Pub Date : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767171
Anjali Manoj, A. H, Keshav Varma, Naveen P. Nair, V. A, A. D, N. M
Commercial fishing has been made more effective with the use of devices based on Sound Navigation and Ranging (SONAR) technology, across the years. FishFinder is one such device, the first of its kind. It is a very trivial device and is used as the basis for all devices that are available in the market today. This device has a lot of drawbacks; it detect objects that have densities different from water, making it hard to identify whether the waves have hit a pool of fish or not. There is no mechanism to identify the type of fish as well, hence purely depending upon the experience of the fisherman. To overcome these drawbacks, certain modifications that could be incorporated into this device is proposed in this paper. The proposed modifications include a Stabilization mechanism, a Real-time tracking mechanism, and a Machine Learning (ML) model that identifies the type of fish with reference to its unique swim bladder size. These modifications, along with future work ideas, could enhance the effectiveness of the FishFinder device, thereby creating pathways to new advancements in the field.
{"title":"Sonar for Commercial Fishing","authors":"Anjali Manoj, A. H, Keshav Varma, Naveen P. Nair, V. A, A. D, N. M","doi":"10.1109/wispnet54241.2022.9767171","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767171","url":null,"abstract":"Commercial fishing has been made more effective with the use of devices based on Sound Navigation and Ranging (SONAR) technology, across the years. FishFinder is one such device, the first of its kind. It is a very trivial device and is used as the basis for all devices that are available in the market today. This device has a lot of drawbacks; it detect objects that have densities different from water, making it hard to identify whether the waves have hit a pool of fish or not. There is no mechanism to identify the type of fish as well, hence purely depending upon the experience of the fisherman. To overcome these drawbacks, certain modifications that could be incorporated into this device is proposed in this paper. The proposed modifications include a Stabilization mechanism, a Real-time tracking mechanism, and a Machine Learning (ML) model that identifies the type of fish with reference to its unique swim bladder size. These modifications, along with future work ideas, could enhance the effectiveness of the FishFinder device, thereby creating pathways to new advancements in the field.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121716976","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767108
R. P., R. P.
The antenna in the current study is an attempt to break the available radiation pattern into multiple beams in order to reduce energy waste. To achieve this, a hybrid substrate integrated waveguide (SIW) is generated by combining a cylindrical cavity with a rectangular cavity. A cross-shaped slot is engraved on the top and bottom face of the cylindrical cavity to allow the antenna to generate six major lobes. At the operating frequency of 5 GHz, the return loss of the antenna is around 21.34 dB. Six major beams with each one having a gain around 6.4 dB and 7.1 dB are generated by the antenna in the current study. The antenna is having a bandwidth of 20 MHz and is linearly polarised.
{"title":"A Hybrid Substrate Integrated Waveguide Cavity based Leaky Wave Antenna Capable of Generating Six Major Beams","authors":"R. P., R. P.","doi":"10.1109/wispnet54241.2022.9767108","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767108","url":null,"abstract":"The antenna in the current study is an attempt to break the available radiation pattern into multiple beams in order to reduce energy waste. To achieve this, a hybrid substrate integrated waveguide (SIW) is generated by combining a cylindrical cavity with a rectangular cavity. A cross-shaped slot is engraved on the top and bottom face of the cylindrical cavity to allow the antenna to generate six major lobes. At the operating frequency of 5 GHz, the return loss of the antenna is around 21.34 dB. Six major beams with each one having a gain around 6.4 dB and 7.1 dB are generated by the antenna in the current study. The antenna is having a bandwidth of 20 MHz and is linearly polarised.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128910088","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767115
T. Kumar, Adithya Jayan, Shreenidhi Bhat, M. Anvith, A. V. Narasimhadhan
The automatic Speech Recognition system (ASR) is the most widely used application in the speech domain. ASR systems generate text data from spoken utterances without manual intervention. In this work, we build an ASR system for the Kannada language. For building the proposed system, we extract Mel Frequency Cepstral Coefficients (MFCC) features from the audio data, and the Kannada language model is developed using corresponding labels. The dictionary generation and phonetic labelings are automated. Recognition performance is compared for both monophonic and triphone models. The word error rate of 15.73 % and the sentence error rate of 55.5 % are achieved for the triphone model. Comparatively, the triphone model gives a better performance than the monophonic model.
{"title":"Monophone and Triphone Acoustic Phonetic Model for Kannada Speech Recognition System","authors":"T. Kumar, Adithya Jayan, Shreenidhi Bhat, M. Anvith, A. V. Narasimhadhan","doi":"10.1109/wispnet54241.2022.9767115","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767115","url":null,"abstract":"The automatic Speech Recognition system (ASR) is the most widely used application in the speech domain. ASR systems generate text data from spoken utterances without manual intervention. In this work, we build an ASR system for the Kannada language. For building the proposed system, we extract Mel Frequency Cepstral Coefficients (MFCC) features from the audio data, and the Kannada language model is developed using corresponding labels. The dictionary generation and phonetic labelings are automated. Recognition performance is compared for both monophonic and triphone models. The word error rate of 15.73 % and the sentence error rate of 55.5 % are achieved for the triphone model. Comparatively, the triphone model gives a better performance than the monophonic model.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"4 8","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120885678","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767142
M. Prabhu, Aravind Hanumanthaiah
Telemedicine has the potential to bridge the huge urban-rural health divide that exists in many developing economies in the fastest and the most affordable way. Cloud Computing holds promise for providing an efficient, cost-effective, and pervasive telemedicine paradigm. With cloud computing, biomedical sensor data can be stored and analyzed remotely by remotely distributed servers. However, a huge volume of data is generated by smart medical devices [1]. Thus, there is a need to leverage the Edge Computing paradigm to process data closer to the source of data generation. This paper presents a healthcare framework that incorporates a promising Edge-IoT ecosystem - the EdgeX Foundry for the telehealth use case of Blood Pressure monitoring. The end-to-end system is broadly divided into three parts: the User subsystem, the Edge subsystem, and the Cloud subsystem. This paper presents the use of EdgeX Foundry for a telehealth application.
{"title":"Edge Computing-Enabled Healthcare Framework to Provide Telehealth Services","authors":"M. Prabhu, Aravind Hanumanthaiah","doi":"10.1109/wispnet54241.2022.9767142","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767142","url":null,"abstract":"Telemedicine has the potential to bridge the huge urban-rural health divide that exists in many developing economies in the fastest and the most affordable way. Cloud Computing holds promise for providing an efficient, cost-effective, and pervasive telemedicine paradigm. With cloud computing, biomedical sensor data can be stored and analyzed remotely by remotely distributed servers. However, a huge volume of data is generated by smart medical devices [1]. Thus, there is a need to leverage the Edge Computing paradigm to process data closer to the source of data generation. This paper presents a healthcare framework that incorporates a promising Edge-IoT ecosystem - the EdgeX Foundry for the telehealth use case of Blood Pressure monitoring. The end-to-end system is broadly divided into three parts: the User subsystem, the Edge subsystem, and the Cloud subsystem. This paper presents the use of EdgeX Foundry for a telehealth application.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122738441","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767172
Aditya Narayan S., Hareesh Kumaar, Sathya Narayanan D., S. S., V. S.
Big tech companies like Amazon, Netflix and Google have tons of data and are still successful in providing specific products and services correctly as per user requirements. This is made possible by the recommendation algorithms that feed on the data we provide, in turn, enabling them to produce accurate results. Movie recommendation systems aspire to help cinema geeks by proposing movies of their penchant, devoid of them needing to do the standard long and arduous method of selecting from huge sets of movies that go up to millions and is onerous and frustrating. In this paper, we aspire to diminish human endeavor by recommending them movies based on their interests. To resolve such troubles, we have built a model using a content-based approach. The idea behind this model is to recommend a movie based on descriptions of movies. Using the movie “GoldenEye” as an example, we obtained the result as “Skyfall” with a similarity score of 66.73% using CountVectorizer, 13.14% using Jaccard Recommender, 14.34% using TF-IDF Keywords, 9.87% using TF-IDF Plot Overview and 71.9% using Google Form responses.
像亚马逊、Netflix和谷歌这样的大型科技公司拥有大量数据，并且仍然成功地根据用户需求提供特定的产品和服务。这是通过推荐算法实现的，这些算法以我们提供的数据为基础，反过来使它们能够产生准确的结果。电影推荐系统希望通过推荐他们喜欢的电影来帮助电影爱好者，而不需要他们从大量的电影中进行标准的、漫长而艰苦的选择，这些电影多达数百万部，这是一项繁重而令人沮丧的工作。在本文中，我们希望通过根据他们的兴趣推荐电影来减少人类的努力。为了解决这些问题，我们使用基于内容的方法构建了一个模型。这个模型背后的想法是根据电影的描述来推荐电影。以电影“GoldenEye”为例，我们得到的结果是“Skyfall”，使用CountVectorizer的相似度为66.73%，使用Jaccard Recommender的相似度为13.14%，使用TF-IDF Keywords的相似度为14.34%，使用TF-IDF Plot Overview的相似度为9.87%，使用Google Form responses的相似度为71.9%。
{"title":"Content-based Movie Recommender System Using Keywords and Plot Overview","authors":"Aditya Narayan S., Hareesh Kumaar, Sathya Narayanan D., S. S., V. S.","doi":"10.1109/wispnet54241.2022.9767172","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767172","url":null,"abstract":"Big tech companies like Amazon, Netflix and Google have tons of data and are still successful in providing specific products and services correctly as per user requirements. This is made possible by the recommendation algorithms that feed on the data we provide, in turn, enabling them to produce accurate results. Movie recommendation systems aspire to help cinema geeks by proposing movies of their penchant, devoid of them needing to do the standard long and arduous method of selecting from huge sets of movies that go up to millions and is onerous and frustrating. In this paper, we aspire to diminish human endeavor by recommending them movies based on their interests. To resolve such troubles, we have built a model using a content-based approach. The idea behind this model is to recommend a movie based on descriptions of movies. Using the movie “GoldenEye” as an example, we obtained the result as “Skyfall” with a similarity score of 66.73% using CountVectorizer, 13.14% using Jaccard Recommender, 14.34% using TF-IDF Keywords, 9.87% using TF-IDF Plot Overview and 71.9% using Google Form responses.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130925574","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767145
Aditya Narayan S., Aditya Nair, V. S.
Air pollution, Asthma, and Gross Domestic Product (GDP) are very important indicators to human life and development and it has been found that air pollution has a big effect on the latter two. In this paper, we find the correlation factor and to what extent air pollution has an effect on those two. For this, we chose 20 American states, handpicked the ones having unique features with respect to pollution levels, asthma cases, GDP numbers, and the datasets for the past 20 years of each state were taken. We chose 6 toxic pollutants, namely PM2.5, Carbon Monoxide, Sulfur Dioxide, PM10, Ozone, and Nitrogen Dioxide with each dataset including daily readings of these pollutants for the past 20 years in each state. The idea behind our model is to use all these data and find the extent to which air pollution is related to the asthma cases and the GDP of a state. For this, we use 4 models, namely Neural Network (NN), Random Forest (RFC), Support Vector Machines (SVM) and K-Nearest Neighbors (KNN). We use metrics like Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and R-Squared to evaluate our results. We observed a positive correlation between rates of asthma and GDP and pollution data. NN gave the best prediction accuracy especially for GDP (Average: 76%) followed closely by SVM. SVM's also had the least MAE while RFC had the least RMSE.
{"title":"Determining the Effect of Correlation between Asthma/Gross Domestic Product and Air Pollution","authors":"Aditya Narayan S., Aditya Nair, V. S.","doi":"10.1109/wispnet54241.2022.9767145","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767145","url":null,"abstract":"Air pollution, Asthma, and Gross Domestic Product (GDP) are very important indicators to human life and development and it has been found that air pollution has a big effect on the latter two. In this paper, we find the correlation factor and to what extent air pollution has an effect on those two. For this, we chose 20 American states, handpicked the ones having unique features with respect to pollution levels, asthma cases, GDP numbers, and the datasets for the past 20 years of each state were taken. We chose 6 toxic pollutants, namely PM2.5, Carbon Monoxide, Sulfur Dioxide, PM10, Ozone, and Nitrogen Dioxide with each dataset including daily readings of these pollutants for the past 20 years in each state. The idea behind our model is to use all these data and find the extent to which air pollution is related to the asthma cases and the GDP of a state. For this, we use 4 models, namely Neural Network (NN), Random Forest (RFC), Support Vector Machines (SVM) and K-Nearest Neighbors (KNN). We use metrics like Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and R-Squared to evaluate our results. We observed a positive correlation between rates of asthma and GDP and pollution data. NN gave the best prediction accuracy especially for GDP (Average: 76%) followed closely by SVM. SVM's also had the least MAE while RFC had the least RMSE.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"120 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115823105","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767136
Jegadish Kumar K. J., K. P., K. A., Gopalakrishnan N., Dinesh J., J. M.
Designing an antenna is always challenging because there is a tradeoff between the gain and the size. More specifically to design an antenna for wireless data communication in ISM band with less interference, low power consumption. To address these issues, this paper proposes a twin-slot radiator for beam-forming with high gain. The antenna operating at 2.4GHz consists of a two-layer stack with a twin-slot radiator and a superstrate separated by air medium. The metamaterial structure is excited with different phase delays through the twin-slot fed radiator to radiate the antenna beam in a specific direction. The performance analysis of the designed antenna is studied by simulation and measurement setups.
{"title":"Design of Twin-slot Radiator Beam-Forming Antenna Using Metasurface","authors":"Jegadish Kumar K. J., K. P., K. A., Gopalakrishnan N., Dinesh J., J. M.","doi":"10.1109/wispnet54241.2022.9767136","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767136","url":null,"abstract":"Designing an antenna is always challenging because there is a tradeoff between the gain and the size. More specifically to design an antenna for wireless data communication in ISM band with less interference, low power consumption. To address these issues, this paper proposes a twin-slot radiator for beam-forming with high gain. The antenna operating at 2.4GHz consists of a two-layer stack with a twin-slot radiator and a superstrate separated by air medium. The metamaterial structure is excited with different phase delays through the twin-slot fed radiator to radiate the antenna beam in a specific direction. The performance analysis of the designed antenna is studied by simulation and measurement setups.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121810130","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767138
A. V, U. S, Obulianand V., Sameeha Banu H., S. S
Based on a sorting network, the proposed approximate median filters (APMF) produce acceptable image quality on low-cost hardware. A specialized comparator is being developed to increase the noise-elimination capabilities of such filters. The inexact median filters (IMF) have a regular and modular architecture. Further, to reduce the power consumed by digital systems clock gating is employed. Clock with a View Into the Future Gating is a unique way of computing each FF's clock enabling signals one cycle ahead of time, based on the current cycle data of the FFs it depends on. By allocating a whole clock cycle for the computation of the enabling signals and their propagation, it avoids the strict timing constraints of adaptive geometric features-based filtering (AGFF) and data-driven. In addition, to give a better assessment of intrinsic mode filter (IMF) performance, a novel error evaluation approach based on a histogram-based error dispersion plot was presented. The proposed filter is effective in terms of power, area, and speed, according to simulation findings. The filter's output quality is comparable to that of a precise filter, despite the trade- off between filtering precision and circuit features. In addition, the deterioration is almost unnoticeable to the naked eye. When the clock power is reduced, the entire system's power is reduced as well.
{"title":"A Low Power Clock Gated Median Filter for Gray Level Images","authors":"A. V, U. S, Obulianand V., Sameeha Banu H., S. S","doi":"10.1109/wispnet54241.2022.9767138","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767138","url":null,"abstract":"Based on a sorting network, the proposed approximate median filters (APMF) produce acceptable image quality on low-cost hardware. A specialized comparator is being developed to increase the noise-elimination capabilities of such filters. The inexact median filters (IMF) have a regular and modular architecture. Further, to reduce the power consumed by digital systems clock gating is employed. Clock with a View Into the Future Gating is a unique way of computing each FF's clock enabling signals one cycle ahead of time, based on the current cycle data of the FFs it depends on. By allocating a whole clock cycle for the computation of the enabling signals and their propagation, it avoids the strict timing constraints of adaptive geometric features-based filtering (AGFF) and data-driven. In addition, to give a better assessment of intrinsic mode filter (IMF) performance, a novel error evaluation approach based on a histogram-based error dispersion plot was presented. The proposed filter is effective in terms of power, area, and speed, according to simulation findings. The filter's output quality is comparable to that of a precise filter, despite the trade- off between filtering precision and circuit features. In addition, the deterioration is almost unnoticeable to the naked eye. When the clock power is reduced, the entire system's power is reduced as well.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"176 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127630874","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767099
P. S., J. K.
Image segmentation is a well-known topic in image processing, and it remains as a hotspot and focal point for image processing techniques. In this paper, we propose a hybrid segmentation method, combining an Adaptive K-Means clustering algorithm and a novel automatic GrabCut segmentation algorithm to improve the performance of the object segmentation from the scene image. The proposed method is divided into six steps: Firstly, the RGB image normalization step is introduced to eliminate light variation and remove bright and shaded regions. Secondly, RGB colour space is converted to L⃰a⃰b⃰ colour space to maintain accurate colour balance. Thirdly, we propose a novel automatic GrabCut segmentation algorithm to eliminate user interaction and make the segmentation process faster. Fourthly, the Adaptive K-Means clustering algorithm and the proposed automatic GrabCut segmentation algorithm are combined to segment foreground objects from the background. Fifthly, the shape refinement step is used to eliminate occlusion, noise, and smear issues from the segmented image. Finally, morphological operations are carried out to enhance the segmentation performance. The performance of the hybrid segmentation method is assessed using the MSRA benchmark dataset.
{"title":"Object Segmentation Based on the Integration of Adaptive K-means and GrabCut Algorithm","authors":"P. S., J. K.","doi":"10.1109/wispnet54241.2022.9767099","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767099","url":null,"abstract":"Image segmentation is a well-known topic in image processing, and it remains as a hotspot and focal point for image processing techniques. In this paper, we propose a hybrid segmentation method, combining an Adaptive K-Means clustering algorithm and a novel automatic GrabCut segmentation algorithm to improve the performance of the object segmentation from the scene image. The proposed method is divided into six steps: Firstly, the RGB image normalization step is introduced to eliminate light variation and remove bright and shaded regions. Secondly, RGB colour space is converted to L⃰a⃰b⃰ colour space to maintain accurate colour balance. Thirdly, we propose a novel automatic GrabCut segmentation algorithm to eliminate user interaction and make the segmentation process faster. Fourthly, the Adaptive K-Means clustering algorithm and the proposed automatic GrabCut segmentation algorithm are combined to segment foreground objects from the background. Fifthly, the shape refinement step is used to eliminate occlusion, noise, and smear issues from the segmented image. Finally, morphological operations are carried out to enhance the segmentation performance. The performance of the hybrid segmentation method is assessed using the MSRA benchmark dataset.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116527094","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 : 2022-03-24DOI: 10.1109/wispnet54241.2022.9767175
Satyanarayana Pamarthi, N. R.
Adhoc networks are becoming a new wireless networking technology built for mobile hosts that are becoming more popular. Instead of relying on fixed infrastructure, ad hoc networks, as opposed to standard mobile wireless networks, are completely mobile. In this paper, we introduce a security mechanism in which packets are encoded and decoded using an arbitrary method selection scheme. The recommended model's functionality is assessed, and it is discovered that there was no reduction in control overhead, however a little delay has been introduced as a result of the authentication approach. Our outcome is that the recommended security architecture will function well for heavily loaded systems with a high mobility and that it may be updated to include other cryptographic algorithms in future versions. Ultimately, the quantitative analysis is carried out, where for the instance of length of the character set to 100; the suggested modified SFO ultimately outperformed to those already in use, with cost function being 22 % significantly greater than available PSO, 20% significantly bigger than available GWO, 19% significantly greater than available WOA as well as 21 % bigger than available SFO. The comparison study with conventional models confirms the suggested model's gives effective performance in terms of dissimilar analysis.
{"title":"Implementation of Modified SFO Algorithm to Enhance QoS in Wireless Mobile Adhoc Networks for IoT Applications","authors":"Satyanarayana Pamarthi, N. R.","doi":"10.1109/wispnet54241.2022.9767175","DOIUrl":"https://doi.org/10.1109/wispnet54241.2022.9767175","url":null,"abstract":"Adhoc networks are becoming a new wireless networking technology built for mobile hosts that are becoming more popular. Instead of relying on fixed infrastructure, ad hoc networks, as opposed to standard mobile wireless networks, are completely mobile. In this paper, we introduce a security mechanism in which packets are encoded and decoded using an arbitrary method selection scheme. The recommended model's functionality is assessed, and it is discovered that there was no reduction in control overhead, however a little delay has been introduced as a result of the authentication approach. Our outcome is that the recommended security architecture will function well for heavily loaded systems with a high mobility and that it may be updated to include other cryptographic algorithms in future versions. Ultimately, the quantitative analysis is carried out, where for the instance of length of the character set to 100; the suggested modified SFO ultimately outperformed to those already in use, with cost function being 22 % significantly greater than available PSO, 20% significantly bigger than available GWO, 19% significantly greater than available WOA as well as 21 % bigger than available SFO. The comparison study with conventional models confirms the suggested model's gives effective performance in terms of dissimilar analysis.","PeriodicalId":432794,"journal":{"name":"2022 International Conference on Wireless Communications Signal Processing and Networking (WiSPNET)","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126694884","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：