3D printed material designs have a large capability in the functional aspect. A cross-spring compliant joint is a hot topic in the sense of multipurpose applications in various engineering fields. A combination of flexible materials embedded in the structural form performs a motion of the system according to deformation of parts elastically, which may fit to a specific engineering purpose. In the present study, a traditional cross-spring pivot (CSP) was improved to provide effectively frictionless and wear free in-plane motion. The behavior of the joint was analyzed based on a non-linear FEA computer analysis to focus the properties with various loading conditions. Improved compliant joints will open a new door for designs of high-precision actuators and robotic manipulators.

View full abstract

Daylily is loved by people because of its unique nutritional value, but because of its unique biological characteristics, the harvesting environment of daylily is poor, and the long-term harvesting may cause certain injuries to the workers' hands. This paper aims to develop a picking robot with strong applicability by studying and summarizing the biological characteristics of daylily, which can accurately identify the picking parts through binocular recognition system and complete the intelligent picking process of daylily.

View full abstract

The covid-19 pandemic has accelerated the growth of online shopping and e-commerce. While shopping and e-commerce have made it convenient for customers to purchase products, issues such as failed/delayed delivery and missing parcels need to be addressed to provide a seamless and secure shopping experience for customers. In Malaysia, the implementation of Pos Laju Ezi Box Kiosk as a delivery system still faces challenges such as upfront costs, high cost of maintaining a management system and vulnerabilities in wireless communication. To overcome the aforesaid problem, this paper proposes a low-cost smart parcel box system with enhanced security. All of the designed system's processes were controlled by an Arduino Mega 2560 in this system. The system will start when couriers message the user via applications with the tracking number for the package in order to obtain the password. When the courier's message and the user-specified message match, the password will be given for security reasons. Once the password has been entered, couriers can insert the package into the parcel box. The system provides a convenient and secure solution for the delivery and retrieval of packages, reducing the risk of theft or damage to the packages..

View full abstract

In order to solve the problem of low contrast image and loss of image details in the foggy weather, the image defogging technique is used to remove the noise in the image and improve the image contrast, so as to recover a clear and fog-free image. In this paper, we mainly introduce three image defogging algorithms: global histogram equalisation, local histogram equalisation and the Retinex algorithm. The advantages and shortcomings of each algorithm are summarised through the study of the principles of each algorithm and the comparative analysis of the experimental result.

View full abstract

In the long history of TCM, it has been said that the shape and number of wrinkles, the depth of the wrinkles and the roughness of the matricular area of the palm are closely related to medical conditions such as asthma and allergic diseases. This study focuses on palmprint classification using deep learning based on TCM. This paper made the palm image dataset according to the characteristics of the wrinkles. In training, an inception V3 model using the Tensor Flow framework and Google Net was used to correctly classify the palmprint part of the thumbprint as negative or positive with a certain probability. This result expected to facilitate diagnosis to asthma and allergic diseases.

View full abstract

In recent decades, the rapid growth of urbanization and industrialization has resulted in a significant increase in solid waste, creating an urgent issue that demands attention. The accumulation of solid waste poses a significant challenge, as it can lead to environmental pollution. Recycling is a viable solution that offers economic and environmental benefits. To address this challenge, various intelligent waste management systems and methods are necessary. This research paper explores the use of image processing techniques to classify different types of recyclable dry waste. The study proposes an automated vision-based recognition system that includes image acquisition, feature extraction, and classification. The intelligent waste material classification system extracts 11 features from each dry waste image. The study employed four classifiers - Quadratic Support Vector Machine (Q-SVM), Cubic Support Vector Machine (C-SVM), Fine K-Nearest Neighbor (Fine KNN), and Weighted K-Nearest Neighbor (Weighted KNN) - to categorize the waste into distinct classes, such as bottle, box, crumble, flat, cup, food container, and tin. Among these, the C-SVM classifier performed impressively well, achieving an accuracy of 83.3% and 81.43% during training and testing, respectively. This classifier exhibited consistent performance and had a shorter computation time, making it a highly effective method. Although using the Speeded-Up Robust Features (SURF) method could enhance the classification process, it may lead to longer response and computation times.

View full abstract

A refinement process by human experts is still needed for areas/feature extractions of interest from aerial images in multiple map makers. The construction/road edge extraction is one of them which is highly important in the preprocessing stage for map-making, while it is difficult to isolate man-made structures from a natural landscape involving different size objects. In the present study, we focused on an actual procedure in the decomposition of the Morphological Component Analysis known as MCA to extract specific patterns as serial and parallel models. In our computer experiments, dictionaries of Curvelet and Local Discrete Cosine Transform known as LDCT were introduced for the MCA decomposition and then two models demonstrated a non-negligible difference in the feature extraction performance. This result may contribute to the extension of future possibilities of structural data analyses especially for buildings and roads from shapes in nature.

View full abstract

Aggression is a human behaviour that has the potential to injure another person physically or emotionally. The aggression states of the human could be identify by using BPQ, however, some of the subjects are not honest while answering the survey. This effects the precision of the survey. In this studies, experimental works have been conducted to investigate the aggression states of the 10 subjects. The experimental protocol is proposed for inducing aggression while brain signals are recorded by using an electroencephalogram (EEG). The subjects are experience 4 states which are relaxing state before starting the experiment, aggression state when playing a video game in muted, aggression state when playing video game in a maximum volume, and post gaming state which is similar with the relaxing state but the time is after playing the video game. The subjects are asked to play a video game “Subway Surfers” while the brain signals are recorded. The original data may contain noises and a Butterworth filter is used to screen it. Then, the signals are cut into pieces called the window to extract significant features of the brain signals. The experimental protocols and signal processing techniques proposed can generate the aggression pattern.

View full abstract

Creating work shift schedules for nurses can be a complex task, as it involves satisfying various requirements that can be difficult to reconcile. Although several studies have investigated the nurse scheduling problem, creating practical work schedules with numerous constraints and evaluation values can still be challenging. To address this issue, we have proposed a method for work revision that utilizes reinforcement learning to improve a constructive nurse scheduling system. In this article, we extend the proposed method to accommodate dynamic nurse scheduling, wherein work schedules are revised or rescheduled in response to sudden absences. Specifically, we demonstrate the effectiveness of our approach in creating feasible work schedules for an unknown nurse who may be absent at any given time, through computational experiments.

View full abstract

This article describes the use of OpenCV for use in augmented reality applications. The implementation of the object recognition functionality is described using the basic algorithms: FAST, BRIEF, as well as by applying a mask and defining contours. Attention is also paid to the practical application of this technology on the example of an augmented reality application to assist a specialist in mounting radio-electronic components on a printed circuit board. Experiments were carried out to measure the recognition time depending on the degree of illumination. An analysis of the filters used for image preprocessing has been carried out..

View full abstract