检索结果-内蒙古大学图书馆

Electrical Power engineering, Communication and Computing Technology(ODICON), Odisha International Conference on

作者： Sumant Kumar Mohapatra Kaliprasanna Swain Puspanjali Mallik Sabita Mali Farida A. Ali Trident Academy of Technology Bhubaneswar Odisha Dept. of Computer Science Shailabala Women's Autonomous College Cuttack India Faculty of Engineering ITER SOA University Bhubaneswar India

ISBN: (数字)9798350354379

ISBN: (纸本)9798350354386

An imbalance in electrical signal flow among neurons causes epilepsy, a complex brain disease that affects other parts of the body and results in seizures. Researchers and neurologists have put their efforts into devising powerful electroencephalogram devices to address the importance of health issues. In this context, machine learning algorithms are used to accurately detect the presence of a seizure signal. This experiment uses the hybridization of two meta-heuristic optimization algorithms: the sparrow search algorithm and the sine cosine algorithm. To conduct the research, this experiment uses the publicly available CHB-MIT EEG dataset, and for feature extraction, it uses the discrete wavelet transform (DWT). ANOVA We use feature selection to identify similar groups. This study uses three classifiers: support vector machines (SVM), Adaptive Neuro Fuzzy Inference System (ANFIS), and Extreme Learning ANFIS (ELANFIS). We got 99.8% accuracy, 98.35% sensitivity, 99.02% specificity, 98% positive predictive value, and 1 for area-under-curve for SSA-SCA-DWT-ELANFIS. This shows that it works better than SSA-SCA-DWT-SVM, SSA-SCA-DWT-ANFIS, and other methods that are already out there. In the future, we can integrate this study with the Internet of Things (IoT).

关键词： Support vector machines Machine learning algorithms Accuracy Transforms Prediction algorithms Feature extraction Electroencephalography Discrete wavelet transforms Classification algorithms Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security: Federated Learning against Man-In-The-Middle Threats with Gradient Boosting Machines and LSTM

Enhancing Security: Federated Learning against Man-In-The-Mi...

引用

IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS)

作者： Suneeta Satpathy Pratik Kumar Swain Sachi Nandan Mohanty Santi Swarup Basa Centre for AI & ML SoA University Odisha India FET Sri Sri University Odisha India School of Computer Science and Engineering VIT-AP University Amaravati Andhra Pradesh India Dept. of Computer Science Maharaja Sriram Chandra Bhanjadeo University Baripada Odisha India

ISBN: (数字)9798350374285

ISBN: (纸本)9798350374292

Federated Learning (FL) can be preferred more in the cyber security community because it can enable training without sharing the actual training data when combined with different learning algorithms. Though these types of learning models maintain the privacy of the data by reducing the data centralization, it is vulnerable to cyber security threats like Man-In-The-Middle (MITM) attacks. The present paper makes an attempt to analyse the performance by integrating Gradient Boosting Machines (GBM) and Long Short-Term Memory (LSTM) with Principal Component Analysis (PCA) in a federated learning framework. Both the models are trained on a converted dataset using PCA that reduces the dimensionality of the data while maintaining its important values. The results indicated that the both models enhanced the confidentiality and integrity of the data against MITM attacks while FL-GBM performed better than FL-LSTM model in terms of accuracy and robustness in maintaining performance consistency across rounds of evaluations. This research further extends the current understanding of secure federated learning architectures and proposes a viable model for practical deployments in sensitive applications.

关键词： Training Federated learning Surveillance Training data Boosting Data models Security

来源：评论

学校读者我要写书评

暂无评论

Principles and Potentials of F5G: The Fifth Generation Fixed Network

Principles and Potentials of F5G: The Fifth Generation Fixed...

引用

Circuits, Power and Intelligent Systems (CCPIS), International Conference on

作者： Sudhir K. Routray Abhishek Javali KP Sharmila M. Pappa Mahesh K. Jha Susanta K. Sarangi Department of Computer Science and Engineering CMR University Bangalore India Department of Electronics and Communication Engineering CMR Institute of Technology Bangalore India Department of Electronics and Communication Engineering SoA (Deemed-to-be) University Bhubaneswar India

In general, 5G is understood to be the fifth generation of mobile communications. However, there is also a fifth generation of wired communications which is led by the optical fiber technologies. This technology too has several attractive features like the wireless mobile 5G. In this article, we present the basic concepts of Fifth Generation Fixed Network (F5G). We show its characteristics and explain how it is going to change the communication landscape. We present the key benefits of F5G and show the main motivations behind its development. There are several applications of F5G and many emerging applications are also being introduced every year. Therefore, this newly developed technology has a lot of commercial importance in the modern world. In addition to the above, F5G is going to be one of the main rivals of 5G in the fixed environment. It is expected that F5G will outperform all its contemporary access area technologies in the fixed domain in the next few years. In this article, we briefly present its applications and future economic prospects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Faster & Smoother Detection of Forest Fire Using YOLO v3

Faster & Smoother Detection of Forest Fire Using YOLO v3

引用

Machine Learning, computer Systems and Security (MLCSS), International Conference on

作者： Susmita Panda Adarsh Padhi Bhabani Shankar Rath Bishal Rout Kumar Supreet Mishra Department of Computer Science and Engineering Institute of Technical Education & Research SOA Deemed to be University Odisha India

The precise detection of fire in a virtual system, such as photos, movies, and live stream videos, is crucial for a variety of applications that use various methods. As the name suggests, fire detection can detect the spreading of the fire in the forest by any means, more precisely. To overcome the difficulties of such natural disasters as the Amazon fire or the great Australian bush fire, such scenarios were very devastating. We proposed a solution utilizing Machine Learning with the help of YOLO [4] which could get us out of this hefty situation by detecting fire as well as reporting in a generalized manner to spread the news of fire to the higher authorities or localities.

关键词： Deep learning Computational modeling Transfer learning Forestry Motion pictures Software Hardware

来源：评论

学校读者我要写书评

暂无评论

Hybrid grasshopper optimization algorithm with simulated annealing for feature selection using high dimensional dataset

Hybrid grasshopper optimization algorithm with simulated ann...

引用

Advanced Innovations in Smart Cities (ICAISC), International Conference on

作者： Bibhuprasad Sahu Jvr Ravindra Sachi Nandan Mohanty Amrutanshu Panigrahi Department of Artificial Intelligence and Data Science Vardhaman College of Engineering(Autonomous) Hyderabad India Department of Electronics & Communication Engineering Vardhaman College of Engineering(Autonomous) Hyderabad India School of Computer Science & Engineering(SCOPE) VIT-AP Amaravati Andhra Pradesh India Department of Computer Science & Engineering SOA (Deemed to be University) Bhubaneswar Odisha

In the era of machine learning, microarray data play a crucial role in identifying cancer diseases. The impact of redundant and noisy features degrades the learning model’s performance. It may also increase the computational cost. The curse of dimensionality is the major concern in the case of microarray datasets. To eliminate this issue, feature selection methods play an effective role. This study proposes a hybrid filter-wrapper feature selection model using mRMR_Plus as a filter and grasshopper optimization algorithm as a wrapper. In the first stage of the proposed model, a ranked base filter mRMR_Plus is used to identify the top-ranked features from the original dataset. Cross-operator embedded simulated annealing (SA) is adopted to basic grasshopper optimization to develop a new wrapper model. The proposed model was tested with different cancer datasets to recognize the best optimal features. The result of mRMR-Plus-GO-SA is compared with different existing approaches. From the result and the comparative study, it’s noteworthy to state that the new mRMR_Plus-GO-SA filter wrapper model performs far better as compared to its counterparts in terms of the number of features selected and accuracy.

关键词： Support vector machines Technological innovation Smart cities Computational modeling Simulated annealing Filtering algorithms Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Tomato Leaf Disease Detection using Neural Networks

Tomato Leaf Disease Detection using Neural Networks

引用

Machine Learning, computer Systems and Security (MLCSS), International Conference on

作者： Vemakoti Santosh Krishna Chaitanya Datti Rakesh Sachikanta Dash Bidush Kumar Sahoo Sasmita Padhy Mamata Nayak Computer Science and Engineering GIET University Gunupur Odisha Computer Science and Engineering GMR Institute Institute of Technology JNTU Kakinada Andhra Pradesh India Computer Science and Engineering GIET University Odisha India School of Computing Science and Engineering VIT Bhopal University Bhopal MP Computer Science and Engineering SOA University Bhubaneswar Odisha

Plants are a very important source of food worldwide. The diseases among them generate production and economic losses leading to a decrease in agricultural product quality and amount. Disease watching by hand is long and susceptible to mistakes. One of such plants is the Tomato plant, the foremost wide consumed vegetable in the Asian nation. Early illness detection is to scale back future losses. It is so crucial that a Convolutional Neural Network (CNN) with two convolutions and two max-pooling layers, together flattening layer followed by two totally connected layers is employed during this study in order to diagnose herbaceous plant diseases. Pictures of tomato leaves with 9 diseases and healthy samples were accustomed to ensure the findings. The images area unit metameric mistreatment image scaling, color threshold and flood filling techniques are used for findings. With our classification drawback mistreatment the notion of transfer learning. Within the tomato crop, nine of the foremost common leaf diseases and one healthy leaves were chosen for categorization. The projected model has a mean accuracy of 91.2 % for the 9 disorders and one healthy category.

关键词： Plant diseases Computational modeling Transfer learning Neural networks Crops Production Information filters

来源：评论

学校读者我要写书评

暂无评论

Sentiment analysis of reviews using Nature Inspired Algorithm

Sentiment analysis of reviews using Nature Inspired Algorith...

引用

Global Conference for Advancement in Technology (GCAT)

作者： Abinash Tripathy Utpal Chandra De Bibhuti Bhusan Dash Sudhansu Shekhar Patra Binod Kumar Pattanayak Trilok Nath Pandey School of Computer Applications KIIT Deemed to be University Bhubaneswar Odisha India Department of Computer Sc. & Engg ITER SOA Deemed to be University Bhubaneswar Odisha India School of Computer Science & Engineering Vellore Institute of Technology Chennai India

Social media now plays an important role is sharing the views or comments about a topic. These comments are available to the users for their processing and future decision making process. As the reviews contains mostly text or emojis, thus, these need to be processed properly to get meaningful information. Nature is always a source for information and knowledge. Many activities happens in the words, that help to classify the reviews or comments. In this paper, Genetic Algorithm (GA) is considered for processing the reviews. GA is based on the process of genetic evaluation. Different GA operations are implemented to get a better classification result. The reviews are processed using the proposed algorithms and finally, the confusion matrix is generated, which helps to generate the evaluation parameters to evaluate the results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine learning techniques used for the histopathological image analysis of oral cancer-a review

引用

Open Bioinformatics Journal 2020年第1期13卷 106-118页

作者： Panigrahi, Santisudha Swarnkar, Tripti Department of Computer Science and Engineering SOA Deemed to be University Bhubaneswar 751030 Odisha India Department of Computer Application SOA Deemed to be University Bhubaneswar 751030 Odisha India

Oral diseases are the 6th most revealed malignancy happening in head and neck regions found mainly in south Asian countries. It is the most common cancer with fourteen deaths in an hour on a yearly basis, as per the WHO oral cancer incidence in India. Due to the cost of tests, mistakes in the recognition procedure, and the enormous remaining task at hand of the cytopathologist, oral growths cannot be diagnosed promptly. This area is open to be looked into by biomedical analysts to identify it at an early stage. At present, with the advent of entire slide computerized scanners and tissue histopathology, there is a gigantic aggregation of advanced digital histopathological images, which has prompted the necessity for their analysis. A lot of computer aided analysis techniques have been developed by utilizing machine learning strategies for prediction and prognosis of cancer. In this review paper, first various steps of obtaining histopathological images, followed by the visualization and classification done by the doctors are discussed. As machine learning techniques are well known, in the second part of this review, the works done for histopathological image analysis as well as other oral datasets using these strategies for growth prognosis and anticipation are discussed. Comparing the pitfalls of machine learning and how it has overcome by deep learning mostly for image recognition tasks are also discussed subsequently. The third part of the manuscript describes how deep learning is beneficial and widely used in different cancer domains. Due to the remarkable growth of deep learning and wide applicability, it is best suited for the prognosis of oral disease. The aim of this review is to provide insight to the researchers opting to work for oral cancer by implementing deep learning and artificial neural networks. © 2020 Swarnkar & Panigrahi.

关键词： Convolutional neural network Cytopathologist Deep learning Histopathology Machine learning Oral cancer

来源：评论

学校读者我要写书评

暂无评论

Generating Higher Order Mutants using PSO with Levy Flight(LFPSO) Algorithm

Generating Higher Order Mutants using PSO with Levy Flight(L...

引用

Machine Learning, computer Systems and Security (MLCSS), International Conference on

作者： Subhasish Mohanty Jyotirmaya Mishra Sudhir Kumar Mohapatra Sachikanta Dash Sasmita Padhy Sameer Kumar Das Computer Science and Engineering GIET University Gunupur Odisha Faculty of Emerging Technologies Sri Sri University Odisha India School of Computing Science and Engineering VIT Bhopal University Bhopal MP Computer Science and Engineering SOA University Bhubaneswar Odisha

Nowadays, test data generation via a search based become popular, and mutation testing plays a very essential role by improving the efficiency of test data creation. In this research, LFPSO with Mutation Testing, a high-order mutation test data generating method, was presented, which was then implemented on large programs from the Software-artifact Infrastructure Repository (SIR). The suggested algorithm LFPSO is then compared against GA, as well as the most extensively used method for developing test data, CRO. For the majority of the benchmark programs, the results show that LFPSO outperforms GA and CRO in terms of computing efficiency.

关键词： Machine learning algorithms Filtering Machine learning C++ languages Benchmark testing computer performance C# languages

来源：评论

学校读者我要写书评

暂无评论

Unmanned Integrated Autonomous Vehicle: Swayambhu

Unmanned Integrated Autonomous Vehicle: Swayambhu

引用

Electrical Power engineering, Communication and Computing Technology(ODICON), Odisha International Conference on

作者： Ankit Anand Murthy Cherukuri Indu Sekhar Samanta Kunjabihari Swain Dept. of Electrical and Electronics Engineering NIST Institute of Science and Technology Berhampur India dept. of Computer Science and Engineering ITER SOA University Bhubaneswar India

ISBN: (纸本)9781665478403

Every human life is valuable. Soldiers are in charge of security at the country's borders. Many soldiers were killed as a result of terror strikes on the frontiers. With advancements in science and technology, Security systems have improved significantly. Robotics is one of the technologies that are now receiving significant attention. The development of autonomous decision-making robots' potential to kill terrorists is one of the most remarkable breakthroughs. These robots can operate at locations where humans cannot reach them. These bots can also execute self-exploiting actions without endangering the soldiers' lives. This autonomous vehicle is intelligent enough to detect buried landmines, bombs, and weaponry, pick bombs with its 6-axis hand and throw them away. The term “autonomous” refers to a system that can control itself and is controlled by the authorized deputed user. This autonomous vehicle has an embedded camera that sends video streams to the headquarters and can also detect suspicious behavior and respond appropriately. This article presents the design and working of an unmanned autonomous vehicle named “Swayambhu.”

关键词： Landmine detection Weapons Metals Wheels Detectors Streaming media Sensors

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：