Pub Date : 2022-12-10DOI: 10.1109/STCR55312.2022.10009097
Sheena Banday, Mir Nazish, Ishfaq Sultan, M. T. Banday
PRESENT is one of the first standard hardware efficient, ultra-lightweight block cyphers designed to secure highly resource-constrained devices. The 4x4 s-boxes and 64-bit permutations provide an optimum level of confusion and diffusion in the cypher. The bitwise permutation involving the rerouting of wires provides faster diffusion in hardware, however, it is far from being an optimal choice to achieve good performance in software. Even though the 4-bit PRESENT s-box requires a small amount of memory to store the pre-defined s-box table, the overall efficiency of a block cypher is determined by both the linear and non-linear strategies used in the design. In this paper, three software techniques for implementing the PRESENT block cypher, namely direct, wide-table and combined wide-table, are being analysed and compared in KEIL MDK IDE and ARM Cortex-M3-based LPC1768 IoT development platform. The techniques have been evaluated for execution time, code footprint, and power and energy consumption. Therefore, this paper helps the designers to select the best software efficient technique as per their application use case.
{"title":"Performance Comparison of Software-Efficient Implementations of the PRESENT Block Cypher","authors":"Sheena Banday, Mir Nazish, Ishfaq Sultan, M. T. Banday","doi":"10.1109/STCR55312.2022.10009097","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009097","url":null,"abstract":"PRESENT is one of the first standard hardware efficient, ultra-lightweight block cyphers designed to secure highly resource-constrained devices. The 4x4 s-boxes and 64-bit permutations provide an optimum level of confusion and diffusion in the cypher. The bitwise permutation involving the rerouting of wires provides faster diffusion in hardware, however, it is far from being an optimal choice to achieve good performance in software. Even though the 4-bit PRESENT s-box requires a small amount of memory to store the pre-defined s-box table, the overall efficiency of a block cypher is determined by both the linear and non-linear strategies used in the design. In this paper, three software techniques for implementing the PRESENT block cypher, namely direct, wide-table and combined wide-table, are being analysed and compared in KEIL MDK IDE and ARM Cortex-M3-based LPC1768 IoT development platform. The techniques have been evaluated for execution time, code footprint, and power and energy consumption. Therefore, this paper helps the designers to select the best software efficient technique as per their application use case.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130691707","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009305
Mary Catherine V G, Binu Paul, Vinoj P G
The demand for Robots in Elderly assistance is increasing due to the lack of human caregivers. In the context of Robot coexisting with the human beings in a home environment, for the safe and friendly interaction it is essential to endow the sense of touch through Tactile sensor systems. This paper proposes a novel scalable approach for tactile sensors based on low cost wearable conductive fabric. Fabric tactile sensor (FABTAC) is conformable with the robot body and can be used as a tactile sensing skin that perceives touch and force applied at the contact location. FABTAC sensors are developed as an array of touch sensors sewed on the cloth substrate with the stainless-steel conductive thread. The thermistor sensors are also sewed to fabric to perceive the temperature information. The FABTAC sensors are integrated on to the custom-made 3D printed Robotic hand and the tactile data is processed with a novel wearable electronic FLORA microcontroller platform. The acquired data can be used to provide a real time tactile feedback for performing assistive tasks like grasping objects of diverse profiles, avoiding slippage. The FABTAC sensors has the advantage of utilizing flexible, light weight sensors with good spatial and temporal resolution. Thus, the system can potentially aid the automation of daily life activities of the Elderly thereby enhancing the quality of their life.
{"title":"Wearable Fabric Tactile Sensors for Robotic Elderly Assistance","authors":"Mary Catherine V G, Binu Paul, Vinoj P G","doi":"10.1109/STCR55312.2022.10009305","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009305","url":null,"abstract":"The demand for Robots in Elderly assistance is increasing due to the lack of human caregivers. In the context of Robot coexisting with the human beings in a home environment, for the safe and friendly interaction it is essential to endow the sense of touch through Tactile sensor systems. This paper proposes a novel scalable approach for tactile sensors based on low cost wearable conductive fabric. Fabric tactile sensor (FABTAC) is conformable with the robot body and can be used as a tactile sensing skin that perceives touch and force applied at the contact location. FABTAC sensors are developed as an array of touch sensors sewed on the cloth substrate with the stainless-steel conductive thread. The thermistor sensors are also sewed to fabric to perceive the temperature information. The FABTAC sensors are integrated on to the custom-made 3D printed Robotic hand and the tactile data is processed with a novel wearable electronic FLORA microcontroller platform. The acquired data can be used to provide a real time tactile feedback for performing assistive tasks like grasping objects of diverse profiles, avoiding slippage. The FABTAC sensors has the advantage of utilizing flexible, light weight sensors with good spatial and temporal resolution. Thus, the system can potentially aid the automation of daily life activities of the Elderly thereby enhancing the quality of their life.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130807683","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009429
Mehvish Ali, Mir Nazish, Suhail Ashaq, Ishfaq Sultan, M. T. Banday
The growing demand for the Internet of Things in the application fields with minimum latency requirements is emerging at a rapid rate. Securing these applications not only requires the design of lightweight crypto primitives with minimal code footprint but with shorter execution times. However, despite being a vital performance indicator for deterministic time-bound applications, this has not received much attention and has often been sub-prioritised. Low-latency block cyphers employing loop unrolling design techniques are a favourable choice for securing real-time IoT applications. However, although loop unrolling increases the speed of the overall design, glitches between the unrolled round functions increase its dynamic power and energy consumption, making the cyphers unfit for low-power IoT devices. In this paper, the hybrid glitch-reduction techniques designed using different combinational and sequential circuits have been proposed. These techniques have been devised for the SIMON block cypher because of its hardware efficiency. Furthermore, the high-speed loop unrolling technique for SIMON64/128 block cypher has been analysed for low-latency behaviour in light of various trade-offs between different design metrics. These techniques have been simulated and analysed in Xilinx ISE for Artix-7 and Spartan-6 FPGA boards regarding various metrics such as power, area, latency, throughput and critical path. The results demonstrate that the proposed approaches for SIMON64/128 block cypher produces better results certifying their use for high-speed IoT applications.
{"title":"Design of Hybrid Glitch-Reduction Techniques for Loop Unrolled SIMON Block Cypher","authors":"Mehvish Ali, Mir Nazish, Suhail Ashaq, Ishfaq Sultan, M. T. Banday","doi":"10.1109/STCR55312.2022.10009429","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009429","url":null,"abstract":"The growing demand for the Internet of Things in the application fields with minimum latency requirements is emerging at a rapid rate. Securing these applications not only requires the design of lightweight crypto primitives with minimal code footprint but with shorter execution times. However, despite being a vital performance indicator for deterministic time-bound applications, this has not received much attention and has often been sub-prioritised. Low-latency block cyphers employing loop unrolling design techniques are a favourable choice for securing real-time IoT applications. However, although loop unrolling increases the speed of the overall design, glitches between the unrolled round functions increase its dynamic power and energy consumption, making the cyphers unfit for low-power IoT devices. In this paper, the hybrid glitch-reduction techniques designed using different combinational and sequential circuits have been proposed. These techniques have been devised for the SIMON block cypher because of its hardware efficiency. Furthermore, the high-speed loop unrolling technique for SIMON64/128 block cypher has been analysed for low-latency behaviour in light of various trade-offs between different design metrics. These techniques have been simulated and analysed in Xilinx ISE for Artix-7 and Spartan-6 FPGA boards regarding various metrics such as power, area, latency, throughput and critical path. The results demonstrate that the proposed approaches for SIMON64/128 block cypher produces better results certifying their use for high-speed IoT applications.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130839863","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009251
Vairavel K S, Logasundari V
In this paper, to control the temperature of the Peltier element for DNA amplification. They are quick variation in temperature and temperature setback method required for DNA amplification. Temperature control at 95℃, 65℃ and 75℃. Peltier element was used for producing the temperature at different stage. Heating and cooling of peltier element was change the polarity of the power supply by using h-bridge. Peltier element temperature depends on current value, doesn’t voltage. Current value of the peltier element control by PWM signal. The PWM signal generated for the PIC microprocessor depends on the RTD temperature values. The PID control logic was programming by microprocessor controller.
{"title":"Development of DNA Amplification Instrument used in Disease Diagnosis","authors":"Vairavel K S, Logasundari V","doi":"10.1109/STCR55312.2022.10009251","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009251","url":null,"abstract":"In this paper, to control the temperature of the Peltier element for DNA amplification. They are quick variation in temperature and temperature setback method required for DNA amplification. Temperature control at 95℃, 65℃ and 75℃. Peltier element was used for producing the temperature at different stage. Heating and cooling of peltier element was change the polarity of the power supply by using h-bridge. Peltier element temperature depends on current value, doesn’t voltage. Current value of the peltier element control by PWM signal. The PWM signal generated for the PIC microprocessor depends on the RTD temperature values. The PID control logic was programming by microprocessor controller.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133798680","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009240
S. Subramanian, Chidamparam Ganesh Babu
The computation of the First-Order plus Time-Delay (FOPTD) model parameters are computed using different techniques. This type models are widely used in the industry to approximate the process models because it is easy to tune the controllers based on the model parameters. The controllers are derived from the models. The model derived from the time domain data. In this article, the closed loop system identification methods are examined. The closed loop / feedback controller is designed based on the step output data as to the original system. The closed loop identification method is executed using different set of inputs/excitation. The model obtained from the closed identification methods and it is validated using model performance metrics. This identification process is illustrated through the FOPTD bench mark system.
{"title":"Open Loop Subspace Identification of a FOPTD System","authors":"S. Subramanian, Chidamparam Ganesh Babu","doi":"10.1109/STCR55312.2022.10009240","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009240","url":null,"abstract":"The computation of the First-Order plus Time-Delay (FOPTD) model parameters are computed using different techniques. This type models are widely used in the industry to approximate the process models because it is easy to tune the controllers based on the model parameters. The controllers are derived from the models. The model derived from the time domain data. In this article, the closed loop system identification methods are examined. The closed loop / feedback controller is designed based on the step output data as to the original system. The closed loop identification method is executed using different set of inputs/excitation. The model obtained from the closed identification methods and it is validated using model performance metrics. This identification process is illustrated through the FOPTD bench mark system.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114485065","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009635
Supriya Suryakant Ingale, S. Ram
In this study, an accurate estimation of elbow joint angle by measuring surface electromyography(sEMG) signal from human biceps muscle is done using machine learning regression methods such as linear and polynomial regression. The result of the regression technique is further validated using Kalman Filter Technique (KL) which gave better accurate results for the angle taken. As the first step of regression analysis, the sEMG signal measured from the human biceps muscle, using the Myoware IC has been preprocessed to make it suitable for further analysis. Then the second step was to extract the features from the measured sEMG signal and in this paper, four features of the time-domain method were extracted to estimate the elbow joint angle, namely integrated EMG (iEMG), LOG, RMS and Mean. The extracted features were then applied to the machine learning regression algorithm to predict the elbow joint angle. The predicted elbow joint angle using regression and the Kalman filter showed that the results found using the Kalman filter gave higher accuracy than polynomial regression.
{"title":"Analysis of Elbow Joint Angle for Prediction based on EMG using Kalman Filtering Technique","authors":"Supriya Suryakant Ingale, S. Ram","doi":"10.1109/STCR55312.2022.10009635","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009635","url":null,"abstract":"In this study, an accurate estimation of elbow joint angle by measuring surface electromyography(sEMG) signal from human biceps muscle is done using machine learning regression methods such as linear and polynomial regression. The result of the regression technique is further validated using Kalman Filter Technique (KL) which gave better accurate results for the angle taken. As the first step of regression analysis, the sEMG signal measured from the human biceps muscle, using the Myoware IC has been preprocessed to make it suitable for further analysis. Then the second step was to extract the features from the measured sEMG signal and in this paper, four features of the time-domain method were extracted to estimate the elbow joint angle, namely integrated EMG (iEMG), LOG, RMS and Mean. The extracted features were then applied to the machine learning regression algorithm to predict the elbow joint angle. The predicted elbow joint angle using regression and the Kalman filter showed that the results found using the Kalman filter gave higher accuracy than polynomial regression.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"1091 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122906880","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009190
Harreni V, Hinduja S N, V. S, A. S, Vanathi P T
Detecting defects in fabric is one of the most important steps in the process of quality control in manufacturing processes. The textile structure can deviate from the design due to improper mechanical motion or yarn breakage on a loom, producing a warp, weft, or point defect like harness misdraw, endout, mispick, and slub. Visual human inspection results in common mistakes and takes more time, both of which might reduce productivity. Therefore, automated fabric defect identification will save time and enable more accurate and rapid defect prediction. Due to the Convolution Neural Network's high level of image classification and recognition accuracy, it is utilised to detect fabric defects. It chooses just appropriate features for object identification from a vast number of created features. The proposed model works on the multipath CNN concept, where first path is CNN with tanh activation layer + GLCM and the second path is VGG – 16 + Gabor. The novel multipath CNN was evaluated using TILDA dataset with total of 2000 images and simulated for 20 epochs.
{"title":"Novel Multipath Convolutional Neural Network Based Fabric Defect Detection System","authors":"Harreni V, Hinduja S N, V. S, A. S, Vanathi P T","doi":"10.1109/STCR55312.2022.10009190","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009190","url":null,"abstract":"Detecting defects in fabric is one of the most important steps in the process of quality control in manufacturing processes. The textile structure can deviate from the design due to improper mechanical motion or yarn breakage on a loom, producing a warp, weft, or point defect like harness misdraw, endout, mispick, and slub. Visual human inspection results in common mistakes and takes more time, both of which might reduce productivity. Therefore, automated fabric defect identification will save time and enable more accurate and rapid defect prediction. Due to the Convolution Neural Network's high level of image classification and recognition accuracy, it is utilised to detect fabric defects. It chooses just appropriate features for object identification from a vast number of created features. The proposed model works on the multipath CNN concept, where first path is CNN with tanh activation layer + GLCM and the second path is VGG – 16 + Gabor. The novel multipath CNN was evaluated using TILDA dataset with total of 2000 images and simulated for 20 epochs.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121930241","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009543
U. S, K. Kausalya, K. S
Object recognition plays a vital role in many applications in computer vision. In sports video recognition an action is a major part, in that object recognition is a key requirement. In the video, many challenges are faced which includes fast motion, occluded objects, different sizes of objects, difficult illumination, and continuous change in the background in identifying the object is a major task. The proposed system’s main aim is to deliver a summary of the existing system’s object detection approaches that belongs to CNN and debug their performance on soccer sport video and their training videos and match with the input soccer video. The performance of object recognition is discussed in various situations.
{"title":"Object Recognition in Soccer Sports Videos","authors":"U. S, K. Kausalya, K. S","doi":"10.1109/STCR55312.2022.10009543","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009543","url":null,"abstract":"Object recognition plays a vital role in many applications in computer vision. In sports video recognition an action is a major part, in that object recognition is a key requirement. In the video, many challenges are faced which includes fast motion, occluded objects, different sizes of objects, difficult illumination, and continuous change in the background in identifying the object is a major task. The proposed system’s main aim is to deliver a summary of the existing system’s object detection approaches that belongs to CNN and debug their performance on soccer sport video and their training videos and match with the input soccer video. The performance of object recognition is discussed in various situations.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122122148","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009185
M. Nirmal, Pramod E Jadhav, Santoshi A. Pawar, Manoj Kharde, Pravara
The goal of this research is to detect a pomegranate plant leaf disease that will identify the diseases by making use of a deep convolutional neural network. Plant diseases are a serious problem in India and other Asian Countries that rely heavily on agriculture. Throughout the course of the year, several diseases can be found causing havoc on the harvest by attacking crops. Plant diseases can be difficult to identify with the naked eye alone. As a consequence of this, the development of a system that is capable of recognizing diseases is of the utmost importance. This paper proposes a deep learning technique to an image of a plant leaf, the disease detection model that has been suggested makes use of a deep convolutional neural network to locate and identify the disease. 447, 56, 56 pictures representing 14 unique species and 26 distinct diseases were utilized throughout the training process of the model. A CNN + LSTM is further developed with the help of a trained model. This proposed technique not only diagnoses a health problem, but it also suggests courses of treatment based on the information that it has gathered. In the vast majority of cases, farmers and other specialists in the sector keep a close eye on plants in order to detect and identify diseases. The proposed framework was developed with the assistance of deep learning technique. According to the findings of the tests, the framework that has been proposed is accurate to the degree of 90.546percent when it comes to differentiating between good and unhealthy leaves. The framework allows for the classification of diseases that affect pomegranate leaf to an accuracy of 97.246 %. The data sets are from Mendeley Data Total: 559 images. In which healthy 287 images were identified and 272 diseases images were identified. Originally data were split in 8:1:1 ratio.
本研究的目的是检测石榴植物叶片病害，并利用深度卷积神经网络对病害进行识别。在印度和其他严重依赖农业的亚洲国家，植物病害是一个严重的问题。在一年中，可以发现几种疾病通过攻击作物对收成造成严重破坏。植物病害很难单凭肉眼识别。因此，开发一种能够识别疾病的系统是至关重要的。本文提出了一种植物叶片图像的深度学习技术，提出的病害检测模型利用深度卷积神经网络对病害进行定位和识别。在整个模型的训练过程中，使用了代表14个独特物种和26种不同疾病的447、56、56张图片。在训练好的模型的帮助下，进一步开发了CNN + LSTM。这项拟议中的技术不仅可以诊断健康问题，还可以根据收集到的信息提出治疗方案。在绝大多数情况下，农民和该部门的其他专家密切关注植物，以便发现和识别疾病。该框架是在深度学习技术的帮助下开发的。根据测试结果，提出的框架在区分好叶和不健康叶方面的准确率为90.546%。该框架允许对影响石榴叶的疾病进行分类，准确率为97.246%。数据集来自Mendeley data Total: 559张图像。其中健康图像287张，疾病图像272张。最初数据是按8:1:1的比例分割的。
{"title":"Deep Learning-based Disease Detection using Pomegranate Leaf Image","authors":"M. Nirmal, Pramod E Jadhav, Santoshi A. Pawar, Manoj Kharde, Pravara","doi":"10.1109/STCR55312.2022.10009185","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009185","url":null,"abstract":"The goal of this research is to detect a pomegranate plant leaf disease that will identify the diseases by making use of a deep convolutional neural network. Plant diseases are a serious problem in India and other Asian Countries that rely heavily on agriculture. Throughout the course of the year, several diseases can be found causing havoc on the harvest by attacking crops. Plant diseases can be difficult to identify with the naked eye alone. As a consequence of this, the development of a system that is capable of recognizing diseases is of the utmost importance. This paper proposes a deep learning technique to an image of a plant leaf, the disease detection model that has been suggested makes use of a deep convolutional neural network to locate and identify the disease. 447, 56, 56 pictures representing 14 unique species and 26 distinct diseases were utilized throughout the training process of the model. A CNN + LSTM is further developed with the help of a trained model. This proposed technique not only diagnoses a health problem, but it also suggests courses of treatment based on the information that it has gathered. In the vast majority of cases, farmers and other specialists in the sector keep a close eye on plants in order to detect and identify diseases. The proposed framework was developed with the assistance of deep learning technique. According to the findings of the tests, the framework that has been proposed is accurate to the degree of 90.546percent when it comes to differentiating between good and unhealthy leaves. The framework allows for the classification of diseases that affect pomegranate leaf to an accuracy of 97.246 %. The data sets are from Mendeley Data Total: 559 images. In which healthy 287 images were identified and 272 diseases images were identified. Originally data were split in 8:1:1 ratio.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130571997","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 : 2022-12-10DOI: 10.1109/STCR55312.2022.10009205
P. K, B. Nataraj
The Internet of Things (IoT) and Blockchain Technology are more trending which are gaining popularity all over the world in recent times. IoT is a collection of several things that consists of sensors, actuators, and many other devices to perform identification and sensing by aggregation of data, interacting with other devices, and advanced processes in a real-time environment. However, at the same time, Blockchain comprises small blocks where each block can have an identity and hash value. Due to the huge sector of applications that can be achieved with IoT devices, threats and huge attacks can occur and make it an insecure state. Therefore, security and privacy have become an integral part of the internet of things. To the best of our knowledge, extensive studies are made on the security threats and different types of attacks in every layer of the Internet of Things. Moreover, the article focuses on the integration of blockchain technology with the Internet of Things (IoT) and the classification of Blockchain IoT (BIoT) attacks. The threat levels and the prevention techniques of attacks in IoT and Blockchain are incorporated respectively.
{"title":"Certain Investigation of Attacks in the Field of Internet of Things and Blockchain Technology","authors":"P. K, B. Nataraj","doi":"10.1109/STCR55312.2022.10009205","DOIUrl":"https://doi.org/10.1109/STCR55312.2022.10009205","url":null,"abstract":"The Internet of Things (IoT) and Blockchain Technology are more trending which are gaining popularity all over the world in recent times. IoT is a collection of several things that consists of sensors, actuators, and many other devices to perform identification and sensing by aggregation of data, interacting with other devices, and advanced processes in a real-time environment. However, at the same time, Blockchain comprises small blocks where each block can have an identity and hash value. Due to the huge sector of applications that can be achieved with IoT devices, threats and huge attacks can occur and make it an insecure state. Therefore, security and privacy have become an integral part of the internet of things. To the best of our knowledge, extensive studies are made on the security threats and different types of attacks in every layer of the Internet of Things. Moreover, the article focuses on the integration of blockchain technology with the Internet of Things (IoT) and the classification of Blockchain IoT (BIoT) attacks. The threat levels and the prevention techniques of attacks in IoT and Blockchain are incorporated respectively.","PeriodicalId":338691,"journal":{"name":"2022 Smart Technologies, Communication and Robotics (STCR)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131928612","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：