Deep Learning Processing Research Articles

Alzheimer's Disease Prediction Using Fly-Optimized Densely Connected Convolution Neural Networks Based on MRI Images.

Alzheimer's is a degenerative brain cell disease that affects around 5.8 million people globally. The progressive neurodegenerative disease known as Alzheimer's Disease (AD), affects the frontal cortex, the part of the brain in charge of memory, language, and cognition. As a result, researchers are utilizing a variety of machine-learning techniques to create an automated method for AD detection. The massive data collected during ROI and biomarker identification takes longer to handle using current methods. This study uses metaheuristic-tuned deep learning to detect the AD-affected region. The research utilizes advanced deep learning and image processing techniques to enhance early and accurate diagnosis of Alzheimer's disease, potentially enhancing patient outcomes and prompt therapy. The capacity of deep neural networks to extract complex patterns from magnetic resonance imaging (MRI) scans makes them indispensable in the diagnosis of AD since they allow the detection of minor aberrations and complex alterations in brain structure and composition. An adaptive histogram approach processes the collected photographs, and a weighted median filter is used in place of the noisy pixels. The next step is to identify the issue region using a deep convolution network-based clustering segmentation process. A correlated information theory approach is used to extract various textural and statistical features from the separated regions. Lastly, the selected features are probed by the fly-optimized densely linked convolution neural networks. The method surpasses state-of-the-art techniques in sensitivity (15.52%), specificity (15.62%), accuracy (9.01%), error rate (11.29%), and F-measure (10.52%) for recognizing AD-impacted regions in MRI scans using the Kaggle dataset.

Learning Virtual View Selection for 3D Scene Semantic Segmentation.

2D-3D joint learning is essential and effective for fundamental 3D vision tasks, such as 3D semantic segmentation, due to the complementary information these two visual modalities contain. Most current 3D scene semantic segmentation methods process 2D images "as they are", i.e., only real captured 2D images are used. However, such captured 2D images may be redundant, with abundant occlusion and/or limited field of view (FoV), leading to poor performance for the current methods involving 2D inputs. In this paper, we propose a general learning framework for joint 2D-3D scene understanding by selecting informative virtual 2D views of the underlying 3D scene. We then feed both the 3D geometry and the generated virtual 2D views into any joint 2D-3D-input or pure 3D-input based deep neural models for improving 3D scene understanding. Specifically, we generate virtual 2D views based on an information score map learned from the current 3D scene semantic segmentation results. To achieve this, we formalize the learning of the information score map as a deep reinforcement learning process, which rewards good predictions using a deep neural network. To obtain a compact set of virtual 2D views that jointly cover informative surfaces of the 3D scene as much as possible, we further propose an efficient greedy virtual view coverage strategy in the normal-sensitive 6D space, including 3-dimensional point coordinates and 3-dimensional normal. We have validated our proposed framework for various joint 2D-3D-input or pure 3D-input based deep neural models on two real-world 3D scene datasets, i.e., ScanNet v2 and S3DIS, and the results demonstrate that our method obtains a consistent gain over baseline models and achieves new top accuracy for joint 2D and 3D scene semantic segmentation. Code is available at https://github.com/smy-THU/VirtualViewSelection.

Advancements and Challenges in the Image-Based Diagnosis of Lung and Colon Cancer: A Comprehensive Review.

Image-based diagnosis has become a crucial tool in the identification and management of various cancers, particularly lung and colon cancer. This review delves into the latest advancements and ongoing challenges in the field, with a focus on deep learning, machine learning, and image processing techniques applied to X-rays, CT scans, and histopathological images. Significant progress has been made in imaging technologies like computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET), which, when combined with machine learning and artificial intelligence (AI) methodologies, have greatly enhanced the accuracy of cancer detection and characterization. These advances have enabled early detection, more precise tumor localization, personalized treatment plans, and overall improved patient outcomes. However, despite these improvements, challenges persist. Variability in image interpretation, the lack of standardized diagnostic protocols, unequal access to advanced imaging technologies, and concerns over data privacy and security within AI-based systems remain major obstacles. Furthermore, integrating imaging data with broader clinical information is crucial to achieving a more comprehensive approach to cancer diagnosis and treatment. This review provides valuable insights into the recent developments and challenges in image-based diagnosis for lung and colon cancers, underscoring both the remarkable progress and the hurdles that still need to be overcome to optimize cancer care.

Terrorism group prediction using feature combination and BiGRU with self-attention mechanism.

The world faces the ongoing challenge of terrorism and extremism, which threaten the stability of nations, the security of their citizens, and the integrity of political, economic, and social systems. Given the complexity and multifaceted nature of this phenomenon, combating it requires a collective effort, with tailored methods to address its various aspects. Identifying the terrorist organization responsible for an attack is a critical step in combating terrorism. Historical data plays a pivotal role in this process, providing insights that can inform prevention and response strategies. With advancements in technology and artificial intelligence (AI), particularly in military applications, there is growing interest in utilizing these developments to enhance national and regional security against terrorism. Central to this effort are terrorism databases, which serve as rich resources for data on armed organizations, extremist entities, and terrorist incidents. The Global Terrorism Database (GTD) stands out as one of the most widely used and accessible resources for researchers. Recent progress in machine learning (ML), deep learning (DL), and natural language processing (NLP) offers promising avenues for improving the identification and classification of terrorist organizations. This study introduces a framework designed to classify and predict terrorist groups using bidirectional recurrent units and self-attention mechanisms, referred to as BiGRU-SA. This approach utilizes the comprehensive data in the GTD by integrating textual features extracted by DistilBERT with features that show a high correlation with terrorist organizations. Additionally, the Synthetic Minority Over-sampling Technique with Tomek links (SMOTE-T) was employed to address data imbalance and enhance the robustness of our predictions. The BiGRU-SA model captures temporal dependencies and contextual information within the data. By processing data sequences in both forward and reverse directions, BiGRU-SA offers a comprehensive view of the temporal dynamics, significantly enhancing classification accuracy. To evaluate the effectiveness of our framework, we compared ten models, including six traditional ML models and four DL algorithms. The proposed BiGRU-SA framework demonstrated outstanding performance in classifying 36 terrorist organizations responsible for terrorist attacks, achieving an accuracy of 98.68%, precision of 96.06%, sensitivity of 96.83%, specificity of 99.50%, and a Matthews correlation coefficient of 97.50%. Compared to state-of-the-art methods, the proposed model outperformed others, confirming its effectiveness and accuracy in the classification and prediction of terrorist organizations.

A Computational Deep Fuzzy Network-Based Neuroimaging Analysis for Brain Hemorrhage Classification.

The boundaries and regions between individual classes in biomedical image classification are hazy and overlapping. These overlapping features make predicting the correct classification result for biomedical imaging data a difficult diagnostic task. Thus, in precise classification, it is frequently necessary to obtain all necessary information before making a decision. This paper presents a novel deep-layered design architecture based on Neuro-Fuzzy-Rough intuition to predict hemorrhages using fractured bone images and head CT scans. To deal with data uncertainty, the proposed architecture design employs a parallel pipeline with rough-fuzzy layers. In this case, the rough-fuzzy function functions as a membership function, incorporating the ability to process rough-fuzzy uncertainty information. It not only improves the deep model's overall learning process, but it also reduces feature dimensions. The proposed architecture design improves the model's learning and self-adaptation capabilities. In experiments, the proposed model performed well, with training and testing accuracies of 96.77% and 94.52%, respectively, in detecting hemorrhages using fractured head images. The comparative analysis shows that the model outperforms existing models by an average of 2.6 ±0.90% on various performance metrics.

AN INTROSPECTION INTO THE EFFICIENT DATA ANALYSIS WITH ARTIFICIAL INTELLIGENCE

By using sophisticated algorithms and machine learning approaches to improve accuracy, artificial intelligence (AI) dramatically improves data analysis. Large datasets can be processed rapidly by AI systems, which can also spot patterns and produce extremely accurate forecasts. More accurate insights and decision-making are made possible by artificial intelligence (AI) through the use of methods like neural networks, deep learning, and natural language processing. The combination of artificial intelligence with data analysis reduces human error, reveals unnoticed relationships, and streamlines procedures in a range of industries, including finance and healthcare. The ongoing development of AI technologies promises even more efficiency and accuracy, revolutionizing the way data is used and understood.

Deep Learning of Cancer Stem Cell Morphology.

Knowledge regarding cancer stem cell (CSC) morphology is limited, and more extensive studies are therefore required. Image recognition technologies using artificial intelligence (AI) require no previous expertise in image annotation. Herein, we describe the construction of AI models that recognize the CSC morphology in cultures and tumor tissues. The visualization of the AI deep learning process enables insight to be obtained regarding unrecognized structures in an image.

Enhancing Web Application Security: A Deep Learning and NLP-based Approach for Accurate Attack Detection

Abstract— Nowadays, web attacks have become more complicated, leading to the difficulty of traditional web application firewalls (WAFs) in recognizing those threats, especially when dealing with new attacks. Hence, machine learning/deep learning (ML/DL) approaches have been applied to the field of web attack detection with proven success. However, most existing ML/DL-based web attack detectors focus on a specific type of attack due to the difference in the payload of various attacks, which sets a border to the capability of those solutions in detecting new attack types. In this paper, we propose a novel DL-based solution for web attack detection, named DL-WAD, leveraging deep learning and natural language processing techniques. Moreover, DL-WAD is designed with a data preprocessing mechanism aimed at differentiating between regular web requests and malicious ones that carry attack payloads encompassing multiple types of web attacks. The experiment results indicate the effectiveness of our solution in protecting the target web services from a wide range of attacks with high accuracy.

Artificial Intelligence in Medical Filed

In the healthcare industry artificial intelligence (AI) has become a disruptive technology that is revolutionizing patient care, diagnostics, and research. This abstract provides an overview of the main points and findings related to AI in healthcare exploring its advancements, applications, and ethical challenges. The rapid growth of AI technologies has led to remarkable improvements in healthcare. AI algorithms have demonstrated exceptional capabilities in analyzing number of patient data, enabling early disease detection, personalized treatment plans, and improved patient outcomes. Machine learning algorithms, such as deep learning and natural language processing, have been effectively employed to analyze medical images, predict disease progression, and support clinical decision-making. AI applications in healthcare span across various domains, including radiology, pathology, genomics, drug discovery, and patient monitoring. Telemedicine and AI-driven virtual health assistants have extended healthcare access to remote areas, empowering patients with self-care tools and enabling real-time communication with healthcare professionals. While it's undeniable that AI brings significant advantages to the field of healthcare, it's vital to emphasize the importance of ethical concerns. Additionally, ensuring that AI algorithms are transparent and interpretable is essential for establishing trust and promoting the responsible use of AI technology in clinical environments.

Variational encoding based on factorized temporal-channel fusion and feature fusion for interpretable remaining useful life prediction

The Prognostics Health Management (PHM) of modern equipment typically employs Remaining Useful Life (RUL) prediction to assess health status. Existing mainstream RUL prediction methods have improved prediction performance by adopting data-driven approaches based on deep learning. However, most methods overlook the impact of noise interference caused by the redundancy of sensor data across channels, leading to a decrease in RUL prediction performance. Furthermore, these methods lack transparency and interpretability, which are crucial for maintenance personnel in accurately diagnosing the degradation process of equipment RUL. Therefore, we propose a Factorized temporal-channel fusion and Feature fusion based Variational Encoding (FFVE) for interpretable RUL prediction. By utilizing the factorization operation, we construct the Factorized Temporal-Channel Fusion (FTCF) block to learn temporal and channel dependencies, thereby reducing redundancy between channels. Through the feature fusion operations which mix original information with extracted feature information, we augment the original information that is lost during the deep network learning process, consequently avoiding performance degradation caused by increasing network depth. Through the above encoding process, sensor data is effectively compressed into a 3D latent space for predicting and interpreting the equipment degradation process. Extensive experiments were conducted on two datasets of the C-MAPSS turbofan aircraft engine and the NASA lithium-ion battery. The results demonstrate that our method outperforms state-of-the-art methods in terms of prediction accuracy. Additionally, our study provides a novel visual means of assessing turbofan engine health status, elucidating the engine RUL degradation process learned by our method.

Yolov3 Tabanlı Atık Tespit Sistemleri

Today, the increase in the number of people, advances in industry and technology cause an increase in the number of wastes generated with the acceleration of production. It is important for the future of our country and the world that these wastes are more easily identified and recycled. In the process of recycling wastes, the classification of wastes as well as their collection requires costly energy and manpower. Wastes are basically separated into paper, plastic, glass and metal. Various studies have been carried out to complete these processes in a shorter and easier way with technologies such as artificial intelligence, deep learning and image processing. In this study, a dataset of paper, plastic and food and beverage wastes that are common in the environment was created. In this dataset, paper cups, plastic water bottles and fast food wastes were detected from different locations in nature and photographed. These images were labeled and trained and tested with YoloV3 in deep learning algorithms. In addition, in order to compare the performance of the new dataset, studies were conducted on a global dataset used in the literature. As a result of the studies, it was observed that it was successful in classifying the newly created dataset and the global dataset.

COVID-19 infection segmentation using hybrid deep learning and image processing techniques

The coronavirus disease 2019 (COVID-19) epidemic has become a worldwide problem that continues to affect people’s lives daily, and the early diagnosis of COVID-19 has a critical importance on the treatment of infected patients for medical and healthcare organizations. To detect COVID-19 infections, medical imaging techniques, including computed tomography (CT) scan images and X-ray images, are considered some of the helpful medical tests that healthcare providers carry out. However, in addition to the difficulty of segmenting contaminated areas from CT scan images, these approaches also offer limited accuracy for identifying the virus. Accordingly, this paper addresses the effectiveness of using deep learning (DL) and image processing techniques, which serve to expand the dataset without the need for any augmentation strategies, and it also presents a novel approach for detecting COVID-19 virus infections in lung images, particularly the infection prediction issue. In our proposed method, to reveal the infection, the input images are first preprocessed using a threshold then resized to 128 × 128. After that, a density heat map tool is used for coloring the resized lung images. The three channels (red, green, and blue) are then separated from the colored image and are further preprocessed through image inverse and histogram equalization, and are subsequently fed, in independent directions, into three separate U-Nets with the same architecture for segmentation. Finally, the segmentation results are combined and run through a convolution layer one by one to get the detection. Several evaluation metrics using the CT scan dataset were used to measure the performance of the proposed approach in comparison with other state-of-the-art techniques in terms of accuracy, sensitivity, precision, and the dice coefficient. The experimental results of the proposed approach reached 99.71%, 0.83, 0.87, and 0.85, respectively. These results show that coloring the CT scan images dataset and then dividing each image into its RGB image channels can enhance the COVID-19 detection, and it also increases the U-Net power in the segmentation when merging the channel segmentation results. In comparison to other existing segmentation techniques employing bigger 512 × 512 images, this study is one of the few that can rapidly and correctly detect the COVID-19 virus with high accuracy on smaller 128 × 128 images using the metrics of accuracy, sensitivity, precision, and dice coefficient.

The impact of architecturally qualified data in deep learning methods for the automatic generation of social housing layouts

The objective of this work is to explore the impact of the data in the automatic generation of social housing layouts with different deep learning models. The design of Social Housing is a subfield of architecture that necessitates, from the architect, a high degree of precision in refining layouts to effectively address both the programmatic requirements and the aspiration to attain the utmost architectural quality to guarantee inhabitants comfort. This dual challenge stands to gain significantly from the incorporation of data-driven generative processes bolstered by machine learning techniques in general and deep learning ones in particular. The most widely used dataset for data-driven layout generation with deep learning methods is RPLAN, a generic floor plan dataset available online. Although it contains a significant amount of plans, it lacks any information about the architectural quality criteria used for the selection of the data. We conducted an initial analysis of the architectural consistency and key quality features of RPLAN. Upon finding several issues that raise doubts about its suitability for training social housing generation models, we proceeded to create PUBLICPLAN, a new dataset based on proposals submitted and evaluated in public architecture competitions in Spain over the past three years. It comprises 2446 distinct layouts extracted from 1279 proposals in Catalonia and the Balearic Islands. All of these layouts demonstrate high architectural standards. Then, we retrained the three most advanced existing models for generating interior plans using PUBLICPLAN and compared their performance to the same models trained with different subsets of RPLAN. Once the models were trained, we conducted several experiments comparing different models and data subsets and evaluating the impact of the quantity and quality of the data on the models' performance. Those experiments involved over two hundred architects and architecture students. We also examined the plausibility of the generated plans being synthetic with a survey asking to distinguish between human and machine generated layout plans. Our results showed that PUBLICPLAN had a significant impact compared to the alternatives with a similar number of cases. In the examination of the feasibility of human-generated plans, over 48.43% of architects and architecture students identified machine-generated plans as being of human origin. Moreover, in qualitative experiments conducted with an equivalent dataset, our qualified dataset PUBLICPLAN demonstrated a significantly superior human rating (72.13%) when evaluated by human assessors, as compared to models trained with RPLAN. This highlights the importance of using qualified datasets in deep learning for the generation of social housing layouts. We also identified challenges and priorities in the research field, both in the deep learning process and architectural design practices.

Dementia Detection from Speech: What If Language Models Are Not the Answer?

A growing focus among scientists has been on researching the techniques of automatic detection of dementia that can be applied to the speech samples of individuals with dementia. Leveraging the rapid advancements in Deep Learning (DL) and Natural Language Processing (NLP), these techniques have shown great potential in dementia detection. In this context, this paper proposes a method for dementia detection from the transcribed speech of subjects. Unlike conventional methods that rely on advanced language models to address the ability of the subject to make coherent and meaningful sentences, our approach relies on the center of focus of the subjects and how it changes over time as the subject describes the content of the cookie theft image, a commonly used image for evaluating one’s cognitive abilities. To do so, we divide the cookie theft image into regions of interest, and identify, in each sentence spoken by the subject, which regions are being talked about. We employed a Long Short-Term Memory (LSTM) neural network to learn different patterns of dementia subjects and control ones and used it to perform a 10-fold cross validation-based classification. Our experimental results on the Pitt corpus from the DementiaBank resulted in a 82.9% accuracy at the subject level and 81.0% at the sample level. By employing data-augmentation techniques, the accuracy at both levels was increased to 83.6% and 82.1%, respectively. The performance of our proposed method outperforms most of the conventional methods, which reach, at best, an accuracy equal to 81.5% at the subject level.

A locally weighted, correlated subdomain adaptive network employed to facilitate transfer learning

Domain adaptation has found extensive applications in diverse fields, including transfer learning, deep learning, and image processing, to effectively address the challenge of mismatched data distributions. Nevertheless, persistent challenges such as limited transfer data and the occurrence of negative transfer continue to exist. These issues not only increase the complexity of model learning but also affect the accuracy of the transfer results. To tackle these challenges, this paper introduces a novel approach called the Related Weighted Subdomain Adaptive Network (RWSAN). This network constructs related subdomain clusters in the source domain to encompass a wider spectrum of associated information. It aims to align target domain subdomains with the related subdomain clusters in the source domain as closely as possible, thus increasing the number of transferable samples from the source domain and solving insufficient transferable samples in some adaptations. To address the issue of negative transfer arising from irrelevant subdomains in the source domain during the transfer process, a related weighted maximum mean discrepancy method is introduced. This method optimizes transfer weights, minimizes the feature distribution disparity between the target domain and the source domain, and mitigates the negative impact of irrelevant subdomains on the target domain, thereby enhancing the accuracy of domain adaptation during transfer. To evaluate the proposed RWSAN method, comprehensive performance tests were conducted using widely used red-green-blue (RGB) and hyperspectral image (HIS) image datasets. The results demonstrate that the RWSAN method effectively resolves insufficient transfer data and negative transfer, proving its high reliability. Additionally, it exhibits excellent performance in error analysis, network convergence analysis, data visualization, and distribution difference.

Beyond Polarity: The Potential Applications and Impacts of Sentiment Analysis and Emotion Detection

Opinion mining and emotion detection are two important techniques in natural language processing that have gained significant attention in recent years. Opinion mining is the process of identifying and extracting subjective information from text, such as opinions, attitudes, and emotions, while emotion detection is the process of identifying and extracting emotions from text. These techniques have a wide range of applications in various domains, including social media analysis, customer feedback analysis, and product reviews. This paper provides an overview of opinion mining and emotion detection techniques in natural language processing. We discuss the various approaches and methods used in opinion mining and emotion detection, including machine learning, deep learning, and natural language processing techniques. We also explore the challenges and limitations of these techniques, including the subjectivity of language, cultural differences, and the lack of labeled data. Furthermore, we examine the current state of the art in opinion mining and emotion detection, highlighting recent research and developments in these areas. We also discuss the potential applications of these techniques in various domains, including marketing, healthcare, and social media analysis. Overall, this paper provides a comprehensive overview of opinion mining and emotion detection in natural language processing. It provides insights into the methods, challenges, and potential applications of these techniques, and highlights the importance of these techniques in understanding and analyzing subjective information in text.

A real-world evaluation of the diagnostic accuracy of radiologists using positive predictive values verified from deep learning and natural language processing chest algorithms deployed retrospectively.

This diagnostic study assessed the accuracy of radiologists retrospectively, using the deep learning and natural language processing chest algorithms implemented in Clinical Review version 3.2 for: pneumothorax, rib fractures in digital chest X-ray radiographs (CXR); aortic aneurysm, pulmonary nodules, emphysema, and pulmonary embolism in CT images. The study design was double-blind (artificial intelligence [AI] algorithms and humans), retrospective, non-interventional, and at a single NHS Trust. Adult patients (≥18 years old) scheduled for CXR and CT were invited to enroll as participants through an opt-out process. Reports and images were de-identified, processed retrospectively, and AI-flagged discrepant findings were assigned to two lead radiologists, each blinded to patient identifiers and original radiologist. The radiologist's findings for each clinical condition were tallied as a verified discrepancy (true positive) or not (false positive). The missed findings were: 0.02% rib fractures, 0.51% aortic aneurysm, 0.32% pulmonary nodules, 0.92% emphysema, and 0.28% pulmonary embolism. The positive predictive values (PPVs) were: pneumothorax (0%), rib fractures (5.6%), aortic dilatation (43.2%), pulmonary emphysema (46.0%), pulmonary embolus (11.5%), and pulmonary nodules (9.2%). The PPV for pneumothorax was nil owing to lack of available studies that were analysed for outpatient activity. The number of missed findings was far less than generally predicted. The chest algorithms deployed retrospectively were a useful quality tool and AI augmented the radiologists' workflow. The diagnostic accuracy of our radiologists generated missed findings of 0.02% for rib fractures CXR, 0.51% for aortic dilatation, 0.32% for pulmonary nodule, 0.92% for pulmonary emphysema, and 0.28% for pulmonary embolism for CT studies, all retrospectively evaluated with AI used as a quality tool to flag potential missed findings. It is important to account for prevalence of these chest conditions in clinical context and use appropriate clinical thresholds for decision-making, not relying solely on AI.

Enhancing local citation recommendation with recurrent highway networks and SciBERT-based embedding

When writing academic papers, referencing statements, claims and previous studies is always an important activity. However, it is considered challenging for scientists to find relevant and appropriate scientific articles which are closely related to their current works in order to reference them in their research. As a consequence of the rapid growth in scientific papers being published every year, researchers might easily get overwhelmed within a huge number of resources. One way to help them find the desired references more easily is to use context-aware citation recommendation. The citation recommender system can automatically provide a list of suitable papers as references based on specified inputs which reflect the researchers’ interests. Among the outstanding achievements of deep learning and natural language processing in recent years, the utilization of deep neural learning architectures have supported to address the problem of citation recommendation. As the result, the neural citation recommendation area has received much attention from the academic community, with the aim of enhancing the precision and correctness of the results of existing citation recommendation systems. Following this research direction, in our paper we present a novel context-aware citation recommendation model, called RHN-DualLCR (Recurrent Highway Networks – Dual Local Citation Recommendation), which integrates Recurrent Highway Networks (RHN), an improved model of the original Bidirectional Long Short-Term Memory (BiLSTM) architecture, and uses a SciBERT-based (Science text of Bidirectional Encoder Representations from Transformers) embedding layer to build up the efficiency of the state-of-the-art local citation recommendation model, which enriches context representation with global information. Our research demonstrates its originality and relevance because we used one of the latest achievements of deep models (RHN model) and natural language processing (SciBERT) applied to the citation recommendation problem. We have conducted experiments on the RHN-DualLCR model on 3 widely known datasets for the citation recommendation problem: ACL-200 (Association for Computational Linguistics), ACL-600 and RefSeer, and also used 2 common evaluation standards Mean Reciprocal Rank (MRR) and the Recall@K (R@K for short) to evaluate the performance of our model. Experimental results show that our proposed model is 3% to 16% better than the original models or state-of-the-art models.

A Deep Learning and Image Processing Pipeline for Object Characterization in Firm Operations

Given the abundance of images related to operations that are being captured and stored, it behooves firms to innovate systems using image processing to improve operational performance that refers to any activity that can save labor cost. In this paper, we use deep learning techniques, combined with classic image/signal processing methods, to propose a pipeline to solve certain types of object counting and layer characterization problems in firm operations. Using data obtained by us through a collaborative effort with real manufacturers, we demonstrate that the proposed pipeline method is able to achieve higher than 93% accuracy in layer and log counting. Theoretically, our study conceives, constructs, and evaluates proof of concept of a novel pipeline method in characterizing and quantifying the number of defined items with images, which overcomes the limitations of methods based only on deep learning or signal processing. Practically, our proposed method can help firms significantly reduce labor costs and/or improve quality and inventory control by recording the number of products in real time, more accurately and with minimal up-front technological investment. The codes and data are made publicly available online through the INFORMS Journal on Computing GitHub site. History: Accepted by Ram Ramesh, Area Editor for Data Science and Machine Learning. Supplemental Material: The software that supports the findings of this study is available within the paper and its Supplemental Information ( https://pubsonline.informs.org/doi/suppl/10.1287/ijoc.2022.0260 ) as well as from the IJOC GitHub software repository ( https://github.com/INFORMSJoC/2022.0260 ). The complete IJOC Software and Data Repository is available at https://informsjoc.github.io/ .

Towards Industry 4.0: Color-Based Object Sorting Using a Robot Arm and Real-Time Object Detection

With the introduction of Industry 4.0, automation and robotics have made great strides, enabling 
 enterprises to improve their manufacturing processes for increased productivity and efficiency. This project 
 introduces a novel method for implementing Industry 4.0 concepts through color-based object sorting employing 
 a robot arm with real-time object identification capabilities. Creating a reliable and effective system that can 
 automatically categorize items based on their color properties is the main goal of this project. To enable seamless 
 object recognition and manipulation in real time, the suggested system integrates robotic manipulation with 
 computer vision algorithms. The system makes use of a convolutional neural network (CNN) for precise object 
 detection, using recent advancements in deep learning and image processing, allowing the robot arm to interact 
 with a variety of items effectively. The training phase and the sorting phase are the two key phases of the 
 approach. The CNN model is trained on a sizable dataset of labeled objects during the training phase to recognize 
 various colors and forms. In order for the robotic arm to recognize things as they go along the conveyor belt and 
 sort them into predetermined bins according to their respective colors, the trained model must be integrated with 
 the robotic arm during the sorting phase. Several experiments are carried out with various lighting setups and 
 object arrangements to evaluate the performance of the suggested system. The outcomes show how well the 
 system performs in terms of exact object detection and reliable sorting. The system's capacity to effectively 
 handle a variety of objects and adapt to changing environmental conditions further emphasizes its suitability for 
 use in actual industrial scenarios. This project has important ramifications for the manufacturing sector, enabling 
 improved automation capabilities and cost-efficiency. An important step towards implementing Industry 4.0 
 principles is the seamless integration of color-based object sorting and real-time object detection using a robotic 
 arm. This will allow industries to optimize their production processes, minimize human intervention, and 
 increase overall productivity. Further developments in robotics and computer vision are anticipated to push the 
 limits of automation and open the door for more advanced and intelligent industrial systems as technology 
 develops.