检索结果-内蒙古大学图书馆

International Conference on informatics and Computing (ICIC)

作者： Henderi Mumammad Hudzaifah Nasrullah Laura Belani Nudiyah Po Abas Sunarya Sofa Sofiana Didik Setiyadi Informatics University of Raharja Tangerang Indonesia Management of Retail Study Program University of Raharja Tangerang Indonesia Informatics Engineering Departement Faculty of Engineering Pamulang University Tangerang Indonesia Infotmatics Faculty of Technolgy and Design Universitas Indonesia Mandiri Jakarta Indonesia

ISBN: (纸本)9798350345728

River pollution has become a severe problem in Indonesia. Industrial waste causes water pollution because the waste is not filtered before being discharged into the river. Illegal waste dumping cannot be prosecuted due to insufficient data and unknown disposal times. Therefore, a tool is needed to measure river water waste to measure polluted water waste data. Studies on river water monitoring devices have shown that there are no portable monitoring tools based on the internet of things for river water waste that follows regulatory standards from the Minister of Health. This study aims to produce a portable monitoring tool based on the internet of things for water waste. The system was developed using TDS sensors, turbidity, pH, MQ-135 sensors, and the system is equipped with a GPS module to indicate the location's latitude. The monitoring system is developed through the stages of system design, testing water samples, setting water quality standards and required hardware and components, setting river water quality parameters, and conducting system testing. The test results show that the system can send the data obtained to dashboard things via an internet connection, the TDS sensor error rate is 2.17%, the pH sensor error rate is 1.87%, the turbidity sensor error rate is 1.66%, the MQ135 sensor value is at the quality limit. The internet of things-based portable river waste monitoring system produced through this research helps related parties to identify and handle polluted rivers. Water according to the standards of the Ministry of Health, and the GPS module shows location measurements and information according to the location's latitude on google maps.

关键词： Error analysis Sensor systems Water pollution Sensors Rivers Pollution measurement Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Enhancing Acute Ischemic Stroke Diagnosis Using IoMT and Deep Learning Technologies

Enhancing Acute Ischemic Stroke Diagnosis Using IoMT and Dee...

引用

Telecommunications Conference (ITC-Egypt), International

作者： Mohamed M. El-Sheikh Aya Bayoumy Nada M. Ahmed Amany Mohamed Eldeeb Fatma I. Rabea Amira A. Nawar Mohamed G. Khattap Hend Galal Eldeen Mohamed Ali Hassan Mariam Mostafa Nayra Ibrahim Reem Ramadan Yomna Refaat Mennatallah Khaled Ali Maher Mohamed Abd Elaziz Ahmed Gamal Abdellatif Ibrahim Radiology and Medical Imaging Faculty of Applied Health Sciences Galala University Suez Egypt Biomedical Informatics Faculty of Computer Science and Engineering Galala University Suez Egypt Artificial Intelligence Science Program Faculty of Computer Science and Engineering Galala University Suez Egypt Department of Electronics and Electrical Communications Engineering Air Defense College Alexandria Egypt

ISBN: (数字)9798350351408

ISBN: (纸本)9798350351415

This paper introduces an alternative technique for diagnosing Acute Ischemic Stroke within the IoMT environment. In the proposed approach, the collected data is transmitted to a cloud-based center where the technique utilizes EfficientNet, a deep learning model, designed to extract features from MRI images thereby enhancing the detection of acute ischemic infarctions. The performance of EfficientNet is compared against two other models, CNN and MobileNet, demonstrating its superior efficacy through metrics such as accuracy, precision, recall, and F1-score, which stand at 92.31%, 92.28%, 92.33%, and 92.30%, respectively.

关键词： Deep learning Accuracy Magnetic resonance imaging Soft sensors Medical services Feature extraction Regulation

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Household Waste Image Identification Using Convolutional Neural Network

SSRN

引用

SSRN 2022年

作者： Sunardi Yudhana, Anton Fahmi, Miftahuddin Department of Electrical Engineering Universitas Ahmad Dahlan Yogyakarta55191 Indonesia Master Program of Informatics Universitas Ahmad Dahlan Yogyakarta55191 Indonesia

Waste identification has been widely carried out using machine learning with various methods. One method that is often used is the Convolutional Neural Network (CNN). Waste identification has a function as machine learning that helps and accelerates the waste management process, especially the waste sorting process. This research was conducted by collecting data by downloading a dataset from Kaggle. The data were then be labeled in a folder according to their type. The dataset folder was entered into a Python machine learning system equipped with the TensorFlow module. The data was preprocessed so that it became simplified and the machine could read the data. The data was trained to be able to distinguish between the types of waste. After that, the CNN method was implemented in machine learning so that the machine could classify the waste image. The results of the CNN implementation show that the system can classify images with the greatest accuracy of 99.83% with a validation accuracy of 76.1% and the smallest loss percentage of about 0.04% at epoch 18. The results show that there was overfitting in the dataset classification process caused by the average accuracy value of the training data and validation data being too large, around 20%. © 2022, The Authors. All rights reserved.

关键词： Waste management

来源：评论

学校读者我要写书评

暂无评论

Borneo Smart Forest Information System for Management of Dipterocarp Plants in Kalimantan Rainforest

Borneo Smart Forest Information System for Management of Dip...

引用

Information Technology International Seminar (ITIS)

作者： Masna Wati Novianti Puspitasari Ummul Hairah Joan Angelina Widians Anindita Septiarini Ade Fiqri Tjikoa Dept. of Informatics Faculty of Engineering Universitas Mulawarman Samarinda Indonesia Dept. of Informatics Universitas Mulawarman Doctoral Program Dept. of Computer Science and Electronics Universitas Gadjah Mada Yogyakarta Indonesia

ISBN: (纸本)9798350398205

Kalimantan’s tropical rainforest is home to indigenous plants of the Dipterocarpaceae family (tribe), which is renowned for having the most endemic species. Dipterocarp is a family of pantropical plants, many of which are used in the wood industry. This study aims to provide information on the potential of Dipterocarp in Kalimantan forests. Education and conservation efforts for Dipterocarp trees, a prominent component of the forest ecosystem, are crucial in light of the significant harm done to Kalimantan’s rainforests. The authors develop the Borneo Smart Forest information system. This system digitally organizes data on the diversity of Dipterocarp in the Kalimantan rainforest based on Web and QR-Code technology. Borneo Smart Forest (BSF) system for monitoring plant inventory and plant markers can be read by smartphones using QR codes. It gives visitors a comprehensive overview of the plants. A QR code is a printed, two-dimensional barcode with limited space for data storage. This technology allows the plant to show earlier administrator-made additions to the inventory information system. The QR code will direct the user to the BSF website, which has data about the plants. The development of this system is one of the efforts to support the achievement of Dipterocarp conservation.

关键词： Seminars Memory Forestry QR codes Vegetation Wood industry Information technology

来源：评论

学校读者我要写书评

暂无评论

Response of the Offshore Jacket Platform at its Ultimate Strength Under Operating and Extreme Loads

SSRN

引用

SSRN 2022年

作者： Othman, Nor Adlina Mohd, Mohd Hairil Offshore Engineering and Naval Architecture Research Interest Group Maritime Technology Program Faculty of Ocean Engineering Technology and Informatics Universiti Malaysia Terengganu Kuala Terengganu21300 Malaysia

Before reassessing the reliability condition of an offshore jacket platform, it is essential to understand the behaviours that the offshore platform exhibits while it is at sea, which are measured in terms of environmental loads: under operating and extreme conditions. Metocean data from a 1-year return period (operating condition) and a 100-year return period (storm condition) are used to predict the four-legs jacket platform's behaviour. Also, two values of minimum design water depth (WD) of 105.9 m and maximum design WD of 115.4 m are chosen. The Structural Analysis Computer Software (SACS), a non-linear finite element analysis software, is used to calculate the jacket platform's ultimate strength, called pushover analysis. The analysis result will determine the Reserve Strength Ratio (RSR) as an approach to examining the offshore jacket platform's ultimate strength. Responses to the offshore jacket platform are base shear design, base shear ultimate, rotation, displacement, and moment, which illustrate the behaviour of the offshore jacket platform. Eight combinations of environmental load directions are applied at 0°, 45°, 90°, 135°, 180°, 225°, 270°, and 315° to obtain the structure's weakest part. 45° is the critical direction for maximum design WD, while 90° is the critical direction for minimum design WD. © 2022, The Authors. All rights reserved.

关键词： Drilling platforms

来源：评论

学校读者我要写书评

暂无评论

Exploring Security Threats by Hardware-Faults in Approximate Arithmetic Computing

Exploring Security Threats by Hardware-Faults in Approximate...

引用

Annual IEEE Northeast Workshop on Circuits and Systems (NEWCAS)

作者： Morgana M. A. Da Rosa Eduardo A. C. Da Costa Rafael I. Soares Sergio Bampi Graduate Program on Computing Federal University of Pelotas (UFPel) Pelotas Brazil Graduate Program on Electronic Engineering and Computing Catholic University of Pelotas (UCPel) Pelotas Brazil PPGC & PGMICRO - Informatics Institute Federal University of Rio Grande do Sul (UFRGS) Porto Alegre Brazil

Approximate computing (AxC) emerged as a design alternative to boost design efficiency by leveraging the inherent error resiliency of many applications. Recent literature shows attackers could exploit some AxC mechanisms to create new attack surfaces. This work proposes integrity checking and exclusive logic-based methods detect attacks by hardware faults on AxC systems. During ASIC-based synthesis, we investigate the security vulnerabilities of the Approximate Parallel Prefix Adder (AxPPA). We compare the expected output of the designer with the output netlists of ASIC-based synthesis. We propose a verification methodology consisting of a golden model (GM) described in a Simulink model and the DUT represented at the netlist level in a standard cell library after logic synthesis. Experimental results show that the AxPPA has an error range of 1.263 × 10 −5 to 0.0098 concerning the designer’s expected output under ASIC-based synthesis attacks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Accuracy-, Delay- and Area-Driven Evaluation of Lower-Part Approximate Parallel Prefix Adder

Accuracy-, Delay- and Area-Driven Evaluation of Lower-Part A...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Morgana M. A. Rosa Eduardo Costa Rafael Soares Sergio Bampi Graduate Program on Computing Federal University of Pelotas (UFPel) Pelotas Brazil Graduate Program on Electronic Engineering and Computing Catholic University of Pelotas (UCPel) Pelotas Brazil PPGC & PGMICRO - Informatics Institute Federal University of Rio Grande do Sul (UFRGS) Porto Alegre Brazil

This work proposes an accuracy-driven evaluation model of an approximate adder (AxA) called an approximate parallel prefix adder (AxPPA). It explores the significance of approximate computing (AxC) in optimizing performance and energy efficiency in computer systems by accepting minor accuracy trade-offs. We examine the AxPPA through a meticulous error analysis model and an automated analysis framework that comprehensively evaluates area and delay based on the fundamental equations of parallel prefix adders (PPAs). Additionally, it emphasizes the importance of lower-part approximation in adders, effectively addressing the elongation of carry chains and enhancing overall efficiency. The choice of approximation method directly impacts computational accuracy, resulting in variations in the number of approximated bits and carry chain length for a given tolerance level. Conducting a thorough comparison of accuracy trade-offs requires a unique design and simulation for each unit and approximation level, which can be time-consuming, particularly in larger circuits. Therefore, the proposed approach facilitates the exploration of larger circuit design space encompassing multiple AxAs, significantly minimizing time investment. In our experiments, the accuracy-driven evaluation of the lower part approximation method in AxA took 71.268 milliseconds for 1 million random inputs, with a K -bits approximation ranging from 1 to 16. The results indicate that AxPPA exhibits a minor error magnitude among the explored literature AxAs, being approximately 50.97% more accurate on average.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Ultra Low-Energy VLSI Approximate Discrete Haar Wavelet Transform for ECG Data Compression

An Ultra Low-Energy VLSI Approximate Discrete Haar Wavelet T...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Arthur Cardozo Morgana M. A. Rosa Rafael Soares Eduardo Costa Sergio Bampi Graduate Program on Computing Federal University of Pelotas (UFPel) Pelotas Brazil Graduate Program on Electronic Engineering and Computing Catholic University of Pelotas (UCPel) Pelotas Brazil PPGC & PGMICRO - Informatics Institute Federal University of Rio Grande do Sul (UFRGS) Porto Alegre Brazil

This work proposes an ultra-low-energy ECG data compression with VLSI DHWT-based (discrete Haar wavelet transform) architecture to enable storage and transmission in resource-constrained environments. We present original, pruned, and approximate DHWT (ODHWT, PDHWT, and AxDHWT, respectively) hardware architectures for ECG data compression at ultra-high energy efficiency. Our best proposal employing the AxDHWT hardware architecture requires just five additions only. Using a PDHWT technique to improve energy efficiency observes the evolution of the signal-to-noise ratio and the ultimate impact on the ECG data compression application. The DHWT-based configurations architecture proposal achieves a minimum compression ratio of 0.125 (i.e., 1/8) and a PRD (percent root difference) <1.34. We implemented the VLSI architectures in 65nm CMOS technology in maximum and fixed frequencies and two different supply voltages. The AxDHWT occupies a die area of 0.64mm 2 . The measured total power is $0.534\mu {\mathrm {W}}$, the higher energy-savings among the ECG data compression architectures.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improved accuracy of long short term memory (LSTM) algorithm in chili price prediction

引用

AIP Conference Proceedings 2024年第1期3222卷

作者： Rizki Ramadhansyah Benny Benyamin Nasution Ade Candra Informatics Engineering Master Program Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Computer Engineering Program Computer Engineering and Informatics Politeknik Negeri Medan Medan Indonesia

The unstable price of chili is still a serious problem in society. Many previous studies have created systems that can predict chili prices. However, there are no chili price prediction results that are considered quite accurate and consistent. So the problem is overcome by processing chili price data using interpolation and dropna on missing values in order to maintain data quality and using the Long Short Term Memory (LSTM) algorithm development in predicting chili prices. This LSTM development was carried out to improve the inconsistent chili price prediction results due to the high error value. LSTM development is carried out in the cell state (ct) and hidden state (ht) with the aim of obtaining better prediction results. Then the accuracy of the error value obtained from the LSTM development in Labuhanbatu district is MAE = 2.589, RMSE = 3.419, and MSE = 11.695.900. This value is lower than using the original LSTM and only using dropna in processing missing value data, namely MAE = 5.517, RMSE = 7.930, and MSE = 62.900.289. Then the difference in percentage error value from the comparison is MAE = 53.07%, RMSE = 56.88%, and MSE = 81.41%. Therefore, it is expected that the low error value results from the development of LSTM can be an indicator of increasing the accuracy of chili price prediction results and making the results more consistent.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Early Detection and Classification of Melanoma Based on Android MobileNet V2 Convolutional Neural Network

Early Detection and Classification of Melanoma Based on Andr...

引用

International Seminar on Application for Technology of Information and Communication (ISemantic)

作者： Jasmine Iswarini Dyah Prabandari Christy Atika Sari Eko Hari Rachmawanto Candra Irawan Bilal R. Altamer Mohamed Ayad Alkhafaji Study Program in Informatics Engineering University of Dian Nuswantoro Semarang Indonesia Study Program in Information Systems University of Dian Nuswantoro Semarang Indonesia Mosul University Presidency University of Mosul Mosul Iraq Department of Computer Science National University of Science and Technology DhiQar Iraq

Melanoma is a malignant form of cancer that affects the skin and has a particularly high mortality rate, so it requires early detection to increase the level of safety for users. Diagnosis and detection of skin cancer are usually done through manual screening and visual inspection. This process requires a long time, has high complexity, is subjective, and is prone to errors. CNN is one of the algorithms with advantages in accurate classification. In this research, early detection and classification of melanoma cancer were carried out based on two classes, namely benign and malignant using the Convolutional Neural Network method. Our proposed method yields an accuracy of 81.11% for the validation data. The accuracy results obtained can be improved by using more datasets and increasing the number of layers used. This study uses the CNN method using MobileNet V2 architecture to detect melanoma skin cancer. The class used is benign and malignant.

关键词：

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：