Pub Date : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528156
Chinmayee Dora, P. Biswal, Figlu Mohanty
Electroencephalogram (EEG) used to read the electrical signals from human scalp for diagnostic purposes. The EEG electrodes sensitive, so the low amplitude EEG signals get corrupted by the wide spectrum and high amplitude electromyogram (EMG) signals. Hence, the recorded EEG have segments that have artifacts with the unacceptable state. Effectively recovering the corrupted signal from a single channel EEG is a challenge. The proposed algorithm enhances the single-channel EEG signal in the presence of EMG artifacts using extreme learning machine (ELM) regressor. For training and testing of the ELM network, EEG signals are subjected to S-transform and the obtained transformation matrix is used as the feature set. S-Transform has the advantage of uniquely combining the gradual resolution and complete referenced phase information for the subjected time series. The ELM is trained using both magnitude and phase of corrupted and clean EEG signals in pairs. This training can reduce the EMG artifact from corrupted EEG signals effectively and enhance the same in the testing stage. The evaluation parameters used for the proposed algorithm are the average root mean square error (RMSE) and the correlation coefficient (CC) between the ground truth EEG signal to the estimated EEG signal. The average RMSE and CC were found to be 0.260 and 0.97 respectively for the simulated dataset.
{"title":"Single-Channel EEG Signal Enhancement in Presence of EMG artifact using ELM-based Regressor","authors":"Chinmayee Dora, P. Biswal, Figlu Mohanty","doi":"10.1109/ICSCC51209.2021.9528156","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528156","url":null,"abstract":"Electroencephalogram (EEG) used to read the electrical signals from human scalp for diagnostic purposes. The EEG electrodes sensitive, so the low amplitude EEG signals get corrupted by the wide spectrum and high amplitude electromyogram (EMG) signals. Hence, the recorded EEG have segments that have artifacts with the unacceptable state. Effectively recovering the corrupted signal from a single channel EEG is a challenge. The proposed algorithm enhances the single-channel EEG signal in the presence of EMG artifacts using extreme learning machine (ELM) regressor. For training and testing of the ELM network, EEG signals are subjected to S-transform and the obtained transformation matrix is used as the feature set. S-Transform has the advantage of uniquely combining the gradual resolution and complete referenced phase information for the subjected time series. The ELM is trained using both magnitude and phase of corrupted and clean EEG signals in pairs. This training can reduce the EMG artifact from corrupted EEG signals effectively and enhance the same in the testing stage. The evaluation parameters used for the proposed algorithm are the average root mean square error (RMSE) and the correlation coefficient (CC) between the ground truth EEG signal to the estimated EEG signal. The average RMSE and CC were found to be 0.260 and 0.97 respectively for the simulated dataset.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127246398","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528162
V. Nagarajan, Pavan Singh
This paper proposes a robust approach for obstacle detection and avoidance algorithm using a single camera. Monocular Vision using single camera architecture cannot identify depth with a single image and thus depends on pixel gradient or keypoint extractors to identify traversable path and obstacles. Pixel gradient does not work well where there are shadows and sharp illumination changes and keypoint extractor does not work well in the absence of dense texture. In this paper we propose an algorithm that is able to use edges as keypoints along with pixel gradient. The entire algorithm was successfully tested on Sphero RVR Rover platform that uses Raspberry Pi and a color camera with IR. The proposed method performs well in obstacle detection and obstacle avoidance and is potentially an alternative to a binocular solution.
{"title":"Obstacle Detection and Avoidance For Mobile Robots Using Monocular Vision","authors":"V. Nagarajan, Pavan Singh","doi":"10.1109/ICSCC51209.2021.9528162","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528162","url":null,"abstract":"This paper proposes a robust approach for obstacle detection and avoidance algorithm using a single camera. Monocular Vision using single camera architecture cannot identify depth with a single image and thus depends on pixel gradient or keypoint extractors to identify traversable path and obstacles. Pixel gradient does not work well where there are shadows and sharp illumination changes and keypoint extractor does not work well in the absence of dense texture. In this paper we propose an algorithm that is able to use edges as keypoints along with pixel gradient. The entire algorithm was successfully tested on Sphero RVR Rover platform that uses Raspberry Pi and a color camera with IR. The proposed method performs well in obstacle detection and obstacle avoidance and is potentially an alternative to a binocular solution.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131398004","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528104
V. Joshi, Ebin Deni Raj
The human mind is an amazing piece of creation that can handle multiple modalities of input seamlessly and help to make sense about the surroundings. When it comes to making sense about speech, 2 main features of input are sound and vision (although there are many other components). Since not every mind is alike, some of them have trouble processing the sound aspect of input therefore vision becomes their primary source to process and understand speech. Lip reading is a skill that is used mainly by people suffering from hearing deformities and it involves large amount of language specific knowledge as well as contextual awareness i.e. using all possible visual clues that help to make sense of what the other person is saying and thus allow them to take part in the conversation. Recent breakthroughs in the field of Deep learning have clearly shown promise with models that have the ability to extract complex, intricate and generalizable patterns both in spatial as well as temporal dimension. In this paper we present FYEO (For Your Eyes Only) an end-to-end deep learning based solution that only uses vision as its single modality of input and generates a single word, character by character. The model is a modified version of the LipNet architecture from Deep Mind, to a subset of words curated from the Oxford-BBC Lip Reading in the Wild (LRW) dataset. Also, as a part of novel work FYEO is extended by adding attention mechanism for further improvement of the model’s contextual awareness and observe the model’s focus while making a prediction. The standard FYEO model achieves a length normalised test CER (character-error-rate) of 25.024%.
人类的大脑是一个神奇的创造物，它可以无缝地处理多种形式的输入，并帮助理解周围的环境。说到理解语音，输入的两个主要特征是声音和视觉(尽管还有许多其他组成部分)。由于并非每个人的大脑都是一样的，有些人在处理声音输入方面有困难，因此视觉成为他们处理和理解语音的主要来源。唇读是一种主要由听力畸形患者使用的技能，它涉及到大量的语言特定知识以及上下文意识，即使用所有可能的视觉线索来帮助理解他人所说的话，从而使他们能够参与到对话中来。深度学习领域最近的突破已经清楚地显示出有能力在空间和时间维度上提取复杂、复杂和可推广的模式的模型的前景。在本文中，我们提出了FYEO (For Your Eyes Only)，这是一种基于端到端深度学习的解决方案，它只使用视觉作为其单一的输入方式，并一个字符一个字符地生成单个单词。该模型是来自Deep Mind的LipNet架构的修改版本，是来自牛津- bbc野生唇读(LRW)数据集的单词子集。此外，作为新颖工作的一部分，FYEO被扩展，加入了注意机制，进一步提高了模型的上下文意识，并在进行预测时观察模型的焦点。标准FYEO模型的长度归一化测试CER(字符错误率)为25.024%。
{"title":"FYEO : A Character Level Model For Lip Reading","authors":"V. Joshi, Ebin Deni Raj","doi":"10.1109/ICSCC51209.2021.9528104","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528104","url":null,"abstract":"The human mind is an amazing piece of creation that can handle multiple modalities of input seamlessly and help to make sense about the surroundings. When it comes to making sense about speech, 2 main features of input are sound and vision (although there are many other components). Since not every mind is alike, some of them have trouble processing the sound aspect of input therefore vision becomes their primary source to process and understand speech. Lip reading is a skill that is used mainly by people suffering from hearing deformities and it involves large amount of language specific knowledge as well as contextual awareness i.e. using all possible visual clues that help to make sense of what the other person is saying and thus allow them to take part in the conversation. Recent breakthroughs in the field of Deep learning have clearly shown promise with models that have the ability to extract complex, intricate and generalizable patterns both in spatial as well as temporal dimension. In this paper we present FYEO (For Your Eyes Only) an end-to-end deep learning based solution that only uses vision as its single modality of input and generates a single word, character by character. The model is a modified version of the LipNet architecture from Deep Mind, to a subset of words curated from the Oxford-BBC Lip Reading in the Wild (LRW) dataset. Also, as a part of novel work FYEO is extended by adding attention mechanism for further improvement of the model’s contextual awareness and observe the model’s focus while making a prediction. The standard FYEO model achieves a length normalised test CER (character-error-rate) of 25.024%.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"62 11","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114045141","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528152
J. K., Sangari A, A. J, Sivamani D, S. D, N. A
Due to rapid developments in high-power semiconductor switches and their control structures, improvement of stability of power system network turns out to be possible with FACTS controllers of different combinations. Unified Power Flow Controller (UPFC) is one of the most commonly used FACTS device. In conventional UPFC, two voltage source inverters(VSI), one is for Static Synchronous Compensator known as STATCOM and another one for Static Synchronous Series Compensator known as SSSC, functioned from a common DC link provided by a DC storage capacitor. To analyze the performance of UPFC in Sliding Mode Control (SMC), it is simulated in MATLAB. It has been observed that the simulation explains P and Q power flow control. SMC is a non-linear control intended to consider the dynamics of the converter for non-linear on-off behavior of the converter. In general, the fuzzy logic encodes human reasoning into a program. Fuzzy Logic Control (FLC) when used as a controlling method for UPFC has better stability, small overshoot and fast response.
{"title":"Implementation of Unified Power Flow Conditioner with SMC and FLC for Power Factor Improvement","authors":"J. K., Sangari A, A. J, Sivamani D, S. D, N. A","doi":"10.1109/ICSCC51209.2021.9528152","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528152","url":null,"abstract":"Due to rapid developments in high-power semiconductor switches and their control structures, improvement of stability of power system network turns out to be possible with FACTS controllers of different combinations. Unified Power Flow Controller (UPFC) is one of the most commonly used FACTS device. In conventional UPFC, two voltage source inverters(VSI), one is for Static Synchronous Compensator known as STATCOM and another one for Static Synchronous Series Compensator known as SSSC, functioned from a common DC link provided by a DC storage capacitor. To analyze the performance of UPFC in Sliding Mode Control (SMC), it is simulated in MATLAB. It has been observed that the simulation explains P and Q power flow control. SMC is a non-linear control intended to consider the dynamics of the converter for non-linear on-off behavior of the converter. In general, the fuzzy logic encodes human reasoning into a program. Fuzzy Logic Control (FLC) when used as a controlling method for UPFC has better stability, small overshoot and fast response.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124082211","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528118
Ayan Bhattacharya, B. Yashwanth, F. V. Jayasudha
In modern days number of cell phone users are increasing at a higher rate. Along with the increasing rate of users also comes the increasing need of more speed for faster browsing, good calling quality and hence invention of cellular technologies like 3G, 4G, 5G, etc. With this evaluation in mobile bands there has been an increase in the number of cellular towers installed to provide flawless network to all the users, but one thing remains unchecked is the energy consumed by these towers. For mobile towers, the consumption of energy is in terms of electricity and which is produced in great amount by either using coal or by burning fossil fuels (Generators that run in Diesels). Based on various network operators, it has been seen that the energy consumed by the radio access networks is the most imminent factor relating to impact on the environment. Also, the current wireless system is not energy efficient mainly the Base Station (BS). In order to restructure the existing network architecture, we need to control each and every system of the base station. We have proposed an innovative and promising method for enhancing the energy efficiency of the wireless networks and have developed solutions on IOT which will surely reduce the operating cost and effects on the environment.
{"title":"Green Radio Technology for Energy Saving in Cellular Towers with Embedded Systems and IOT","authors":"Ayan Bhattacharya, B. Yashwanth, F. V. Jayasudha","doi":"10.1109/ICSCC51209.2021.9528118","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528118","url":null,"abstract":"In modern days number of cell phone users are increasing at a higher rate. Along with the increasing rate of users also comes the increasing need of more speed for faster browsing, good calling quality and hence invention of cellular technologies like 3G, 4G, 5G, etc. With this evaluation in mobile bands there has been an increase in the number of cellular towers installed to provide flawless network to all the users, but one thing remains unchecked is the energy consumed by these towers. For mobile towers, the consumption of energy is in terms of electricity and which is produced in great amount by either using coal or by burning fossil fuels (Generators that run in Diesels). Based on various network operators, it has been seen that the energy consumed by the radio access networks is the most imminent factor relating to impact on the environment. Also, the current wireless system is not energy efficient mainly the Base Station (BS). In order to restructure the existing network architecture, we need to control each and every system of the base station. We have proposed an innovative and promising method for enhancing the energy efficiency of the wireless networks and have developed solutions on IOT which will surely reduce the operating cost and effects on the environment.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116718249","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 : 2021-07-01DOI: 10.1109/icscc51209.2021.9528251
{"title":"[ICSCC 2021 Front cover]","authors":"","doi":"10.1109/icscc51209.2021.9528251","DOIUrl":"https://doi.org/10.1109/icscc51209.2021.9528251","url":null,"abstract":"","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122594222","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528290
A. M, Anas Kunjumuhammed, Jithin Tomy, Urmila G, M. Sivadas, Ambili Mohan
The rotary inverted pendulum is a nonlinear and intrinsically unstable system that is broadly used for experimental studies and analysis. This paper focuses on the development of a nonlinear model for the rotary inverted pendulum, which encompasses the complex dynamics of the system unlike the linear model. The nonlinear behavior of the system is analyzed and validated for varying inputs. Further, the system is stabilized using a PID controller in the upright position. The controller is validated when the system is subjected to output disturbance.
{"title":"Stabilization of Rotary Inverted Pendulum using PID Controller","authors":"A. M, Anas Kunjumuhammed, Jithin Tomy, Urmila G, M. Sivadas, Ambili Mohan","doi":"10.1109/ICSCC51209.2021.9528290","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528290","url":null,"abstract":"The rotary inverted pendulum is a nonlinear and intrinsically unstable system that is broadly used for experimental studies and analysis. This paper focuses on the development of a nonlinear model for the rotary inverted pendulum, which encompasses the complex dynamics of the system unlike the linear model. The nonlinear behavior of the system is analyzed and validated for varying inputs. Further, the system is stabilized using a PID controller in the upright position. The controller is validated when the system is subjected to output disturbance.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121749068","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528122
Anurag Sharma, Suman Mohanty, Md. Ruhul Islam
In the recent time due to advancement of technology, Malware and its clan have continued to advance and become more diverse. Malware otherwise Malicious Software consists of Virus, Trojan horse, Adware, Spyware etc. This said software leads to extrusion of data (Spyware), continuously flow of Ads (Adware), modifying or damaging the system files (Virus), or access of personal information (Trojan horse). Some of the major factors driving the growth of these attacks are due to poorly secured devices and the ease of availability of tools in the Internet with which anyone can attack any system. The attackers or the developers of Malware usually lean towards blending of malware into the executable file, which makes it hard to detect the presence of malware in executable files. In this paper we have done experimental study on various algorithms of Machine Learning for detecting the presence of Malware in executable files. After testing Naïve Bayes, KNN and SVM, we found out that SVM was the most suited algorithm and had the accuracy of 94%. We then created a web application where the user could upload executable file and test the authenticity of the said executable file if it is a Malware file or a benign file.
{"title":"An Experimental Analysis on Malware Detection in Executable Files using Machine Learning","authors":"Anurag Sharma, Suman Mohanty, Md. Ruhul Islam","doi":"10.1109/ICSCC51209.2021.9528122","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528122","url":null,"abstract":"In the recent time due to advancement of technology, Malware and its clan have continued to advance and become more diverse. Malware otherwise Malicious Software consists of Virus, Trojan horse, Adware, Spyware etc. This said software leads to extrusion of data (Spyware), continuously flow of Ads (Adware), modifying or damaging the system files (Virus), or access of personal information (Trojan horse). Some of the major factors driving the growth of these attacks are due to poorly secured devices and the ease of availability of tools in the Internet with which anyone can attack any system. The attackers or the developers of Malware usually lean towards blending of malware into the executable file, which makes it hard to detect the presence of malware in executable files. In this paper we have done experimental study on various algorithms of Machine Learning for detecting the presence of Malware in executable files. After testing Naïve Bayes, KNN and SVM, we found out that SVM was the most suited algorithm and had the accuracy of 94%. We then created a web application where the user could upload executable file and test the authenticity of the said executable file if it is a Malware file or a benign file.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131914983","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528296
Roshna B. Raj, A. Tripathi, Shiny Nair, Deepak Gupta, T. Shahana, T. Mukundan
Bandwidth improvement in amorphous oxide thin film transistors, demands lower overlap length between the contact and gate. But lowering overlap length can lead to lower efficiency of current transfer between the metal and the semiconductor due to reduced area for current injection. The influence of semiconductor thickness on this injection area is studied by fabricating three batches of TFTs; batch 1 with thickness of 5 nm, batch 2 with thickness of 10 nm and batch 3 with thickness of 30 nm. As the value of overlap length is scaled down the devices failed to operate with steadily increasing transconductance beyond a limiting value of overlap length. Batch 1 displayed a limiting overlap length of 5 µm and batch 2 provided a limiting overlap length of 10 µm. Batch 3 devices failed to display field effect operation even at an overlap length as high as 10 µm. It is found that lower thickness can lead to better immunity towards overlap length changes. The hump displayed by transconductance in thicker devices points to Schottky contact formation. Hence thickness of the semiconductor limits the extent to which overlap length can be scaled in thin film transistors.
{"title":"Effect of Active Layer Thickness Variation on Overlap Length Scaling in a-IGZO Thin Film Transistors","authors":"Roshna B. Raj, A. Tripathi, Shiny Nair, Deepak Gupta, T. Shahana, T. Mukundan","doi":"10.1109/ICSCC51209.2021.9528296","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528296","url":null,"abstract":"Bandwidth improvement in amorphous oxide thin film transistors, demands lower overlap length between the contact and gate. But lowering overlap length can lead to lower efficiency of current transfer between the metal and the semiconductor due to reduced area for current injection. The influence of semiconductor thickness on this injection area is studied by fabricating three batches of TFTs; batch 1 with thickness of 5 nm, batch 2 with thickness of 10 nm and batch 3 with thickness of 30 nm. As the value of overlap length is scaled down the devices failed to operate with steadily increasing transconductance beyond a limiting value of overlap length. Batch 1 displayed a limiting overlap length of 5 µm and batch 2 provided a limiting overlap length of 10 µm. Batch 3 devices failed to display field effect operation even at an overlap length as high as 10 µm. It is found that lower thickness can lead to better immunity towards overlap length changes. The hump displayed by transconductance in thicker devices points to Schottky contact formation. Hence thickness of the semiconductor limits the extent to which overlap length can be scaled in thin film transistors.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"228 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130538610","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528123
Isha Ganguli, Rajat Subhra Bhowmick, Shivam Biswas, J. Sil
The immense real-time applicability of Python coding makes the task of evaluating the code highly intriguing, in the Natural Language Processing (NLP) domain. Evaluation of computer programs induces a challenge of logical and arithmetic understanding. Therefore, it is indeed very relevant to analyze the empirical ability of current state-of-the-art sequence-based neural architectures in evaluating small computer programs. One of the possible applications of such analysis is the auto-evaluation of erroneous Python code. In this context, we focused our work on evaluating small python code blocks with or without error and examined the efficiency of the latest T5 Transformer network model in this task. In terms of accuracy, different Rouge scores, and BLEU scores, the performance measurements has been calculated. Observations reveal that T5 Transformer is able to compute the output for both correct and erroneous python code blocks with more than 65% accuracy.
{"title":"Empirical Auto-Evaluation of Python Code for Performance Analysis of Transformer Network Using T5 Architecture","authors":"Isha Ganguli, Rajat Subhra Bhowmick, Shivam Biswas, J. Sil","doi":"10.1109/ICSCC51209.2021.9528123","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528123","url":null,"abstract":"The immense real-time applicability of Python coding makes the task of evaluating the code highly intriguing, in the Natural Language Processing (NLP) domain. Evaluation of computer programs induces a challenge of logical and arithmetic understanding. Therefore, it is indeed very relevant to analyze the empirical ability of current state-of-the-art sequence-based neural architectures in evaluating small computer programs. One of the possible applications of such analysis is the auto-evaluation of erroneous Python code. In this context, we focused our work on evaluating small python code blocks with or without error and examined the efficiency of the latest T5 Transformer network model in this task. In terms of accuracy, different Rouge scores, and BLEU scores, the performance measurements has been calculated. Observations reveal that T5 Transformer is able to compute the output for both correct and erroneous python code blocks with more than 65% accuracy.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130861422","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：