Pub Date : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974489
Satyarth Upadhyaya, Anish Parajuli, S. Shakya
Multi-label classification refers to classifying data into two or more, usually independent, set of output labels. This approach is suitable for deep learning applications in multi-faceted subjects like software development, where it is desirable to yield multiple outcomes. This paper proposes a CNN based deep learning model on public datasets of programming language platforms like GitHub and Stack Overflow to infer intelligence to aid decision making process regarding the choice of programming languages for a given software development requirement. For this research, we’ve developed a training model with pre-trained vector embedding layer and multi-channel one dimensional CNN layers, followed by Multi Layer Perceptron layer to provide multi label outputs. We have managed to achieve 92%, 98% accuracy and 22%, 4% loss with our two experimental setups for Github and Stack Overflow respectively. The model performed well when tested on software development requirements. Stack Overflow dataset was observed to be noticeably better performing than the Github dataset for actual software development use cases. The implications of these models were also found to be good for trend prediction and source code use cases.
{"title":"Predictive use cases of CNN based multi label classification for programming languages","authors":"Satyarth Upadhyaya, Anish Parajuli, S. Shakya","doi":"10.1109/ICCCIS48478.2019.8974489","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974489","url":null,"abstract":"Multi-label classification refers to classifying data into two or more, usually independent, set of output labels. This approach is suitable for deep learning applications in multi-faceted subjects like software development, where it is desirable to yield multiple outcomes. This paper proposes a CNN based deep learning model on public datasets of programming language platforms like GitHub and Stack Overflow to infer intelligence to aid decision making process regarding the choice of programming languages for a given software development requirement. For this research, we’ve developed a training model with pre-trained vector embedding layer and multi-channel one dimensional CNN layers, followed by Multi Layer Perceptron layer to provide multi label outputs. We have managed to achieve 92%, 98% accuracy and 22%, 4% loss with our two experimental setups for Github and Stack Overflow respectively. The model performed well when tested on software development requirements. Stack Overflow dataset was observed to be noticeably better performing than the Github dataset for actual software development use cases. The implications of these models were also found to be good for trend prediction and source code use cases.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114636632","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974476
Suresh Wati, N. Rakesh, Parmanand Astya
The Underwater medium is extremely demanding and uncalculable caused by number of issues, for example limited bandwidth, node mobility, battery power limited, more severe noise, and interference, shadow zones, movements of the sensor nodes with high water currents, high error rate, Attenuation, Absorption, Corrosion and fouling and long and varying propagation delay. In this paper taken many protocols which is solve node mobility issues and also define which one is more efficient compare to others one. Node mobility is a major problem that created cause of mobile nature of nodes. Due to environmental conditions the source and the destination nodes displaces from their original positions during communication, A communication failure is occure in this situation.
{"title":"Data communication Issues in Underwater Sensor Network","authors":"Suresh Wati, N. Rakesh, Parmanand Astya","doi":"10.1109/ICCCIS48478.2019.8974476","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974476","url":null,"abstract":"The Underwater medium is extremely demanding and uncalculable caused by number of issues, for example limited bandwidth, node mobility, battery power limited, more severe noise, and interference, shadow zones, movements of the sensor nodes with high water currents, high error rate, Attenuation, Absorption, Corrosion and fouling and long and varying propagation delay. In this paper taken many protocols which is solve node mobility issues and also define which one is more efficient compare to others one. Node mobility is a major problem that created cause of mobile nature of nodes. Due to environmental conditions the source and the destination nodes displaces from their original positions during communication, A communication failure is occure in this situation.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122026367","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974548
Shivangi Satija, Tejsi Sharma, B. Bhushan
Traditional Networks are dominated by hardware constraints and have inflexible architectural design, thus restricting research and innovation. SDN is an innovation in networking which provides administrators to centrally manage and conFigure entire network. SDN simplifies and improves network management. Intelligent SDN controllers conFigure network elements and cooperate with applications to enhance the network. Primary objective of SD-WSN is that existing WSN can profit by making use of SDN. WSN’s deployment can be developed to improve transmission performance. In this survey, the basics of SDN, WSN, SD-WSN are explained. Also developments in WSN through SDN and its challenges have been discussed. Besides, the paper also summarizes the architecture of SDN and WSN. Future research and related challenges have been discussed towards the end.
{"title":"Innovative approach to Wireless Sensor Networks: SD-WSN","authors":"Shivangi Satija, Tejsi Sharma, B. Bhushan","doi":"10.1109/ICCCIS48478.2019.8974548","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974548","url":null,"abstract":"Traditional Networks are dominated by hardware constraints and have inflexible architectural design, thus restricting research and innovation. SDN is an innovation in networking which provides administrators to centrally manage and conFigure entire network. SDN simplifies and improves network management. Intelligent SDN controllers conFigure network elements and cooperate with applications to enhance the network. Primary objective of SD-WSN is that existing WSN can profit by making use of SDN. WSN’s deployment can be developed to improve transmission performance. In this survey, the basics of SDN, WSN, SD-WSN are explained. Also developments in WSN through SDN and its challenges have been discussed. Besides, the paper also summarizes the architecture of SDN and WSN. Future research and related challenges have been discussed towards the end.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128029762","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974552
Tejsi Sharma, Shivangi Satija, B. Bhushan
Blockchain is a decentralized and distributed public ledgers which holds sensitive and invariant data in an encrypted and secured manner to ensure no mid-way alterations are possible in a transaction, proving user a secure and trustable facility. While cryptocurrency like Bitcoin are major and most popular faces, Blockchain technology has gained a huge momentum recently. Objective of this paper is to layout a detailed survey on blockchain technology, to explain some important terminologies related to Blockchain, to compare IoT and traditional network on the basis of security, compatibility and capacity and to provide an insight on blockchain based IoT and Industrial IoT. Later, the challenges faced while adopting blockchain in IoT and it’s future scopes are discussed.
{"title":"Unifying Blockchian and IoT:Security Requirements, Challenges, Applications and Future Trends","authors":"Tejsi Sharma, Shivangi Satija, B. Bhushan","doi":"10.1109/ICCCIS48478.2019.8974552","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974552","url":null,"abstract":"Blockchain is a decentralized and distributed public ledgers which holds sensitive and invariant data in an encrypted and secured manner to ensure no mid-way alterations are possible in a transaction, proving user a secure and trustable facility. While cryptocurrency like Bitcoin are major and most popular faces, Blockchain technology has gained a huge momentum recently. Objective of this paper is to layout a detailed survey on blockchain technology, to explain some important terminologies related to Blockchain, to compare IoT and traditional network on the basis of security, compatibility and capacity and to provide an insight on blockchain based IoT and Industrial IoT. Later, the challenges faced while adopting blockchain in IoT and it’s future scopes are discussed.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125072277","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974559
Anjali Chandra, Shrish Verma, A. S. Raghuvanshi, N. Bodhey, N. Londhe, K. Subham
Corpus callosum is the most significant human brain structures. The majority of neurological disorder directly or indirectly reflect on Corpus Callosum morphological characteristics. The mid-sagittal view of the Tl weighted brain MRI completely portray corpus callosum anatomical structure. The segmentation of corpus callosum from brain MRI is very challenging task due to low contrast in surrounding organ and tissues. We propose a novel Corpus Callosum segmentation method using semantic pixel-wise segmentation termed as SegNet, a practical deep convolutional neural network architecture. The applied architecture comprises of two networks namely encoder and decoder with pixel-specific classification layer. The proposed model’s encoder network comprises of series of convolution, batch normalization and max-pool layers. The function of decoder network is to map the feature maps of the low-resolution encoder to the full input resolution featuremaps for the classification of pixels. The segmentation output can be used for better extraction of features and classification of diseases in medical diagnosis.
{"title":"SegNet-based Corpus Callosum segmentation for brain Magnetic Resonance Images (MRI)","authors":"Anjali Chandra, Shrish Verma, A. S. Raghuvanshi, N. Bodhey, N. Londhe, K. Subham","doi":"10.1109/ICCCIS48478.2019.8974559","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974559","url":null,"abstract":"Corpus callosum is the most significant human brain structures. The majority of neurological disorder directly or indirectly reflect on Corpus Callosum morphological characteristics. The mid-sagittal view of the Tl weighted brain MRI completely portray corpus callosum anatomical structure. The segmentation of corpus callosum from brain MRI is very challenging task due to low contrast in surrounding organ and tissues. We propose a novel Corpus Callosum segmentation method using semantic pixel-wise segmentation termed as SegNet, a practical deep convolutional neural network architecture. The applied architecture comprises of two networks namely encoder and decoder with pixel-specific classification layer. The proposed model’s encoder network comprises of series of convolution, batch normalization and max-pool layers. The function of decoder network is to map the feature maps of the low-resolution encoder to the full input resolution featuremaps for the classification of pixels. The segmentation output can be used for better extraction of features and classification of diseases in medical diagnosis.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114449710","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974530
Pulkit Singh, B. Acharya, R. Chaurasiya
Lightweight cryptography is an exciting field which hits the perfect balance between safety, higher performance, low power consumption, and compactness. Many compact algorithms such as PRESENT, HIGHT, LILLIPUT, KLEIN, KATAN, SFN, and PICCOLO have made the mark in recent years that can be used as lightweight cryptosystems. The reprogrammable devices are highly attractive solutions for encryption algorithm in hardware implementation. A strong focus is placed on high-throughput implementations, which are required to support security for logistics and tracking applications. In this paper, two pipelined architectures are designed for achieving high throughput. Among them, sub-pipelined implementation achieves a high throughput of 684.06 Mbps and 654.20 Mbps on xc5vlx50t-3ff1136 and xc4vlx25-12ff668 devices, respectively. All results are simulated and verified for different devices of Xilinx in Spartan & Virtex families.
{"title":"Pipelined Architectures of LILLIPUT Block Cipher for RFID Logistic Applications","authors":"Pulkit Singh, B. Acharya, R. Chaurasiya","doi":"10.1109/ICCCIS48478.2019.8974530","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974530","url":null,"abstract":"Lightweight cryptography is an exciting field which hits the perfect balance between safety, higher performance, low power consumption, and compactness. Many compact algorithms such as PRESENT, HIGHT, LILLIPUT, KLEIN, KATAN, SFN, and PICCOLO have made the mark in recent years that can be used as lightweight cryptosystems. The reprogrammable devices are highly attractive solutions for encryption algorithm in hardware implementation. A strong focus is placed on high-throughput implementations, which are required to support security for logistics and tracking applications. In this paper, two pipelined architectures are designed for achieving high throughput. Among them, sub-pipelined implementation achieves a high throughput of 684.06 Mbps and 654.20 Mbps on xc5vlx50t-3ff1136 and xc4vlx25-12ff668 devices, respectively. All results are simulated and verified for different devices of Xilinx in Spartan & Virtex families.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"41 6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131922875","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974547
Sahil Lamba, Suyash Gupta, Nipun Soni
Recognition of handwriting is an active and difficult study area. The identification mechanism for handwriting plays a very significant part in the globe of today. Recognition of handwriting is a very common and costly job. Currently, finding the right significance of handwritten papers is very hard. There are many places where words, alphabets and digits need to be recognized. There are many postal addresses for applications, bank checks where we have to recognise handwriting. This review article will concentrate on various techniques that are used to recognize handwriting. There are basically two distinct kinds of internet and offline handwriting recognition scheme for handwriting. There are many methods for the identification scheme of offline handwriting. This review document will depict the constraints and superiorities of various techniques used for the identification scheme for handwriting. Recognition of handwriting has been researched over many years. Handwriting identification system can be used to fix many complicated issues and facilitate the job of beings. So this article is an overview with its limitations and precision rate of distinct approaches to handwriting recognition system.
{"title":"Handwriting Recognition System- A Review","authors":"Sahil Lamba, Suyash Gupta, Nipun Soni","doi":"10.1109/ICCCIS48478.2019.8974547","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974547","url":null,"abstract":"Recognition of handwriting is an active and difficult study area. The identification mechanism for handwriting plays a very significant part in the globe of today. Recognition of handwriting is a very common and costly job. Currently, finding the right significance of handwritten papers is very hard. There are many places where words, alphabets and digits need to be recognized. There are many postal addresses for applications, bank checks where we have to recognise handwriting. This review article will concentrate on various techniques that are used to recognize handwriting. There are basically two distinct kinds of internet and offline handwriting recognition scheme for handwriting. There are many methods for the identification scheme of offline handwriting. This review document will depict the constraints and superiorities of various techniques used for the identification scheme for handwriting. Recognition of handwriting has been researched over many years. Handwriting identification system can be used to fix many complicated issues and facilitate the job of beings. So this article is an overview with its limitations and precision rate of distinct approaches to handwriting recognition system.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116743363","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974525
M. Nigus, R. Priyadarshini, Rakesh Mehra
The memristive device is a nanoscale nonlinear passive two-terminal fourth fundamental circuit element in addition to the three previously known passive fundamental circuit elements namely resistor, capacitor, and inductor. However aside from its non-volatile memory nature, this memristor resistance/ memristance controlled in the circuit operation by the amount of charge applied between its terminals. The memristor device SPICE modeling is significant for memristive circuit and neuromorphic system design. Nowadays probabilistic switching behavior observed in many fabricated memristor devices that inspired stochastic learning rule for memristor-based neuromorphic learning system application. In this paper, a stochastic metastable switch memristor model (MSSs) is used for binary-weighted memristor-based artificial synapse circuitry presentation. Using this MSSs memristor SPICE model a binary-weighted memristor-based artificial synapse circuit presented. The presented circuit shows a binary response to the signal given to the memristor implemented in the binary synaptic circuit using a stochastic memristor device model. The authors left the implementation of the proposed binary synaptic circuit in a memristor-based artificial neural network that functions through the clipped perceptron (CP) learning algorithm as future work.
{"title":"Binary-Weighted Synaptic Circuit for Neuromorphic Learning System Using Stochastic Memristor SPICE Model","authors":"M. Nigus, R. Priyadarshini, Rakesh Mehra","doi":"10.1109/ICCCIS48478.2019.8974525","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974525","url":null,"abstract":"The memristive device is a nanoscale nonlinear passive two-terminal fourth fundamental circuit element in addition to the three previously known passive fundamental circuit elements namely resistor, capacitor, and inductor. However aside from its non-volatile memory nature, this memristor resistance/ memristance controlled in the circuit operation by the amount of charge applied between its terminals. The memristor device SPICE modeling is significant for memristive circuit and neuromorphic system design. Nowadays probabilistic switching behavior observed in many fabricated memristor devices that inspired stochastic learning rule for memristor-based neuromorphic learning system application. In this paper, a stochastic metastable switch memristor model (MSSs) is used for binary-weighted memristor-based artificial synapse circuitry presentation. Using this MSSs memristor SPICE model a binary-weighted memristor-based artificial synapse circuit presented. The presented circuit shows a binary response to the signal given to the memristor implemented in the binary synaptic circuit using a stochastic memristor device model. The authors left the implementation of the proposed binary synaptic circuit in a memristor-based artificial neural network that functions through the clipped perceptron (CP) learning algorithm as future work.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124692313","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 : 2019-10-01DOI: 10.1109/ICCCIS48478.2019.8974458
Abel KahsayGebreslassie, YaecobGirmayGezahegn, Misgina Tsighe Hagos, AchimIbenthal, Pooja
The human Gastrointestinal (GI) tract can be affected by different diseases and endoscopy has been seen to perform well for diagnosing GI tract problems. Accurate identification of underlying problems in GI tract endoscopic images is important as it affects decision-making on treatment and follow-up. In developing countries trained endoscopic experts are small in number and expensive. Even though medical recognition is a promising field of application for Artificial Intelligence (AI) publicly available datasets for such tasks are small in number. Kvasir dataset is one of the publicly available medical datasets. It consists of gastrointestinal endoscopic images that belong to eight different classes. We have automated recognition of GI tract landmarks and diseases, for classes that are available in Kvasir, with the use of Convolutional Neural Networks (CNNs). CNNs are widely used for visual recognition due to their ability to capture local features and their computational efficiency compared to fully connected networks. We have fine-tuned a residual model based on ResNet50 and a dense model based on DenseNet121 on Kvasir dataset. The models’ performance on a test set that consists of 75 images from each class is 86.9% for dense model and 87.8% for residual model. We have also built a user interface for users to select images and get recognition results. The interface built can serve as a decision support system for classifying GI tract endoscopic images. It can also further be extended for recognition in videos by feeding the video input as a sequence of images.
{"title":"Automated Gastrointestinal Disease Recognition for Endoscopic Images","authors":"Abel KahsayGebreslassie, YaecobGirmayGezahegn, Misgina Tsighe Hagos, AchimIbenthal, Pooja","doi":"10.1109/ICCCIS48478.2019.8974458","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974458","url":null,"abstract":"The human Gastrointestinal (GI) tract can be affected by different diseases and endoscopy has been seen to perform well for diagnosing GI tract problems. Accurate identification of underlying problems in GI tract endoscopic images is important as it affects decision-making on treatment and follow-up. In developing countries trained endoscopic experts are small in number and expensive. Even though medical recognition is a promising field of application for Artificial Intelligence (AI) publicly available datasets for such tasks are small in number. Kvasir dataset is one of the publicly available medical datasets. It consists of gastrointestinal endoscopic images that belong to eight different classes. We have automated recognition of GI tract landmarks and diseases, for classes that are available in Kvasir, with the use of Convolutional Neural Networks (CNNs). CNNs are widely used for visual recognition due to their ability to capture local features and their computational efficiency compared to fully connected networks. We have fine-tuned a residual model based on ResNet50 and a dense model based on DenseNet121 on Kvasir dataset. The models’ performance on a test set that consists of 75 images from each class is 86.9% for dense model and 87.8% for residual model. We have also built a user interface for users to select images and get recognition results. The interface built can serve as a decision support system for classifying GI tract endoscopic images. It can also further be extended for recognition in videos by feeding the video input as a sequence of images.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125623370","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}
Researchers and scientists have contributed a lot for handicapped or physically disabled people to adopt techniques that may help to smooth their mobility in daily life reducing their painful effort, instead of being dependent on others specially while using traditional tools like wheelchair. Many people continuously need help of someone while moving somewhere with the wheelchair. By having an automated control system incorporated with the wheelchair, they would become more independent. The main goal of this project is to fabricate an android controlled wheelchair using Arduino, which can be navigated easily by disabled people with own effort. The inputs will have to be provided through android application which has navigation control and other features, also this application is integrated with home automation system for controlling home appliances. This wheelchair is able to detect any obstacle or crack on the path towards the direction of motion and alerts the user with the help of sonar sensor and IR sensor. The enriched results of this project fabricated a path for further advancement of this technology and finally being manufactured.
{"title":"An Implementation of Motorized Wheelchair for Handicapped Persons","authors":"Md. Raseduzzaman Ruman, A. Barua, Shubho Mohajan, Debashis Paul, Apurbo Kumar Sarker, Md. Raihan Rabby","doi":"10.1109/ICCCIS48478.2019.8974484","DOIUrl":"https://doi.org/10.1109/ICCCIS48478.2019.8974484","url":null,"abstract":"Researchers and scientists have contributed a lot for handicapped or physically disabled people to adopt techniques that may help to smooth their mobility in daily life reducing their painful effort, instead of being dependent on others specially while using traditional tools like wheelchair. Many people continuously need help of someone while moving somewhere with the wheelchair. By having an automated control system incorporated with the wheelchair, they would become more independent. The main goal of this project is to fabricate an android controlled wheelchair using Arduino, which can be navigated easily by disabled people with own effort. The inputs will have to be provided through android application which has navigation control and other features, also this application is integrated with home automation system for controlling home appliances. This wheelchair is able to detect any obstacle or crack on the path towards the direction of motion and alerts the user with the help of sonar sensor and IR sensor. The enriched results of this project fabricated a path for further advancement of this technology and finally being manufactured.","PeriodicalId":436154,"journal":{"name":"2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS)","volume":"110 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117294050","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：