2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)最新文献_第2页

Comparisons of Deep Learning Approaches to Detect Lung Cancer through Efficient Computer Based CT-based Screening 通过高效计算机 CT 筛查检测肺癌的深度学习方法比较

2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) Pub Date : 2024-02-01 DOI: 10.1109/ACDSA59508.2024.10468003

Wael Natafji, Daniel Einarson

引用次数: 0

A Comparative Study of Certain Convolutional Neural Network Architectures for X-ray Image Analysis in Bone Fracture Detection and Identification 用于 X 射线图像分析的某些卷积神经网络架构在骨骨折检测和识别中的比较研究

2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) Pub Date : 2024-02-01 DOI: 10.1109/ACDSA59508.2024.10468017

Mashrur Kabir, Tasnia Jasim Tahiti, Tasnim Ahsan Prome

{"title":"A Comparative Study of Certain Convolutional Neural Network Architectures for X-ray Image Analysis in Bone Fracture Detection and Identification","authors":"Mashrur Kabir, Tasnia Jasim Tahiti, Tasnim Ahsan Prome","doi":"10.1109/ACDSA59508.2024.10468017","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10468017","url":null,"abstract":"This research systematically evaluates the performance of diverse Convolutional Neural Network (CNN) architectures in enhancing the accuracy of bone fracture detection in medical imaging. The study aims to understand the intricate nuances exhibited by CNNs when analyzing X-ray images, high-lighting the significance of a robust framework with high sensitivity and specificity. To address the issue of imbalanced datasets, a carefully preprocessed, normalized, and augmented dataset from multiple medical institutions is utilized. The implementation of CNN architectures, such as ResNet, VGGNet, and InceptionNet, involves meticulous configuration and hyperparameter tuning to optimize feature extraction in this complex problem domain. Through extensive experimentation and thorough examination of metrics including accuracy, F1 score, sensitivity, and specificity, the efficacy of each architecture in identifying fractures and distinguishing them from benign anomalies in X-ray images is uncovered. The analysis provides a comprehensive understanding of the strengths and limitations of each architecture, enabling well-informed decisions regarding their suitability in clinical settings. This research represents a significant advancement in the field of bone fracture detection in medical imaging, offering valuable insights into the transformative potential of CNN architectures in improving diagnostic accuracy and informing clinical decision-making.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"541 ","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528562","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}

引用次数: 0

Crowd-Based Road Surface Assessment Using Smartphones on Bicycles 使用智能手机对骑自行车的人群进行路面评估

2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) Pub Date : 2024-02-01 DOI: 10.1109/ACDSA59508.2024.10468027

Kay Massow, Friedrich Maiwald, Max Thiele, Jan Heimendahl, Robert Protzmann, I. Radusch

{"title":"Crowd-Based Road Surface Assessment Using Smartphones on Bicycles","authors":"Kay Massow, Friedrich Maiwald, Max Thiele, Jan Heimendahl, Robert Protzmann, I. Radusch","doi":"10.1109/ACDSA59508.2024.10468027","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10468027","url":null,"abstract":"The surface quality assessment procedures of roads used by motor vehicles are widely addressed in research, recently with a focus on continuous assessment using crowd data. Although, the bicycle infrastructure is becoming increasingly important for urban mobility and the shift towards sustainable transportation, its monitoring and maintenance is currently underrepresented in research and in the awareness of road authorities. In this paper, we evaluate different approaches to assess the surface quality of bicycle lanes and paths using crowd data from smartphones carried on bicycles. The applicability of data from smartphone sensors acquired on moving bicycles is quite limited in its usage towards the calculation of established surface assessment metrics. Thus, we consider various metrics, with a focus on robustness regarding the named limitations. The evaluation is done in a first step in controlled test rides on known surface types. In the second step, the most promising metric is evaluated against its reproducibility with different bikes and riders on multiple test rides on a random track.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"509 9","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528565","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}

引用次数: 0

Collaborative Filtering-based Movie Recommendation Services Using Opinion Mining 使用意见挖掘的基于协作过滤的电影推荐服务

2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) Pub Date : 2024-02-01 DOI: 10.1109/ACDSA59508.2024.10467884

Luong Vuong Nguyen

{"title":"Collaborative Filtering-based Movie Recommendation Services Using Opinion Mining","authors":"Luong Vuong Nguyen","doi":"10.1109/ACDSA59508.2024.10467884","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467884","url":null,"abstract":"This article explores the fusion of collaborative filtering (CF) techniques with opinion mining methodologies to enhance movie recommendation systems. The proposed approach harnesses user-item interaction data to employ CF algorithms for generating initial movie recommendations. Furthermore, opinion mining techniques are integrated to analyze textual reviews and extract implicit sentiment signals associated with movies. Leveraging sentiment-aware adjustments, the model refines CF-based recommendations by incorporating user sentiments expressed in reviews. In specifically, conducting aspect-based sentiment analysis on movie reviews leveraging a Long Short-Term Memory (LSTM) neural network architecture. The methodology involves applying LSTM-based sentiment analysis to extract sentiments from movie reviews, followed by aspect identification and sentiment assignment to specific movie elements or aspects. This aspect-focused sentiment analysis approach using LSTM-based sentiment analysis contributes to a comprehensive understanding of movie reviews. The fusion of CF with opinion mining techniques in movie recommendation systems represents a significant advancement toward enhancing recommendation accuracy and personalization.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"373 ","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528855","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}

引用次数: 0

AI-Powered Segmentation Revolutionizes Scaffold Design in Regenerative Dentistry 人工智能驱动的细分技术彻底改变了再生牙科中的支架设计

2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) Pub Date : 2024-02-01 DOI: 10.1109/ACDSA59508.2024.10467382

Andrej Thurzo, Petra Jungová, L. Danišovič

{"title":"AI-Powered Segmentation Revolutionizes Scaffold Design in Regenerative Dentistry","authors":"Andrej Thurzo, Petra Jungová, L. Danišovič","doi":"10.1109/ACDSA59508.2024.10467382","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467382","url":null,"abstract":"The era of 3D printing of biocompatible personalized scaffolds has arrived, and Cone Beam Computed Tomography (CBCT) is essential for 3D reproduction of individualized human anatomy. When designing the shape of the personalized scaffold, the starting point is typically the CBCT scan, which must first be segmented to define the complementary shape of the scaffold. In the past, this was usually a lengthy manual segmentation process that could take hours. Today, artificial intelligence-based software can perform automatic segmentation of the various structures in the maxillo-facial region directly from CBCT data in seconds. This study presents a novel workflow comparing manual segmentation in Invivo (Anatomage, San Jose, CA, USA) with AI-automated segmentation in Diagnocat (Miami, FL, USA). In 24 cases, the time required for segmentation were compared and evaluated with a paired t-test. This revealed a statistically significant difference in segmentation time between the two groups, with the AI-driven analysis being significantly faster. The difference in average segmentation time between manual (36.03 minutes) and AI-driven analysis (4.96 minutes) showed that AI-driven analysis was on average more than five time faster than manual segmentation. AI-driven analysis reduces segmentation time by 86.17% compared to manual segmentation of CBCT. This means that AI-driven analysis can save clinicians a lot of time. The presented feasibility of AI-automated workflow with STL (Standard Triangle Language) output models suitable for 3D modeling of scaffold shapes - complementary to individual anatomy in Meshmixer (Autodesk, San Rafael, CA, USA), were suitable for 3D printing with hydroxyapatite. This has significance for various workflows in regenerative dentistry.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"119 ","pages":"1-3"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529008","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}

引用次数: 0

Assessment of software-defined UAVs operating in remote areas 评估在偏远地区运行的软件定义无人机

2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) Pub Date : 2024-02-01 DOI: 10.1109/ACDSA59508.2024.10467479

Mahamat Ismael Hassan, Daouda Ahmat, Samuel Ouya, Mahamat Borgour Hassan, Mahamat Charfadine Salim, Bachar Salim Haggar

{"title":"Assessment of software-defined UAVs operating in remote areas","authors":"Mahamat Ismael Hassan, Daouda Ahmat, Samuel Ouya, Mahamat Borgour Hassan, Mahamat Charfadine Salim, Bachar Salim Haggar","doi":"10.1109/ACDSA59508.2024.10467479","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467479","url":null,"abstract":"The flexibility of programmable networks is proposed in this research to revolutionize UAV management by providing optimum performance independent of network density or individual UAV distance. For greater control and administration of drone networks, we recommend deploying software-defined networking (SDN). Extensive comparative testing across three SDN controllers has highlighted the significant effect controller selection may have on network performance: bandwidth, packet loss, mobility, and resilience are all significantly impacted. A Mininet-WiFi SDN network emulators was used to perform drone simulations in the selected controller. This study looked at the implementation of Unmanned Aerial Vehicles (UAVs) in three different Software-Defined Networking (SDN) controllers: ODL, Floodlight, and RYU. Four scenarios were simulated for each controller, with a constant topology and various numbers of UAVs (15, 20, 25, and 30+) stationed at varied distances (60, 80, 100, and 100+ meters) from each controller. The results of the practical experiments conducted in this work are analyzed and discussed in the “Results and Discussion” section.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"818 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528748","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}

引用次数: 0

Enlarging the Time Budget for Neural Network Based Predictors for Access Interval Prediction 扩大基于神经网络预测器的访问间隔预测的时间预算

2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) Pub Date : 2024-02-01 DOI: 10.1109/ACDSA59508.2024.10467779

Simon Friedrich, Arjun Sivasankar, E. Matús, Gerhard Fettweis

{"title":"Enlarging the Time Budget for Neural Network Based Predictors for Access Interval Prediction","authors":"Simon Friedrich, Arjun Sivasankar, E. Matús, Gerhard Fettweis","doi":"10.1109/ACDSA59508.2024.10467779","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467779","url":null,"abstract":"Embedded systems implemented on a single chip commonly contain several Processing Elements (PEs). To optimize both area and energy efficiency, these individual PEs are often linked to the same Tightly Coupled Memory (TCM). Nonetheless, the advantage of memory sharing is offset by potential conflicts. Recently introduced systems with offline conflict detection and memory arbitration avoid the performance degradation of online arbiters. Access Interval Prediction (AIP) is exploited to detect the conflicts offline by forecasting the time interval between two memory accesses. In this context, neural network models for time-series prediction are the State-of-the-Art AIP units. However, the influence of the latency of these neural network predictors on the accuracy of the AIP system has not been considered yet. Our analysis shows a significant degradation of the system accuracy by the predictor latency. To enlarge the time budget for calculation, we introduce a novel neural network AIP predictor that predicts the next-but-one memory access. Further, we present an advanced system model that integrates two independent next-but-one predictors. By combining multiple predictors, we can maintain the high accuracy of the AIP system even for implementations that exhibit high latency. For example, our system model demonstrates a 2.59 times higher accuracy compared to the State-of-the-Art AIP with neural networks when executing the models with a latency of 5 cycles.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"711 ","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529055","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}

引用次数: 0

A Heuristics and Machine Learning Hybrid Approach to Adaptive Cyberattack Detection 自适应网络攻击检测的启发式和机器学习混合方法

2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) Pub Date : 2024-02-01 DOI: 10.1109/ACDSA59508.2024.10467929

Makoto Iwabuchi, Akihito Nakamura

{"title":"A Heuristics and Machine Learning Hybrid Approach to Adaptive Cyberattack Detection","authors":"Makoto Iwabuchi, Akihito Nakamura","doi":"10.1109/ACDSA59508.2024.10467929","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467929","url":null,"abstract":"Cybersecurity is more significant now than ever, and the severity of the threat has escalated. One possible countermeasure is the Intrusion Detection and Prevention System (IDPS), which enables the detection of malicious activities in the network based on signature-matching and other detection methods. A signature represents the specific pattern of an attack. However, it occasionally misses malicious traffic or raises false alerts when the detection method is not carefully configured with the latest information. That is, it is susceptible to false positives or false negatives. This paper presents a highly accurate cyberattack detection method with the automatic generation of tailored signatures for a rapid response to emerging threats. We combine heuristics for known attacks and machine learning (ML) techniques to detect unforeseen attack patterns in traffic, i.e. a hybrid method. Rule-based judgment for heuristics and anomaly detection for ML are used, respectively. This study introduces a novel approach by employing machine learning with a packet-to-image conversion technique. We convert network packet data into images and utilize the image data for training and classifying attack patterns. By transforming the problem to anomaly detection in image data, the evaluation results revealed that the method has high accuracy.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"38 3","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140528945","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}

引用次数: 0

2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) Pub Date : 2024-02-01 DOI: 10.1109/acdsa59508.2024.10468001

引用次数: 0

Performance Evaluation of Deep Learning Models for Detection of Brain Tumors from CT Scans 从 CT 扫描检测脑肿瘤的深度学习模型性能评估

2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA) Pub Date : 2024-02-01 DOI: 10.1109/ACDSA59508.2024.10467770

Vaibhav Mishra

{"title":"Performance Evaluation of Deep Learning Models for Detection of Brain Tumors from CT Scans","authors":"Vaibhav Mishra","doi":"10.1109/ACDSA59508.2024.10467770","DOIUrl":"https://doi.org/10.1109/ACDSA59508.2024.10467770","url":null,"abstract":"With brain tumors being a leading cause of death in the world, this paper explores the use of deep learning algorithms in medical imaging tasks specifically the detection of brain tumors from CT scans. The study employs a dataset comprising 230 images of normal and brain tumor patients which are used to train and evaluate the performance of seven deep learning models including six pre-trained models: ResNet-50, MobileNet-V2, InceptionNet, VGG-16, Xception, and DenseNet along with a custom baseline CNN model. Transfer learning is used for pre-trained model detection of brain tumors from CT scans while the custom CNN model is compared against pre-trained models with specific hyperparameters. Results indicate that MobileNet-V2 outperforms other models with a test accuracy of 98%, making it a promising candidate for efficient brain tumor detection. The baseline CNN model and InceptionNet closely followed, achieving a 97% test accuracy. The study shows the innovative potential of using deep learning in medical imaging and provides valuable insights for optimization of deep learning models for brain tumor detection addressing a significant need in medical diagnostics.","PeriodicalId":518964,"journal":{"name":"2024 International Conference on Artificial Intelligence, Computer, Data Sciences and Applications (ACDSA)","volume":"203 ","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2024-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140529329","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}

引用次数: 0