Showing 8 results for Machine Learning
Mohammad Reza Mehregan, Arman Rezasoltani, Amir Mohammad Khani, Ali Hosseinzade Kashan,
Volume 0, Issue 0 (10-2025)
Abstract
In the modern industrial view, it is strategically imperative to predict failure of industrial machinery with a view to reducing the occurrence of unexpected failures and enhancing operational efficiency. This study seeks to introduce a new hybrid machine learning model for predictive maintenance, combining the use of deep learning and advanced ensemble machine learning models. The model presented follows a stacking ensemble structure, where XGBoost, CatBoost, Gradient Boosting, and a deep neural network are base learners. Thereafter, the LightGBM, acting as a meta-model, is used to collect its predictions. Further, in this study, the Optuna hyperparameter optimization framework is employed to optimize the hyperparameters automatically, and the NearMiss algorithm solves the class imbalance problem by enhancing the representation of the minority class and removing the bias in favor of the majority class. As can be seen in the experimental results, the combined model outperforms the single models, achieving an outstanding accuracy of 96.17%. This is followed by a precision of 97.86%, a recall of 94.4%, and an F1 score of 96.1%. It is worth noting that though the XGBoost models' independent results were high (with an F1 score of 89/41) and better than the 16 individual models studied in this paper and regarded as a comparison to the hybrid model, the hybrid model significantly defeated the independent models by nearly 7 percentage points, hence the strong suit of the smart ensemble framework in model combination. The model has been tried using industrial data with 10000 records of a milling machine system, which is representative of most industrial machinery. The model aids in making decisions in preventive maintenance processes in a more informed and timely way by detecting failures accurately before they happen, avoiding unwanted situations of unplanned downtime and operation costs. One can arrive at the conclusion based on these results that the mentioned hybrid model can offer a solid and workable way of predicting failures in the industrial context and can also be integrated into the actual maintenance processes without any issues.
Maria Moghadam, Iraj Mahdavi, Ali Tajdin, Babak Shirazi,
Volume 0, Issue 0 (10-2025)
Abstract
Addressing the complex challenges of supply chain management requires integrating sustainable practices, advanced technologies, and innovative solutions. This review article explores the concept of sustainable closed-loop supply chains as a means to balance economic, social, and environmental goals. We examine the relationship between sustainable closed-loop supply chains and advanced technologies such as artificial intelligence, machine learning, game theory, and metaheuristic algorithms. Various aspects of supply chain models, sustainability, and the integration of innovative solutions are analyzed to identify key challenges and opportunities in the implementation of sustainable closed-loop supply chains. We highlight the potential benefits of adopting such practices, including cost savings, enhanced brand reputation, and increased customer loyalty. The article also discusses the importance of managing risks associated with cost, environment, social issues, and operations. Our review emphasizes the need for ongoing research and collaboration among stakeholders to address existing research gaps and foster a comprehensive understanding of sustainable closed-loop supply chains. This includes empirical studies on real-world implementation, advanced optimization techniques, sustainable business models, and policy frameworks. Ultimately, this article aims to contribute to the development of more resilient, efficient, and sustainable supply chains that benefit businesses and society alike.
Vankamamidi S Naresh, O Sri Nagesh, S Sivaranjanireddi,
Volume 31, Issue 2 (6-2020)
Abstract
Cognitive based (Chatbot) blood bank provides the communication platform among the stakeholders of blood bank. In the past the blood recipient will have to contact the blood bank and the blood donors individually, which is a time consuming process. To address this issue in this paper we propose a Secure Dynamic Interactive Blood Bank based on Cognitive Computing which can fulfill the blood request of the needy with less hardship. Hence the proposed work aims to overcome this problem by requesting the recipient to simply send a message to a chatbot. The motivated individuals who are willing to donate blood can register their name by interacting with the chatbot. If the requested blood group is available at the blood bank / registered donor then the recipient will get contact details of the blood bank / registered donors available at that instant. Donor data will be maintained in Cloud database. The proposed system is a cognitive chatbot, which acts as a communication platform among the stakeholders such as blood bank, blood donor and the needy. This system is built using cognitive technology of Google; it makes conversations using chatbots very similar to human conversations, thereby making the proposed system more efficient compared to the existing ones.
K.v.k Sasikanth, K. Samatha, N. Deshai, B. V. D. S. Sekhar, S. Venkatramana,
Volume 31, Issue 3 (9-2020)
Abstract
The Today’s interconnected world generates huge digital data, while millions of users share their opinions, feelings on various topics through popular applications such as social media, different micro blogging sites, and various review sites on every day. Nowadays Sentiment Analysis on Twitter Data which is considered as a very important problem particularly for various organizations or companies who want to know the customers feelings and opinions about their products and services. Because of the data nature, variety and enormous size, it is very practical for several applications, range from choice and decision creation to product assessment. Tweets are being used to convey the sentiment of a tweeter on a specific topic. Those companies keeping survey millions of tweets on some kind of subjects to evaluate actual opinion and to know the customer feelings. This paper major goal would be to significantly collect, recognize, filter, reduce and analyze all such relevant opinions, emotions, and feelings of people on different product or service could be categorized into positive, negative or neutral because such categorization improves sales growth about a company's products or films, etc. We initiate that the Naïve Bayes classifier be the mainly utilized machine learning method for mining feelings from large data like twitter and popular social network because of its more accuracy rates. In this paper, we scrutinize sentiment polarity analysis on Twitter data in a distributed environment, known as Apache Spark.
Sofia Kassami, Abdelah Zamma, Souad Ben Souda,
Volume 33, Issue 3 (9-2022)
Abstract
Modeling supply chain planning problems is considered one of the most critical planning issues in Supply Chain Management (SCM). Nowadays, decisions making must be sufficiently sustainable to operate appropriately in a complex and uncertain environment of the market for many years to beyond the next decade. Therefore, making these decisions in the presence of uncertainty is a critical issue,as highlighted in a large number of relevant publications over the past two decades.The purpose of this investigation is to model a multilevel supply chain problem and determine the constraints that prevent the flow from performing properly, subject to various sources and types of uncertainty that characterize the flow. Therefore, it attempts to establish a generic model that relies on the stochastic approach. Several studies have been conducted on uncertainty in order to propose an optimal solution to this type of problem. Thus, in this study, we will use the method of "Mixed integer optimization program" which is the basis of the algorithm that will be employed. This inaccuracy of the supply chain is handled by the fuzzy sets. In this paper, we intend to provide a new model for determining optimal planning of tactical and strategical decision-making levels, by building a conceptual model. Therefore, it enables us to model the mathematical programming problem. We investigate in this attempt, attention to solving the mathematical model. So in the resolution we are going through the algorithm in machine learning, therefore providing as in the end an optimal solution for the planning of production.
Iwa Kustiyawan, Mas Rahman Roestan, Catur Riani,
Volume 34, Issue 4 (12-2023)
Abstract
This research aims to identify the initial OEE (Overall Equipment Efficiency) values on automated packaging machines with a 2d barcode track and trace system. Quantitative research methods used to obtain the OEE value, analysis of factors affecting the OEE values, developing a strategy to make improvements, and evaluate these strategies on the level of machine productivity. The importance of the subject lies in the need to improve the efficiency and productivity of pharmaceutical packaging processes. The pharmaceutical industry is facing increasing pressure to optimize operations and reduce waste. Implementing effective performance measurement tools such as Overall Equipment Effectiveness (OEE) can help identify areas for improvement and enhance productivity. This study found that the track-and-trace system was below the company's standard, indicating room for improvement. Then, countermeasures were implemented to increase productivity and machine effectiveness, and the initial OEE value of the automated packaging machine with 2D barcodes improved. Thus, this study demonstrated the effectiveness of the proposed framework in evaluating and improving OEE in pharmaceutical packaging processes, highlighting the significance of digitalization and automation technologies in enhancing productivity.
Arifa Khan, Saravanan P,
Volume 35, Issue 3 (9-2024)
Abstract
Optimizing production in the plastic extrusion industry is a pivotal task for small scale industries. To enhance the efficiency in today’s competitive market being a small-scale manufacturer over their peers is challenging. With the limited resources, having constraints on manpower, capital, space, often facing fluctuations in demand and production, simultaneously maintaining high quality became very important for the success. Among the plethora of KPIS used in manufacturing, Overall Equipment Effectiveness (OEE) stands out as corner stone. In this study, we collected real-world data from a plastic extrusion company. i.e., an HDPE Pipe manufacturing company. It serves as the backdrop for our study, this is based on the plastic extrusion sector and set out a goal of enhancing OEE through a comparative investigation of various ML models. To forecast and estimate OEE values, we used various Machine Learning models and examine each algorithm’s performance using metrics like Mean Squared Error (MSE) and model comparisons using the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC), creating a comprehensive picture of each algorithm’s strength which enables the small businesses to make informed decisions and empowers them to stay agile and adapt to the changes in the manufacturing environment.
Mehdi Dadehbeigi, Ali Taherinezhad, Alireza Alinezhad,
Volume 36, Issue 1 (3-2025)
Abstract
Today, data mining and machine learning are recognized as tools for extracting knowledge from large datasets with diverse characteristics. With the increasing volume and complexity of information in various fields, decision-making has become more challenging for managers and decision-making units. Data Envelopment Analysis (DEA) is a tool that aids managers in measuring the efficiency of the units under their supervision. Another challenge for managers involves selecting and ranking options based on specific criteria. Choosing an appropriate multi-criteria decision-making (MCDM) technique is crucial in such cases. With the spread of COVID-19 and the significant financial, economic, and human losses it caused, data mining has once again played a role in improving outcomes, predicting trends, and reducing these losses by identifying patterns in the data. This paper aims to assess and predict the efficiency of countries in preventing and treating COVID-19 by combining DEA and MCDM models with machine learning models. By evaluating decision-making units and utilizing available data, decision-makers are better equipped to make effective decisions in this area. Computational results are presented in detail and discussed in depth.
