检索结果-内蒙古大学图书馆

Attar: RRAM-based in-memory attention accelerator with software-hardware co-optimization

Science China(information sciences) 2025年第3期68卷 371-387页

作者： Bing LI Ying QI Ying WANG Yinhe HAN Information Engineering College Capital Normal University Research Center for Intelligent Computing Systems Institute of Computing TechnologyChinese Academy of Sciences

The attention mechanism has become a pivotal component in artificial intelligence, significantly enhancing the performance of deep learning applications. However, its quadratic computational complexity and intricate computations lead to substantial inefficiencies when processing long sequences. To address these challenges, we introduce Attar, a resistive random access memory(RRAM)-based in-memory accelerator designed to optimize attention mechanisms through software-hardware co-optimization. Attar leverages efficient Top-k pruning and quantization strategies to exploit the sparsity and redundancy of attention matrices, and incorporates an RRAM-based in-memory softmax engine by harnessing the versatility of the RRAM crossbar. Comprehensive evaluations demonstrate that Attar achieves a performance improvement of up to 4.88× and energy saving of 55.38% over previous computing-in-memory(CIM)-based accelerators across various models and datasets while maintaining comparable accuracy. This work underscores the potential of in-memory computing to enhance the efficiency of attention-based models without compromising their effectiveness.

关键词： RRAM computing-in-memory attention pruning quantization

来源：评论

学校读者我要写书评

暂无评论

A Knowledge-Based System of Ethno-Medicinal Plants in Lanao Del Sur for Treating Diseases 3

A Knowledge-Based System of Ethno-Medicinal Plants in Lanao ...

引用

3rd International Conference on Digital Transformation and Applications, ICDXA 2024

作者： MacAdaya, Muhammad Mubin M. Wade, Janice F. Mindanao State University Department of Information Sciences College of Information and Computing Sciences Marawi City Philippines Mindanao State University Department of Computing Sciences College of Information and Computing Sciences Marawi City Philippines

ISBN: (纸本)9798350373424

This paper presents a comprehensive exploration of the ethno-medicinal knowledge in Lanao del Sur, a region rich in biodiversity and culture. Focusing on the traditional uses of plants for therapeutic purposes, the study integrates indigenous knowledge with modern technology to develop a knowledge-based system for recommending ethno-medicinal plants to treat common diseases. Knowledge had been acquired from local people with expertise in ethnomedicinal practices;that acquired knowledge would be translated into rules that can be read by the rule engine;and after translating all the knowledge into rules, it would be tested for its correctness in recommendation. This interdisciplinary approach contributes to the preservation of traditional knowledge and opens avenues for sustainable healthcare practices that bridge the gap between traditional wisdom and contemporary science. The paper advocates for recognizing and integrating ethno-medicinal practices into mainstream healthcare systems, fostering a harmonious coexistence of cultural heritage and modern advancements in medical science within Lanao del Sur and beyond. © 2024 IEEE.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Sign the Voice: An Embedded Software for Voice to Sign Language Translation 2

Sign the Voice: An Embedded Software for Voice to Sign Langu...

引用

2nd International Conference on computing and Data Analytics, ICCDA 2024

作者： Peleo, Donna Lyn C. Patalay, Myra M. Cruz, Jesfer M. Dela Ramirez, Emmanuel A. College of Computing and Information Technologies National University Manila Philippines College of Computing and Information Sciences University of Technology and Applied Sciences Shinas Oman

ISBN: (纸本)9798331542573

This qualitative research study entitled Sign the Voice: An Embedded Software for Voice to Sign Language Translation aimed to bridge the communication barriers between hearing teachers and auditory-challenged students. This explored the current technologies used in the development of systems for Persons with Disabilities particularly the Deaf Community. This study aimed to develop an embedded software to translate in real-time a human's voice to sign language, making communication accessible between them. The researchers conducted interviews, focus groups, observation, and case studies. This study investigated the design process and usability of embedded software. Software testing and thematic analysis will then be conducted to test its effectiveness. The researchers considered the diverse needs of auditory-challenged students, real-time processing, and the accuracy of the translation to make sure the communication process is effective between hearing teachers and auditory-challenged students. Preliminary findings suggested promising results in terms of user satisfaction, highlighting the potential of the proposed embedded software to provide accessible communication between the hearing teachers and auditory-challenged students. The implications of this study will provide more IT opportunities for these auditory-challenged students, give diversity in the IT industry, and could lead to more opportunities for applied research by developing improved technological solutions. The cultural, societal, and ethical impacts of this proposed system were of high consideration. © 2024 IEEE.

关键词： Embedded software

来源：评论

学校读者我要写书评

暂无评论

Hybrid segmentation-based agricultural leaf disease detection (Hy-SALDD) using black widow optimization for feature selection, and Bayesian-optimized SVM classification

引用

International Journal of information Technology (Singapore) 2025年 1-15页

作者： Jain, Aaditya Dwivedi, Rakesh Kumar College of Computing Sciences & Information Technology Teerthanker Mahaveer University Moradabad India

Plant diseases pose a significant threat to agricultural productivity, often leading to severe crop losses. Early, precise detection and classification using computerized image processing can help mitigate damage, reducing losses and boosting yields. This paper presents Hy-SALDD (Hybrid Segmentation-based Agricultural Leaf Disease Detection), an innovative approach for identifying plant leaf diseases. The method integrates enhanced segmentation, feature extraction, and classification techniques. A hybrid segmentation model combining improved PSP-Net and enhanced HED efficiently isolates diseased regions in leaf images. Feature extraction incorporates deep features from the segmentation model and texture features using LBP. Feature selection is optimized through the Black Widow Optimization (BWO) technique, ensuring a compact and discriminative feature set. Classification is performed using a Bayesian-optimized SVM, improving detection accuracy. The proposed framework demonstrates significant potential for precise and efficient plant disease diagnosis. © Bharati Vidyapeeth's Institute of Computer Applications and Management 2025.

关键词： Bayesian optimization BWO HED network LBP PSP-Net Support vector machine

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review of Machine Learning and Deep Learning Approaches for Spectral Image Classification in Agricultural Applications Using Aerial Photography

引用

Computers, Materials & Continua 2024年第3期78卷 2967-3000页

作者： Usman Khan Muhammad Khalid Khan Muhammad Ayub Latif Muhammad Naveed Muhammad Mansoor Alam Salman A.Khan Mazliham Mohd Su’ud College of Computing and Information Sciences Karachi Institute of Economics and TechnologyKarachi75190Pakistan Faculty of Computing and Informatics(FCI) Multimedia UniversityCyberjaya63100Malaysia Faculty of Computing Riphah International UniversityIslamabad46000Pakistan Faculty of Engineering and Information Technology School of Computer ScienceUniversity of Technology SydneySydneyAustralia

Recently,there has been a notable surge of interest in scientific research regarding spectral *** potential of these images to revolutionize the digital photography industry,like aerial photography through Unmanned Aerial Vehicles(UAVs),has captured considerable *** encouraging aspect is their combination with machine learning and deep learning algorithms,which have demonstrated remarkable outcomes in image *** a result of this powerful amalgamation,the adoption of spectral images has experienced exponential growth across various domains,with agriculture being one of the prominent *** paper presents an extensive survey encompassing multispectral and hyperspectral images,focusing on their applications for classification challenges in diverse agricultural areas,including plants,grains,fruits,and *** meticulously examining primary studies,we delve into the specific agricultural domains where multispectral and hyperspectral images have found practical ***,our attention is directed towards utilizing machine learning techniques for effectively classifying hyperspectral images within the agricultural *** findings of our investigation reveal that deep learning and support vector machines have emerged as widely employed methods for hyperspectral image classification in ***,we also shed light on the various issues and limitations of working with spectral *** comprehensive analysis aims to provide valuable insights into the current state of spectral imaging in agriculture and its potential for future advancements.

关键词： Machine learning deep learning unmanned aerial vehicles multi-spectral images image recognition object detection hyperspectral images aerial photography

来源：评论

学校读者我要写书评

暂无评论

SPoTem: Handgun Detection in Videos using Spatial, Pose, and Temporal Features 24

SPoTem: Handgun Detection in Videos using Spatial, Pose, and...

引用

8th International Conference on Innovation in Artificial Intelligence, ICIAI 2024

作者： Flores, Juan Miguel H. Liban, Liam R. Ribaya, Robert Lawrence T. Paguio, Idan Andrei B. Suarez, Jessie James P. University of Santo Tomas College of Information and Computing Sciences Philippines

ISBN: (纸本)9798400709302

Recent advancements in deep learning have led to the creation of automated real-time weapon detection systems, primarily leveraging object detection framework and body pose keypoints extraction to extract features of hand regions as spatial features and body pose features. However, these approaches aren't able to contextualize the spatial features and pose features, limiting their effectiveness. This research introduces a unified architecture called SPoTem that incorporates spatial features, pose features, and temporal features for gun detection. The proposed approach starts by detecting the poses of persons in a video frame using OpenPose to locate the hand regions. Afterwards, the hand region is cropped, and DarkNet-53 is used to extract spatial features from it. Next, human pose keypoints are then put into an image to obtain a binary human pose image which is then fed into a convolutional neural network for human pose feature extraction. As for the temporal component, this study explores two (2) methods of extracting temporal features from the video using a long short-term memory (LSTM). The first one is through using a sequence of pose features and the other is a sequence of spatial features. This study shows that adding temporal features have improved the performance with respect to detecting guns in videos. Furthermore, results have shown that temporal features using sequences of human pose keypoints are more stable and effective at handgun detection in videos. © 2024 ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Enhancing Blood Vessel Images using Contrast Limited Adaptive Histogram Equalization and Adaptive Gaussian Thresholding for Anemia Detection in Palpebral Eye Conjunctiva 24

Enhancing Blood Vessel Images using Contrast Limited Adaptiv...

引用

8th International Conference on Innovation in Artificial Intelligence, ICIAI 2024

作者： Lagman, Elaine Bhel L. Malabanan, Kirstine Kate M. Mendoza, Matthew B. Saavedra, Raeniel T. Suarez, Jessie James P. University of Santo Tomas College of Information and Computing Sciences Philippines

ISBN: (纸本)9798400709302

For diagnosing anemia, physicians often depend on understanding a patient's medical history, particularly risk factors, and conducting physical exams but the most common approach for confirming anemia is through a Complete Blood Count (CBC). There are now non-invasive methods being developed for anemia detection, as highlighted in various studies. Previous studies noted that pallor or paleness, often resulting from a low hemoglobin (Hb) count or concentration due to various pathologies, can indicate whether a person is anemic. These non-invasive techniques focus on different body parts showing pallor, such as the palm, the tongue, and the eye conjunctiva. These methods provide a way to determine anemia without the need for invasive procedures. This study investigates a non-invasive method for anemia detection by analyzing blood vessels in the palpebral eye conjunctiva. It combines datasets from various sources and focuses on modifying the preprocessing techniques by using Contrast Limited Adaptive Histogram Equalization and Adaptive Gaussian Thresholding which highlighted the blood vessels present in the palpebral eye conjunctiva. Furthermore, this study proposes the use of AdaBoost with Convolutional Neural network (CNN) to detect anemia in the palpebral eye conjunctiva. The AdaBoost-CNN model, especially post-CLAHE and AGT preprocessing, exhibits an accuracy of 82.06%, precision of 82.42%, recall of 43.94%, and F1 Score of 55.90%. © 2024 ACM.

关键词： Noninvasive medical procedures

来源：评论

学校读者我要写书评

暂无评论

ProMorph: Melanoma Classification in Dermoscopic Images using Proportional Morphological Dilation and Convolutional Neural networks 24

ProMorph: Melanoma Classification in Dermoscopic Images usin...

引用

8th International Conference on Innovation in Artificial Intelligence, ICIAI 2024

作者： Caasi, Michael Angelo A. Espinosa, Rio S. Vinzon, Jerielle P. Abante, Arlan Floyd R. Suarez, Jessie James P. University of Santo Tomas College of Information and Computing Sciences Philippines

ISBN: (纸本)9798400709302

Skin cancer is one of the leading and deadly diseases affecting an estimated 2-3 million non-melanoma skin cancers and 132,000 melanoma skin cancers occur globally each year. It represents the most common group of cancers diagnosed worldwide, with an estimated 1.5 million new cases in 2020. Most studies first segment skin lesion images to focus on the region of interest and then use a classifier to identify the type of skin lesion. However, this does not consider that the surrounding skin can provide more context to the classifier. Hence, this study introduces ProMorph, a novel approach for improving melanoma classification in dermoscopic images by employing proportional morphological dilation. In contrast to fixed dilation methods, ProMorph adapts the dilation process based on the size of the skin lesion. The study evaluates ProMorph on ISIC 2016 and ISIC 2018 datasets, comparing its performance against absolute dilation methods. Results demonstrate that ProMorph outperforms absolute dilation in metrics such as AUC, recall, and F1, showcasing its efficacy in enhancing melanoma classification. The best results of the model are highlighted: ProMorph achieved an AUC of 0.8029 on ISIC 2016, surpassing Absolute Dilation with an AUC of 0.7608 on the same dataset. Similarly, on ISIC 2018, ProMorph achieved an AUC of 0.8988 compared to Absolute Dilation's AUC of 0.88. Furthermore, this study outperforms all previous studies in the ISIC 2016 dataset with respect to recall. © 2024 ACM.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Classification Framework for Autoimmune Liver Disease using Machine Learning and Deep Learning Techniques 5

Classification Framework for Autoimmune Liver Disease using ...

引用

5th Technology Innovation Management and Engineering Science International Conference, TIMES-iCON 2024

作者： George, E. Ben Rosline, G. Jeba Varghese, Abraham Rajesh, Gnana D. Department of Information Technology College of Computing and Information Sciences University of Technology and Applied Sciences Muscat Oman Department of Information Technology College of Computing and Information Sciences University of Technology and Applied Sciences Al Mussanah Oman

ISBN: (纸本)9798350362602

—Autoimmune diseases affect people of all ages, genders, and ethnic backgrounds, making it one of the most widespread health issues we face today. These disorders occur when the immune system mistakenly targets healthy cells within the body and causing a wide range of potentially life-threatening diseases. There are over 80 recognized autoimmune disorders, including type-1 diabetes, rheumatoid arthritis, Graves' disease, alopecia, celiac disease, and autoimmune liver disease(AiLD). Autoimmune liver disease is one such chronic disorder characterized by liver inflammation and damage. If not detected on time and untreated within the given time, it might lead to liver cirrhosis or liver cancer. Identifying and treating autoimmune liver disease is a complex and time consuming process which involves symptom analysis, laboratory tests, and clinical assessments. Detecting the disease can be more challenging because many symptoms of autoimmune liver diseases overlap with those of other autoimmune conditions. As a result, there is a need for an optimized, accurate, efficient, and cost-effective methodology to identify the disease without extensive and invasive procedures such as organ transplants. This paper introduces an innovative approach that employs the power of supervised machine learning and deep learning techniques to predict the onset of autoimmune liver diseases in advance. The machine learning model is constructed using a comprehensive dataset comprising the complete medical history of patients, physical examination records, histopathology and genetic data. Along with the machine learning model, the deep learning model is also developed for liver MRI images of various patients to make accurate prediction. This system provides a second opinion for medical professionals that may avoid the need for extensive and invasive medical procedures, including biopsies, and ultimately improve patient care and outcomes. ©2024 IEEE.

关键词： Autoimmune Liver Disease Classification Deep Learning Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Virtual and Augmented Reality in Interactive Entertainment: Unlocking New Dimensions of Immersive Interaction 2

Virtual and Augmented Reality in Interactive Entertainment: ...

引用

2nd International Conference on computing and Data Analytics, ICCDA 2024

作者： Al Balushi, Jasim Sharki Ghulam Al Jabri, Malak Ibrahim Ahmed Palarimath, Suresh Mohamed, Chithik Raja Radhakrishnan, Venkateswaran Thumu, Muni Balaji College of Computing and Information Sciences University of Technology and Applied Sciences Salalah Oman

ISBN: (纸本)9798331542573

Virtual Reality (VR) offers an immersive experience with position tracking and 3D near-eye displays, enabling users to enter virtual surroundings. Conversely, Augmented Reality (AR) superimposes computer-generated content onto the real world, integrating digital and physical environments through visual, aural, tactile, and other sensory modalities. Both technologies are transforming user engagement with content, providing the opportunity to explore remote locations, communicate with digital characters, or assume leading roles in interactive entertainment events. While VR completely immerses users in simulated surroundings, AR enriches real-world contexts by incorporating interactive elements and contextual data. This study examines the transformative effects of VR and AR in interactive entertainment, emphasizing its various uses, benefits, and constraints. It emphasizes how new technologies have transformed narrative, facilitating enhanced user involvement and a more dynamic feeling of presence. The review analyzes the present and prospective capabilities of VR and AR in transforming social interactions, narrative-centric experiences, and cooperative gameplay. In addition to entertainment, the article examines the ramifications of AR and VR in education, training, and healthcare, where immersive environments demonstrate significant efficacy. The report highlights the crucial impact these technologies have in enhancing human-computer interaction across various industries. © 2024 IEEE.

关键词： Virtual environments

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：