Pub Date : 2021-12-03DOI: 10.1109/SPICSCON54707.2021.9885246
Sajeeb Chandra Das, L. Paul, Md. Najmul Hossain, Md. Zulfiker Mahmud, R. Azim
A dual band spiral-shaped patch antenna (SPA) is designed and proposed for 5G and WiFi-5/6 applications. The Rogers RT 5880 (lossy) substrate with a compact size of 20×20×0.79 mm3 has been used to design the spiral patch antenna. The dual band antenna resonates at 3.61 GHz (3.53–3.7 GHz) and 5.56 GHz (4.7–7.24 GHz) with very good reflection coefficients of −41.29 dB and −37.85 dB respectively which cover lower 5G (n48 CBRS (USA): 3.55 – 3.7 GHz, Korea: 3.4–3.7 GHz), WiFi-5 (5.15–5.85 GHz) and WiFi-6 (5.925 – 7.125 GHz) bands. It has gain of 1.503 dB, 2.767 dB and directivity of 3.057 dBi, 3.368 dBi and VSWR of 1.017, 1.025 at resonant frequencies 3.61GHz and 5.56 GHz respectively. The peak gain and directivity of the SPA are 3.95 dB and 5 dBi. The spiral-shaped patch with optimized dimensions enhances the antenna performances and ensures good impedance matching to make it suitable for lower 5G and WiFi-5/6 applications.
{"title":"A Dual Band Miniaturized Spiral-shaped Patch Antenna for 5G and WiFi-5/6 Applications","authors":"Sajeeb Chandra Das, L. Paul, Md. Najmul Hossain, Md. Zulfiker Mahmud, R. Azim","doi":"10.1109/SPICSCON54707.2021.9885246","DOIUrl":"https://doi.org/10.1109/SPICSCON54707.2021.9885246","url":null,"abstract":"A dual band spiral-shaped patch antenna (SPA) is designed and proposed for 5G and WiFi-5/6 applications. The Rogers RT 5880 (lossy) substrate with a compact size of 20×20×0.79 mm3 has been used to design the spiral patch antenna. The dual band antenna resonates at 3.61 GHz (3.53–3.7 GHz) and 5.56 GHz (4.7–7.24 GHz) with very good reflection coefficients of −41.29 dB and −37.85 dB respectively which cover lower 5G (n48 CBRS (USA): 3.55 – 3.7 GHz, Korea: 3.4–3.7 GHz), WiFi-5 (5.15–5.85 GHz) and WiFi-6 (5.925 – 7.125 GHz) bands. It has gain of 1.503 dB, 2.767 dB and directivity of 3.057 dBi, 3.368 dBi and VSWR of 1.017, 1.025 at resonant frequencies 3.61GHz and 5.56 GHz respectively. The peak gain and directivity of the SPA are 3.95 dB and 5 dBi. The spiral-shaped patch with optimized dimensions enhances the antenna performances and ensures good impedance matching to make it suitable for lower 5G and WiFi-5/6 applications.","PeriodicalId":159505,"journal":{"name":"2021 IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124999935","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 : 2021-12-03DOI: 10.1109/SPICSCON54707.2021.9885671
Samrat Alam, Sajal Das Shovon, Naimul Hoque Joy
In 2020 COVID-19 has taken the world by storm. Scientists from around the world are still working to develop a more effective vaccine for this disease. AstraZeneca, Moderna, Sputnik V and Comirnaty (Pfizer) are just a few of the vaccines that have been developed and are now being used by large populations. Social media is a powerful tool for people to express their opinions on current events, such as COVID-19 and its vaccine. It is highly noticeable that people are becoming increasingly concerned about the availability and effectiveness of these vaccines and other remedies for COVID-19. Healthcare organizations and professionals can acquire useful insights into vaccination safety by evaluating people’s sentiments. Furthermore, it can also assist to prevent unnecessary panic and the spread of misinformation among people. In this paper, a comprehensive analysis of people’s sentiments regarding the vaccination against COVID-19 is shown. Twitter’s data regarding the vaccine for COVID-19 from January to December of 2020 was collected from Kaggle for analysis. Necessary preprocessing techniques have been used to prepare and label the data based on textual sentiment using the lexical semantic methods: TextBlob and VADER. Various machine learning methods like Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), merged model (RNN+CNN) and Logistic Regression have been used to analyze the public sentiments and to visualize their concerns regarding the vaccination against COVID-19 throughout 2020. Then, the results from both TextBlob and VADER were compared in order to obtain the highest possible accuracy and to better understand the reasons for them.
{"title":"Machine learning and Lexical Semantic-based Sentiment Analysis for Determining the Impacts of the COVID-19 Vaccine","authors":"Samrat Alam, Sajal Das Shovon, Naimul Hoque Joy","doi":"10.1109/SPICSCON54707.2021.9885671","DOIUrl":"https://doi.org/10.1109/SPICSCON54707.2021.9885671","url":null,"abstract":"In 2020 COVID-19 has taken the world by storm. Scientists from around the world are still working to develop a more effective vaccine for this disease. AstraZeneca, Moderna, Sputnik V and Comirnaty (Pfizer) are just a few of the vaccines that have been developed and are now being used by large populations. Social media is a powerful tool for people to express their opinions on current events, such as COVID-19 and its vaccine. It is highly noticeable that people are becoming increasingly concerned about the availability and effectiveness of these vaccines and other remedies for COVID-19. Healthcare organizations and professionals can acquire useful insights into vaccination safety by evaluating people’s sentiments. Furthermore, it can also assist to prevent unnecessary panic and the spread of misinformation among people. In this paper, a comprehensive analysis of people’s sentiments regarding the vaccination against COVID-19 is shown. Twitter’s data regarding the vaccine for COVID-19 from January to December of 2020 was collected from Kaggle for analysis. Necessary preprocessing techniques have been used to prepare and label the data based on textual sentiment using the lexical semantic methods: TextBlob and VADER. Various machine learning methods like Recurrent Neural Network (RNN), Convolutional Neural Network (CNN), merged model (RNN+CNN) and Logistic Regression have been used to analyze the public sentiments and to visualize their concerns regarding the vaccination against COVID-19 throughout 2020. Then, the results from both TextBlob and VADER were compared in order to obtain the highest possible accuracy and to better understand the reasons for them.","PeriodicalId":159505,"journal":{"name":"2021 IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125910172","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 : 2021-12-03DOI: 10.1109/SPICSCON54707.2021.9885581
Md. Shakhawat Hossen, Sibly Noman
This paper focuses on the selection criterion of S band patch antenna for university student led low cost nanosatellite missions. These nanosatellites are most often known as Cube Satellites (CubeSats). Different design challenges are categorized and discussed here based on the design considerations and limitations of previous research works. And a novel S band (2 – 4 GHz) operated coaxial feed patch antenna is also proposed in the following manuscript. The simulated results show good agreement for the operating frequency of 2.69 GHz and desirable performance in gain and directivity. The antenna is simulated in a Far-field region and the directivity is measured at 7.114 dBi which is convenient for most of the ground communications, high speed data download links, inter-satellite communications, remote sensing, and other satellite applications. As the proposed antenna design is focused on low cost solution for the CubeSat antennas, Rogers RT5870 is used as substrate material for mitigating the electrical loss at its best. The reflection parameter is observed as −11.116 dB, which is very feasible comparing with other existing CubeSat antennas.
{"title":"Antenna Design for University Low Cost Student-Built CubeSat Missions","authors":"Md. Shakhawat Hossen, Sibly Noman","doi":"10.1109/SPICSCON54707.2021.9885581","DOIUrl":"https://doi.org/10.1109/SPICSCON54707.2021.9885581","url":null,"abstract":"This paper focuses on the selection criterion of S band patch antenna for university student led low cost nanosatellite missions. These nanosatellites are most often known as Cube Satellites (CubeSats). Different design challenges are categorized and discussed here based on the design considerations and limitations of previous research works. And a novel S band (2 – 4 GHz) operated coaxial feed patch antenna is also proposed in the following manuscript. The simulated results show good agreement for the operating frequency of 2.69 GHz and desirable performance in gain and directivity. The antenna is simulated in a Far-field region and the directivity is measured at 7.114 dBi which is convenient for most of the ground communications, high speed data download links, inter-satellite communications, remote sensing, and other satellite applications. As the proposed antenna design is focused on low cost solution for the CubeSat antennas, Rogers RT5870 is used as substrate material for mitigating the electrical loss at its best. The reflection parameter is observed as −11.116 dB, which is very feasible comparing with other existing CubeSat antennas.","PeriodicalId":159505,"journal":{"name":"2021 IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131536132","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 : 2021-12-03DOI: 10.1109/SPICSCON54707.2021.9885414
Md. Mijanur Rahman, A. Uzzaman, S. Sami
This study is concerned with the development of a deep neural network-based framework, including a “convolutional neural network (CNN)” encoder and a “Long Short-Term Memory (LSTM)” decoder in an automatic image captioning application. The proposed model percepts information points in a picture and their relationship to one another in the viewpoint. Firstly, a CNN encoder excels at retaining spatial information and recognizing objects in images by extracting features to produce vocabulary that describes the photos. Secondly, an LSTM network decoder is used for predicting words and creating meaningful sentences from the built keywords. Thus, in the proposed neural network-based system, the VGG-19 model is presented for defining the proposed model as an image feature extractor and sequence processor, and then the LSTM model provides a fixed-length output vector as a final prediction. A variety of images from several open-source datasets, such as Flickr 8k, Flickr 30k, and MS COCO, were explored and used for training as well as testing the proposed model. The experiment was done on Python with Keras and TensorFlow backend. It demonstrated the automatic image captioning and evaluated the performance of the proposed model using the BLEU (BiLingual Evaluation Understudy) metric.
{"title":"Implementing Deep Neural Network Based Encoder-Decoder Framework for Image Captioning","authors":"Md. Mijanur Rahman, A. Uzzaman, S. Sami","doi":"10.1109/SPICSCON54707.2021.9885414","DOIUrl":"https://doi.org/10.1109/SPICSCON54707.2021.9885414","url":null,"abstract":"This study is concerned with the development of a deep neural network-based framework, including a “convolutional neural network (CNN)” encoder and a “Long Short-Term Memory (LSTM)” decoder in an automatic image captioning application. The proposed model percepts information points in a picture and their relationship to one another in the viewpoint. Firstly, a CNN encoder excels at retaining spatial information and recognizing objects in images by extracting features to produce vocabulary that describes the photos. Secondly, an LSTM network decoder is used for predicting words and creating meaningful sentences from the built keywords. Thus, in the proposed neural network-based system, the VGG-19 model is presented for defining the proposed model as an image feature extractor and sequence processor, and then the LSTM model provides a fixed-length output vector as a final prediction. A variety of images from several open-source datasets, such as Flickr 8k, Flickr 30k, and MS COCO, were explored and used for training as well as testing the proposed model. The experiment was done on Python with Keras and TensorFlow backend. It demonstrated the automatic image captioning and evaluated the performance of the proposed model using the BLEU (BiLingual Evaluation Understudy) metric.","PeriodicalId":159505,"journal":{"name":"2021 IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)","volume":"347 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134496600","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 : 2021-12-03DOI: 10.1109/SPICSCON54707.2021.9885430
Md. Appel Mahmud Pranto, Nafiz Al Asad
Mental health is equally treated as important as physical health. Sound mental health leads to a peaceful life. Mental has a big impact on our thoughts, feelings, and behaviors. People’s mental health could be disturbed like facing depression. Depression is a major concern nowadays. People like to share their feelings and thoughts using several social media like Facebook, Twitter, WhatsApp, etc. In this paper, we propose a model based on federated learning and deep learning combined to monitor mental health using these social media data. In the proposed system data is collected from the user’s keyboard as people use the keyboard to type their thoughts, feelings on social media. Depression level is detected on daily basis using federated learning and recurrent neural network (RNN). The global model is saved into the global server. User’s local device inherits global model to test their daily used data on the keyboard. After testing, the user’s test data is sent anonymously to the global dictionary and then the global dictionary is updated daily using all user’s anonymous tested data. Then using this updated global sentiment dictionary global model is trained again and sent to all user’s local devices to monitor their mental health. Our proposed model acquires 93.46% accuracy on 60th day.
{"title":"A Comprehensive Model to Monitor Mental Health based on Federated Learning and Deep Learning","authors":"Md. Appel Mahmud Pranto, Nafiz Al Asad","doi":"10.1109/SPICSCON54707.2021.9885430","DOIUrl":"https://doi.org/10.1109/SPICSCON54707.2021.9885430","url":null,"abstract":"Mental health is equally treated as important as physical health. Sound mental health leads to a peaceful life. Mental has a big impact on our thoughts, feelings, and behaviors. People’s mental health could be disturbed like facing depression. Depression is a major concern nowadays. People like to share their feelings and thoughts using several social media like Facebook, Twitter, WhatsApp, etc. In this paper, we propose a model based on federated learning and deep learning combined to monitor mental health using these social media data. In the proposed system data is collected from the user’s keyboard as people use the keyboard to type their thoughts, feelings on social media. Depression level is detected on daily basis using federated learning and recurrent neural network (RNN). The global model is saved into the global server. User’s local device inherits global model to test their daily used data on the keyboard. After testing, the user’s test data is sent anonymously to the global dictionary and then the global dictionary is updated daily using all user’s anonymous tested data. Then using this updated global sentiment dictionary global model is trained again and sent to all user’s local devices to monitor their mental health. Our proposed model acquires 93.46% accuracy on 60th day.","PeriodicalId":159505,"journal":{"name":"2021 IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126132808","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 : 2021-12-03DOI: 10.1109/SPICSCON54707.2021.9885316
Vrushank Changawala, Keshav Sharma, M. Paunwala
This paper attempts to survey newer approaches that do not use convolutional neural networks (CNNs) conventionally to the evolving field of medical image classification. While analyzing, firstly, an all feed-forward architecture MLP-Mixer and secondly, the inverted convolutional kernels coined as Involution with the baseline ResNets, both models yield comparable results in detecting Covid19 and pneumonia using Chest X-ray images. On top of that, merging Involution kernels into ResNet architectures can produce promising performance while training on roughly 40% fewer parameters. This paper further compares these two architectures with various CNN-based models. We hope this survey further helps the research community to utilize the capabilities of these newly introduced architectures in the medical field. [Code: https://github.com/Vrushank264/Averting-from-CNNs]
{"title":"Averting from Convolutional Neural Networks for Chest X-Ray Image Classification","authors":"Vrushank Changawala, Keshav Sharma, M. Paunwala","doi":"10.1109/SPICSCON54707.2021.9885316","DOIUrl":"https://doi.org/10.1109/SPICSCON54707.2021.9885316","url":null,"abstract":"This paper attempts to survey newer approaches that do not use convolutional neural networks (CNNs) conventionally to the evolving field of medical image classification. While analyzing, firstly, an all feed-forward architecture MLP-Mixer and secondly, the inverted convolutional kernels coined as Involution with the baseline ResNets, both models yield comparable results in detecting Covid19 and pneumonia using Chest X-ray images. On top of that, merging Involution kernels into ResNet architectures can produce promising performance while training on roughly 40% fewer parameters. This paper further compares these two architectures with various CNN-based models. We hope this survey further helps the research community to utilize the capabilities of these newly introduced architectures in the medical field. [Code: https://github.com/Vrushank264/Averting-from-CNNs]","PeriodicalId":159505,"journal":{"name":"2021 IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128155223","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 : 2021-12-03DOI: 10.1109/SPICSCON54707.2021.9885712
Md. Nazmul Islam, Taufiq Abdullah, Md. Eakub Ali
The main purpose of this experiment is to analyze automatic sampling period quantization with respect to instantaneous derivatives of the signal. The derivatives of the signal have been computed using two individual time periods. The derivative result is compared by the detector to achieve the sampling time for soft and sharp regions. The system is quantized to get 1-bit time coding. The time and signal are integrated with a semi-synchronous model. This paper includes simulations and comparative discussions.
{"title":"Pulse Code Modulations with Derivative Dependent Automatic Sampling Time Quantization and Coupled Encoding","authors":"Md. Nazmul Islam, Taufiq Abdullah, Md. Eakub Ali","doi":"10.1109/SPICSCON54707.2021.9885712","DOIUrl":"https://doi.org/10.1109/SPICSCON54707.2021.9885712","url":null,"abstract":"The main purpose of this experiment is to analyze automatic sampling period quantization with respect to instantaneous derivatives of the signal. The derivatives of the signal have been computed using two individual time periods. The derivative result is compared by the detector to achieve the sampling time for soft and sharp regions. The system is quantized to get 1-bit time coding. The time and signal are integrated with a semi-synchronous model. This paper includes simulations and comparative discussions.","PeriodicalId":159505,"journal":{"name":"2021 IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130227086","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 : 2021-12-03DOI: 10.1109/SPICSCON54707.2021.9885682
Md. Tanvir Shahed, A. Rashid
In this paper, a low power split capacitor array structure based successive approximation register (SAR) type analog to digital converter (ADC) is proposed. To minimize power, this ADC combines the capacitive digital to analog converter (DAC) with the sample and hold (S/H) circuit, uses the Split binary-weighted capacitor array for the DAC, and utilizes the open-loop comparator. The ADC consumes low power with good performance. The DAC efficiently uses charge recycling to achieve a high speed of operation. The proposed ADC is designed using 0.18-μm CMOS technology. At a 1.8-V supply and 2 MS/s, the ADC achieves a spurious-free dynamic range (SFDR) of 54 dB and consumes 0.27633 mW.
{"title":"Design of a 10 Bit Low Power Split Capacitor Array SAR ADC","authors":"Md. Tanvir Shahed, A. Rashid","doi":"10.1109/SPICSCON54707.2021.9885682","DOIUrl":"https://doi.org/10.1109/SPICSCON54707.2021.9885682","url":null,"abstract":"In this paper, a low power split capacitor array structure based successive approximation register (SAR) type analog to digital converter (ADC) is proposed. To minimize power, this ADC combines the capacitive digital to analog converter (DAC) with the sample and hold (S/H) circuit, uses the Split binary-weighted capacitor array for the DAC, and utilizes the open-loop comparator. The ADC consumes low power with good performance. The DAC efficiently uses charge recycling to achieve a high speed of operation. The proposed ADC is designed using 0.18-μm CMOS technology. At a 1.8-V supply and 2 MS/s, the ADC achieves a spurious-free dynamic range (SFDR) of 54 dB and consumes 0.27633 mW.","PeriodicalId":159505,"journal":{"name":"2021 IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122952171","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 : 2021-12-03DOI: 10.1109/SPICSCON54707.2021.9885596
Mac Akmal-Jahan, J. Niranjana, B. Vithusa, SF. Jumani, RF. Zulfa
The utilization of vehicles increases with the increased number of populations. Unplanned parking strategies causes additional traffic problems, waste of time, unwanted conflicts among drivers, damages etc. Vehicles need appropriate parking areas based on their size and dimension to be fit well. In Sri Lanka, a manual processing is adopted to handle most of the parking areas, which wastes energy, time and causes stress. In city areas, parking vehicles on the road-side is strictly restricted. In this paper, an automated system of vehicle classification for allocating parking slots in public premises is proposed. This system can capture a set of vehicle images, identify the type of vehicle, estimate the size of vehicle and allocate a good fit parking slot based on their dimensional and type parameters. Geometrical or dimensional attributes and Histogram of Oriented Gradient features are extracted, and Support Vector Machine is used for classification. Feature fusion is exploited to investigate the impact of fusion strategy on system performance. Principal Component Analysis is applied to reduce the dimension of the feature vector, which results further significant improvement in the system performance.
{"title":"HOG and Dimensional Feature based Vehicle Classification for Parking Slot Allocation","authors":"Mac Akmal-Jahan, J. Niranjana, B. Vithusa, SF. Jumani, RF. Zulfa","doi":"10.1109/SPICSCON54707.2021.9885596","DOIUrl":"https://doi.org/10.1109/SPICSCON54707.2021.9885596","url":null,"abstract":"The utilization of vehicles increases with the increased number of populations. Unplanned parking strategies causes additional traffic problems, waste of time, unwanted conflicts among drivers, damages etc. Vehicles need appropriate parking areas based on their size and dimension to be fit well. In Sri Lanka, a manual processing is adopted to handle most of the parking areas, which wastes energy, time and causes stress. In city areas, parking vehicles on the road-side is strictly restricted. In this paper, an automated system of vehicle classification for allocating parking slots in public premises is proposed. This system can capture a set of vehicle images, identify the type of vehicle, estimate the size of vehicle and allocate a good fit parking slot based on their dimensional and type parameters. Geometrical or dimensional attributes and Histogram of Oriented Gradient features are extracted, and Support Vector Machine is used for classification. Feature fusion is exploited to investigate the impact of fusion strategy on system performance. Principal Component Analysis is applied to reduce the dimension of the feature vector, which results further significant improvement in the system performance.","PeriodicalId":159505,"journal":{"name":"2021 IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126674306","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}
Unmanned aerial vehicle (UAV)-assisted wireless network is envisioned as a dominant network in 6G to cope with sudden surge of data rate demand and to provide flexible data connectivity. This network works as a moving hotspot. Existing UAV deployment techniques suffer from limited throughput and user satisfaction. In this paper, we propose a novel UAV deployment algorithm exploiting the fuzzy c-means clustering to overcome the limitations involved in k-means clustering so that a higher network throughput can be achieved and to ensure a higher user satisfaction. We compare the performance of the proposed UAV deployment algorithm with the performance of the state-of-the-art k-means algorithm. Simulation results show that the proposed method outperforms the k-means algorithm in terms of network throughput, user satisfaction ratio, and consistency in throughput. Up to 9% improvement in the network throughput is obtained due to the proposed method. We see that the network throughput is proportional to the number of UAVs, and more users can be satisfied by the proposed method.
{"title":"A Fuzzy Logic Approach for Improving Throughput of the UAV-Assisted Wireless Networks","authors":"Sadia Afrin, Md. Sakir Hossain, Md.R. Iqbal, Alif Refat, Ahsan U. Tamim","doi":"10.1109/SPICSCON54707.2021.9885326","DOIUrl":"https://doi.org/10.1109/SPICSCON54707.2021.9885326","url":null,"abstract":"Unmanned aerial vehicle (UAV)-assisted wireless network is envisioned as a dominant network in 6G to cope with sudden surge of data rate demand and to provide flexible data connectivity. This network works as a moving hotspot. Existing UAV deployment techniques suffer from limited throughput and user satisfaction. In this paper, we propose a novel UAV deployment algorithm exploiting the fuzzy c-means clustering to overcome the limitations involved in k-means clustering so that a higher network throughput can be achieved and to ensure a higher user satisfaction. We compare the performance of the proposed UAV deployment algorithm with the performance of the state-of-the-art k-means algorithm. Simulation results show that the proposed method outperforms the k-means algorithm in terms of network throughput, user satisfaction ratio, and consistency in throughput. Up to 9% improvement in the network throughput is obtained due to the proposed method. We see that the network throughput is proportional to the number of UAVs, and more users can be satisfied by the proposed method.","PeriodicalId":159505,"journal":{"name":"2021 IEEE International Conference on Signal Processing, Information, Communication & Systems (SPICSCON)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128479829","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：