Automatic Sorting Research Articles

Classification and ecological relevance of soundscapes in urban informal settlements

Abstract Sound exerts wide‐ranging influence on humans. The quality of that influence depends on the sound source and context in which it is perceived, but nature sounds are generally preferred by people and associated with health and well‐being benefits. In many environments, sounds are highly mixed giving rise to a multi‐source ‘soundscape’ that may vary through days or seasons. The complex and dynamic nature of soundscapes makes them challenging to quantify or classify to rigorously compare them and their contributing sources quantitatively through space and time. We address this challenge by developing an analytical procedure resulting in a generalized soundscape classification framework that (i) elucidates dominant sound sources (e.g. biophony vs. anthrophony) and (ii) can be used to improve our understanding of spatial and temporal variation in soundscapes across different contexts. We also address a knowledge gap in urban sound research by describing the soundscapes of urban informal settlements in Fiji and Indonesia. Despite the growing emphasis on improving the physical design and quality of life in urban informal settlements, little is known about soundscapes in these settings or their relationship to human health and well‐being. We identified seven soundscape classes representing relative dominance by (i) sustained geophony, biophony dominated by (ii) insect stridulation or (iii) bird song, anthrophony dominated by (iv) machines, (v) vehicles, (vi) human voices or (vii) a mixture of the former. These classes were applicable in both Indonesia and Fiji but differed in their prevalence between the countries, times of day and seasons in expected ways. Future automatic sorting of new sound data into this classification framework is provided by a supervised classification model that attained an overall testing accuracy of 94% and Cohen's kappa of 0.93. Our procedure yields broadly applicable, informative soundscape classes indicative of dominant sound sources, including natural sounds, that are known to have different effects on human health. Therefore, our soundscape classification framework can be used in conjunction with health, well‐being, or economic data, to aid the development, assessment and scaling of sustainable design solutions for liveable cities and especially for improving urban informal settlement environments. Read the free Plain Language Summary for this article on the Journal blog.

The supply and demand balance of recyclable textiles in the Nordic countries

The textile industry is on its early steps towards circular economy. Being a highly resource-intensive and waste-generating industry, it is essential to embrace fiber-to-fiber recycling in addressing the increasing textile waste problem. Several innovative initiatives are happening within this area, not least in the Nordic countries, where automated sorting and fiber-to-fiber recycling technologies and capacities are developing. These large investments require economy of scale; however, this is challenged by the fractioned supply due to the specific fiber requirements of the recycling facilities. To ensure economy of scale and support strategic planning, it is important to investigate the balance of the demand of those capacities with the supply of recyclables generated in the region. Local and regional perspectives are needed in order to avoid unnecessary transportation of low value materials. Based on a synthetises of existing textile flow studies and interviews with relevant actors in four Nordic countries, this study investigates the balance between the supply of recyclable textiles and the sorting and recycling capacity. This is accomplished by estimating the volumes of recyclables and their fiber composition (based on developed weighting average method) and comparing these with the current and upcoming capacities in each country and in the Nordics as a whole. The findings indicate that the upcoming automatic sorting and recycling capacity will be sufficient to deal with the total recyclable fraction in the Nordic region, except for some of the synthetic fibers. However, there are imbalances between supply and demand within individual countries, highlighting opportunities for collaboration.

Fast Adaptive Binarization of QR Code Images for Automatic Sorting in Logistics Systems

With the development of technology, QR codes play an important role in information exchange. In order to work out the problem of uneven illumination in automatic sorting in logistics systems, an adaptive method in binarization is presented. The proposed method defines the block windows’ size adaptively for local binarization based on the traits of the QR code. It takes advantage of integral images to calculate the sum of gray values in a block. The method can binarize the QR code with high quality and speed under uneven illumination. Compared with several existing algorithms, it is shown that the proposed method is more effective. The experimental results validate that the proposed method has a higher recognition accuracy and is more efficient in binarization.

SWDet: Anchor-Based Object Detector for Solid Waste Detection in Aerial Images

As we all know, waste pollution is one of the most serious environmental issues in the world. Efficient detection of solid waste (SW) in aerial images can improve subsequent waste classification and automatic sorting on the ground. However, traditional methods have some problems, such as poor generalization and limited detection performance. This article presents an anchor-based object detector for solid waste in aerial images (SWDet). Specifically, we construct asymmetric deep aggregation (ADA) network with structurally reparameterized asymmetric blocks to extract waste features with inconspicuous appearance. Besides, considering the waste with blurred boundaries caused by the resolution of aerial images, this article constructs efficient attention fusion pyramid network (EAFPN) to obtain contextual information and multiscale geospatial information via attention fusion. And the model can capture the scattering features of irregular shape waste. In addition, we construct the dataset for solid waste aerial detection (SWAD) by collecting aerial images of SW in Henan Province, China, to validate the effectiveness of our method. Experimental results show that SWDet outperforms most of existing methods for SW detection in aerial images.

Fuzzy Power, Converter for Color Sorting System

Intelligent robot technology is currently widely applied to all facets of human production and existence. Future development must focus on using intelligent robots rather than humans to achieve automatic sorting. In the field of sorting robots, color sorting robots are a significant research object. This paper examines the color recognition principle of the TAOS Company’s TCS3200 color sensor, based on the introduction of the theory of three primary colors. It goes into detail about how important white balance is. An ATmega16 single-chip microcomputer serves as the robot's brain, color and grey sensors serve as its sense organs, and steering gears are used as its moving parts in the design of a color block sorting robot. It is capable of recognizing, organizing, and manipulating various color blocks. The technique of multiple detections and high probability results are used in color recognition, which greatly increases detection accuracy. There is a specific practical benefit to the system.

Inkjet-Printed UHF RFID Sticker for Traceability and Spoilage Sensing of Fruits

This article presents an ink-jet printed ultrahigh-frequency (UHF) radio frequency identification (RFID) label for tagging fruits. The proposed tag antenna is based on a hybrid configuration, which consists of a loop, dipole-like strips (DLSs), and eye-shaped rectangular nested slots. The loop fulfills impedance matching proposes, while the eye-shaped slots assist to maintain high imaginary impedance to mitigate capacitive effects of high permittivity surfaces of fruits. Moreover, the dipole strips help to reduce the loss resistance caused by the high permittivity of the surface of the fruit. Therefore, the overall tag configuration provides a good impedance match with the Alien H3 RFID chip in the whole U.S. UHF RFID band. Furthermore, the fabricated prototype of the proposed tag antenna achieved a read range of 3 m after mounting on apple. Moreover, an automatic weighing and billing experiment is performed by placing the tagged apples inside a refrigerator. Overall, the performance of the proposed tag antenna is tested after mounting on apple fruits of different shapes and sizes, which indicates the robustness of this tag. Moreover, the tag antenna is also tested for sensing spoilage of apple fruits. The read range of the proposed tag antenna reduces up to 42% on spoiled apples. Therefore, this tag can be suitable for automatic sorting, weighting, and billing of fruits in smart cities, vending machines, and departmental stores.

Fuzzy Power, Converter for Coin Sorting System Based on Weight, Edge

Nowadays, intelligent robot technology is extensively used in every aspect of human existence and production. To achieve automatic sorting, future development must concentrate on employing intelligent robots instead of humans. Coin sorting robots are an important research object in the field of sorting robots. This paper focuses on a machine vision (MV) sorting especially difficult application, in which the `part' is an Indian coin. The lack of distinguishing characteristics between denominations and the variation in features within a single denomination makes the application difficult in part. Even though coin recognition algorithms have been published in the literature, most applications are evaluated offline using the coins' weights. In the end, it was determined that none of these three methods achieved the desired 95% accuracy at 1000 coins per minute.

Retracted: Intelligent Optimization Design of Automatic Sorting Robot Process

Retracted: Intelligent Optimization Design of Automatic Sorting Robot Process

Design and implementation of automatic sorting car based on OpenMV

The system uses the OpenMV algorithm module combined with the k-means framework through the Euclidean distance formula to facilitate the automation of logistics sorting, which identifies the color of logistics parcels in the LAB color space. It sends the identified color information to the motion drive module, which sorts and transports the logistics parcels to the designated storage area. The fusion of algorithms allows the system to identify colors and transportation accurately.

A new method of construction waste classification based on two-level fusion.

The automatic sorting of construction waste (CW) is an essential procedure in the field of CW recycling due to its remarkable efficiency and safety. The classification of CW is the primary task that guides automatic and precise sorting. In our work, a new method of CW classification based on two-level fusion is proposed to promote classification performance. First, statistical histograms are used to obtain global hue information and local oriented gradients, which are called the hue histogram (HH) and histogram of oriented gradients (HOG), respectively. To fuse these visual features, a bag-of-visual-words (BoVW) method is applied to code HOG descriptors in a CW image as a vector, and this process is named B-HOG. Then, based on feature-level fusion, we define a new feature to combine HH and B-HOG, which represent the global and local visual characteristics of an object in a CW image. Furthermore, two base classifiers are used to learn the information from the color feature space and the new feature space. Based on decision-level fusion, we propose a joint decision-making model to combine the decisions from the two base classifiers for the final classification result. Finally, to verify the performance of the proposed method, we collect five types of CW images as the experimental data set and use these images to conduct experiments on three different base classifiers. Moreover, we compare this method with other extant methods. The results demonstrate that our method is effective and feasible.

Evaluating the Environmental and Economic Performance of Municipal Solid Waste Disposal by All-Component Resource Recovery

Disposal of municipal solid waste (MSW) has become increasingly challenging. In this study, we used life cycle assessment (LCA) to evaluate environmental impacts and financial performance of a new approach for MSW disposals, namely All-components Resource Recovery (AcRR), which is based on automatic sorting. We compared AcRR with the standardized Waste-to-Energy incineration (WtE) to provide decision-making support for MSW management. The results show that WtE and AcRR are both good MSW resource treatment methods. Through MSW disposal, WtE generates electricity, while AcRR generates secondary resources such as metals, plastics, pulp and organic fertilizers. WtE releases trace amounts of HCl, PM10, heavy metals, dioxins and dust, while AcRR does not produce such pollutants; AcRR produces more odor gases such as SO2 and H2S. AcRR produces four environmental issues, i.e., Global Warming, Acidification, Photochemical Ozone Synthesis, and Eutrophication, each of which has a smaller impact than WtE; WtE has two more impacts than AcRR: Human Toxicity and Soot and Ashes. The total environmental impact potential of WtE is 3.38 times that of AcRR, and the greenhouse gas emission equivalent is 6.82 times that of AcRR. The cost of construction and operation of AcRR is lower than that of WtE, while the net profit of AcRR is much higher. In conclusion, AcRR is able to screen the mixed MSW into various secondary resources with less environmental emissions and environmental impacts and better financial performance; it may be a promising MSW disposal approach, especially for small cities, but a corresponding supporting industrial system is needed.

Design and production of an automatic solid waste sorting machine with smart digital counter

Sorting of objects is the first step of a waste management process. These objects should be sorted according to the type of material for effective waste recycling. Therefore, the focus of this work is to design and produce an automated sorting machine that can be used to sort metals and non-metals autonomously. The automatic sorting machine with a smart digital counter was designed to use a microcontroller (Arduino Mega) to control the conveyor systems which consist of the conveyor support, driving unit and the driven unit. The sorting mechanisms consist of the inductive sensor, infrared Sensor and the actuating system using servo motor. The conveyor system helps in the conveyance of objects towards the sorting chute. The actuating system receives signal from the microcontroller and the device does the sorting of the objects based on their characteristics while the digital counter counts the number of metallic objects dropping into the designated cart. The time taken for the inductive sensor to sense an object, the waiting period for the servo motor to be actuated and the time taken for the counter to count after a metallic object is sensed are 1s, 2s and 1s respectively. After its development, it was tested and observed to meet the design requirements.

Post-consumer plastic sorting infrastructure improvements planning: Scenario-based modeling of greenhouse gas savings with sustainable costs

With the increasing share of waste material recovery, household plastic waste is one of the biggest problems. In most countries, mainly manual sorting is used. Meanwhile, new automated technologies are being developed to expand the range of classifiable types to increase material recovery. The overall automation of the sorting process can help the EU's established recycling targets to be effectively met. However, the new technologies are feasible only in the case of large-capacity centers, which must be conveniently located in the existing infrastructure. This paper presents a two-stage model aiming to modernize the current sorting infrastructure for plastic waste. The approach uses multi-criteria optimization to minimize environmental impact at a reasonable price. The result is the optimal location of new automatic sorting centers, and waste stream flows using existing manual sorting facilities. The model is applied through an initial case study inspired by the Czech Republic data. Optimization output proposes four new automatic sorting lines with a total capacity of 158 kt per year. In most cases, manual sorting is used to reduce the transported weight of plastic waste, while automatic sorting lines separate the remaining, hardly recognized part. More than 60% of separately collected plastic is sorted and determined for material recovery.

Automatic sorting of low-value recyclable waste: a comparative experimental study

Automatic sorting of low-value recyclable waste: a comparative experimental study

Application of information-intelligence technologies in pharmacy intravenous admixture services in a Chinese third-class a hospital

BackgroundPharmacy intravenous admixture service (PIVAS) center has emerged as an important department of hospital as it can improve occupational protection and ensure the safety and effectiveness of intravenous infusions. However, medication errors were considered to be a significant challenge in PIVAS, so information-intelligence technologies were introduced to optimize the management of PIVAS. Our article summarized the application of information-intelligence technologies in PIVAS of a large third-class A hospital in China, and provided an example for PIVAS in other hospitals at home and abroad.MethodsPrescription-reviewing rules containing intravenous medications and infusion solution guideline were recorded in the database of prescription-cheking system. Drugs information were recorded in the PIVAS management system with special identification and warning labels to reduce intravenous infusion errors. Automatic labeling device was used to label the infusion bags, and the quality control program database of intelligent compounding robot for cytotoxic drugs was established ingeniously. Automatic sorting devices were applied for the third batch of finished infusion admixtures, and intelligent logistics robots were used to transport the infusion to the ward.ResultsAfter establishing and implementing of prescription-reviewing rules in the prescription-cheking system database, the number of prescriptions checked by pharmacists increased from 18 to 43 per minute. The success rate of intervention with irrational medical orders increased from 85.89% to 99.06% (P < 0.05). By introducing various intelligent devices, automatic labeling significantly enhanced work efficiency and reduced the error rate (P < 0.001). Furthermore, the use of intelligent intravenous compounding robots significantly reduced the risk of errors (P < 0.001).ConclusionsThe application of information-intelligence technologies in PIVAS can improve work efficiency and reduce error risk. However, some intelligent devices have failed to achieve the expected effect in practical use, and further improvements are needed to meet the demands of PIVAS in the future.

Design of intelligent garbage classifier system based on machine vision

With the rapid development of society, the amount of garbage produced in life is increasing day by day. How to deal with the garbage and how to classify the garbage scientifically and effectively are hot topics in the current society. To solve the above problems, this paper proposes an intelligent garbage classifier based on machine vision. The design uses STM32F103C8T6 single chip microcomputer as the core controller of the intelligent garbage collector. The hardware part of the system is composed of computer vision identification module, power module, photoelectric switch module, ultrasonic module, stepper motor driver and other modules. At the same time, different kinds of garbage are identified through the visual module. The single-chip microcomputer completes the software test of garbage classification through the stepper motor. Finally, the performance of the intelligent garbage collector is verified through experiments. The results show that the intelligent garbage classifier can realize the key functions of intelligent identification and automatic sorting and achieve high accuracy in the process of identifying different garbage. The design has great practical value.

Design, Analysis and Experimental Research of Dual-Tendon-Driven Underactuated Gripper

To improve the adaptive clamping performance of traditional single-tendon-driven underactuated grippers for grasping multiple categories of objects, a novel dual-tendon-driven underactuated gripper is proposed in this paper. First, two independent tendons with different winding paths are designed in the gripper to realize the changeable resultant moment of the end knuckle rotating joint and the movement sequences of gripper knuckles driven by different tendons are analysed too. Then, some kinematic analysis and dynamical simulations are carried out to verify the validation of the knuckle structure and dual-tendon winding path design. At last, a prototype of the novel gripper is manufactured and some grasping experiments are carried out on multiple categories of objects, with different sizes and shapes. The experimental results show that all the objects can be clamped tightly. Compared with the traditional single-tendon-driven gripper, the novel one can achieve a more flexible grasping operation and a larger end clamping force, which are more suitable for the adaptive grasping requirements of robotic automatic sorting.

Study on egg sorting model based on visible-near infrared spectroscopy

To realize the automatic sorting of eggs, the sorting models are established in this paper by using the visible-near infrared spectroscopy technique and taking the eggshell colour, integrity, as well as the feeding mode as sorting indexes. A variety of methods are selected to remove the noise and systematic error by preprocess the spectral information. The backpropagation neural network (BP), the Principal Component Analysis (PCA) coupled with BP and the Soft Independent Modeling of Class Analogy (SIMCA) sorting method are used to identify the eggshell colours (white, pink, green), eggshell integrity (intact, cracked) and laying hen feeding mode (caged and cage-free) by their characteristic band, respectively. The prediction correlation coefficient (Rv), the prediction mean square error (RMSEP), the prediction standard error (SEP), the recognition rate () and the rejection rate () are used to evaluate the established models. The results show that the established classification models have high prediction accuracy and small errors. The non-destructive testing (NDT) technology has great potential for large-scale intelligent laying hen farms.

E-Commerce Sorting Equipment and System Based on Cloud Computing

In order to solve the problems of order reduction and customer churn caused by sorting delays, the author proposes a method for e-commerce sorting equipment based on cloud computing. This method mainly adopts double-layer sorting equipment; compared with single-layer automatic sorting equipment, double-layer sorting equipment has the characteristics of higher efficiency and smaller floor space. The sorting method adopts the “group sorting” method, which can effectively improve the sorting efficiency of the sorting equipment. The algorithm method adopts the mathematical model based on cloud computing for calculation. Experimental Results. The author adopts the cloud computing-based “composition sorting” double-layer sorting equipment; compared with the traditional single-layer sorting equipment, the throughput of the single-layer sorting strategy is 0.72 pieces/s when the conveying speed of the conveyor belt is the same, the throughput of the two-layer same-direction strategy is 1.46 pieces/s, the throughput of the balanced load strategy is 1.97 pieces/s, and the throughput of the group sorting load strategy is 2.57 pieces/s. This method can effectively solve the problems of order reduction and customer churn caused by sorting delays.

A Novel Efficient Convolutional Neural Algorithm for Multi-Category Aliasing Hardware Recognition.

When performing robotic automatic sorting and assembly operations of multi-category hardware, there are some problems with the existing convolutional neural network visual recognition algorithms, such as large computing power consumption, low recognition efficiency, and a high rate of missed detection and false detection. A novel efficient convolutional neural algorithm for multi-category aliasing hardware recognition is proposed in this paper. On the basis of SSD, the novel algorithm uses Resnet-50 instead of VGG16 as the backbone feature extraction network, and it integrates ECA-Net and Improved Spatial Attention Block (ISAB): two attention mechanisms to improve the ability of learning and extract target features. Then, we pass the weighted features to extra feature layers to build an improved SSD algorithm. At last, in order to compare the performance difference between the novel algorithm and the existing algorithms, three kinds of hardware with different sizes are chosen to constitute an aliasing scene that can simulate an industrial site, and some comparative experiments have been completed finally. The experimental results show that the novel algorithm has an mAP of 98.20% and FPS of 78, which are better than Faster R-CNN, YOLOv4, YOLOXs, EfficientDet-D1, and original SSD in terms of comprehensive performance. The novel algorithm proposed in this paper can improve the efficiency of robotic sorting and assembly of multi-category hardware.