Pub Date : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212142
S. Hussain, M. Roopa
In IoT-LLN networks, RPL is a widely used routing protocol. RPL provides a lightweight and efficient way to route packets between devices in LLNs, creating a mesh network topology. For network bootstrapping and maintenance purposes, it periodically transmits DIO, DIS, DAO, and DAO-ACK packets. The lower-layer 6TiS CH protocol uses only a single minimal cell in a slotframe to transfer control messages. This increases the transmitting control messages' queue size. The packets in the transmission queue that have been waiting for a long time are removed from the queue. Network-associated nodes transfer control messages simultaneously, which causes the collision. Because of these issues, nodes waiting to join the network are not receiving the required control messages, and remain unassociated. Network-associated nodes must receive the DIO packets regularly to update the network topology information. If these nodes do not receive the DIO packets, it causes unnecessary parent-switching measures. Extensive simulations were done using Contiki-NG's COOJA simulator with varying network sizes, slotframe lengths, and hop sequences. Increased network size, slotframe lengths, and hop sequence caused more control message collisions, and parent-switching.
{"title":"Evaluating the Impact of RPL Control Overhead on Network Performance","authors":"S. Hussain, M. Roopa","doi":"10.1109/ICECAA58104.2023.10212142","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212142","url":null,"abstract":"In IoT-LLN networks, RPL is a widely used routing protocol. RPL provides a lightweight and efficient way to route packets between devices in LLNs, creating a mesh network topology. For network bootstrapping and maintenance purposes, it periodically transmits DIO, DIS, DAO, and DAO-ACK packets. The lower-layer 6TiS CH protocol uses only a single minimal cell in a slotframe to transfer control messages. This increases the transmitting control messages' queue size. The packets in the transmission queue that have been waiting for a long time are removed from the queue. Network-associated nodes transfer control messages simultaneously, which causes the collision. Because of these issues, nodes waiting to join the network are not receiving the required control messages, and remain unassociated. Network-associated nodes must receive the DIO packets regularly to update the network topology information. If these nodes do not receive the DIO packets, it causes unnecessary parent-switching measures. Extensive simulations were done using Contiki-NG's COOJA simulator with varying network sizes, slotframe lengths, and hop sequences. Increased network size, slotframe lengths, and hop sequence caused more control message collisions, and parent-switching.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131475594","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212329
Gurpreet Singh, Subham Kumar Singh
Throughout the past couple of decades, machine learning (ML) has made its way into scientific research and engineering. Machine learning (ML) strategies are widely employed in processing information, data mining, especially scientific computation. Data visualization is essential. Despite the fact that numerous types of visualization tools are commonly used, the majority of them need sufficient coding knowledge, are developed for specific purposes, or are not free. Virtual reality (VR) provides intuitive interactivity and comprehensive visualization. Researchers use virtual reality to make it possible for any biomedical specialist to use a machine learning (DL) framework for picture analysis. Although ML models can be effective instruments for assessing information, they can additionally be difficult to comprehend and create. We have developed a ML development system based on virtual reality in order to render the technology more user-friendly and approachable. The intuitive interactivity and vivid visualisation are offered by virtual reality (VR). Any technical discipline can create a machine learning (ML) approach to recognising pictures using VR. This paper offers a thorough analysis of ML visualisation techniques, resources, and procedures. By looking at the visual analytical pipeline customers, and researchers place data visualisation into the visual analytics methodology. It present an analysis of the many chart types that are available for data visualisation and discuss guidelines for using each one while taking into account the unique circumstances of the given utilise case. There look more closely at a few of the latest and greatest exciting visualisation tools. We research visualisation challenges in each domain because each ML model is unique in terms to VR strategies. Finally, we present a summary of the main difficulties with ML visualisations.
{"title":"Analysis of Data Visualization Techniques Useful for Machine Learning and Visual Reality","authors":"Gurpreet Singh, Subham Kumar Singh","doi":"10.1109/ICECAA58104.2023.10212329","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212329","url":null,"abstract":"Throughout the past couple of decades, machine learning (ML) has made its way into scientific research and engineering. Machine learning (ML) strategies are widely employed in processing information, data mining, especially scientific computation. Data visualization is essential. Despite the fact that numerous types of visualization tools are commonly used, the majority of them need sufficient coding knowledge, are developed for specific purposes, or are not free. Virtual reality (VR) provides intuitive interactivity and comprehensive visualization. Researchers use virtual reality to make it possible for any biomedical specialist to use a machine learning (DL) framework for picture analysis. Although ML models can be effective instruments for assessing information, they can additionally be difficult to comprehend and create. We have developed a ML development system based on virtual reality in order to render the technology more user-friendly and approachable. The intuitive interactivity and vivid visualisation are offered by virtual reality (VR). Any technical discipline can create a machine learning (ML) approach to recognising pictures using VR. This paper offers a thorough analysis of ML visualisation techniques, resources, and procedures. By looking at the visual analytical pipeline customers, and researchers place data visualisation into the visual analytics methodology. It present an analysis of the many chart types that are available for data visualisation and discuss guidelines for using each one while taking into account the unique circumstances of the given utilise case. There look more closely at a few of the latest and greatest exciting visualisation tools. We research visualisation challenges in each domain because each ML model is unique in terms to VR strategies. Finally, we present a summary of the main difficulties with ML visualisations.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132219051","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212358
K. K, O. G., Moulieswaran V, Miduna A, Mohammad Afnaan T M
In this research study, the “Magic Mirror”. “a voice-controlled wall mirror, is designed and implemented. It is a device that can simultaneously serve as a mirror and an interactive display, showing multimedia content such as time, date, and weather. Using voice commands, the user can communicate with the mirror. It is a device that can simultaneously serve as a mirror and an interactive display, showing multimedia content such as time, date and weather. The user can communicate with the mirror via voice commands. The Magic Mirror has a number of features, including voice commands via an LCD display and microphone, as well as real-time data and information updates. Users can communicate with the Magic Mirror via voice commands. The smart mirror is a mirror that can reflect light and display information, is a vibrant way to integrate two applications. The user can be recognized by Smart Mirror using the voice recognition model. To obtain current data to display on a Magic mirror, the Pi will connect to the internet.
{"title":"A Novel Two-Way Mirror with the Help of the Internet of Things","authors":"K. K, O. G., Moulieswaran V, Miduna A, Mohammad Afnaan T M","doi":"10.1109/ICECAA58104.2023.10212358","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212358","url":null,"abstract":"In this research study, the “Magic Mirror”. “a voice-controlled wall mirror, is designed and implemented. It is a device that can simultaneously serve as a mirror and an interactive display, showing multimedia content such as time, date, and weather. Using voice commands, the user can communicate with the mirror. It is a device that can simultaneously serve as a mirror and an interactive display, showing multimedia content such as time, date and weather. The user can communicate with the mirror via voice commands. The Magic Mirror has a number of features, including voice commands via an LCD display and microphone, as well as real-time data and information updates. Users can communicate with the Magic Mirror via voice commands. The smart mirror is a mirror that can reflect light and display information, is a vibrant way to integrate two applications. The user can be recognized by Smart Mirror using the voice recognition model. To obtain current data to display on a Magic mirror, the Pi will connect to the internet.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133170845","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212425
D. Babu, Syed Mizbahuddin, Thouti Bharath Kumar, S. Supreeth, Goud Arukala, Naredla Phaneendra Reddy, A. .. S. Kumar
Plant diseases are mostly affecting leaves. In most of the cases, manual disease identification method fails to identify the disease correctly due to the similar symptoms of various diseases. People lack sufficient knowledge of plant diseases. The inability to detect the plant disease leads to crop production loss. Moreover, farmers have suffered significant losses as a result of a lack of sufficient understanding and direction to address the issue. This necessitates the need to develop a novel technology to detect the plant diseases. This study has attempted to develop an effective plant disease detection model using Convolutional Neural Networks (CNN). The proposed model has the ability to detect multiple diseases that occur in a single plant species. The results show the efficiency of the proposed model.
{"title":"Leaf Disease Detection using Machine Learning Algorithms","authors":"D. Babu, Syed Mizbahuddin, Thouti Bharath Kumar, S. Supreeth, Goud Arukala, Naredla Phaneendra Reddy, A. .. S. Kumar","doi":"10.1109/ICECAA58104.2023.10212425","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212425","url":null,"abstract":"Plant diseases are mostly affecting leaves. In most of the cases, manual disease identification method fails to identify the disease correctly due to the similar symptoms of various diseases. People lack sufficient knowledge of plant diseases. The inability to detect the plant disease leads to crop production loss. Moreover, farmers have suffered significant losses as a result of a lack of sufficient understanding and direction to address the issue. This necessitates the need to develop a novel technology to detect the plant diseases. This study has attempted to develop an effective plant disease detection model using Convolutional Neural Networks (CNN). The proposed model has the ability to detect multiple diseases that occur in a single plant species. The results show the efficiency of the proposed model.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132723555","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212163
Sidhant Chourasiya, Gyanesh Samanta, Devadarshan K Sardar, Ponnu Sharma, C. Kumar
The development of weaponized software presents substantial cybersecurity challenges, with the Pegasus spyware, developed by the Israeli group NSO, serving as a prominent example. This malicious code operates covertly, infiltrating target systems without the user's knowledge, extracting sensitive information, and monitoring user behavior. This research aims to investigate the unique characteristics and implications of the Pegasus spyware. Specifically, its zero-click functionality is understood, where exploitation occurs without user interaction and its reliance on zero-day vulnerabilities for system compromise. Furthermore, the study aims to explore the extent of control granted to the Pegasus operator, including command execution, data access, and remote manipulation of hardware components. Through an in-depth analysis, this study examines the technical intricacies of the Pegasus spyware. This study explores its methods of propagation, emphasizing its ability to exploit zero-day vulnerabilities without requiring user engagement. Moreover, mechanisms employed by spyware to establish command and control channels are investigated using HTTPS connections, leading to potential avenues for tracking and detection. The findings reveal the elusive nature of Pegasus, leaving minimal traces of its activities on infected systems. The software's sophisticated techniques and reliance on secure communication channels pose significant challenges in detecting and tracking its presence. The study also highlights the extensive control granted to the Pegasus operator, enabling comprehensive surveillance and data exfiltration from compromised systems. The Pegasus spyware represents a formidable cybersecurity threat due to its stealthy infiltration, powerful surveillance capabilities, and limited traceability. Mitigating this threat necessitates innovative approaches to detect and prevent its deployment. This research provides valuable insights into the workings of Pegasus and paves the way for developing effective countermeasures and mitigation strategies to safeguard systems and user privacy.
{"title":"Pegasus Spyware: A Vulnerable Behaviour-based Attack System","authors":"Sidhant Chourasiya, Gyanesh Samanta, Devadarshan K Sardar, Ponnu Sharma, C. Kumar","doi":"10.1109/ICECAA58104.2023.10212163","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212163","url":null,"abstract":"The development of weaponized software presents substantial cybersecurity challenges, with the Pegasus spyware, developed by the Israeli group NSO, serving as a prominent example. This malicious code operates covertly, infiltrating target systems without the user's knowledge, extracting sensitive information, and monitoring user behavior. This research aims to investigate the unique characteristics and implications of the Pegasus spyware. Specifically, its zero-click functionality is understood, where exploitation occurs without user interaction and its reliance on zero-day vulnerabilities for system compromise. Furthermore, the study aims to explore the extent of control granted to the Pegasus operator, including command execution, data access, and remote manipulation of hardware components. Through an in-depth analysis, this study examines the technical intricacies of the Pegasus spyware. This study explores its methods of propagation, emphasizing its ability to exploit zero-day vulnerabilities without requiring user engagement. Moreover, mechanisms employed by spyware to establish command and control channels are investigated using HTTPS connections, leading to potential avenues for tracking and detection. The findings reveal the elusive nature of Pegasus, leaving minimal traces of its activities on infected systems. The software's sophisticated techniques and reliance on secure communication channels pose significant challenges in detecting and tracking its presence. The study also highlights the extensive control granted to the Pegasus operator, enabling comprehensive surveillance and data exfiltration from compromised systems. The Pegasus spyware represents a formidable cybersecurity threat due to its stealthy infiltration, powerful surveillance capabilities, and limited traceability. Mitigating this threat necessitates innovative approaches to detect and prevent its deployment. This research provides valuable insights into the workings of Pegasus and paves the way for developing effective countermeasures and mitigation strategies to safeguard systems and user privacy.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116505503","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212149
Ravinder Kumar, K. Sharma, R. Pandey
Low values of noise and power along with high values of common mode rejection ratio (CMRR) are desired for Operational Transconductance Amplifier (OTA) for enhancing the performance of the handheld electronic healthcare systems. However, achieving low-noise operation with high CMRR and low-power dissipation (Pdiss) is a complex task with conventional design techniques. In this work, low-noise complementary cascode partial positive feedback OTA functioning at ±0.5 V is presented which is implemented in technology node of $0.18 mumathrm{m}$. The presented OTA has gain of 76.16 dB, gain bandwidth product of 57 kHz, noise of $0.1 mumathrm{V}/surd{text{Hz}}$ at 1 kHz, Pdiss of 718 nW CMRR of 104.64 dB. Health care, medical and biological electronic systems are expected to be benefitted with presented low-noise OTA.
{"title":"Low-power Complementary Cascode Partial Positive Feedback Operational Transconductance Amplifier","authors":"Ravinder Kumar, K. Sharma, R. Pandey","doi":"10.1109/ICECAA58104.2023.10212149","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212149","url":null,"abstract":"Low values of noise and power along with high values of common mode rejection ratio (CMRR) are desired for Operational Transconductance Amplifier (OTA) for enhancing the performance of the handheld electronic healthcare systems. However, achieving low-noise operation with high CMRR and low-power dissipation (Pdiss) is a complex task with conventional design techniques. In this work, low-noise complementary cascode partial positive feedback OTA functioning at ±0.5 V is presented which is implemented in technology node of $0.18 mumathrm{m}$. The presented OTA has gain of 76.16 dB, gain bandwidth product of 57 kHz, noise of $0.1 mumathrm{V}/surd{text{Hz}}$ at 1 kHz, Pdiss of 718 nW CMRR of 104.64 dB. Health care, medical and biological electronic systems are expected to be benefitted with presented low-noise OTA.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115118500","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212367
D. Yogapriya, M. Uma
Agarwood is a fragrant darkish resinous wood fashioned whilst Aquilaria trees are inflamed with a positive form of mould and appear like wooden defects. The maximum precious non-wood product has been traded in global markets because of its one-of-a-kind aroma and may be processed into incense and perfumes. Agarwood grade is decided via numerous characteristics, such as black colour intensity, scent, texture, and weight thru visual inspection. However, this can lead to numerous issues such as fake grading outcomes. Historically, the carving procedure of separation of the uninfected Aquilaria wood that lacks the dark resinous was carried out with the aid of the usage of easy tools like a knife and chisel. Therefore, a professional employee is required to complete the venture. In this paper, the Convolutional Neural network (CNN) technique is used to classify Agarwood primarily based on the functions extraction from Gabor filter out and percent of black shade estimation. At the start, the pies of seven companies of wooden defects or knots are recognized: dry, decayed, aspect, encased, horn, leaf, and sound disorder with a total pattern of 410 knots. Then, these images of knots are matched into 3-grade groups of Agarwood. Next, the experimental consequences display that the Agarwood may be categorized into 3-grade organizations based on the knot and black intensity. A fixed of decided pictures of knots were used as hint patterns and carved on portions of timber blocks via the usage of a Computer Numerical Control (CNC) machine in which the total time taken for every carving technique was calculated. For each photograph, two Gabor filter-out features and a percent of black colour were used as inputs. In the end, the total accuracy of the experiments is 98% and the total carving time is accelerated with the CNN erased of grade organization quantity.
{"title":"Agarwood Grade Estimation Procedure using Cnn and Sculpture Automation","authors":"D. Yogapriya, M. Uma","doi":"10.1109/ICECAA58104.2023.10212367","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212367","url":null,"abstract":"Agarwood is a fragrant darkish resinous wood fashioned whilst Aquilaria trees are inflamed with a positive form of mould and appear like wooden defects. The maximum precious non-wood product has been traded in global markets because of its one-of-a-kind aroma and may be processed into incense and perfumes. Agarwood grade is decided via numerous characteristics, such as black colour intensity, scent, texture, and weight thru visual inspection. However, this can lead to numerous issues such as fake grading outcomes. Historically, the carving procedure of separation of the uninfected Aquilaria wood that lacks the dark resinous was carried out with the aid of the usage of easy tools like a knife and chisel. Therefore, a professional employee is required to complete the venture. In this paper, the Convolutional Neural network (CNN) technique is used to classify Agarwood primarily based on the functions extraction from Gabor filter out and percent of black shade estimation. At the start, the pies of seven companies of wooden defects or knots are recognized: dry, decayed, aspect, encased, horn, leaf, and sound disorder with a total pattern of 410 knots. Then, these images of knots are matched into 3-grade groups of Agarwood. Next, the experimental consequences display that the Agarwood may be categorized into 3-grade organizations based on the knot and black intensity. A fixed of decided pictures of knots were used as hint patterns and carved on portions of timber blocks via the usage of a Computer Numerical Control (CNC) machine in which the total time taken for every carving technique was calculated. For each photograph, two Gabor filter-out features and a percent of black colour were used as inputs. In the end, the total accuracy of the experiments is 98% and the total carving time is accelerated with the CNN erased of grade organization quantity.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"171 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116237982","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212175
M. Eswaran, B. P, Pradeepa V
Human blastocyst is an embryo on its 5th day of development. The formation of 32 cell stage is called Blastocyst stage and its size is about 0.2mm. Blastocyst analysis is to automate blastocyst morphology by analyzing with multiple images. A fertilized egg is cultured for five days before being put into the uterus when using blastocysts in in-vitro fertilization. It might be a more successful fertility treatment alternative than standard in-vitro fertilization. The Blastocyst assessment aims to increase in-vitro fertilization success rates based on women age. Deep learning is an enabling technology to fulfill all of the above requirements and this model helps in assessing the morphology and cellular composition of blastocysts. Approximately 40% of human blastocysts are genetically normal, however this number drops to 25% if the woman was aged over 40 when her eggs were collected. The model performance is evaluated based on accuracy, loss, Precision and recall values. The Higher accuracy in blastocyst assessment can be achieved by training a DenseNet model on a large dataset of elucidated blastocyst images. This Model achieved a significantly higher accuracy of 92% by assessing the blastocyst development based on women age.
{"title":"Assessment of Human Blastocyst using Deep Learning Algorithm","authors":"M. Eswaran, B. P, Pradeepa V","doi":"10.1109/ICECAA58104.2023.10212175","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212175","url":null,"abstract":"Human blastocyst is an embryo on its 5th day of development. The formation of 32 cell stage is called Blastocyst stage and its size is about 0.2mm. Blastocyst analysis is to automate blastocyst morphology by analyzing with multiple images. A fertilized egg is cultured for five days before being put into the uterus when using blastocysts in in-vitro fertilization. It might be a more successful fertility treatment alternative than standard in-vitro fertilization. The Blastocyst assessment aims to increase in-vitro fertilization success rates based on women age. Deep learning is an enabling technology to fulfill all of the above requirements and this model helps in assessing the morphology and cellular composition of blastocysts. Approximately 40% of human blastocysts are genetically normal, however this number drops to 25% if the woman was aged over 40 when her eggs were collected. The model performance is evaluated based on accuracy, loss, Precision and recall values. The Higher accuracy in blastocyst assessment can be achieved by training a DenseNet model on a large dataset of elucidated blastocyst images. This Model achieved a significantly higher accuracy of 92% by assessing the blastocyst development based on women age.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116538138","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212162
D. Bhimrao, Digvijay B. Kanase, Dr. H.T. Jadhav
This research work provides a detailed study of power quality issues in a three-phase four-wire system caused by nonlinear load penetration at the distribution side. Non-conventional sources, primarily photovoltaic cell, is directly connected to the Static synchronous compensator (DSTATCOM) at the side of the DC-link capacitor to maintain the constant voltage required by the Voltage source converter, i.e. DSTATCOM, which improves overall power quality issues within the distribution system. Unbalanced loads, a high reactive power burden, and poor voltage control are common issues of three-phase three-wire and three-phase four-wire systems. But the most significant issue in the three-phase system's four-wire distribution system is neutral current. The effectiveness of DSTATCOM over other custom power devices for improving power quality is determined by the use of control algorithms. A control algorithm suitable for a static synchronous compensator for determining power quality is developed. The analysis is carried out using the synchronous reference frame (SRF) method. Nowadays, Renewable Energy (RE) based power quality enhancement approaches are of considerable interest to many researchers; this work describes a comprehensive evaluation of a Distribution Static Compensator operated with a solar photovoltaic system. This research addresses the photovoltaic fed three-leg static synchronous compensator (PV DSTATCOM) for enhancing power quality.
{"title":"PV Operated DSTATCOM for Power Quality Enhancement for the Three Phase Four Wire Distribution System","authors":"D. Bhimrao, Digvijay B. Kanase, Dr. H.T. Jadhav","doi":"10.1109/ICECAA58104.2023.10212162","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212162","url":null,"abstract":"This research work provides a detailed study of power quality issues in a three-phase four-wire system caused by nonlinear load penetration at the distribution side. Non-conventional sources, primarily photovoltaic cell, is directly connected to the Static synchronous compensator (DSTATCOM) at the side of the DC-link capacitor to maintain the constant voltage required by the Voltage source converter, i.e. DSTATCOM, which improves overall power quality issues within the distribution system. Unbalanced loads, a high reactive power burden, and poor voltage control are common issues of three-phase three-wire and three-phase four-wire systems. But the most significant issue in the three-phase system's four-wire distribution system is neutral current. The effectiveness of DSTATCOM over other custom power devices for improving power quality is determined by the use of control algorithms. A control algorithm suitable for a static synchronous compensator for determining power quality is developed. The analysis is carried out using the synchronous reference frame (SRF) method. Nowadays, Renewable Energy (RE) based power quality enhancement approaches are of considerable interest to many researchers; this work describes a comprehensive evaluation of a Distribution Static Compensator operated with a solar photovoltaic system. This research addresses the photovoltaic fed three-leg static synchronous compensator (PV DSTATCOM) for enhancing power quality.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122037994","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 : 2023-07-19DOI: 10.1109/ICECAA58104.2023.10212266
Gunji Prem Prasad, G. Kathrine, Jemimah M Kuruvilla, Mohammed Moosa Razeek J
This research study intends to explore various challenges that humans have encountered as well as any that may arise in the near future. Poor sanitation facility is one of the main causes of malnutrition and it leads to a number of diseases, which also indirectly impacts other sectors. Excessive use of resources that are not renewable is another considerable issue. There is a lot of energy resource wastage; for example, streetlights in cities and on highways are often left ON during the day, this may cause energy wastage. Also, it is already known fact that the non-renewable energy resources are very limited. Therefore, an alternative energy source such as renewable energy like wind, solar power, and others are required. In future there might be a rise in the electricity consumption, therefore some innovative ways should be developed to fulfill the requirements. Through innovative technologies, energy can be efficiently utilized. IIoT aims to automate system-based monitoring and control of devices. Integrating the use of renewable energy and leveraging technology in the sanitation sector will promote social development.
{"title":"Implementation of Industry 4.0 in the Energy Sector","authors":"Gunji Prem Prasad, G. Kathrine, Jemimah M Kuruvilla, Mohammed Moosa Razeek J","doi":"10.1109/ICECAA58104.2023.10212266","DOIUrl":"https://doi.org/10.1109/ICECAA58104.2023.10212266","url":null,"abstract":"This research study intends to explore various challenges that humans have encountered as well as any that may arise in the near future. Poor sanitation facility is one of the main causes of malnutrition and it leads to a number of diseases, which also indirectly impacts other sectors. Excessive use of resources that are not renewable is another considerable issue. There is a lot of energy resource wastage; for example, streetlights in cities and on highways are often left ON during the day, this may cause energy wastage. Also, it is already known fact that the non-renewable energy resources are very limited. Therefore, an alternative energy source such as renewable energy like wind, solar power, and others are required. In future there might be a rise in the electricity consumption, therefore some innovative ways should be developed to fulfill the requirements. Through innovative technologies, energy can be efficiently utilized. IIoT aims to automate system-based monitoring and control of devices. Integrating the use of renewable energy and leveraging technology in the sanitation sector will promote social development.","PeriodicalId":114624,"journal":{"name":"2023 2nd International Conference on Edge Computing and Applications (ICECAA)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-07-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123812741","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：