Pub Date : 2024-04-05DOI: 10.53759/7669/jmc202404044
Manikandan J, Kayalvizhi K, Yuvaraj Nachimuthu, Jeena R
With the demand for better, more user-friendly HMIs, voice recognition systems have risen in prominence in recent years. The use of computer-assisted vocal pathology categorization tools allows for the accurate detection of voice pathology diseases. By using these methods, vocal disorders may be diagnosed early on and treated accordingly. An effective Deep Learning-based tool for feature extraction-based vocal pathology identification is the goal of this project. This research presents the results of using EfficientNet, a pre-trained Convolutional Neural Network (CNN), on a speech pathology dataset in order to achieve the highest possible classification accuracy. An Artificial Rabbit Optimization Algorithm (AROA)-tuned set of parameters complements the model's mobNet building elements, which include a linear stack of divisible convolution and max-pooling layers activated by Swish. In order to make the suggested approach applicable to a broad variety of voice disorder problems, this study also suggests a unique training method along with several training methodologies. One speech database, the Saarbrücken voice database (SVD), has been used to test the proposed technology. Using up to 96% accuracy, the experimental findings demonstrate that the suggested CNN approach is capable of detecting speech pathologies. The suggested method demonstrates great potential for use in real-world clinical settings, where it may provide accurate classifications in as little as three seconds and expedite automated diagnosis and treatment.
{"title":"AROA based Pre-trained Model of Convolutional Neural Network for Voice Pathology Detection and Classification","authors":"Manikandan J, Kayalvizhi K, Yuvaraj Nachimuthu, Jeena R","doi":"10.53759/7669/jmc202404044","DOIUrl":"https://doi.org/10.53759/7669/jmc202404044","url":null,"abstract":"With the demand for better, more user-friendly HMIs, voice recognition systems have risen in prominence in recent years. The use of computer-assisted vocal pathology categorization tools allows for the accurate detection of voice pathology diseases. By using these methods, vocal disorders may be diagnosed early on and treated accordingly. An effective Deep Learning-based tool for feature extraction-based vocal pathology identification is the goal of this project. This research presents the results of using EfficientNet, a pre-trained Convolutional Neural Network (CNN), on a speech pathology dataset in order to achieve the highest possible classification accuracy. An Artificial Rabbit Optimization Algorithm (AROA)-tuned set of parameters complements the model's mobNet building elements, which include a linear stack of divisible convolution and max-pooling layers activated by Swish. In order to make the suggested approach applicable to a broad variety of voice disorder problems, this study also suggests a unique training method along with several training methodologies. One speech database, the Saarbrücken voice database (SVD), has been used to test the proposed technology. Using up to 96% accuracy, the experimental findings demonstrate that the suggested CNN approach is capable of detecting speech pathologies. The suggested method demonstrates great potential for use in real-world clinical settings, where it may provide accurate classifications in as little as three seconds and expedite automated diagnosis and treatment.","PeriodicalId":516221,"journal":{"name":"Journal of Machine and Computing","volume":"6 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140738313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-05DOI: 10.53759/7669/jmc202404047
Yang-ha Chun, Moon-Ki Cho
Drones, which were initially developed for military applications, have recently been studied and applied to various fields. In this paper, we propose a DANET algorithm that uses a large number of drones to build a wireless communication network infrastructure, and in situations where communication is not possible, such as in disaster areas, we propose a DANET algorithm that uses drones to form a network so that nodes that want to join the network can efficiently acquire IP addresses without collision. In a DANET, a pool of IP addresses is gradually passed to the drones in the next zone in blocks, and the drones in each zone distribute IPs to newly joining nodes, thereby increasing the IP address allocation rate and reducing the IP allocation time to form a temporary but efficient network. Drones assign their own IP addresses through simple Request and Response message exchanges with land-based stations or M-Droin (Mother Droin) in the divided zones that can assign IP addresses. Therefore, DANET can completely eliminate the process of IP collision avoidance (Duplicate Address Detection) and the process of network separation or integration caused by the movement of ships. This paper presents a new possibility for building wireless network infrastructure in unconnected areas such as disaster areas by performing simulations under various conditions to verify the applicability of DANET.
无人机最初是为军事应用而开发的，最近已被研究并应用于各个领域。在本文中，我们提出了一种 DANET 算法，利用大量无人机构建无线通信网络基础设施，在无法进行通信的情况下（如灾区），我们提出了一种 DANET 算法，利用无人机组成网络，使想要加入网络的节点可以高效地获取 IP 地址，而不会发生碰撞。在 DANET 中，IP 地址池以块为单位逐渐传递给下一区域的无人机，每个区域的无人机将 IP 分配给新加入的节点，从而提高 IP 地址分配率，缩短 IP 分配时间，形成一个临时但高效的网络。无人机通过与划分区域内可分配 IP 地址的陆基站或 M-Droin（母 Droin）进行简单的请求和响应信息交换，分配自己的 IP 地址。因此，DANET 可以完全消除避免 IP 碰撞的过程（重复地址检测）以及因船只移动而造成的网络分离或整合过程。本文通过在各种条件下进行模拟，验证了 DANET 的适用性，为在灾区等未联网地区建设无线网络基础设施提供了一种新的可能性。
{"title":"Regional IP Allocation Techniques Using Drones","authors":"Yang-ha Chun, Moon-Ki Cho","doi":"10.53759/7669/jmc202404047","DOIUrl":"https://doi.org/10.53759/7669/jmc202404047","url":null,"abstract":"Drones, which were initially developed for military applications, have recently been studied and applied to various fields. In this paper, we propose a DANET algorithm that uses a large number of drones to build a wireless communication network infrastructure, and in situations where communication is not possible, such as in disaster areas, we propose a DANET algorithm that uses drones to form a network so that nodes that want to join the network can efficiently acquire IP addresses without collision. In a DANET, a pool of IP addresses is gradually passed to the drones in the next zone in blocks, and the drones in each zone distribute IPs to newly joining nodes, thereby increasing the IP address allocation rate and reducing the IP allocation time to form a temporary but efficient network. Drones assign their own IP addresses through simple Request and Response message exchanges with land-based stations or M-Droin (Mother Droin) in the divided zones that can assign IP addresses. Therefore, DANET can completely eliminate the process of IP collision avoidance (Duplicate Address Detection) and the process of network separation or integration caused by the movement of ships. This paper presents a new possibility for building wireless network infrastructure in unconnected areas such as disaster areas by performing simulations under various conditions to verify the applicability of DANET.","PeriodicalId":516221,"journal":{"name":"Journal of Machine and Computing","volume":"101 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140736170","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-05DOI: 10.53759/7669/jmc202404037
Sincy John, A. Danti
The representation of facial features in three-dimensional space plays a pivotal role in various applications such as facial recognition, virtual reality, and digital entertainment. However, achieving high-fidelity reconstructions from two-dimensional facial images remains a challenging task, particularly in preserving fine texture details. This research addresses this problem by proposing a novel approach that leverages a combination of advanced techniques, including Resnet, Flame model, Bi-FPN, and a differential render architecture. The primary objective of this study is to enhance texture details in reconstructed 3D facial images. The integration of Bi-FPN (Bi-directional Feature Pyramid Network) enhances feature extraction and fusion across multiple scales, facilitating the preservation of texture details across different regions of the face. The objective is to accurately represent facial features from 2D images in three-dimensional space. By combining these methods, the proposed framework achieves significant improvements in preserving fine texture details and overall facial structure. Experimental results demonstrate the effectiveness of the approach, suggesting its potential for various applications such as virtual try-on and facial animation.
{"title":"3D Face Reconstruction with Feature Enhancement using Bi-FPN for Forensic Analysis","authors":"Sincy John, A. Danti","doi":"10.53759/7669/jmc202404037","DOIUrl":"https://doi.org/10.53759/7669/jmc202404037","url":null,"abstract":"The representation of facial features in three-dimensional space plays a pivotal role in various applications such as facial recognition, virtual reality, and digital entertainment. However, achieving high-fidelity reconstructions from two-dimensional facial images remains a challenging task, particularly in preserving fine texture details. This research addresses this problem by proposing a novel approach that leverages a combination of advanced techniques, including Resnet, Flame model, Bi-FPN, and a differential render architecture. The primary objective of this study is to enhance texture details in reconstructed 3D facial images. The integration of Bi-FPN (Bi-directional Feature Pyramid Network) enhances feature extraction and fusion across multiple scales, facilitating the preservation of texture details across different regions of the face. The objective is to accurately represent facial features from 2D images in three-dimensional space. By combining these methods, the proposed framework achieves significant improvements in preserving fine texture details and overall facial structure. Experimental results demonstrate the effectiveness of the approach, suggesting its potential for various applications such as virtual try-on and facial animation.","PeriodicalId":516221,"journal":{"name":"Journal of Machine and Computing","volume":"22 S18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140740229","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：