. Beginning with mild symptoms that usually goes unnoticed, the disorder gets worse as it progresses hindering the general abilities of person. Early AD symptoms being ordinarily simple, detection occurs only on disease progression to an advance irreversible stage. Early detection of AD is thus critical to reduce the adverse effects of the disease. Earlier detection can prove promising for the development of specific treatment strategies that improve or slow AD progression. Machine Learning (ML) approach has become increasingly useful in the detection of Alzheimer’s disease in recent years. In this paper, early detection of Alzheimer’s disease using different machine learning algorithms for predictive categorization of patients is presented. The study suggests that random forest algorithm offers best performance for early prediction of Alzheimer’s disease with an accuracy of 93.69%. A GUI for users to enter parameters for early detection and display the categorized result for random forest algorithm is also designed.
{"title":"Early Alzheimer’s Detection Using Random Forest Algorithm","authors":"Pranjlee Kolte, Nandani Rabra, Aditya Shrivastava, Anushka Khadatkar, Himanshu Choudhary, Divya Shrivastava","doi":"10.1109/IConSCEPT57958.2023.10170234","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170234","url":null,"abstract":"Alzheimer’s disease (AD) is a progressive neurological ailment causing damage to brain cells. Beginning with mild symptoms that usually goes unnoticed, the disorder gets worse as it progresses hindering the general abilities of person. Early AD symptoms being ordinarily simple, detection occurs only on disease progression to an advance irreversible stage. Early detection of AD is thus critical to reduce the adverse effects of the disease. Earlier detection can prove promising for the development of specific treatment strategies that improve or slow AD progression. Machine Learning (ML) approach has become increasingly useful in the detection of Alzheimer’s disease in recent years. In this paper, early detection of Alzheimer’s disease using different machine learning algorithms for predictive categorization of patients is presented. The study suggests that random forest algorithm offers best performance for early prediction of Alzheimer’s disease with an accuracy of 93.69%. A GUI for users to enter parameters for early detection and display the categorized result for random forest algorithm is also designed.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"114 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131475119","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170275
Kavitha Kumari.K.S, L. Chitra, Jibin M Abraham, Noyal Joseph, Yedu Krishnan T.K
Electric vehicle (EV) performance is influenced by a variety of parameters like battery life, cell voltage and health, safety and charging-discharging speeds. In EVs, the battery management is a crucial task which facilitates the effective functioning of battery. This paper suggests an improved monitoring of battery State-Of-Charge (SOC) using Internet of Things (IOT) and Artificial Intelligence (AI). This paper focus on a problem for researchers in order to ensure the safety of cars and users by exactly estimating SOC, monitoring and spotting in-time breakdowns of the rechargeable batteries of electric vehicles respectively. The voltage obtained from the Photovoltaic (PV) system is improved by the Boost integrated fly back rectifier energy DC-DC (BIFRED) converter which is controlled by an cascaded ANFIS controller. The SOC of the battery is monitored by Recurrent Neural Networks (RNN) and the data is stored in IOT. The IOT allows for the continuous monitoring and transmission of all battery-related data to the cloud, enabling for the capture of real-time battery information. Thus this paper clearly focus on monitoring and estimating time breakdown of the rechargeable batteries of vehicles.
{"title":"The Role of IOT & AI in Battery Management of Electric Vehicles","authors":"Kavitha Kumari.K.S, L. Chitra, Jibin M Abraham, Noyal Joseph, Yedu Krishnan T.K","doi":"10.1109/IConSCEPT57958.2023.10170275","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170275","url":null,"abstract":"Electric vehicle (EV) performance is influenced by a variety of parameters like battery life, cell voltage and health, safety and charging-discharging speeds. In EVs, the battery management is a crucial task which facilitates the effective functioning of battery. This paper suggests an improved monitoring of battery State-Of-Charge (SOC) using Internet of Things (IOT) and Artificial Intelligence (AI). This paper focus on a problem for researchers in order to ensure the safety of cars and users by exactly estimating SOC, monitoring and spotting in-time breakdowns of the rechargeable batteries of electric vehicles respectively. The voltage obtained from the Photovoltaic (PV) system is improved by the Boost integrated fly back rectifier energy DC-DC (BIFRED) converter which is controlled by an cascaded ANFIS controller. The SOC of the battery is monitored by Recurrent Neural Networks (RNN) and the data is stored in IOT. The IOT allows for the continuous monitoring and transmission of all battery-related data to the cloud, enabling for the capture of real-time battery information. Thus this paper clearly focus on monitoring and estimating time breakdown of the rechargeable batteries of vehicles.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122331888","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10169937
Pavan Adulapuram, C. Kumar, Tejaswini Tula, Farasha Mehroz Mohammed Abdul, Sritha Katrapally, Lavan Kumar Pakala
Due to significant short-channel effects scaling circuits for typical single-gate MOSFET’s is extremely difficult. Circuits are scaled down to rise operational speed, consume less space, and improve control over channel by gate configurations. But as a result of diluted geometries, lower supply voltage and higher frequencies all have impact on device, scaling faces a number of challenges. The short-channel effect issue in MOSFETs is subsidized by the use of FinFET. For good control, a second gate is added to double gate device and is placed opposite to first gate. The mostly used subcircuits particularly in arithmetic circuits are EX-OR, EX-NOR circuits which are created to boost speed and power. As a result, EX-OR, EX-NOR circuit which is based on CADENCE VIRTUOSO tool at 18nm, uses a 0.7v supply voltage performs better than a complex logic circuit.
{"title":"A FinFET pass transistor based XOR and XNOR circuit designed for 18nm technology","authors":"Pavan Adulapuram, C. Kumar, Tejaswini Tula, Farasha Mehroz Mohammed Abdul, Sritha Katrapally, Lavan Kumar Pakala","doi":"10.1109/IConSCEPT57958.2023.10169937","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10169937","url":null,"abstract":"Due to significant short-channel effects scaling circuits for typical single-gate MOSFET’s is extremely difficult. Circuits are scaled down to rise operational speed, consume less space, and improve control over channel by gate configurations. But as a result of diluted geometries, lower supply voltage and higher frequencies all have impact on device, scaling faces a number of challenges. The short-channel effect issue in MOSFETs is subsidized by the use of FinFET. For good control, a second gate is added to double gate device and is placed opposite to first gate. The mostly used subcircuits particularly in arithmetic circuits are EX-OR, EX-NOR circuits which are created to boost speed and power. As a result, EX-OR, EX-NOR circuit which is based on CADENCE VIRTUOSO tool at 18nm, uses a 0.7v supply voltage performs better than a complex logic circuit.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116473934","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170489
A. Lavanya, S. Nagaraj, Lekhya M
Vedic multiplier uses adders as its fundamental building block. One of the crucial performance criteria for many digital circuits is the circuit’s operating speed, which ultimately depends on the basic adder unit’s delay. This project is devoted to the construction and analysis of a speed Vedic multiplier that uses various adders to analyse speed, area, and power. Using the carry increment adder and Halfadders in Verilog HDL, a 16-bit Vedic multiplier is created. Modelsim is used to simulate the modules, while Xilinx ISE 14.7 is used to synthesise them. In this project, a carry increment adder-based Vedic multiplier will be implemented using the CLA, and its performance will be compared to Vedic multiplier implemented using the ripple carry adder.. In this project an implementation of Vedic Multiplier using carry increment adder and comparing it with the Vedic multiplier using Ripple Carry Adder will be performed. The synthesis report shows that CIA-CLA has 1% lesser area than Vedic Multiplier using Ripple Carry Adder and CIA-RCA. and CIA-CLA has 10% greater delay than Vedic Multiplier using Ripple Carry Adder and CIA-RCA.
吠陀乘数法使用加法器作为其基本构件。许多数字电路的关键性能标准之一是电路的运行速度，这最终取决于基本加法器单元的延迟。这个项目致力于建造和分析一个速度吠陀乘数器，它使用各种加法器来分析速度、面积和功率。利用Verilog HDL中的进位增量加法器和半加法器，创建了一个16位的吠陀乘法器。使用Modelsim对模块进行仿真，使用Xilinx ISE 14.7对模块进行合成。在本项目中，将使用CLA实现基于进位增量加法器的吠陀乘法器，并将其性能与使用纹波进位加法器实现的吠陀乘法器进行比较。在本项目中，将使用进位增量加法器实现吠陀乘法器，并将其与使用纹波进位加法器的吠陀乘法器进行比较。综合报告显示，CIA-CLA比使用纹波进位加法器和CIA-RCA的吠陀乘法器面积小1%。CIA-CLA比使用纹波进位加法器和CIA-RCA的吠陀乘法器延迟高10%。
{"title":"Design and Implementation of Vedic Multiplier using Carry Increment Adder","authors":"A. Lavanya, S. Nagaraj, Lekhya M","doi":"10.1109/IConSCEPT57958.2023.10170489","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170489","url":null,"abstract":"Vedic multiplier uses adders as its fundamental building block. One of the crucial performance criteria for many digital circuits is the circuit’s operating speed, which ultimately depends on the basic adder unit’s delay. This project is devoted to the construction and analysis of a speed Vedic multiplier that uses various adders to analyse speed, area, and power. Using the carry increment adder and Halfadders in Verilog HDL, a 16-bit Vedic multiplier is created. Modelsim is used to simulate the modules, while Xilinx ISE 14.7 is used to synthesise them. In this project, a carry increment adder-based Vedic multiplier will be implemented using the CLA, and its performance will be compared to Vedic multiplier implemented using the ripple carry adder.. In this project an implementation of Vedic Multiplier using carry increment adder and comparing it with the Vedic multiplier using Ripple Carry Adder will be performed. The synthesis report shows that CIA-CLA has 1% lesser area than Vedic Multiplier using Ripple Carry Adder and CIA-RCA. and CIA-CLA has 10% greater delay than Vedic Multiplier using Ripple Carry Adder and CIA-RCA.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130084699","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170204
S. Pradeep Kumar, Anusha Daripelly, Sai Meghana Rampelli, Surya Kiran Reddy Nagireddy, Akhila Badishe, Amulya Attanthi
Speech communication involves transmitting information through speech between individuals or between individuals and machines in different areas such as speaker identification and automatic speech recognition. However, background noise can hinder effective communication by interfering with speech signals. Therefore, it is necessary to improve speech signals to minimize external disturbances. The process used to generate a more precise voice synthesis from an unclear audio source is called speech enhancement, which employs different algorithms to enhance speech quality. Wavelet transform is used to remove background noise from the messy audio while retaining essential speech information. To eliminate noise from the signal and achieve a clear signal, a semi-soft thresholding approach is employed, which removes chaotic coefficients from the wavelet. The primary objective of this paper is to use semi-soft thresholding to eliminate noise from signal and produce a clear signal. Noise reduction is a critical aspect of speech enhancement that has various applications, including speaker identification, prosthetic devices, VoIP, telepresence, and mobile devices.
{"title":"Noise Reduction Algorithm for Speech Enhancement","authors":"S. Pradeep Kumar, Anusha Daripelly, Sai Meghana Rampelli, Surya Kiran Reddy Nagireddy, Akhila Badishe, Amulya Attanthi","doi":"10.1109/IConSCEPT57958.2023.10170204","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170204","url":null,"abstract":"Speech communication involves transmitting information through speech between individuals or between individuals and machines in different areas such as speaker identification and automatic speech recognition. However, background noise can hinder effective communication by interfering with speech signals. Therefore, it is necessary to improve speech signals to minimize external disturbances. The process used to generate a more precise voice synthesis from an unclear audio source is called speech enhancement, which employs different algorithms to enhance speech quality. Wavelet transform is used to remove background noise from the messy audio while retaining essential speech information. To eliminate noise from the signal and achieve a clear signal, a semi-soft thresholding approach is employed, which removes chaotic coefficients from the wavelet. The primary objective of this paper is to use semi-soft thresholding to eliminate noise from signal and produce a clear signal. Noise reduction is a critical aspect of speech enhancement that has various applications, including speaker identification, prosthetic devices, VoIP, telepresence, and mobile devices.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115108577","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}
In today’s world, a typical job ad on the web attracts a massive number of applications in a short period of time. Manual screening of these resumes is not only time-consuming but also very expensive for the hiring companies. To address these challenges, this research paper proposes a solution that aims to automatically classify resumes to their corresponding suitable positions. To find the best possible solution, different ML techniques like Decision Tree, Random Forest, KNN, Support Vector are researched and the most accurate one is chosen. This approach has the potential to revolutionize the hiring process by reducing costs, saving time, and ensuring fairness.
{"title":"Resume Classification Using ML Techniques","authors":"B Surendiran, Tejus Paturu, Harsha Vardhan Chirumamilla, Maruprolu Naga Raju Reddy","doi":"10.1109/IConSCEPT57958.2023.10169907","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10169907","url":null,"abstract":"In today’s world, a typical job ad on the web attracts a massive number of applications in a short period of time. Manual screening of these resumes is not only time-consuming but also very expensive for the hiring companies. To address these challenges, this research paper proposes a solution that aims to automatically classify resumes to their corresponding suitable positions. To find the best possible solution, different ML techniques like Decision Tree, Random Forest, KNN, Support Vector are researched and the most accurate one is chosen. This approach has the potential to revolutionize the hiring process by reducing costs, saving time, and ensuring fairness.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"190 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116491941","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 : 2023-05-25DOI: 10.1109/IConSCEPT57958.2023.10170218
K. S. Vikash, Kaavya Jayakrishnan, Siddharth Ramanathan, G. Rohith, Vijayendra Hanumara
Deaf and mute people use sign language naturally. This article provides an application that addresses the problem of sign language detection by using computer vision and machine learning. The proposed system is a sign language interpreter that recognizes and understands the sign language words. These detected words and phrases are placed together as a sentence, enabling the user to get a complete translation. The system will collect video of a signer using a camera, and computer vision algorithms to recognize hand motions and movements. The user’s dominant hand (left or right) will conduct most of this activity. Single Shot MultiBox Detector (SSD) MobileNet V2 Deep learning technique is used to recognize the hand motions and movements and convert the identified signs into text output. The system will be trained on a dataset of sign language phrases, and its accuracy will be assessed using a range of performance indicators. The suggested technique is 96% accurate in identifying the type of sign language and 100% accurate in translating it to interpretation.
{"title":"An approach to Generation of sentences using Sign Language Detection","authors":"K. S. Vikash, Kaavya Jayakrishnan, Siddharth Ramanathan, G. Rohith, Vijayendra Hanumara","doi":"10.1109/IConSCEPT57958.2023.10170218","DOIUrl":"https://doi.org/10.1109/IConSCEPT57958.2023.10170218","url":null,"abstract":"Deaf and mute people use sign language naturally. This article provides an application that addresses the problem of sign language detection by using computer vision and machine learning. The proposed system is a sign language interpreter that recognizes and understands the sign language words. These detected words and phrases are placed together as a sentence, enabling the user to get a complete translation. The system will collect video of a signer using a camera, and computer vision algorithms to recognize hand motions and movements. The user’s dominant hand (left or right) will conduct most of this activity. Single Shot MultiBox Detector (SSD) MobileNet V2 Deep learning technique is used to recognize the hand motions and movements and convert the identified signs into text output. The system will be trained on a dataset of sign language phrases, and its accuracy will be assessed using a range of performance indicators. The suggested technique is 96% accurate in identifying the type of sign language and 100% accurate in translating it to interpretation.","PeriodicalId":240167,"journal":{"name":"2023 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication (IConSCEPT)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132196047","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：