检索结果-内蒙古大学图书馆

Modeling and optimization of numerical studies on CuSbS2 thin film solar cell with ∼ 15% efficiency

Optik 2024年 300卷

作者： Prakash, Krishna Valeti, Naga Jyothi Indraja, Bodem Singha, Monoj Kumar Dept. of Electronics and Communication SRM University AP Andhra Pradesh India Dept. of Computer Science NRI Institute of Technology Andhra Pradesh India Dept. of Electronics and Communication University of Allahabad India

In this paper, the Silvaco TCAD simulation tool is utilized for modeling of ternary chalcostibite copper antimony sulfide (CuSbS2) thin film solar cells (TFSCs). The earth-abundant CuSbS2 is a promising material as a solar absorber and hole transport layer due to its high optical absorption coefficient, and low cost. CuSbS2 based solar cell can be fabricated in vacuum-free environment. Mostly CdS is used as electron transport layer (ETL) in CuSbS2 based solar cell but the efficiency is low due to creation of Schottky barrier at the back-contact and substantial carrier recombination at the CuSbS2/CdS interface. Hence, a (ITO/n-TiO2/p-CuSbS2/Au) np heterojunction-based solar cell has been developed. The observed maximum power conversion efficiency (PCE) of 15.26% (open circuit voltage (Voc) = 823 mV, short circuit current (Jsc) = 28.48 mA/cm2, fill factor (FF) = 65.1%) is achieved by optimizing the absorber thickness (400 nm) of the solar cell. Different parameters like effect of absorber thickness, back contact, bandgap, carrier concentration, temperature, and defect density are optimized to find the best possible efficiency of the solar cell. The device also exhibits good performance stability at high temperatures. Based on results, a (ITO/n-TiO2/p-CuSbS2/Au) np heterojunction-based fabricated solar cell device is possible in future. © 2024 Elsevier GmbH

关键词： Thin films

来源：评论

学校读者我要写书评

暂无评论

Traffic Signs Classification using Convolutional Neural Networks: A review 2

Traffic Signs Classification using Convolutional Neural Netw...

引用

2nd International Conference on Secure Cyber Computing and Communications, ICSCCC 2021

作者： Palak Sangal, A.L. Dr B R Ambedkar National Institute of Technology Dept. of Computer Science and Engineering Jalandhar India

ISBN: (纸本)9781665444156

With advancement in artificial intelligence (AI), Deep learning models are used to imitate the actions of human beings. These activities of personage are controlled by their brain and similar to that, machines are capable of data processing, decision making, speech recognition and language translations just like human beings. One of the applications of deep learning includes Autonomous Vehicles design i.e., driver less cars. To implement this, we need an automatic traffic sign recognition (TSR) model. These models are designed with the use of convolutional neural networks (CNN). The main task of this model isto extract the various features of the different traffic sign images and classify according to unique categories. This paper includes a comprehensive review of various models that can be used for classifying traffic signs. Researchers have applied various CNN models to predict the class of traffic sign and these are proven to be better than machine learning algorithms. CNN works asa feed forward neural network which has been stimulated from animal visual cortex. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Classifying the DNA sequence using Optimized Naive Bayes Approach: A Comparative Analysis of Machine Learning Algorithms

Classifying the DNA sequence using Optimized Naive Bayes App...

引用

Computational Intelligence, Communication technology and Networking (CICTN), International Conference on

作者： Aditya Pai H Chandrappa S Guru Prasad M S Ganesh Pathak Atul Thakare Pratik Kumar MIT School of Computing MIT Art Design and Technology University Pune India Dept. of Computer Science and Engineering JAIN (Deemed-to-be University) Bengaluru India Dept. of Computer Science and Engineering Graphic Era (Deemed to be University) Dehradun India Department of Computer Application Graphic Era (Deemed-to-be University) Dehradun India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

In bioinformatics, the exact classification of DNA sequences is essential to increasing comprehension of genetic structures and functionalities. This research introduces an enhanced Naive Bayes approach (ENB) specifically designed to handle more complexities related to DNA sequence data. This research integrates advanced feature weighting and optimized probability estimation techniques to enhance classification accuracy substantially. The proposed work demonstrated superior efficacy to traditional ML algorithms like Random Forest, SVM, Decision-Trees, K-Nearest Neighbors, Gradient Boosting etc. The proposed method attained a level of accuracy of 98%, and proposed approach performs better than the other models, with 94% accuracy in Logistic Regression coming in second.

关键词： Support vector machines Logistic regression Accuracy Machine learning algorithms Nearest neighbor methods Boosting Bayes methods Complexity theory Medical diagnosis Random forests

来源：评论

学校读者我要写书评

暂无评论

Visualization of Semantic Differential Questionnaire: A Case Study of Sofas and Stylish Products

Visualization of Semantic Differential Questionnaire: A Case...

引用

Joint 8th International Conference on Digital Arts, Media and technology and 6th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2023

作者： Li, Mei Lee, Suiang-Shyan Chen, Chong-Wen Huang, Yi-Jheng National Tsing Hua University Dept. of Arts and Design Hsinchu Taiwan E-SOFT Corp. Dept. of Research & Development Taipei Taiwan National Kaohsiung University of Science and Technology Dept. of Cultural and Creative Industries Kaohsiung Taiwan Yuan Ze University Dept. of Computer Science and Engineering Taoyuan Taiwan

ISBN: (纸本)9798350396546

Nowadays, consumers not only pay attention to the price of a product, but also to its design and taste. Designers try to design products that meet the feelings and needs of consumers. However, how can these feelings be translated into design elements? In the field of Kansei engineering, researchers try to find the answer. When studying the relationship between consumers' feelings and design elements, the semantic differential method is often used in Kansei engineering. This study built a visualization system to visualize the data from a semantic differential questionnaire. Our survey targets were sofas and stylish products. We classified design elements into six factors: style, shape, material, color, value, and emotion. Each factor contained two sets of scales with polar adjectives, meaning opposing adjective words. We then collected 68 semantic differential questionnaires based on these factors. Finally, we displayed our results in six types of charts: two tree charts, a comprehensive analysis chart, a heatmap, a donut radar chart, a line chart, and a bar chart. When the results of the semantic differential questionnaire are visualized in these charts, it helps designers to see patterns in the data and makes it easier to interpret the results © 2023 IEEE.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Bringing DNS Service to 5G Edge for Reduced Latencies in mMTC Applications

arXiv

引用

arXiv 2023年

作者： Harrilal-Parchment, Ricardo Pineda, Diana Akkaya, Kemal Aydeger, Abdullah Perez-Pons, Alexander Dept. of Electrical and Computer Engineering Florida International University MiamiFL33174 United States Dept. of Electrical Engineering and Computer Science Florida Institute of Technology MelbourneFL32901 United States

5G brings many improvements to cellular networks in terms of performance, such as lower latency, improved network efficiency, and higher throughput, making it an attractive candidate for many applications. One such domain is industrial applications that may require real-time guarantees to transmit time-critical control messages. Assuming the immense number of devices exchanging data in support of Massive Machine-Type Communications (mMTC) applications, the capability of the cellular infrastructure to handle a large number of real-time transmissions may be inadequate. For such cases, there exists an acute desire to reduce any overheads as much as possible in order to guarantee certain deadlines. One such target is the Domain Name System (DNS) service, for which queries precede almost every new network request. This incorporates additional communication delays based on the response time, which in turn is affected by the proximity of the DNS server. While bringing DNS service to the edge has been touted as a logical solution, its integration with 5G systems is still challenging. This is due to the inability to access the DNS query information at the application layer since the User Equipment (UE) traffic is tunneled through to the core network. To this end, we propose a novel approach that can identify DNS queries at the base stations through Software-Defined Networking (SDN) capabilities. Specifically, we develop an SDN controller which is used to identify and extract DNS queries at the base station and handle the query at the edge without going through the 5G core network. This approach was implemented in a virtualized 5G network, in which we demonstrate that it is feasible and can potentially bring significant performance gains, especially in the case of mMTC applications. © 2023, CC BY-NC-ND.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

TrustEvent: Cross-Platform IoT Trigger Event Verification Using Edge Computing

TrustEvent: Cross-Platform IoT Trigger Event Verification Us...

引用

IEEE International Conference on Communications (ICC)

作者： Trent Reichenbach Chenglong Fu Xiaojiang Du Jia Di Yuede Ji Dept. of Electrical and Computer Engr Stevens Institute of Technology Hoboken NJ USA Dept. of Software and Information Systems UNC Charlotte Charlotte NC USA Dept. of Computer Science and Engr University of Arkansas Fayetteville AR USA Dept. Computer Science and Engr University of North Texas Denton TX USA

ISBN: (数字)9781728190549

ISBN: (纸本)9781728190556

As smart home IoT systems gain popularity, they inevitably become targets for security risks and concerns. Among various cyber-attacks targeting these systems, the fake event attack poses significant issues due to its ability to manipulate secure devices through automation rules. In response to this threat, we propose TrustEvent - a system designed to offer end-to-end event signature verification. By integrating TrustEvent with existing home automation platforms, event authenticity is verified against signatures generated from edge devices before these events trigger automation rule execution. Notably, we have developed a signature proxy module, enhancing our system's compatibility across various platform scenarios. We have implemented a TrustEvent prototype in conjunction with existing commercial smart home IoT platforms, evaluating its overhead in the process. Our experimentation demonstrates that our system only marginally increases the automation execution latency, by an average of 3.74 seconds, representing a acceptable compromise for enhanced security.

关键词： Handwriting recognition Automation System performance Instruments Prototypes Smart homes Static analysis

来源：评论

学校读者我要写书评

暂无评论

Deepflow: A Software-Defined Measurement System for Deep Learning 3

Deepflow: A Software-Defined Measurement System for Deep Lea...

引用

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Lakineni, Prasanna Kumar Kumar, Saurabh Modi, Sanjay Joshi, Kapil Mareeskannan, V. Lande, Jayapal Gitam University Gitam School of Technology Department of Cse Visakhapatnam India Invertis University Invertis Institute of Computer Applications Bareilly India Lovely Professional University Phagwara India Uttaranchal University Uttaranchal Institute of Technology India St. Martin's Engineering College Dept. of Cse Telangana Secunderabad India Sr University School of Computer Science and Artificial Intelligence Telangana Warangal India

ISBN: (纸本)9798350399264

Delivering perfectly alright real-time traffic information is crucial for managing a wide range of networks, particularly vehicular communications, anomaly analysis, networking accounting, and available bandwidth. Application networking might be able to give fine-grained evaluation by offering details for each sent rules of just an Open circulation switching. Providing absolutely adequate real-time traffic information in hardware switches also poses serious problems because of the size constraints of TCAMs that can only accommodate a minimal number of rules in contrast to the number of current fluxes in the networks. Inside this editorial, we initiate Intense Flow going, a scheme for modular app assessing that's also premised on an efficient method that a) flexibly senses the channel's highest traffic references and locations prefixes, b) collects coarse-grained stream size readings for less energetic identifiers and perfectly alright metrics for the more engaged users;c) includes historical metrics to coach a cloud-based a profound learners model that has the potential to create short forecasts anytime precise f Due to the lack of the need for additional flow sampling methods that compromise accuracy, a large increase in the number of totally acceptable flows that may be recorded is now possible.. Deep Flowing can provide incredibly high accuracy for estimating flow quantities at various hierarchy levels, according to a rigorous experimental analysis using a prototype versions and actual networking signals. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Design of a Respiration Imitator for a Breathable Soft Robot 19

Design of a Respiration Imitator for a Breathable Soft Robot

引用

19th International Conference on Electrical engineering/Electronics, computer, Telecommunications and Information technology, ECTI-CON 2022

作者： Kitmuti, Tanapon Sukvichai, Kanjanapan Hasegawa, Shoichi Intarapanich, Apichart Kasetsart University Dept. of Electrical Engineering Bangkok Thailand Tokyo Institute of Technology Precision and Intelligence Laboratory Tokyo Japan National Science and Technology Development Agency National Electronics and Computer Technology Center Phatumthani Thailand

ISBN: (纸本)9781665485845

Insomnia affected human productivity and cause long term health problems. Sleeplessness mostly cause by stress especially in adults. The synchronized breathing between two human or between human and animal could reduce stress. But having a real animal was impractical in many situations, thus, the soft animal robot could be developed to be a human companion. In this research, the soft-stuffed breathable doll was introduced. Robot respiration imitator was designed to mimic the real breathing mechanism by using artificial ribs and spine created from 3D materials. The materials were selected using the flexibility and rigidity properties from simulations, by considering the several 3D printable materials. Robot ribs were created from TPFE material while the imitator core was constructed from ABS material. The Maxon DC motor was used as the imitator actuator in order to crate sophisticate breathing motion. The magnetic encoder was attached to the motor for a precise control. The repository imitator was experimented before and after installed into the soft bear doll skin. The cushion was wrapped around the imitator for safety and good feeling when the robot was hugged. The experiments showed that the designed repository system worked properly for desired motions. © 2022 IEEE.

关键词： Animals

来源：评论

学校读者我要写书评

暂无评论

Wheat Disease Severity Assessment Using Federated Learning CNNs for Agriculture Transformation

Wheat Disease Severity Assessment Using Federated Learning C...

引用

Technological Advancements in Computational sciences (ICTACS), International Conference on

作者： Harshit Narang Rishabh Saklani Karan Purohit Purushottam Das Bharat Bhushan Sagar Manisha Manjul Computer Science and Engineering Graphic Era Hill University Dehradun India Computer Science and Engineering Birla Institute of Technology Mesra Ranchi India Dept. Of Computer Science and Engineering DSEU G B Pant Okhla Campus I New Delhi

In order to stop the spread and improve the agricultural productivity it is important to rightly detect and assess infection of wheat. The research's goal is to assess the seriousness of wheat diseases using CNN and collaborative learning. In this plants of wheat having 5 different diseases namely leaf rust, fusarium head blight, wheat stripe mosaic virus, powdery mildew and septoria leaf blotch are photographed. The model has been trained via federated learning that enables several devices with the capability to simultaneously train the machine learning model while maintaining the data privacy. The results displayed that CNN with federated learning is capable of predicting the seriousness of various wheat illnesses accurately with an average accuracy of 0.85. This enables the farmers and specialists to take appropriate measures to avoid disease spread and boost farming productivity. The results of the study demonstrate how cooperative learning works. CNN is an option to improve agricultural productivity, halt the spread of infections, and assess the seriousness of wheat problems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

IoT Security Detection and Evaluation for Smart Cyber Infrastructures Using LSTMs with Attention Mechanism 3

IoT Security Detection and Evaluation for Smart Cyber Infras...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Pillai, Sanjaikanth E Vadakkethil Somanathan Polimetla, Kiran Prakash, Chidurala Sai Pareek, Piyush Kumar Pawar, Priyanka Pramod School Of Electrical Engineering And Computer Science University Of North Dakota Grand Forks United States Adobe Inc. Dept. Of Information Technology AustinTX United States Sr University Department Of Electrical And Electronics Engineering Warangal India Nitte Meenakshi Institute Of Technology Department Of Aiml And Ipr Cell Bengaluru India University Of The Cumberlands Department Of Information Technology WilliamsburgKY United States

ISBN: (纸本)9798350318609

A computer network may be impacted by malware, computer viruses, and other hostile attacks. One of the most important elements of network security as an active defence technology is Intrusion Detection System (IDS). Issues with traditional intrusion detection systems include low detection effectiveness, inaccurate results, and an inability to handle new types of intrusions. This paper implemented a deep LSTMs with attention mechanism approach for IDS. The proposed technique is determined on Bot-IoT dataset, and z-score normalization is performed to normalize data. Information Gain (IG) is utilized to choose the features. A deep LSTMs with attention mechanism is used to effectively identify and categorize IDS effectively. The IG-deep LSTMs with attention mechanism achieves better accuracy using of 99.70% and 99.60% in NSL-KDD and CIC-IDS2017 datasets respectively. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：