检索结果-内蒙古大学图书馆

9th International Conference on Advanced Computing and Communication Systems, ICACCS 2023

作者： Persia Abishal, B. Juliet, Sujitha Karunya Institute of Technology and Sciences Department of Computer Science and Engineering TamilNadu India

ISBN: (纸本)9798350397376

Along with humans, birds lead lovely lives and are amazing creatures. One of the signs of climatic change is birds. From mid-level consumers to top predators, birds play a significant role in all trophic levels. Currently, extinction threatens many of these bird species. Naturally, each bird is unique in terms of its traits as well as its physical attributes, including shape, size, beak, feathers, silhouette, and others. As opposed to audio-based classification, bird photos are particularly useful in identifying species. By far, the most comfortable method for humans to identify birds is by visual classification. One of the crucial components of image categorization is the dataset of birds, which has been gathered. From the input image, the features are retrieved, and then classification is performed. Both regression and classification are performed using the Random Forest method. To create autographs using tensor flow, the input image is first transformed to grayscale and then to matrix format. As a consequence, the characteristics of the provided bird image are extracted, the bird's name is determined, and the bird's origin is also shown. © 2023 IEEE.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

EEG evoked automated emotion recognition using deep convolutional neural network 5

EEG evoked automated emotion recognition using deep convolut...

引用

5th IEEE International Conference on Electrical, computer and Communication Technologies, ICECCT 2023

作者： Abgeena, Abgeena Garg, Shruti Birla Institute of Technology Mesra Department of Computer Science and Engineering Ranchi India

ISBN: (纸本)9781665493604

As life continues to change in the digital era, it is crucial to perceive a person's emotional state. Affective computing is receiving more attention with the increase in the human-computer interface (HCI). Human emotion recognition employing electroen-cephalogram (EEG) signals has been studied to obtain a person's emotional status for different stimuli. However, it is difficult to identify clear patterns in EEG signals because they have low electrical impulses and are highly sensitive to noise. A deep convolutional neural network (DCNN) was employed in the present study to recognize emotions in EEG signals. For this purpose, a publicly available dataset, DREAMER, was utilized in this study to assess the applicability of the model for emotion classification. The dataset consisted of three-dimensional emotions, that is, valence, arousal, and dominance (VAD). 2D emotions arousal and valence were the most-recognized emotions in existing research. The present study identified the 3D emotions present in the above-mentioned dataset. In this study, raw EEG signals from the DREAMER dataset were pre-processed. Subsequently, three EEG rhythms, theta, alpha, and beta, were extracted using a bandpass filter. The power spectral density (PSD) was computed using fast Fourier transform (FFT) in the feature extraction. Finally, a 1D CNN model is applied to the classification of emotions. In addition, the performance of the proposed model was compared with two machine learning (ML) classifiers: random forest (RF) and extreme Gradient Boosting (XGBoost) classifiers. The highest accuracy (ACC) of 97.6% was obtained using the proposed model in the dominance dimension. The working principles were compared and discussed to determine the suitability of the model for emotion recognition applications. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Bias Mitigation in News Recommender Systems Using Preference Correction 7

Bias Mitigation in News Recommender Systems Using Preference...

引用

2023 7th International Conference On Computing, Communication, Control And Automation, ICCUBEA 2023

作者： Shinde, Shilpa Gaikwad, Mrunalini Ansari, Hamza Kale, Purvaja Lunawat, Smital Ramrao Adik Institute of Technology University of Mumbai Department of Computer Engineering India

ISBN: (纸本)9798350304268

This paper presents a novel approach for mitigating biases in news recommendation systems while also incorporating a user's personal preferences to provide a personalised recommendations. The proposed hybrid content and collaborative-based filtering system ranks news categories according to weights based on user history, resulting in a recommendation system that recommends news articles from a purely unbiased perspective. The method of 'preference correction' is incorporated to further recommend articles that the user will also prefer to read, improving the overall user experience. This approach can be applied to any news dataset that collects user impressions and has the potential to enhance awareness among readers and burst filter bubbles. © 2023 IEEE.

关键词： collaborative based recommendation content-based recommendation cosine similarity hybrid ensemble voting

来源：评论

学校读者我要写书评

暂无评论

Outlier detection in maize field using Isolation Forest: A one-class classifier 1

Outlier detection in maize field using Isolation Forest: A o...

引用

1st IEEE International Conference on Networking and Communications, ICNWC 2023

作者： Michael, J Justina Thenmozhi, M. SRM Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350336009

In agriculture, manual weed identification remains a challenge for farmers and agriculturalists. Recent technologies address the problem of weeds through several methods among which outlier detection is one powerful technique. Outlier detection is an effective weed identification method because it builds the model only by training the positive samples, hence known as one-class classification (OCC). In the context of agriculture, all crops except the target crop are considered to be weeds. This makes OCC a suitable method to identify weeds. In this work, we build OCC-IF-WD (One-Class Classification using Isolation Forest for Weed Detection) model that treats the target class as an inlier and all other classes as outliers. To train this model, an original dataset from Kaggle is used. Isolation Forest, which is a one-class classifier was used to build the model. OCC-IFWD recognizes maize as an inlier and all its associated weeds as outliers. The model was trained with 1082 images. The model was tested against various categories of outliers to examine its performance level. The results show the highest accuracy of 90.2% when the model is tested to differentiate between maize (inlier) and blackgrass (outlier). Also, a precision of 87%, recall of 94%, and Fl-score of 91% were recorded from the model. © 2023 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Design and Development of a Mobile-Based Data Acquisition System for Aerial Bridge Inspection 15

Design and Development of a Mobile-Based Data Acquisition Sy...

引用

15th IEEE International Conference on Humanoid, Nanotechnology, Information technology, Communication and Control, Environment, and Management, HNICEM 2023

作者： Himongala, Ryan P. Aleluya, Earl Ryan M. Clar, Steve E. Pao, Jeanette C. Alagon, Francis Jann A. Salaan, Carl John O. Lavilles, Rabby Q. College of Computer Studies Department of Computer Applications Philippines College of Engineering Department of Computer Engineering and Mechatronics Philippines College of Engineering Department of Electrical Engineering Philippines Graduate School of Engineering Philippines College of Computer Studies Mindanao State University - Iligan Institute of Technology Department of Information Technology Iligan City9200 Philippines

ISBN: (纸本)9798350381177

Infrastructures such as bridges are ubiquitous in today's world, but over time, corrosion, continuous vibrations, heavy loads, natural disasters, and aging have actively weakened their structural integrity. Hence, it is crucial to periodically assess the bridge's condition to maintain its structural soundness. Nevertheless, conventional bridge inspection techniques involve inspectors to visually assess a bridge's condition and manually capture images of its defects. UAVs for bridge inspections typically improve the conventional approach. This method provides a visual system by mounting a camera on the UAV equipped with a software application dedicated to data acquisition. However, the application operates primarily on desktop computers or laptops while incompatible with smartphones and tablets, limiting its portability and making it inconvenient for inspectors. In this study, the researchers developed an application for mobile devices to further improve data acquisition. The application is designed to display a real-time video feed from the shelled UAV, capture visual data of bridge defects, and allow users to review the data after the inspection. The researchers tested and evaluated the application's performance regarding its functionality. Results show that the application has successfully improved the portability and efficiency of the inspection process, achieving its intended features and functionalities while adhering to the requirements. © 2023 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Cross-Lingual Speaker Identification for Indian Languages

Cross-Lingual Speaker Identification for Indian Languages

引用

2023 International Conference Recent Advances in Natural Language Processing: Large Language Models for Natural Language Processing, RANLP 2023

作者： Rizvi, Amaan Jamatia, Anupam Rudrapal, Dwijen Chakma, Kunal Gambäck, Björn Department of Computer Science and Engineering National Institute of Technology Agartala Tripura India Department of Computer Science Norwegian University of Science and Technology Trondheim Norway

ISBN: (纸本)9789544520922

The paper introduces a cross-lingual speaker identification system for Indian languages, utilising a Long Short-Term Memory dense neural network (LSTM-DNN). The system was trained on audio recordings in English and evaluated on data from Hindi, Kannada, Malayalam, Tamil, and Telugu, with a view to how factors such as phonetic similarity and native accent affect performance. The model was fed with MFCC (mel-frequency cepstral coefficient) features extracted from the audio file. For comparison, the corresponding melspectrogram images were also used as input to a ResNet-50 model, while the raw audio was used to train a Siamese network. The LSTM-DNN model outperformed the other two models as well as two more traditional baseline speaker identification models, showing that deep learning models are superior to probabilistic models for capturing low-level speech features and learning speaker characteristics. © 2023 Incoma Ltd. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

An Early Recommendation Tool to Enhance Medicinal Plant Growth based on GIS and Soil Data

An Early Recommendation Tool to Enhance Medicinal Plant Grow...

引用

2023 International Conference on computer, Electronics and Electrical engineering and their Applications, IC2E3 2023

作者： Muskan, Syeda Roopashree, S. Abhina, B. Jagruthi, G. Challa, Suryateja Rv Institute of Technology and Management Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350338003

Ayurvedic medicinal plants are in the spotlight, solving the major problem which is being arisen in the modern world. Ayurvedic plants are acquiring great attention in the prescription field owing to having fewer deadly effects on human life and being much less expensive than chemical-based medicines. Based on the available statistics many scientists have shown plenty of interest in the research of recognizing and nurturing medicinal plants. The serious concern is the extension of medicinal plants affecting the life of the needy. In this paper, a novel method is proposed to identify the geographical location and the best suitable soil type of the medicinal plant species in the region of Karnataka, India. The work targets on few vulnerable plants and employs the random forest algorithm (decision tree algorithm) for the recommendation of the medicinal plants based on the soil and GIS data. Hence, an appropriate and easy access solution for the real-time information on the Ayurvedic herbs of Karnataka. The expected outcome of the system is a recommendation tool to grow, conserve and enhance the knowledge of medicinal plants by using the decision tree algorithm, revealing the vital details of herbs such as conservation status, soil type, region name, geo-location and climate condition for the growth of the medicinal plants to help its stakeholders. The system helps to preserve the ancient and traditional medicinal knowledge by identifying the medicinal plants using decision tree based predictive model. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Lightweight and Homomorphic Security Protocols for IoT 18th

Lightweight and Homomorphic Security Protocols for IoT

引用

18th International Conference on Data Science and Artificial Intelligence, ICDSAI 2022

作者： Singh, Ishaan Jain, Aakarshee Dhody, Ikjot Singh Chandavarkar, B.R. Department of Computer Science and Engineering National Institute of Technology Karnataka Surathkal India

ISBN: (纸本)9783031161773

The rise in usage of IoT devices for data collection in various fields has been astronomical in recent times. There has been an increased requirement to process the collected data on various cloud providers as IoT devices are compute-constrained. However, online data processing presents a substantial security challenge, especially in sensitive data, such as finance and medicine. The motivation behind this chapter comes from the observation that the encryption algorithms used for IoT devices need to be lightweight because IoT devices are not capable of heavy computation and the algorithm must be homomorphic. This is important because when the encrypted data moves from the device’s private environment to the public network, the data integrity is a major factor for such sensors and measurement devices. In this way, the data never needs to be in its decrypted form outside the organization’s ecosystem. This chapter aims to first present the limitations of IoT devices in the context of IoT networks. Then, the chapter analyses some of the most popular security protocols for IoT networks and subsequently understands the need for lightweight and homomorphic encryption. Then, the chapter presents and compares the most widely used lightweight and homomorphic algorithms/schemes, finally presenting the observations and conclusions based on the study. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Based Improved Phishing Detection using Adversarial Auto Encoder

Machine Learning Based Improved Phishing Detection using Adv...

引用

2023 International Conference on System, Computation, Automation and Networking, ICSCAN 2023

作者： Balaji, S. Sathishkumar, R. Sharmila, G. Arikaran, N. Nivas, K. Dhamotharan, S. Manakula Vinayagar Institute of Technology Department of Computer Science and Engineering Puducherry India

ISBN: (纸本)9798350315127

Phishing scams are frequently used by malicious actors to get login credentials from unsuspecting users. One method for detecting phishing is machine learning. Despite the fact that the accuracy of machine learning algorithms is mostly determined by the training data, there isn't much easily accessible attack data. We present a method for enhancing the datasets used by machine learning algorithms. We create samples that resemble phishing websites using an Adversarial Auto Encoder (AAE) and offer metrics to judge the effectiveness of the samples. We compare these samples to models created from actual data. Some of the created samples could be impossible for the current model to recognize. After that, training is done with the remaining samples. Improved levels of accuracy and reliability are provided by the upgraded machine learning models. In other words, phishing detection is improved during model construction by merging data from real phishing sites with AAE fake data. © 2023 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Diabetes Estimation Through Data Mining Using Optimization, Clustering, and Secure Cloud Storage Strategies

引用

SN computer Science 2024年第6期5卷 781页

作者： Gupta, Shyam S. Pandey, Tushar Kumar Raju, Vadali Pitchi Shrivastava, Rajeev Pandey, Rajeev Nigam, Ankita Roy, Vandana Department of Computer Science and Engineering Amity School of Engineering and Technology (ASET) Amity University College of Community Science Central Agricultural University Indur Institute of Engineering & amp Technology Princeton Institute of Engineering & amp Technology for Women Hyderabad DoCSE UIT-RGPV Department of CSE Princeton Institute of Engineering and Technology for Women Hyderabad Department of EC Gyan Ganga Institute of Technology and Sciences

Asian Indians face a unique risk for type 2 diabetes, with earlier onset and diagnosis at lower BMIs than other populations. Their susceptibility to diabetes-related health risks is higher compared to white populations. India struggles with low public awareness, a shortage of healthcare professionals, and limited treatment accessibility. Innovative strategies using available technological resources could significantly improve diabetes management in India. These challenges, common in developing countries, suggest that insights from India’s experience could benefit global diabetes management. This study aims to develop a hybrid model for predicting type 2 diabetes mellitus (T2-DM) to enhance awareness and preventive strategies. Using the Pima Indian Diabetes Dataset, the model’s effectiveness is validated through various performance metrics. The Fuzzy C-Means (FCM) clustering method is introduced, outperforming traditional models by creating more cohesive clusters with fewer variables. To enhance FCM's effectiveness, the Particle Swarm Optimization (PSO) technique is integrated, preserving FCM's strengths while improving efficiency. The hybrid model's sensitivity is 5.85% higher than K-Means + C4.5, and specificity is 2.79% higher. The proposed model achieves greater accuracy (96.58%) than previous methods. This approach aims to improve diabetes care in India and offers a model adaptable worldwide, addressing a critical global health challenge. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： BMI Data mining Diabetic retinopathy FCM PSO T1-DM T2DM

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：