Pub Date : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284921
Tareq Tayeh, Sulaiman A. Aburakhia, Ryan Myers, A. Shami
Surface anomaly detection plays an important quality control role in many manufacturing industries to reduce scrap production. Machine-based visual inspections have been utilized in recent years to conduct this task instead of human experts. In particular, deep learning Convolutional Neural Networks (CNNs) have been at the forefront of these image processing-based solutions due to their predictive accuracy and efficiency. Training a CNN on a classification objective requires a sufficiently large amount of defective data, which is often not available. In this paper, we address that challenge by training the CNN on surface texture patches with a distance-based anomaly detection objective instead. A deep residual-based triplet network model is utilized, and defective training samples are synthesized exclusively from non-defective samples via random erasing techniques to directly learn a similarity metric between the same-class samples and out-of-class samples. Evaluation results demonstrate the approach's strength in detecting different types of anomalies, such as bent, broken, or cracked surfaces, for known surfaces that are part of the training data and unseen novel surfaces.
{"title":"Distance-Based Anomaly Detection for Industrial Surfaces Using Triplet Networks","authors":"Tareq Tayeh, Sulaiman A. Aburakhia, Ryan Myers, A. Shami","doi":"10.1109/IEMCON51383.2020.9284921","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284921","url":null,"abstract":"Surface anomaly detection plays an important quality control role in many manufacturing industries to reduce scrap production. Machine-based visual inspections have been utilized in recent years to conduct this task instead of human experts. In particular, deep learning Convolutional Neural Networks (CNNs) have been at the forefront of these image processing-based solutions due to their predictive accuracy and efficiency. Training a CNN on a classification objective requires a sufficiently large amount of defective data, which is often not available. In this paper, we address that challenge by training the CNN on surface texture patches with a distance-based anomaly detection objective instead. A deep residual-based triplet network model is utilized, and defective training samples are synthesized exclusively from non-defective samples via random erasing techniques to directly learn a similarity metric between the same-class samples and out-of-class samples. Evaluation results demonstrate the approach's strength in detecting different types of anomalies, such as bent, broken, or cracked surfaces, for known surfaces that are part of the training data and unseen novel surfaces.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"40 1","pages":"0372-0377"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73046930","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284888
Douglas de Farias Medeiros, M. Villarim, F. D. De Carvalho, C. P. de Souza
In a world getting more and more connections, the growth in the number of devices sharing information with each other is evident. Therefore, as the number of connected devices and their applications grows, the amount of data shared by these devices also increases considerably. Thus, in order to be able to send data from one device to another and that data passing through intermediate devices, it is necessary to define from which path the data should be sent, characterizing the routing concept. In this context, this work aims to implement and analyze routing protocols for ad hoc wireless network called DVR (Distance Vector Routing), AODV (Ad Hoc On-Demand Distance Vector) and DSR (Dynamic Source Routing) using the Cupcarbon network simulator. LoRa wireless communication technology and a network topology distributed along avenues in the city of João Pessoa, Brazil, were considered and simulated. The quantitative analysis criteria were the packet delivery rate, the average end-to-end delay and throughput. The energy consumption profiles of each network node were also obtained according to each protocol. The results showed that the DSR protocol had lower energy consumption and AODV obtained better general performance, but with higher consumption. The DVR protocol showed better results in terms of latency.
在一个连接越来越多的世界里，相互共享信息的设备数量的增长是显而易见的。因此，随着连接的设备及其应用程序数量的增加，这些设备共享的数据量也会大幅增加。因此，为了能够将数据从一个设备发送到另一个设备，并且数据通过中间设备，有必要定义应该从哪个路径发送数据，这是路由概念的特征。在这种情况下，本工作旨在使用Cupcarbon网络模拟器实现和分析称为DVR(距离矢量路由)，AODV (ad hoc按需距离矢量)和DSR(动态源路由)的自组织无线网络的路由协议。考虑并模拟了LoRa无线通信技术和沿巴西jo o Pessoa市道路分布的网络拓扑结构。定量分析的标准是数据包传输速率、端到端平均延迟和吞吐量。并根据各协议得到各网络节点的能耗曲线。结果表明，DSR协议能耗较低，AODV协议总体性能较好，但能耗较高。DVR协议在延迟方面表现出更好的结果。
{"title":"Implementation and Analysis of Routing Protocols for LoRa Wireless Mesh Networks","authors":"Douglas de Farias Medeiros, M. Villarim, F. D. De Carvalho, C. P. de Souza","doi":"10.1109/IEMCON51383.2020.9284888","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284888","url":null,"abstract":"In a world getting more and more connections, the growth in the number of devices sharing information with each other is evident. Therefore, as the number of connected devices and their applications grows, the amount of data shared by these devices also increases considerably. Thus, in order to be able to send data from one device to another and that data passing through intermediate devices, it is necessary to define from which path the data should be sent, characterizing the routing concept. In this context, this work aims to implement and analyze routing protocols for ad hoc wireless network called DVR (Distance Vector Routing), AODV (Ad Hoc On-Demand Distance Vector) and DSR (Dynamic Source Routing) using the Cupcarbon network simulator. LoRa wireless communication technology and a network topology distributed along avenues in the city of João Pessoa, Brazil, were considered and simulated. The quantitative analysis criteria were the packet delivery rate, the average end-to-end delay and throughput. The energy consumption profiles of each network node were also obtained according to each protocol. The results showed that the DSR protocol had lower energy consumption and AODV obtained better general performance, but with higher consumption. The DVR protocol showed better results in terms of latency.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"63 1","pages":"0020-0025"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73577401","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284930
Ramin Sahba, Amin Sahba, F. Sahba
One of the topics that is highly regarded and researched in the field of artificial intelligence and machine learning is object detection. Its use is especially important in autonomous vehicles. The various methods used to detect objects are based on different types of data, including image, radar, and lidar. Using a point clouds is one of the new methods for 3D object detection proposed in some recent work. One of the recently presented efficient methods is PointPillars network. It is an encoder that can learn from data available in a point cloud and then organize it as a representation in vertical columns (pillars). This representation can be used for 3D object detection. in this work, we try to develop a high performance model for 3D object detection based on PointPillars network exploiting a combination of lidar, radar, and image data to be used for autonomous vehicles perception. We use lidar, radar, and image data in nuScenes dataset to predict 3D boxes for three classes of objects that are car, pedestrian, and bus. To measure and compare results, we use nuScenes detection score (NDS) that is a combined metric for detection task. Results show that increasing the number of lidar sweeps, and combining them with radar and image data, significantly improve the performance of the 3D object detector. We suggest a method to combine different types of input data (lidar, radar, image) using a weighting system that can be used as the input for the encoder.
{"title":"Using a Combination of LiDAR, RADAR, and Image Data for 3D Object Detection in Autonomous Vehicles","authors":"Ramin Sahba, Amin Sahba, F. Sahba","doi":"10.1109/IEMCON51383.2020.9284930","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284930","url":null,"abstract":"One of the topics that is highly regarded and researched in the field of artificial intelligence and machine learning is object detection. Its use is especially important in autonomous vehicles. The various methods used to detect objects are based on different types of data, including image, radar, and lidar. Using a point clouds is one of the new methods for 3D object detection proposed in some recent work. One of the recently presented efficient methods is PointPillars network. It is an encoder that can learn from data available in a point cloud and then organize it as a representation in vertical columns (pillars). This representation can be used for 3D object detection. in this work, we try to develop a high performance model for 3D object detection based on PointPillars network exploiting a combination of lidar, radar, and image data to be used for autonomous vehicles perception. We use lidar, radar, and image data in nuScenes dataset to predict 3D boxes for three classes of objects that are car, pedestrian, and bus. To measure and compare results, we use nuScenes detection score (NDS) that is a combined metric for detection task. Results show that increasing the number of lidar sweeps, and combining them with radar and image data, significantly improve the performance of the 3D object detector. We suggest a method to combine different types of input data (lidar, radar, image) using a weighting system that can be used as the input for the encoder.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"6 1","pages":"0427-0431"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74337952","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284867
Asif ur Rehman, M. Iqbal
This paper presents an off-grid photovoltaic (PV) system for a house in the rural community of Pakistan. The designed system is capable of satisfying all the electrical needs of the house throughout the year. This off-grid solar PV system is expected to provide 40 kWh per month as per data collected from the electric bill of the house. Steady-state modeling of the system is carried out in Homer software. The results of the homer simulation show the annual expected electrical output of this system by using the solar irradiance, temperature, and humidity data of the selected location. The designed system uses four solar panels of 140 watts each making a total of 560 watts solar panels, four batteries of 125 Ah each, and an inverter of 1 kW to meet the electrical requirements of the selected house. This paper also presents a simple method of control and data-logging of the designed system.
{"title":"Design and Control of an Off-Grid Solar System for a Rural House in Pakistan","authors":"Asif ur Rehman, M. Iqbal","doi":"10.1109/IEMCON51383.2020.9284867","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284867","url":null,"abstract":"This paper presents an off-grid photovoltaic (PV) system for a house in the rural community of Pakistan. The designed system is capable of satisfying all the electrical needs of the house throughout the year. This off-grid solar PV system is expected to provide 40 kWh per month as per data collected from the electric bill of the house. Steady-state modeling of the system is carried out in Homer software. The results of the homer simulation show the annual expected electrical output of this system by using the solar irradiance, temperature, and humidity data of the selected location. The designed system uses four solar panels of 140 watts each making a total of 560 watts solar panels, four batteries of 125 Ah each, and an inverter of 1 kW to meet the electrical requirements of the selected house. This paper also presents a simple method of control and data-logging of the designed system.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"194 1","pages":"0786-0790"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79750196","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284855
Matěj Bartík
This paper presents an in-sight about one of the most widely used power optimization technique: a power gating. The power gating technique has been used for use cases, where part of a system is required to be (temporally) disconnected from a power source to reduce the overall system's power consumption. However, we discovered an issue which makes a discrete variant (external MOSFET transistors in power supply paths of an integrated circuit) of the power gating technique unsuitable for low power designs such as battery-operated IoT (Internet of Things) nodes.
{"title":"External Power Gating Technique – An Inappropriate Solution for Low Power Devices","authors":"Matěj Bartík","doi":"10.1109/IEMCON51383.2020.9284855","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284855","url":null,"abstract":"This paper presents an in-sight about one of the most widely used power optimization technique: a power gating. The power gating technique has been used for use cases, where part of a system is required to be (temporally) disconnected from a power source to reduce the overall system's power consumption. However, we discovered an issue which makes a discrete variant (external MOSFET transistors in power supply paths of an integrated circuit) of the power gating technique unsuitable for low power designs such as battery-operated IoT (Internet of Things) nodes.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"28 1","pages":"0241-0245"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79809046","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284924
Devaj Parikh, K. George
The use of quadcopters is increasing in more and more fields in daily lives and is not limited to military applications from where they originated. They are moving towards entertainment, real-estate, delivery, and so on. The unconventional man-machine interface is a generous topic to explore now and in the future. One among them is Brain-Computer Interface (BCI) which has proven to be a very powerful tool to establish communication without any motor movements of the limbs. BCI based on motor imagery (MI) requires very long training sessions to be used effectively. On the other hand, BCI based on steady-state visual evoked potential (SSVEP) has a limited number of sessions because electroencephalography (EEG) signal detection time (signal window length) and accuracy get the highest priority as performance parameters. This paper presents mathematical modeling and numerical simulation of a quadcopter and BCI. An application is presented with the help of a DJI Flight Simulator and an Emotiv Epoc+ headset.
{"title":"Quadcopter Control in Three-Dimensional Space Using SSVEP and Motor Imagery-Based Brain-Computer Interface","authors":"Devaj Parikh, K. George","doi":"10.1109/IEMCON51383.2020.9284924","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284924","url":null,"abstract":"The use of quadcopters is increasing in more and more fields in daily lives and is not limited to military applications from where they originated. They are moving towards entertainment, real-estate, delivery, and so on. The unconventional man-machine interface is a generous topic to explore now and in the future. One among them is Brain-Computer Interface (BCI) which has proven to be a very powerful tool to establish communication without any motor movements of the limbs. BCI based on motor imagery (MI) requires very long training sessions to be used effectively. On the other hand, BCI based on steady-state visual evoked potential (SSVEP) has a limited number of sessions because electroencephalography (EEG) signal detection time (signal window length) and accuracy get the highest priority as performance parameters. This paper presents mathematical modeling and numerical simulation of a quadcopter and BCI. An application is presented with the help of a DJI Flight Simulator and an Emotiv Epoc+ headset.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"20 1","pages":"0782-0785"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76843646","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284851
Ala Abu Hilal, Thabet M. Mismar
This paper aims to build a positioning system that allows a Drone to locate a sound source effectively. The system consists of an application that communicates remotely with three sensors to compute the location of an object. The collected data from the sensors will be used to find the intersection point where the sound originates. All system components are built to work wirelessly to avoid any wiring problems by populating the data from the sensors, then instructing the Drone to move and capture a picture. This work is convenient in many sites, like tracking an object motion to do some tasks or following its operator by detecting the voice. The experiments showed consistent actions, when the sensors identify the sound signal, the process of computing, transmitting, and Drone moving was very successful. In all trials, the Drone detected the sound and was moving toward the source directly. Then, a picture was captured approximately one meter away far from the object, which is an appropriate distance.
{"title":"Drone Positioning System Based on Sound Signals Detection for Tracking and Photography","authors":"Ala Abu Hilal, Thabet M. Mismar","doi":"10.1109/IEMCON51383.2020.9284851","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284851","url":null,"abstract":"This paper aims to build a positioning system that allows a Drone to locate a sound source effectively. The system consists of an application that communicates remotely with three sensors to compute the location of an object. The collected data from the sensors will be used to find the intersection point where the sound originates. All system components are built to work wirelessly to avoid any wiring problems by populating the data from the sensors, then instructing the Drone to move and capture a picture. This work is convenient in many sites, like tracking an object motion to do some tasks or following its operator by detecting the voice. The experiments showed consistent actions, when the sensors identify the sound signal, the process of computing, transmitting, and Drone moving was very successful. In all trials, the Drone detected the sound and was moving toward the source directly. Then, a picture was captured approximately one meter away far from the object, which is an appropriate distance.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"51 1","pages":"0008-0011"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80343405","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284907
B. Comar
This paper discusses the design and performance of a forward error correction (FEC) code classification system that is used to determine the size of an unknown codeword from a stream of bits. The classification system is a deep neural network that is trained and tested on half rate low density parity check (LDPC) codes. Tests were performed on streams of codewords using codes of up to 250 different sizes. The CNN based classifier performs very well.
{"title":"LDPC Codeword Size Determination Using Convolutional Neural Networks","authors":"B. Comar","doi":"10.1109/IEMCON51383.2020.9284907","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284907","url":null,"abstract":"This paper discusses the design and performance of a forward error correction (FEC) code classification system that is used to determine the size of an unknown codeword from a stream of bits. The classification system is a deep neural network that is trained and tested on half rate low density parity check (LDPC) codes. Tests were performed on streams of codewords using codes of up to 250 different sizes. The CNN based classifier performs very well.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"25 1","pages":"0351-0356"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82592331","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284922
Cassandra Frances Laffan, James Elliott Coleshill, Brodie Stanfield, Michael Stanfield, A. Ferworn
The field of search and rescue (SAR) has not yet fully benefited from strides in haptic technologies. In this research, we seek to rectify this issue by proposing a novel application of IFTech's “As Real As It Gets” (ARAIG) wearable haptic suit for firefighters. First, we examine recent research in this field in order to lay down the groundwork for our project. Next, we present a wearable haptic system in which the ARAIG suit is outfitted with peripheral sensors in order to track the emergency responder's path; the system will then recreate the path and relay exit directions via haptic feedback to the wearer. Thus, the first responder does not have to dedicate more attention than necessary to remembering their entry path. Finally, the future of this project is outlined, which includes a physical implementation of this proposed system.
{"title":"Using the ARAIG Haptic Suit to Assist in Navigating Firefighters Out of Hazardous Environments","authors":"Cassandra Frances Laffan, James Elliott Coleshill, Brodie Stanfield, Michael Stanfield, A. Ferworn","doi":"10.1109/IEMCON51383.2020.9284922","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284922","url":null,"abstract":"The field of search and rescue (SAR) has not yet fully benefited from strides in haptic technologies. In this research, we seek to rectify this issue by proposing a novel application of IFTech's “As Real As It Gets” (ARAIG) wearable haptic suit for firefighters. First, we examine recent research in this field in order to lay down the groundwork for our project. Next, we present a wearable haptic system in which the ARAIG suit is outfitted with peripheral sensors in order to track the emergency responder's path; the system will then recreate the path and relay exit directions via haptic feedback to the wearer. Thus, the first responder does not have to dedicate more attention than necessary to remembering their entry path. Finally, the future of this project is outlined, which includes a physical implementation of this proposed system.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"29 1","pages":"0439-0444"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81384662","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 : 2020-11-04DOI: 10.1109/IEMCON51383.2020.9284946
Parth Parikh, Mrunank Mistry, Dhruvam Kothari, S. Khachane
A Bloom filter is a space-efficient probabilistic data structure that allows for set membership queries with some degree of false positives. In this paper, we propose a technique to add search functionality using a variant of Bloom filters - Spectral Bloom filters. Apart from being space-efficient, our proposed solution produces results comparable to search techniques such as Inverted Index and is a strong candidate for client-side searching.
{"title":"Spectral Bloom Filters for Client Side Search","authors":"Parth Parikh, Mrunank Mistry, Dhruvam Kothari, S. Khachane","doi":"10.1109/IEMCON51383.2020.9284946","DOIUrl":"https://doi.org/10.1109/IEMCON51383.2020.9284946","url":null,"abstract":"A Bloom filter is a space-efficient probabilistic data structure that allows for set membership queries with some degree of false positives. In this paper, we propose a technique to add search functionality using a variant of Bloom filters - Spectral Bloom filters. Apart from being space-efficient, our proposed solution produces results comparable to search techniques such as Inverted Index and is a strong candidate for client-side searching.","PeriodicalId":6871,"journal":{"name":"2020 11th IEEE Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON)","volume":"31 1","pages":"0867-0875"},"PeriodicalIF":0.0,"publicationDate":"2020-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81690455","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：