检索结果-内蒙古大学图书馆

2024 IEEE International Conference on Computing, Applications and Systems, COMPAS 2024

作者： Afroj, Maharin Jahan, Israt Islam, Md Polash Saifur Rahman, Md. Bangladesh University of Business and Technology Dept. of Computer Science and Engineering Dhaka Bangladesh Stockholm University Dept. of Computer and Systems Sciences Stockholm Sweden

ISBN: (纸本)9798331529765

The crucial field of fruit classification in computer vision and deep learning brings about breakthroughs that have broad applications in the retail and agricultural industries. By automating the identification and sorting of various fruit types, these technologies enhance efficiency, accuracy, and scalability, benefiting processes from farm production to market distribution. The integration of sophisticated algorithms and neural networks not only improves the speed and reliability of fruit classification but also offers the potential for real-time quality control and inventory management, revolutionizing traditional methods and paving the way for more innovative, data-driven approaches in these sectors. This study introduces LightNN, a novel and effective paradigm with a lightweight architecture that tackles the complex problems related to computational efficiency. Combining a small classifier with a simplified feature extractor, LightNN achieves the ideal balance between simplicity and accuracy. The feature extractor is capable of extracting hierarchical features from RGB images by using convolutional layers with ReLU activations and max-pooling procedures. The flattened output is then processed by the classifier, which consists of fully connected layers with ReLU activations and dropout regularisation. Remarkably, LightNN, with just 298,835 parameters, manages to get a respectable 96.37% test accuracy in fruit categorization tasks. The results highlight LightNN's promise as an effective and efficient fruit classifying method, particularly in situations with constrained computational resources. © 2024 IEEE.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

BanglaGPT: A Generative Pretrained Transformer-Based Model for Bangla Language 2

BanglaGPT: A Generative Pretrained Transformer-Based Model f...

引用

2nd International Conference on Information and Communication Technology for Sustainable Development, ICICT4SD 2023

作者： Salim, Md. Shahidul Murad, Hasan Das, Dola Ahmed, Faisal Khulna University of Engineering Technology Dept. of Computer Science and Engineering Khulna9203 Bangladesh Chattogram University of Engineering Technology Dept. of Computer Science and Engineering Chattogram4349 Bangladesh

ISBN: (纸本)9798350358667

Natural Language Processing (NLP) has entered a new era with the advent of pre-trained language models, paving the way for constructing robust language models. Pretrained transformer-based models such as GPT-2 have become prevalent due to their cutting-edge efficiency. However, these approaches rely heavily on resource-intensive languages, forcing other languages to adopt multilingual frameworks (mGPT). The mGPT model could perform better for low-resource languages such as Bangla because the model has been trained on a diverse dataset spanning multiple languages. Recent studies show that the language-specific GPT model outperforms the multilingual mGPT model. In this research, we have proposed a pretrained monolingual GPT model called BanglaGPT using the objective of causal language modeling (CLM). Due to the lack of available large datasets for NLP tasks in Bangla, we have created a Bangla language model dataset called BanglaCLM using a 26.24 GB Bangla corpus scraped from several public websites. We have used a subword-based tokenization algorithm named Byte-Pair Encoding (BPE) for Bangla and finally trained the Bangla-GPT2 model from scratch using the BanglaCLM dataset. Our pretrained BanglaGPT provides state-of-the-art performance for Bangla text generation with a perplexity score of 2.86 and a loss score of 0.45 on the test set. © 2023 IEEE.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

LeXNet++: Layer-wise eXplainable ResUNet++ framework for segmentation of colorectal polyp cancer images

引用

Neural Computing and Applications 2025年第1期37卷 213-229页

作者： Das, Surajit Khan, Soumya Suvra Sengupta, Diganta Debashis, De Dept. of Information Technology Meghnad Saha Institute of Technology Behind Urbana Complex Near Ruby General Hospital Anandapur Rd Uchhepota Kolkata700150 India Dept. of Computer Science & Engineering Meghnad Saha Institute of Technology Behind Urbana Complex Near Ruby General Hospital Anandapur Rd Uchhepota Kolkata700150 India Dept. of Computer Science & Engineering Heritage Institute of Technology Chowbaga Road West Bengal Anandapur Kolkata700107 India Dept. of Computer Science & Engineering Maulana Abul Kalam Azad University of Technology West Bengal NH-12 Simhat Haringhata West Bengal Nadia741249 India

Colorectal polyps are benign lesions that develop in the colon and can progress to cancer if left untreated. Clinical observations from medical images are often preferred over computational results due to the lack of trust in the machine learning models, thereby posing serious challenge for the explainability of the results. In order to computationally diagnose colorectal polyps from cancerous images and explain the results, we propose a Layer-wise eXplainable ResUNet++ (LeXNet++) framework for segmentation of the cancerous images, followed by layer-wise explanation of the results. We utilize a publicly accessible dataset that contains of 612 raw images with a resolution of 256×256×3 and an additional 612 clinically annotated and labeled images with a resolution of 256×256×1, which includes the infected region. The LeXNet++ framework comprises of three components—encoder, decoder and the bridge. The encoder and the decoder components each comprise of four layers. Each of the four layers in the encoder and the decoder comprises of 14 and 11 internal sub-layers, respectively. Among the sub-layers of the encoder and the decoder, there are three 3×3 convolutional layers with an additional 3×3 convolution-transpose layer in the decoder. The output of each of the sub-layers has been explained through heatmap generation after each iteration which have been further explained. The encoder and the decoder are connected by the bridge which comprises of three sub-layers. The results obtained from these three sub-layers have also been explained to inculcate trust in the findings. In this study, we have used three models to segment the images, namely UNet, ResUNet, and proposed LeXNet++. LeXNet++ exhibited the best result among the three models in terms of performance;hence, only LeXNet++ was explained layer-wise. Apart from explanation of the results fetched in this study, the performance of the proposed explainable model has been observed to be 2% greater than the existing poly

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Smart City Surveillance: Survey on Current Status and Future Trends 14

Smart City Surveillance: Survey on Current Status and Future...

引用

14th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2023

作者： Neyaz, Hera Paul, Hrituparna Srivastava, Anima Singh, Shiksha Dept. of Computer Science and Engineering Shambhunath Institute of Engineering and Technology India

This paper presents a comprehensive survey on surveillance and security aspects of a smart city. Multiple dimensions of a smart city surveillance system have been discussed. The current trends and methodologies are thoroughly researched and presented. The algorithms of novel methods are reviewed along with analytics and methodologies. Impact of XAI in the smart city surveillance is discussed. Advantages and disadvantages of current infrastructures have been included in the broad literature survey. Lastly, the challenges and future trends are conferred to. © Grenze Scientific Society, 2023.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Evaluating Machine Learning Methods for Bangla Text Emotion Analysis

Evaluating Machine Learning Methods for Bangla Text Emotion ...

引用

2024 Asia Pacific Conference on Innovation in Technology, APCIT 2024

作者： Akter, Tahmina Akter, Mst. Sharmin Mahmud, Tanjim Islam, Dilshad Hossain, Mohammad Shahadat Andersson, Karl Port City International University Dept. of Computer Science and Engineering Chittagong Bangladesh Rangamati Science and Technology University Dept. of Computer Science and Engineering Rangamati4500 Bangladesh Chattogram Veterinary and Animal Sciences University Dept. of Physical and Mathematical Sciences Bangladesh University of Chittagong Dept. of Computer Science and Engineering Chittagong4331 Bangladesh Luleå University of Technology Cybersecurity Laboratory Luleå97187 Sweden

ISBN: (纸本)9798350361537

Text-based emotion identification goes beyond simple sentiment analysis by capturing emotions in a more nuanced way, akin to shades of gray rather than just positive or negative sentiments. This paper details our experiments with emotion analysis on Bangla text. We collected a corpus of user comments from various social media groups discussing socioeconomic and political topics to identify six emotions: sadness, disgust, surprise, fear, anger, and joy. We evaluated the performance of four widely used machine learning algorithms - RF, DT, k-NN, and SVM - alongside three popular deep learning algorithms - CNNs, LSTM, and Transformer Learning - using TF-IDF feature extraction and word embedding techniques. The results showed that among the machine learning algorithms, DT, RF, k-NN, and SVM achieved accuracy scores of 82%, 84%, 73%, and 83%, respectively. In contrast, the deep learning models CNN and LSTM both achieved higher performance with an accuracy of 85% and 86% respectively. These findings highlight the effectiveness of traditional ML and DL approaches in detecting emotions from Bangla social media texts, indicating significant potential for further advancements in this area. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Smart Attendance Management System Using Face Recognition 1

Smart Attendance Management System Using Face Recognition

引用

1st International Conference on Advances in computer science, Electrical, Electronics, and Communication Technologies, CE2CT 2025

作者： Rawat, Shivam Goyal, Shweta Rawat, Nikita Graphic Era Hill University Dept. Computer Science & Engineering Dehradun India Graphic Era deemed to be University Dept. of Electrical Engineering Dehradun India

ISBN: (纸本)9798331518578

Managing attendance in educational institutions is often a time-consuming and error-prone task, with traditional methods like roll calls or sign-in sheets being inefficient and susceptible to proxy attendance. This paper presents a Smart Attendance Management System that leverages facial recognition technology to automate the attendance process. By using cameras to capture images of students, the system recognizes their faces and marks their attendance in real time. Developed in Python, the system employs the K-Nearest Neighbours (KNN) algorithm for accurate face recognition. Once attendance is recorded, it is stored in a CSV file and can be visualized using the flask web application. The proposed system significantly reduces manual effort, ensures accuracy, and operates efficiently in real-time environments. © 2025 IEEE.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

DeepLeaf-Attentive: Integrating Attention Mechanisms for Crop Leaf Disease Identification 26

DeepLeaf-Attentive: Integrating Attention Mechanisms for Cro...

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Ahmed, Tanvir Mou, Farzana Sharmin Engineering Dhaka University of Engineering & Technology Dept. of Computer Science Dhaka Gazipur Bangladesh University of Birmingham Dept. of Computer Science Birmingham United Kingdom

ISBN: (纸本)9798350359015

Crop leaf diseases have a detrimental impact on agricultural production. Visual inspection by organic farmers for disease detection is time-consuming and ineffective. To address this, we propose DeepLeaf-Attentive, a novel deep learning model for classifying crop leaf diseases. It combines MobileNet architecture with additional layers and attention mechanism. It is trained on a dataset of 30,000 images including data augmentation representing 60 classes with 500 images per class. The model achieves outstanding performance, with 97.21% accuracy, 97.72% precision, 97.43% recall, 97.49% F1-score and 18.0 ms inference time. Comparative evaluations against state-of-the-art approaches demonstrate the superiority of DeepLeaf-Attentive in crop leaf disease classification. By providing a reliable and efficient tool, our model will empower farmers to accurately identify and categorize various crop leaf diseases, facilitating informed decision-making and enabling the implementation of targeted and timely treatment strategies. The adoption of DeepLeaf-Attentive can significantly improve disease management practices in agriculture, leading to enhanced crop yields, reduced economic losses, and sustainable farming practices. By revolutionizing crop leaf disease identification, our research contributes to the advancement of precision agriculture, benefiting farmers and supporting global food security. © 2023 IEEE.

关键词： Attention Mechanisms Crop Leaf Disease Identification Deep Learning DeepLeaf-Attentive MobileNet Transfer Learning

来源：评论

学校读者我要写书评

暂无评论

Ink Detection from Carbonized Herculaneum Papyri using Deep Learning 26

Ink Detection from Carbonized Herculaneum Papyri using Deep ...

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Mou, Farzana Sharmin Ahmed, Tanvir University of Birmingham Dept. of Computer Science Birmingham United Kingdom Dhaka University of Engineering & Technology Gazipur Dept. of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798350359015

A Roman villa in the town of Herculaneum, next to Pompeii, housed a library with thousands of ancient Greek and Roman scrolls. The eruption of Mount Vesuvius buried this villa approximately 2000 years old ago which has been discovered. The scrolls can no longer be opened without breaking them because they were carbonized by the heat of the volcano. Since Herculaneum ink is carbon-based, it affords no X-ray contrast against the underlying carbon-based papyrus. Some detached papyrus fragments that can be read under infrared light can be used as ground truth data for a machine learning model that could identify otherwise undetectable ink from X-rays. The process of ink detection involves locating the inked portions of the papyrus using data from a 3D X-ray scan of the papyrus surface. The model has been trained by selecting a pixel from the binary label picture and sampling a subvolume from the surface volume at the same coordinates. In order to update the model weights, then backpropagate the known label data. Once trained, the model can be used to predict the appearance of a label picture from diverse input data. Three distinct models, namely U-Net, Attention U-Net, and a Pretrained Autoencoder with Attention U-Net, have been applied. Then, utilizing those three models, ensemble approaches have been employed (average, voting, and weighted average) to choose the optimum outcome. The best dice score of 0.766 has been achieved by the average ensembling technique. This project shows how machine learning can detect ink in 3D scans and decipher carbonized parchment contents. © 2023 IEEE.

关键词： attention mechanism computer vision ensemble technique ink detection pretrained autoencoder unet

来源：评论

学校读者我要写书评

暂无评论

Unveiling DNS Spoofing Vulnerabilities: An Ethical Examination Within Local Area Networks 26

Unveiling DNS Spoofing Vulnerabilities: An Ethical Examinati...

引用

26th International Conference on computer and Information Technology, ICCIT 2023

作者： Jony, Asaduzzaman Islam, Muhammad Nazrul Sarker, Iqbal H. Dept. of Computer Science and Engineering Dhaka Bangladesh Dept. of Computer Science and Engineering Dhaka Bangladesh Edith Cowan University PerthWA-6027 Australia

ISBN: (纸本)9798350359015

Nowadays DNS spoofing has become one of the terrible attacks which is triggered by exploiting IP address conflict detection vulnerability on the DHCP server side. DHCP server running on latest operating systems can detect IP address conflict which makes proposed attack ineffective. On the other hand, DNS spoofing attack using server side DNS cache poisoning is very difficult and unfeasible task as the public DNS servers are very secured and deployed behind several security appliances. Again, DNS spoofing attack is initiated by poisoning the client's DNS cache, which is uncertain as it requires a malware to be installed in target user's computer. Therefore, the objective of this study is to introduce an innovative approach for ethically launching a DNS spoofing attack within a Local Area Network (LAN) for illustrating the vulnerabilities and security flaws of the DNS protocol. To achieve this objective, attacker introduces a rogue DHCP server in the LAN and forcefully redirects user's traffic to a malicious or rogue default gateway. Secondly, a python (scapy) based DNS spoofing engine is deployed in the rogue DHCP server that tampers the DNS responses replied by the DNS server. The scapy alters the IP address of legitimate website with an IP address of malicious or phishing website which is managed by the attacker and looks like legitimate website. As a result, compromised user is redirected to that identical looking phishing website and becomes victim of phishing attack. Finally, the effectiveness and validation of the proposed attack were demonstrated using the Kali Linux and multi-vendor network emulation software (EVE-NG). © 2023 IEEE.

关键词： DNS Spoofing Ethical Considerations LAN security Phishing Python Scapy Rogue DHCP Wireshark

来源：评论

学校读者我要写书评

暂无评论

The Effects of Selected Preferred Music on Perceived Emotions through Audiovisual Stimuli 9

The Effects of Selected Preferred Music on Perceived Emotion...

引用

9th IEEE/ACIS International Conference on Big Data, Cloud Computing, and Data science, BCD 2024

作者： Thaiwong, Thunrada Fukumoto, Makoto Graduate School of Computer Science and Engineering Fukuoka Institute of Technology Fukuoka Japan Fukuoka Institute of Technology Dept. of Computer Science and Engineering Fukuoka Japan

ISBN: (纸本)9798350394191

Music surrounds us, and there is no denying that music in visual media can shape and evoke emotions. Yet, understanding how musical preference influences emotions through audio and visual stimuli remains an important task. To address this task, we investigated the role of musical preference effect on perceived emotions induced through music and visual stimuli (i.e., animation), using a 7-point scale for valence-arousal ratings and physiological responses in electroencephalogram (EEG) band power. The perceived emotions are categorized into four states: happiness, calmness, fear, and sadness. One emotional state contains 4 sessions: (1) Preferred Music, (2) Unfamiliar Music, (3) Preferred Music+Animation, and (4) Unfamiliar Music+ Animation. Behavior-wise, the rating results showed that the presence of preferred music resulted in higher perceived valence ratings, particularly in happiness. However, no stimulus had a significant effect on perceived arousal ratings and satisfaction ratings. Physiologically, the EEG indexes showed that the presence of preferred music appears to affect an increase in alpha power across various emotions except sadness, whereas unfamiliar music seems to affect beta power, particularly in happiness and calmness. Overall, these findings supported that musical preference is an affective factor reflecting the levels of valence and alpha power in EEG. Nevertheless, our findings did not confirm a significant difference between only preferred music and combining it with animation. Interestingly, we also found that participants were more likely to be attracted to and perceive positive (i.e., happiness and calmness) emotions easily through preferred music and/or visual stimuli than negative (i.e., fear) emotions. © 2024 IEEE.

关键词： Animation

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：