Pub Date : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663716
S. Sharath, Vidyadevi G. Biradar, M.S. Prajwal, B. Ashwini
Crowd counting plays a significant role in analyzing the crowd behavior in high density areas. Deep learning techniques may be utilized to count the crowd from given high density images. This gives situation awareness and facilitates in imposing necessary actions to control the crowd in various scenarios when needed. In this paper a deep convolutional neural network model has been developed for crowd counting. The model has been developed using VGG16 pre-trained model and it is tuned up for crowd counting using transfer learning. The dataset used in this work is ShanghaiTech crowd dataset, that contains 482 high density crowd images. Image augmentation is applied to enlarge the dataset. The model gives a training accuracy of 83% and 79% of validation accuracy.
{"title":"Crowd Counting in High Dense Images using Deep Convolutional Neural Network","authors":"S. Sharath, Vidyadevi G. Biradar, M.S. Prajwal, B. Ashwini","doi":"10.1109/DISCOVER52564.2021.9663716","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663716","url":null,"abstract":"Crowd counting plays a significant role in analyzing the crowd behavior in high density areas. Deep learning techniques may be utilized to count the crowd from given high density images. This gives situation awareness and facilitates in imposing necessary actions to control the crowd in various scenarios when needed. In this paper a deep convolutional neural network model has been developed for crowd counting. The model has been developed using VGG16 pre-trained model and it is tuned up for crowd counting using transfer learning. The dataset used in this work is ShanghaiTech crowd dataset, that contains 482 high density crowd images. Image augmentation is applied to enlarge the dataset. The model gives a training accuracy of 83% and 79% of validation accuracy.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127611786","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663586
D. R. Janardhana, V. P. Pavan Kumar, S. R. Lavanya, A. Manu
The Internet of Things (IoT) is the 21st century’s fastest-growing technology. Nearly by the end of 2025, 75 billion IoT devices will be get connected to the internet. As a result, safeguarding devices from attacks and maintaining user privacy-related data has become extremely difficult. In this paper, we propose an efficient model to detect security and privacy related threats in IoT environment using different machine learning and deep learning algorithms on open-source standard dataset like NSL-KDD (Knowledge Discovery Data) and UNSW-NB15, which were made accessible for conducting research activities purposes. Here we analyzed the feature set of the data required to detect various threats mentioned in the given dataset using proposed model. This paper examines the binary and multiclass attacks classification using neural network and machine learning approaches. RNN model outperformed with higher accuracy in detecting threats with 99.4 percent for binary classification and 96.2 percent for multiclass classification.
{"title":"Detecting Security and Privacy Attacks in IoT Network using Deep Learning Algorithms","authors":"D. R. Janardhana, V. P. Pavan Kumar, S. R. Lavanya, A. Manu","doi":"10.1109/DISCOVER52564.2021.9663586","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663586","url":null,"abstract":"The Internet of Things (IoT) is the 21st century’s fastest-growing technology. Nearly by the end of 2025, 75 billion IoT devices will be get connected to the internet. As a result, safeguarding devices from attacks and maintaining user privacy-related data has become extremely difficult. In this paper, we propose an efficient model to detect security and privacy related threats in IoT environment using different machine learning and deep learning algorithms on open-source standard dataset like NSL-KDD (Knowledge Discovery Data) and UNSW-NB15, which were made accessible for conducting research activities purposes. Here we analyzed the feature set of the data required to detect various threats mentioned in the given dataset using proposed model. This paper examines the binary and multiclass attacks classification using neural network and machine learning approaches. RNN model outperformed with higher accuracy in detecting threats with 99.4 percent for binary classification and 96.2 percent for multiclass classification.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121056801","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663634
C. Skanda, B. Srivatsa, B. S. Premananda
Communication at nano-scale provides high operational speed and low power consumption. Quantum-dot Cellular Automata (QCA) is used to create nano-scale digital logic circuits. It can replace CMOS technology in nano-scale due to the latter reaching its physical limit. Designing communication networks at nano-scale minimizes cost and energy dissipation. This study presents a QCA based crossbar switch and banyan network. The paper proposes the banyan network in single layer structure with energy and cost analysis. The work aims to minimize the cells, area, latency and energy dissipation in the banyan network. The proposed 2x2 crossbar switch has improvement of 55.44% in terms of cell count, and 93.12% in cost function compared to reference network. The designed 4x4 banyan network has a reduction of 54.18% in terms of cell count w.r.t. the reference networks. The networks are realized in the CAD tool QCA Designer 2.0.3 and energy analysis is performed in QCA Designer-E.
{"title":"Design of Compact and Energy Efficient Banyan Network for Nano Communication","authors":"C. Skanda, B. Srivatsa, B. S. Premananda","doi":"10.1109/DISCOVER52564.2021.9663634","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663634","url":null,"abstract":"Communication at nano-scale provides high operational speed and low power consumption. Quantum-dot Cellular Automata (QCA) is used to create nano-scale digital logic circuits. It can replace CMOS technology in nano-scale due to the latter reaching its physical limit. Designing communication networks at nano-scale minimizes cost and energy dissipation. This study presents a QCA based crossbar switch and banyan network. The paper proposes the banyan network in single layer structure with energy and cost analysis. The work aims to minimize the cells, area, latency and energy dissipation in the banyan network. The proposed 2x2 crossbar switch has improvement of 55.44% in terms of cell count, and 93.12% in cost function compared to reference network. The designed 4x4 banyan network has a reduction of 54.18% in terms of cell count w.r.t. the reference networks. The networks are realized in the CAD tool QCA Designer 2.0.3 and energy analysis is performed in QCA Designer-E.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127361615","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663692
Jignesh Karia, Mukundan Sundararajan, G. Srinivasa Raghavan
Master Data Management (MDM) in enterprises deal with fixed data/information regarding different aspects of business that are considered single record of truth and form the basis for all business transactions. Enterprises manage their master data by several methods to ensure that it is a unique comprehensive representation of the entity by spending considerable resources in MDM but at the cost of time delays for updating the master data records or structure and with copies of the master data distributed across the enterprise units for operational needs that many times has modifications not reflected back into the master tables. Issues of delays in the master data updates lead to business impacts while the distributed nature of master data across an organization or organizations impacts data quality. Distributed ledger technology (DLT) is one approach that uses blockchain to obtain consensus to cut down the approval cycle time and the distributed nature makes it uniquely suited to manage synchronizing master data updates across the network of required users in the enterprise. Choice of correct business processes to benefit from using DLT for MDM is critical to obtain benefits from improvements. This paper shows a method to select from candidate business processes with coarse or fine process data and the value that can be gained from implementation of DLT for MDM.
{"title":"Distributed Ledger Systems to Improve Data Synchronization in Enterprise Processes","authors":"Jignesh Karia, Mukundan Sundararajan, G. Srinivasa Raghavan","doi":"10.1109/DISCOVER52564.2021.9663692","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663692","url":null,"abstract":"Master Data Management (MDM) in enterprises deal with fixed data/information regarding different aspects of business that are considered single record of truth and form the basis for all business transactions. Enterprises manage their master data by several methods to ensure that it is a unique comprehensive representation of the entity by spending considerable resources in MDM but at the cost of time delays for updating the master data records or structure and with copies of the master data distributed across the enterprise units for operational needs that many times has modifications not reflected back into the master tables. Issues of delays in the master data updates lead to business impacts while the distributed nature of master data across an organization or organizations impacts data quality. Distributed ledger technology (DLT) is one approach that uses blockchain to obtain consensus to cut down the approval cycle time and the distributed nature makes it uniquely suited to manage synchronizing master data updates across the network of required users in the enterprise. Choice of correct business processes to benefit from using DLT for MDM is critical to obtain benefits from improvements. This paper shows a method to select from candidate business processes with coarse or fine process data and the value that can be gained from implementation of DLT for MDM.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115489057","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663594
G. Mrudula, C. S. Kumar
Obstructive sleep apnea is a type of sleep disordered breathing (SDB), marked by pauses in breath during sleep. Sleep apnea monitoring devices are extremely expensive and unavailable in rural areas. The focus of this work is to develop a cost-effective sleep apnea screening system based on single channel electrocardiography (ECG) signal. Initially we built a baseline system that used heart rate variability information as input to a CNN classifier. The baseline system performance was evaluated for time domain (TD), frequency domain (FD), and TD and FD HRV features. The baseline model had an overall accuracy of 78.39%, specificity of 70.58% and sensitivity of 86.2%. In an attempt to increase the system performance, two methods were employed. Initially covariance normalization (CVN) was applied to the input features. CVN reduces the noisy factors induced to the input features due to patient specific variations. Subsequently we used neural networks to extract the bottleneck features (BNF) from bottleneck layer of the CNN model. This layer compresses the neural network, allowing the extraction of lower-dimensional information from the network. System performance was evaluated with the BNF extracted from the baseline model with HRV features as input, and also from the baseline model built using normalized HRV features. Upon performance evaluation, it was found that, compared to the baseline model, the BNF extracted from TD and FD HRV features shows a performance improvement of1.39%and BNF extracted from normalized TD and FD HRV features improved the overall accuracy by 1.7%.
{"title":"Covariance Normalization and Bottleneck Features for Improving the Performance of Sleep Apnea Screening System","authors":"G. Mrudula, C. S. Kumar","doi":"10.1109/DISCOVER52564.2021.9663594","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663594","url":null,"abstract":"Obstructive sleep apnea is a type of sleep disordered breathing (SDB), marked by pauses in breath during sleep. Sleep apnea monitoring devices are extremely expensive and unavailable in rural areas. The focus of this work is to develop a cost-effective sleep apnea screening system based on single channel electrocardiography (ECG) signal. Initially we built a baseline system that used heart rate variability information as input to a CNN classifier. The baseline system performance was evaluated for time domain (TD), frequency domain (FD), and TD and FD HRV features. The baseline model had an overall accuracy of 78.39%, specificity of 70.58% and sensitivity of 86.2%. In an attempt to increase the system performance, two methods were employed. Initially covariance normalization (CVN) was applied to the input features. CVN reduces the noisy factors induced to the input features due to patient specific variations. Subsequently we used neural networks to extract the bottleneck features (BNF) from bottleneck layer of the CNN model. This layer compresses the neural network, allowing the extraction of lower-dimensional information from the network. System performance was evaluated with the BNF extracted from the baseline model with HRV features as input, and also from the baseline model built using normalized HRV features. Upon performance evaluation, it was found that, compared to the baseline model, the BNF extracted from TD and FD HRV features shows a performance improvement of1.39%and BNF extracted from normalized TD and FD HRV features improved the overall accuracy by 1.7%.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"149 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123160210","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663698
Sachin S. Bhat, Preema Dsouza, K. Sharanyalaxmi, Shreeraksha, Tejasvini, A. Ananth
Countless numbers of plants are available in this world. Identifying each and every plant and then classifying them has become one of the important and difficult tasks.Various parts of plants such as flowers, seeds, leaves can be used for identification, but recognizing leaves is the simplest and most effective method. Deep learning technique brings out effective way of leaf recognition system. Here we have used customised Convolutional Neural Network model to recognize the leaves specially growing in western ghats. A separate dataset has been created by collecting more than 50000 leaf samples of 48 different types of plants. The relevant information about the set of plants are collected from the botanists. Various architectures of CNN such as InceptionV3, MobileNet, VGG16, DensNet are used to evaluate the results. Model gives a satisfactory accuracy of 93.79% on 48 classes.
{"title":"Classification of Plant Leaves of Western Ghats using Deep Learning","authors":"Sachin S. Bhat, Preema Dsouza, K. Sharanyalaxmi, Shreeraksha, Tejasvini, A. Ananth","doi":"10.1109/DISCOVER52564.2021.9663698","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663698","url":null,"abstract":"Countless numbers of plants are available in this world. Identifying each and every plant and then classifying them has become one of the important and difficult tasks.Various parts of plants such as flowers, seeds, leaves can be used for identification, but recognizing leaves is the simplest and most effective method. Deep learning technique brings out effective way of leaf recognition system. Here we have used customised Convolutional Neural Network model to recognize the leaves specially growing in western ghats. A separate dataset has been created by collecting more than 50000 leaf samples of 48 different types of plants. The relevant information about the set of plants are collected from the botanists. Various architectures of CNN such as InceptionV3, MobileNet, VGG16, DensNet are used to evaluate the results. Model gives a satisfactory accuracy of 93.79% on 48 classes.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125053929","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663644
Abhinandan Krishnan, Pannaga Sudarshan
This paper primarily focuses on the ‘Localization and Control’ problem with the holonomic class of mobile robots. The paper discusses a computationally less intensive with high rate localization and navigation techniques for a three wheeled omni-directional mobile robot, using wheel encoders and kinematic relations. Insight to an elegant and pragmatic approach to navigate the robot from point A to point B in the defined workspace, enabling the robot to autonomously reach a target position and orientation defined by the user, is given. Implementation of the ‘Go to Pose’ algorithm is done for both single-waypoint and multi-waypoint navigation. The experimental results obtained reinforce the robustness of the algorithm that incorporates PID controller.
本文主要研究完整类移动机器人的“定位与控制”问题。利用轮式编码器和运动学关系，讨论了一种计算量小、速度快的三轮全向移动机器人定位与导航技术。给出了一种优雅而实用的方法，使机器人在定义的工作空间中从A点导航到B点，使机器人能够自主地到达用户定义的目标位置和方向。“Go to Pose”算法的实现是针对单路点和多路点导航完成的。实验结果表明，加入PID控制器后，该算法具有较好的鲁棒性。
{"title":"Self-Localization and Waypoints following of Holonomic Three Wheeled Omni-Directional Mobile Robot","authors":"Abhinandan Krishnan, Pannaga Sudarshan","doi":"10.1109/DISCOVER52564.2021.9663644","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663644","url":null,"abstract":"This paper primarily focuses on the ‘Localization and Control’ problem with the holonomic class of mobile robots. The paper discusses a computationally less intensive with high rate localization and navigation techniques for a three wheeled omni-directional mobile robot, using wheel encoders and kinematic relations. Insight to an elegant and pragmatic approach to navigate the robot from point A to point B in the defined workspace, enabling the robot to autonomously reach a target position and orientation defined by the user, is given. Implementation of the ‘Go to Pose’ algorithm is done for both single-waypoint and multi-waypoint navigation. The experimental results obtained reinforce the robustness of the algorithm that incorporates PID controller.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123289328","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663667
Vinay Itagi, Mayur Javali, H. Madhukeshwar, Pooja Shettar, P. Somashekar, D. Narayan
Software Defined networking (SDN) is an emerging technology for effectively managing the network resources. SDN architecture has two planes namely control and data plane. Control plane manages the network using global view of the network topology and data plane helps routing and forwarding of packets. Centralised nature of controller poses security threats to SDN environment. Distributed Denial of Service (DDoS) attack is the most popular cyber attack which can cause economic loss due to network disruption. Thus, the design of DDoS detection system which can detect the attacks accurately in SDN environment is an important research issue. The purpose of this study is to develop a real-time method for detecting DDoS attacks using a bi-directional recurrent neural network (BRNN). We use deep learning models for the classification of DDoS attacks with real-time SDN data.Results demonstrated that BRNN has greater accuracy than feed forward neural network when we use Mininet emulator to create SDN environment.
{"title":"DDoS Attack Detection in SDN Environment using Bi-directional Recurrent Neural Network","authors":"Vinay Itagi, Mayur Javali, H. Madhukeshwar, Pooja Shettar, P. Somashekar, D. Narayan","doi":"10.1109/DISCOVER52564.2021.9663667","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663667","url":null,"abstract":"Software Defined networking (SDN) is an emerging technology for effectively managing the network resources. SDN architecture has two planes namely control and data plane. Control plane manages the network using global view of the network topology and data plane helps routing and forwarding of packets. Centralised nature of controller poses security threats to SDN environment. Distributed Denial of Service (DDoS) attack is the most popular cyber attack which can cause economic loss due to network disruption. Thus, the design of DDoS detection system which can detect the attacks accurately in SDN environment is an important research issue. The purpose of this study is to develop a real-time method for detecting DDoS attacks using a bi-directional recurrent neural network (BRNN). We use deep learning models for the classification of DDoS attacks with real-time SDN data.Results demonstrated that BRNN has greater accuracy than feed forward neural network when we use Mininet emulator to create SDN environment.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121083963","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663654
U. Nagesh, Manjunath Kotari, S. C. Chethan
Today the amount of importance given to waste management by the Municipal Corporation and public people created an unhygienic environment in the city leading to various deadly diseases. The garbage bins provided by municipality at public places are mismanaged due to poor information system and complete manual operations. Implementation of a clear communication system at either ends of the system will be a solution for a cleaner, hygienic city. In view of this, we propose and design an intelligent Smart Waste Management Using IoT. In this system we have deployed multiple garbage bins which are fitted with sensors modules and low cost embedded communicating devices to assist in tracking the level of waste in garbage container. The bins are identified by a unique identifier across the city so that it is easy to track the status of each container from an interactive web interface and a smart phone application. We integrate these networked smart bins to Google maps through suitable APIs to track them in real time. When the level reaches the preset threshold limit, the transmitter module will send the level along with unique ID of the bin through MQTT messages. This data can then be accessed by the concerned municipal authorities through interactive map and web applications and also immediate decision could be taken to track and reach them. We have also added several features such as bin tracking, nearest bin identification, remote garbage level indication etc.
{"title":"Integration of MQTT Protocol with Map APIs for Smart Garbage Management","authors":"U. Nagesh, Manjunath Kotari, S. C. Chethan","doi":"10.1109/DISCOVER52564.2021.9663654","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663654","url":null,"abstract":"Today the amount of importance given to waste management by the Municipal Corporation and public people created an unhygienic environment in the city leading to various deadly diseases. The garbage bins provided by municipality at public places are mismanaged due to poor information system and complete manual operations. Implementation of a clear communication system at either ends of the system will be a solution for a cleaner, hygienic city. In view of this, we propose and design an intelligent Smart Waste Management Using IoT. In this system we have deployed multiple garbage bins which are fitted with sensors modules and low cost embedded communicating devices to assist in tracking the level of waste in garbage container. The bins are identified by a unique identifier across the city so that it is easy to track the status of each container from an interactive web interface and a smart phone application. We integrate these networked smart bins to Google maps through suitable APIs to track them in real time. When the level reaches the preset threshold limit, the transmitter module will send the level along with unique ID of the bin through MQTT messages. This data can then be accessed by the concerned municipal authorities through interactive map and web applications and also immediate decision could be taken to track and reach them. We have also added several features such as bin tracking, nearest bin identification, remote garbage level indication etc.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"129 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124231484","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 : 2021-11-19DOI: 10.1109/DISCOVER52564.2021.9663665
K. Neelima, Satyam
The computationally intensive designs such as Multiplier Accumulator Unit need to be revisited for ascertaining better performance. Design of MAC unit using Variable Precision multiplier is explored in this paper with adoption of this concept to multipliers like Array, Carry Save, Booth and Vedic Multipliers. The variable precision MAC unit saves the computation memory as the partial results are computed with less memory so that the final result has a size of 2n x m for multiplication of n x m bits. The Verilog HDL modeling is used for the designs and Xilinx ISE 14.5 with ISIM simulator are used to functionally verify for Zynq 7000 series FPGA (XC7Z020-1CLG484). Among these, Vedic VPMAC FIR Filter proved to be better for area and delay by atleast 23.05% and 17.16% respectively, with a trade-off of 2.04% in power dissipation when compared with the other three designs. Also when compared with existing designs, it uses less area, delay and power dissipation by at least 8.06%, 8.58% and 2% respectively.
为了获得更好的性能，需要重新考虑诸如乘法器累加器单元之类的计算密集型设计。本文探讨了可变精度乘法器的MAC单元设计，并将此概念应用于Array、Carry Save、Booth和Vedic乘法器等乘法器。可变精度MAC单元节省了计算内存，因为部分结果使用较少的内存进行计算，因此对于n x m位的乘法，最终结果的大小为2n x m。Verilog HDL建模用于设计，Xilinx ISE 14.5与ISIM模拟器用于Zynq 7000系列FPGA (XC7Z020-1CLG484)的功能验证。其中，Vedic VPMAC FIR滤波器与其他三种设计相比，在面积和延迟方面分别至少提高23.05%和17.16%，功耗降低2.04%。与现有设计相比，其面积、延迟和功耗分别降低至少8.06%、8.58%和2%。
{"title":"High Performance Variable Precision Multiplier and Accumulator Unit for Digital Filter Applications","authors":"K. Neelima, Satyam","doi":"10.1109/DISCOVER52564.2021.9663665","DOIUrl":"https://doi.org/10.1109/DISCOVER52564.2021.9663665","url":null,"abstract":"The computationally intensive designs such as Multiplier Accumulator Unit need to be revisited for ascertaining better performance. Design of MAC unit using Variable Precision multiplier is explored in this paper with adoption of this concept to multipliers like Array, Carry Save, Booth and Vedic Multipliers. The variable precision MAC unit saves the computation memory as the partial results are computed with less memory so that the final result has a size of 2n x m for multiplication of n x m bits. The Verilog HDL modeling is used for the designs and Xilinx ISE 14.5 with ISIM simulator are used to functionally verify for Zynq 7000 series FPGA (XC7Z020-1CLG484). Among these, Vedic VPMAC FIR Filter proved to be better for area and delay by atleast 23.05% and 17.16% respectively, with a trade-off of 2.04% in power dissipation when compared with the other three designs. Also when compared with existing designs, it uses less area, delay and power dissipation by at least 8.06%, 8.58% and 2% respectively.","PeriodicalId":413789,"journal":{"name":"2021 IEEE International Conference on Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114819345","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：