CNN-Based Inspection Module for Liquid Carton Recycling by the Reverse Vending Machine

The problem of plastic waste is being addressed in a variety of ways, ranging from manual waste sorting to reverse vending machines. On the other side, businesses are becoming increasingly concerned about waste management. Several ways to producing reverse vending machines have been tested, including the use of plastic sensors. However, the findings were unsatisfactory due to imprecise detection. This study looks into the use of ESP32-Cam combined with machine learning for high-precision plastic bottle detection in reverse vending machines. It is envisioned that high-precision plastic bottle detection would be used in reverse vending machines. It is intended that by providing an incentive for each identified plastic bottle, people will be motivated to collect plastic bottles and deposit them into reverse vending machines, thereby supporting digital humanities through enhanced waste management practices.

With the ever-increasing amount of waste disposal by mankind, the requirement for waste management is paramount. Apart from dumping waste in landfills, recycling is another popular solution adopted by the world to manage waste. As an effective collection mechanism of plastic waste, automatic recycle bins are employed in many countries in common places like subways and, malls. Furthermore, different rewarding mechanisms are in place to motivate the consumers to return the plastic waste. Reverse vending machines which encourage the collection of plastic waste and provide rewards are used in some countries. However, existing reverse vending machines lack features like separating plastic based on their plastic category. PET bottles and Yoghurt cups are some of the mostly disposed plastic containers in Sri Lanka. There are companies that use these types only to recycle and manufacture unique recycled products. This paper focuses on developing a reverse vending machine with plastic type sorting function to be used in the Sri Lankan context. The existing mechanisms were reviewed and a solution is designed to operate with Near-infrared (MR) plastic sorting and gravity transfer method. Furthermore, an appropriate rewarding mechanism is also proposed.

Collection of plastic bottles by reverse vending machine using object detection technique

Improper waste disposal remains to be one of the most salient global environmental concerns. Consequential to economic growth and consumerism, the praxis of sustainability has become stunted as the amount of waste illicitly discarded continue to swell over the years, harming ecosystems, exacerbating global warming and aggravates human adversity. As such, the primary contributors for this concern are Polyethylene terephthalate (PET) bottles and cans, which are widely accessible and also extensively utilized for daily consumption. However, while many countries already have efficient waste management mechanisms in place, challenges regarding recycling efforts persist in afflicting developing countries including the Philippines. Considering this persistent and wide-scale issue, 'Bote-Cannected' is a reverse vending machine that was designed and built to encourage recycling by accepting both plastic bottles and cans for disposal. Delving on the design, Bote-Cannected's system utilized Arduino and Raspberry Pi technologies to automate the sorting and processing of items. Thereafter, the said machine was made to automatically segregate items one at a time, and assign points based on material type and size. Despite minor challenges linked to the design, durability, and overall functionality, 'Bote-Cannected' received high satisfaction ratings from users. Ultimately, its successful application showcased its strong potential in encouraging recycling behaviours and address pressing environmental concerns.

The prevalence of polyethylene terephthalate (PET) in beverage packaging has increased microplastic (MP) accumulation in the environment. MP can become a component of air pollution, especifically of particulate matter with a diameter of less than 2.5 microns (PM2.5). Unfortunately, Thailand has a low recycling rate for plastic bottles, with only 4.5% being recycled. Reverse Vending Machines (RVMs) were introduced in the early 2010s as a potential solution to this problem. RVMs incentivize recycling by providing rewards or refunds for each bottle deposited, thereby reducing the amount of PET waste and MP in the environment. This study analyzed usage and waste collection data from RVMs located at 15 locations of a hypermarket chain in Thailand from June 2020 to December 2022. The results showed that the average PET bottles collected from each machine was approximately 670 kg per year, which was lower than the break-even point of 3,200 kg per year. Economic feasibility indicators also suggested that the use of RVMs might not be economically sound. This study proposed suggestions to improve the business model of RVMs and offered policy recommendations to the government on how to enhance the effectiveness of RVMs.

At present, there are many types of beverage packages such as cans and plastic bottles which lead to a large number of waste beverage cans. Furthermore, throwing beverage cans away without management tends to be an ineffective way to get optimal utilization of resources. Hence, the primary emphasis of this work is on the development of automatic sorting of beverage cans for reverse vending machines. In addition, the accuracy testing of sorting beverage cans by the machine was designed based on three techniques which are easy to implement and which will bring sustainable energy innovations with communities’ participation. There are two sampling groups of cans and plastic bottles in the experimental studies. The first group is the group which already has data in the system for using this in a prototype of sorting process. The latter one is the group without data in the system or which has never been used before.
 Furthermore, the reverse vending machine has two types of proximity sensors; inductive and capacitive which work together. The experimental results of sorting beverage cans and bottles on two sample groups show that the average accuracy of sorting is 99.20%. The sorting of beverage cans and bottles based on magnetic hinge and barcode provides an average accuracy of 79.20% and 50.00%, respectively. Classifying using the proximity sensor has the fastest operation with an average of 2.66 seconds, followed by barcode and hinge. Those takes 4.01 and 5.21 seconds, respectively.

Domain- and task-specific transfer learning for medical segmentation tasks

We developed a computer-aided diagnosis (CADx) method for classification between benign nodule, primary lung cancer, and metastatic lung cancer and evaluated the following: (i) the usefulness of the deep convolutional neural network (DCNN) for CADx of the ternary classification, compared with a conventional method (hand-crafted imaging feature plus machine learning), (ii) the effectiveness of transfer learning, and (iii) the effect of image size as the DCNN input. Among 1240 patients of previously-built database, computed tomography images and clinical information of 1236 patients were included. For the conventional method, CADx was performed by using rotation-invariant uniform-pattern local binary pattern on three orthogonal planes with a support vector machine. For the DCNN method, CADx was evaluated using the VGG-16 convolutional neural network with and without transfer learning, and hyperparameter optimization of the DCNN method was performed by random search. The best averaged validation accuracies of CADx were 55.9%, 68.0%, and 62.4% for the conventional method, the DCNN method with transfer learning, and the DCNN method without transfer learning, respectively. For image size of 56, 112, and 224, the best averaged validation accuracy for the DCNN with transfer learning were 60.7%, 64.7%, and 68.0%, respectively. DCNN was better than the conventional method for CADx, and the accuracy of DCNN improved when using transfer learning. Also, we found that larger image sizes as inputs to DCNN improved the accuracy of lung nodule classification.

Final lesion volume (FLV) is a surrogate outcome measure in anterior circulation stroke (ACS). In posterior circulation stroke (PCS), this relation is plausibly understudied due to a lack of methods that automatically quantify FLV. The applicability of deep learning approaches to PCS is limited due to its lower incidence compared to ACS. We evaluated strategies to develop a convolutional neural network (CNN) for PCS lesion segmentation by using image data from both ACS and PCS patients. We included follow-up non-contrast computed tomography scans of 1018 patients with ACS and 107 patients with PCS. To assess whether an ACS lesion segmentation generalizes to PCS, a CNN was trained on ACS data (ACS-CNN). Second, to evaluate the performance of only including PCS patients, a CNN was trained on PCS data. Third, to evaluate the performance when combining the datasets, a CNN was trained on both datasets. Finally, to evaluate the performance of transfer learning, the ACS-CNN was fine-tuned using PCS patients. The transfer learning strategy outperformed the other strategies in volume agreement with an intra-class correlation of 0.88 (95% CI: 0.83–0.92) vs. 0.55 to 0.83 and a lesion detection rate of 87% vs. 41–77 for the other strategies. Hence, transfer learning improved the FLV quantification and detection rate of PCS lesions compared to the other strategies.

Breast ultrasound image classification and physiological assessment based on GoogLeNet

One of the most powerful ideas in deep learning is the transfer learning technique. Transfer learning can be utilized to take a knowledge from what a deep neural network has learned from a particular task and apply that knowledge to a different task. Transfer learning is very useful when the size of the training samples of interest is small to train a neural network from scratch. This research focuses on the concept of transfer learning where the Convolutional Neural Network (CNN) power can be utilized as a features extractor to help with classifying benign from malignant breast cancer images. In addition, Support Vector Machine (SVM) classifier based on Radial Basis Function (RBF) was adapted for its flexibility in fitting the data dimension space adequately by tuning the kernel width. The hybridization between CNN and RBF-Based SVM showed robust results for both the dataset and the application task of this research. The contribution of this paper can be summarized in three major parts. First, a CNN was implemented from scratch on a large number of available spine images to classify images of two different spine views (sagittal and axial) in order to transfer the learning process to the CNN of breast images. Second, retrain the spine CNN on the images of breast cancer to classify between benign and malignant cases by fine-tuning. Finally, the features were extracted from the retrained CNN and fed to RBF-Based SVM to classify benign from malignant breast mammogram images.

In this study, we investigated how shapes are classified based on local and global features by four representative convolutional neural networks (CNNs), i.e., AlexNet, VGG, ResNet and Inception. While the local features are based on simple components, such as orientation of line segment, the global features are based on the whole object, such as whether an object has a hole. For example, solid triangles and solid squares are differentiated by local features, solid circles and rings are differentiated by a global feature. Two sets of experiments were performed in this research. In the first experiment, we examined how the four CNNs pre-trained on ImageNet (with transfer learning) learned to differentiate the regular shapes (equilateral-triangles, squares, circles and rings). Our results showed that the pre-trained CNNs exhibited faster learning rates in the tasks discriminating the local features than in the tasks discriminating the global feature. However, the transfer learning of discriminating the global feature in regular shapes were better generalized to irregular shapes than the transfer learning of discriminating local features. In the second experiment, the CNNs were trained from scratch (with random weights initialization) to discriminate local and global features in regular and irregular shapes. Different from the transfer learning, the CNNs exhibited faster learning rates in discriminating the global feature than the local features. Similar to transfer learning, the CNNs exhibited excellent learning generalization to discriminating the global feature of irregular shapes, but poor learning generalization to discriminating the local features in the irregular shapes. The overarching goal of this research is to create a paradigm and benchmark to directly compare how the CNNs and primate visual systems process geometrical invariants. In contrast to the ImageNet approach which employs natural images to train CNNs, we employed the “ShapeNet” approach which features geometrical shapes with well-defined properties. The ShapeNet approach will not only help elucidate the strengths and limitations of CNN computation, but also provide insights into visual information processing in the primates.

Among the many deep learning methods, the convolutional neural network (CNN) model has an excellent performance in image recognition. Research on identifying and classifying image datasets using CNN is ongoing. Animal species recognition and classification with CNN is expected to be helpful for various applications. However, sophisticated feature recognition is essential to classify quasi-species with similar features, such as the quasi-species of parrots that have a high color similarity. The purpose of this study is to develop a vision-based mobile application to classify endangered parrot species using an advanced CNN model based on transfer learning (some parrots have quite similar colors and shapes). We acquired the images in two ways: collecting them directly from the Seoul Grand Park Zoo and crawling them using the Google search. Subsequently, we have built advanced CNN models with transfer learning and trained them using the data. Next, we converted one of the fully trained models into a file for execution on mobile devices and created the Android package files. The accuracy was measured for each of the eight CNN models. The overall accuracy for the camera of the mobile device was 94.125%. For certain species, the accuracy of recognition was 100%, with the required time of only 455 ms. Our approach helps to recognize the species in real time using the camera of the mobile device. Applications will be helpful for the prevention of smuggling of endangered species in the customs clearance area.

The leather industry plays a crucial role in the production of high-quality leather products to remain competitive in the market. Due to various reasons such as material handling and turning, leather defects can appear at different stages of the production process. This paper proposed deep learning techniques, specifically transfer learning, deep convolutional neural networks (D-CNN), and ensemble learning for automating leather defect detection and classification. The dataset was taken from the open source Kaggle. The dataset was preprocessed from the beginning. However, we performed Error Level Analysis (ELA) to detect possible changes or fraud in the image. We also used data augmentation techniques (resizing, rescaling, flipping, rotation, zooming, and contrasting) on the dataset to improve the model performance. This study investigated deep learning architectures for automatic leather defect detection, comparing them with seven deep convolutional neural networks (D-CNN) models and transfer learning architectures. Furthermore, we introduce and evaluate two novel ensemble models: MER built on transfer learning architecture (MobileNetV2, EfficientNetB0, and ResNet50) and AZL built on D-CNN architecture (AlexNet, ZfNet, and LeNet). A key contribution of this study is the demonstration of significant performance improvements achieved by strategically integrating squeeze and excitation and label smoothing techniques into transfer learning, D-CNN, and ensemble frameworks. Our proposed MER ensemble method achieves a state-of-the-art of 96.39% for leather defect detection. The proposed model was evaluated using performance metrics including precision, recall, F1-score, AUC, ROC, and Matthews Correlation Coefficient (MCC). Additionally, Grad-CAM was employed for explainable AI to visualize and interpret the model’s decision-making process. Comparative analysis against separate transfer learning and D-CNN models fails to establish the superior performance of our MER ensemble, which highlights the potential to significantly advance automated quality inspection in leather production. This study provides insights into evaluating the best deep learning techniques for leather defect classification, paving the way for more accurate, efficient, and reliable industrial applications. Proposes a robust deep learning-based framework for automated leather defect detection using transfer learning, deep CNNs, and two novel ensemble models (MER and AZL), enhanced with squeeze-and-excitation and label smoothing techniques. Achieves state-of-the-art performance with the proposed MER ensemble model, achieve 96.39% accuracy, and demonstrates superior results across precision, recall, F1-score, AUC–ROC, and MCC. Integrates Error Level Analysis (ELA), extensive data augmentation, and Grad-CAM–based explainable AI to ensure data reliability, improve generalization, and provide transparent visual interpretation of defect regions for industrial quality inspection.

Deep convolutional neural networks with ensemble learning and transfer learning for capacity estimation of lithium-ion batteries