Showing papers in "Procedia Computer Science in 2021"

TL;DR: A deep learning method in image classification for the detection of colorectal cancer with ResNet architecture demonstrates the profoundly reliable and reproducible outcomes for biomedical image analysis.

TL;DR: It is found that CRISP-DM is still a de-factor standard in data mining, but there are challenges since the most studies do not foresee a deployment phase and the contribution of the paper is to identify best practices and process phases in which data mining analysts can be better supported.

TL;DR: Facebook’s Prophet Forecasting model and ARIMA Forecasting Model are compared to compare their performance and accuracy on dataset containing the confirmed cases, deaths, and recovered numbers, obtained from the Kaggle website to forecast the trend of the disease in Indonesia.

TL;DR: This paper aims to present a study of the RPA tools associated with AI that can contribute to the improvement of the organizational processes associated with Industry 4.0.

TL;DR: This research makes use of Long-Short Term Memory (LSTM) model as well as the Word2Vec model to develop a sentiment assessment technique with respect to hotel reviews, particularly in Indonesian language.

TL;DR: In this article, the authors applied five machine learning algorithms: Support Vector Machine (SVM), Random Forest, Logistic Regression, Decision tree (C4.5) and KNN on the Breast Cancer Wisconsin Diagnostic dataset, after obtaining the results, a performance evaluation and comparison is carried out between these different classifiers.

TL;DR: The presented model systematically supports the selection of an appropriate procedural model for a concrete project based on 15 criteria subsumed under the following categories: scope, time, costs, organization context, and project-team characteristics.

TL;DR: How deep learning or deep neural networks can facilitate flexible IDS with learning capability to detect recognized and new or zero-day network behavioral features, consequently ejecting the systems intruder and reducing the risk of compromise is proposed.

TL;DR: This design adopts the idea of “Internet of Things close to life and easy to use” as a design concept, and builds a smart home system based on the internet of things.

TL;DR: In this paper, a pre-trained transformer model BERT (Bidirectional Encoder Representations from Transformers) is fine-tuned to execute the task of detecting spam emails from non-spam (HAM).

TL;DR: This study provides an analysis of the numerous state-of-the-art NLP and ML strategies currently in use to identify phishing emails at various stages of the attack, with an emphasis on ML strategies.

TL;DR: In this article, the authors investigate enabling technologies of Industry 4.0, focusing on technologies that have a greater impact on safety management, identifying and describing the main characteristics of such technologies according to their use in an industrial environment.

TL;DR: This research aims to provide governments with an accurate prediction of Indonesia’s future exports by building an integrated machine learning model that integrates ARIMA and LSTM models based on their specialties to obtain the most accurate model.

TL;DR: In this paper, the authors proposed a novel real-time object detection model based on You Only Look Once Version 2 (YOLO-v2) deep learning framework for tiny vehicle objects.

TL;DR: A system for automatic detection and prevention cyberbullying considering the main characteristics of cyberbullies such as Intention to harm an individual, Repeatedly and over time and using abusive curl language or hate speech using supervised machine learning is described.

TL;DR: A systematic literature review of wearable IoT devices for healthcare is conducted and the utilization of wearable devices in handling the problem in the healthcare aspects, including disease detection, monitoring, and curing is discussed.

TL;DR: A table is developed that links the relationship between quality management practices and Industry 4.0 technologies that improve quality, as it aimed to explore how quality management processes could benefit and adapt in the era of digital technologies.

TL;DR: The findings indicate that the level of e-banking was 77% and positively linked with the IT governance applied by the banks, and it is recommended that the regulators to encourage banking sector to apply more e-Banking applications and tools.

TL;DR: A dedicated dataset was built that includes medical information related to patients being treated in the ”AOU Federico II” hospital of Naples that aims to predict the LT4 treatment trend for patients suffering from hypothyroidism, using different machine learning algorithms.

TL;DR: This paper investigates recent publications combining the blockchain technology and supply chain management and classifies them regarding the complexity to be mapped on the blockchain, identifying the increase of supply chain transparency as the main objective.

TL;DR: In this article, a machine learning model based on the multilayer perceptron artificial neural network structure was used, which effectively predicts the behavior of the series mentioned in up to six days.

TL;DR: A-Star’s current usage in the field of pathfinding is examined, comparing A* to other search algorithms, and potential future developments for A-Star's development are analyzed.

TL;DR: The paper elaborates on the concepts of digital infrastructure, service-oriented architecture, and microservices, and outlines the prerequisites for obtaining a sustainable digital infrastructure based on services, in which cloud services constitute an important part.

TL;DR: In this article, the security and application of WSNs are emphasized, and the node deployment environment of wireless sensor networks is usually very complex, and it is necessary to study the security of the WSN nodes so as to reduce security threats and network attacks.

TL;DR: A survey was conducted to identify the students’ preference for their convenience in the adoption of online learning and the results can be a reference for educators to make the most suitable tools as an option for the implementation of Open and Distance Learning.

TL;DR: The focus of this research is to expose the main security aspects of this specific architecture, in this cost-effective era, to disassemble the core components of a given type of application.

TL;DR: In this paper, the authors provide an overview on the technology of digital twin and its application domains with a detailed discussion on its networking requirements and proposed enabling technologies to fulfill them, including low latency of real-time communication, data security and quality.

TL;DR: This paper presents an automatic solution for the detection of clandestine waste dumps using unmanned aerial vehicle images in the Saint Louis area of Senegal, West Africa and shows that the model recognizes well the areas concerned but presents difficulties on some areas lacking clear ground truths.

TL;DR: What tools of the Industry 4.0 are used by the companies, what are the reasons that push companies to use these tools and what advantages are from their use are analyzed to show that the most important I4.0 tools integrated with lean production will be IoT and Big Data, which will allow companies to improve their flexibility and productivity.

TL;DR: An Auto-regressive Integrated Moving Average (ARIMA) model is proposed to forecast better visibility for the variant value of parameters p, d, q using the grid technique to show that ARIMA has the lowest MSE value.