Owing to the recent development of AI technology, various studies on computer-aided diagnosis systems for CT image interpretation are being conducted. In particular, studies on the detection of lung cancer which is leading the death rate are being conducted in image processing and artificial intelligence fields. In this study, to improve the anatomical interpretation ability of CT images, the lung, soft tissue, and bone were set as regions of interest and configured in each channel. The purpose of this study is to select a detector with optimal performance by improving the quality of CT images to detect lung cancer tumors. Considering the dataset construction phase, pixel arrays with Hounsfield units applied to the regions of interest (lung, soft tissue, and bone region) were configured as three-channeled, and a histogram processing the technique was applied to create a dataset with an enhanced contrast. Regarding the deep learning phase, the one-stage detector (RetinaNet) performs deep learning on the dataset created in the previous phase, and the detector with the best performance is used in the CAD system. In the evaluation stage, the original dataset without any processing was used as the reference dataset, and a two-stage detector (Faster R-CNN) was used as the reference detector. Because of the performance evaluation of the developed detector, a sensitivity, precision, and F1-score rates of 94.90%, 96.70%, and 95.56%, respectively, were achieved. The experiment reveals that an image with improved anatomical interpretation ability improves the detection performance of deep learning and human vision.

Read more…

Soft robots have softer, more flexible, and more compliant characteristics than traditional rigid robots. These qualities encourage more secure relationships between people and machines. Nevertheless, traditional robots continue to rule the commercial sector. Due to the high cost of gripper production, soft robots are very far from being commercially feasible. This research focuses on fabricating a soft robotic gripper with the potential for mass production using injection molding technology. The material used for manufacture is Thermoplastic Elastomer (TPE). This study gives an injection molding optimization strategy by using Moldex 3D simulation to minimize production time for soft grippers. Furthermore, using an Ansys workbench, this study simulated soft gripper deflections with variable pressures by finite element analysis and then compared it with the actual experiment. The simulation results of TPE warpage volume shrinkage are 11.969% and 11.96% in the molding experiment. Thus, the shrinkage and warpage for the simulation and actual experiment are similar. According to the simulation outcome, the success of TPE hollow injection molding facilitates soft gripper creation. The maximum pressure used in the FEM simulation of the bending experiment was achieved at the pressure of 50 kPa with 152.02 mm of deformation and compared to the experimental data, 145,03 mm. This error is less than 5%. Finally, a better soft gripper design was achieved by Ansys simulation, and the soft gripper appears to be ready for mass-produced by TPE injection molding.

Read more…

Passive remote monitoring applications of underwater signal processing in a shallow water environment are an impactful area of research for environmental and marine-life monitoring. The majority of the sound source localization techniques require carefully placed synchronized hydrophone arrays, which can be complicated and hard to maintain. In this paper, we utilized the modal dispersions of a signal to derive a localization method for a noisy, shallow water environment. Our proposed algorithm employs modal selection to process the most noise- resistive dispersion curves, improving the accuracy and noise-resistivity of the existing methods. Moreover, we proposed a 2D localization method with multiple unsynchronized hydrophones and minimal hardware requirements and limitations. Furthermore, we analyzed the effects of underwater ambient noise on the accuracy of the proposed method, using simulated and real recorded explosion and whale sounds, and compared our algorithm’s localization performance with others. Simulation results show increased localization accuracy of 30m for the recorded explosion sound and 360m for the Whale sound.

Read more…

In recent years, the adoption of ICT education has increased in educational settings. Research and development of educational support robots have garnered considerable interest as a promising approach to inspire and engage students. Conventional robots provide learning support through button operations by the learners. However, the frequent need for button operation to request support may lead to a tedious impression on the learner and lower the efficiency of the learning process. Therefore, in this study, we developed a Perplexion Estimation Method that estimates the learner’s state of perplexity by analyzing their facial expressions and provides autonomous learning support. We verified the impact of a teacher-type robot (referred to as the proposed robot) that autonomously provides learning support by estimating the learners’ perplexity states in joint learning with university students. The results of a subject experiment showed that the impression of the proposed robot was not different from that of the conventional robot. However, the proposed robot demonstrated the ability to provide optimal support timing compared to the conventional robot. Based on these results, it is expected that the utilization of the perplexion estimation method with teacher-type robots can create a learning environment similar to human-to-human interaction.

Read more…

Due to the variations in weather conditions, photovoltaic systems adopt a technique based on maximum power point tracking to extract the maximal power of the solar module. In the literature, there are many different methods classical and intelligent of maximum power point tracking (MPPT). But, due to the semiconductor effect, the current-voltage characteristics of the solar module is nonlinear. This affects its efficiency and make its control not easy. In this contribution, we present a new fuzzy PV MPPT based on custom defuzzification. The obtained power using the proposed fuzzy PV MPPT based on custom defuzzification is significant compared to Pertub & observe and fuzzy PV MPPT in term of performances indices such as: Rise time and overshoot.

Read more…

Metal Oxide Semiconductor Field-Effect Transistors are commonly taught in courses for electrical engineers as they are the most common components within integrated circuits. However, despite numerous papers and books on MOSFETs, students still struggle with understanding their behaviour, particularly in the saturation region. This paper presents an expanded explanation of MOSFET behaviour, with a consistent and causal derivation of Level 1 MOSFET behaviour from a few equations, aimed at students without an extensive technological background. The paper provides illustrative explanations to help them understand MOSFET behaviour and addresses common students’ questions, such as why the current is limited by charge carriers in the semiconductor substrate and why characteristic curves do not follow a parabolic curve in saturation. In addition to providing a comprehensive introduction to MOSFET behaviour from a circuit designer’s perspective, this paper also offers valuable insights into interpreting AC parameters in modern MOSFET models. These parameters are often key to understanding and solving circuit problems related to small signal behaviour and frequency response, as demonstrated through various industrial application examples. These examples highlight how to bridge modern MOS models, such as the BSIM model, with MOS-Level 2 modelling, which is easily interpreted by users. By presenting these real-world examples, analysed by a symbolic analysis tool incorporating the BSIM to Level 2 AC model, this paper provides a practical and accessible approach to teaching MOSFETs and their applications in industry.

Read more…

The levelized cost of electricity production is highly dependent on the cost of fuel oil on the world market. In order to reduce the dependency on the fuel oil, many countries are adopting an energy transition towards distributed generation. Distributed generation can be described as various means of generating electricity at or near where it will be used. Such generating mode can be a solar PV system, wind turbine generator and other renewable energy sources. However, it entails lots of challenges as it uses power electronics devices as the power grid interface, which causes a reduction in the system inertia and at the same time affecting the frequency, thereby affecting the stability. To enhance this stability, appropriate control measures need to be adopted. This paper brings forward a novel approach for frequency control support of a wind turbine generator (WTG) in a diesel generation mix. The novelty of this research paper explained on the concurrent application of a Proportional derivative (PD) and a Proportional Integral Derivative (PID) for speed and frequency control in a WTG. The analysis of this experimental research was carried out through the modelling of the rate of change of frequency (RoCoF) using MATLAB / Simulink software. The results showed that the use of these controllers in presence of WTG provide frequency support to the system as the frequency varied within the acceptable limit of 0.5Hz. Additionally, this experimental research work also proved that the use of speed / governor control in form of the PID improved the RoCoF and provided an enhancement in the stability of the test system. Finally, this paper confirmed that the integration of WTG to the grid required the use of appropriate control algorithm for an efficient exploitation of this kind of renewable energy source.

Read more…

The attributes of the vehicle routing problem (VRP) are as many additional characteristics or constraints which aim to better take into account the specificities of real application cs. The variants of the VRP thus formed are the support of an extremely rich literature, comprising an immense variety of heuristics. This article constitutes an industrial application and an objective synthesis of successful and challenging heuristic concepts for time-windowed VRP problems. The purpose will be to minimize transport costs and determining the optimal number of trucks by applying a transport algorithm. The results show that the solution method should help to increase the competitiveness of transportation operations in this important economic sector.

Read more…

Over the past ten years, deep learning models have considerably advanced research in artificial intelligence, particularly in the segmentation of medical images. One of the key benefits of medical picture segmentation is that it allows for a more accurate analysis of anatomical data by separating only pertinent areas. Numerous studies revealed that these models could make accurate predictions and provide results that were on par with those of doctors. In this study, we investigate different methods of deep learning with medical image segmentation, like the V-net and U-net models. Improve the V-net model by adding attention in 2D with a decoder to get high performance through the training model. Using tumors of severe forms, size, and location, we downloaded the BRAST 2018 data set from Kaggle and manually segmented structural T1, T1ce, T2, and Flair MRI images. To enhance segmentation performance, we also investigated several benchmarking and preprocessing procedures. It’s significant to note that our model was applied on Colab-Google for 35 epochs with a batch size of 8. In conclusion, we offer a memory-effective and effective tumor segmentation approach to aid in the precise diagnosis of oncological brain diseases. We have tested residual connections, decoder attention, and deep supervision loss in a comprehensive ablation study. Also, we looked for the U-Net encoder and decoder depth, convolutional channel count, and post-processing approach.

Read more…

As a result of rising expectations for quality, the employment of advanced technical requirements for future fifth-generation (5G) new radio is required. The error-correction coding method is one of the most important components of a new generation. The 5G NR New Radio Low-Density Parity Check (LDPC) codes, which have been adopted by the 5G standard, are a standout solution in terms of high coding gain, high throughput, and low power dissipation. This paper presents an implementation of 5th generation (5G) New Radio (NR) and 5G NR low-density parity check codes, which are performed with the aid of a proper architecture. LABVIEW will be used in wireless communications to reduce the cost, space, and power. Simultaneously, this increased the speed. The circuit design supports a constraint length of 1360 and a code rate of 0.5. The LDPC encoder and decoder are implemented on an NI MY RIO 1900 ZYNQ FPGA at a 33 MHZ core frequency starter kit. Xilinx Vivado 18.2 series was used for the simulation. The implemented design shows an area overhead reduction of 50% compared with the referenced designs of the Xilinx 7 series device. In MY RIO ZYNQ, the proposed method achieved 21000 LUTs compared with Xilinx 7-series solutions, and it has a much higher throughput (224 vs. 87 and 5 MBit/s), followed by MY RIO ZYNQ, which is better than previous state-of-the-art solutions in terms of area and higher data rates. Moreover, the implemented 5G NR LDPC decoder tested against an additive white Gaussian noise channel (AWGN) and consequently has gained more popularity in many applications.

Read more…

Recent studies show the benefits of lean manufacturing implementation in agri-food industries to improve operational and environmental performance. However, only a restricted number of studies have addressed the implementation of lean practices in food companies located in developing countries. This study aims to assess the current implementation status of lean practices in Moroccan agri-food companies, particularly small and medium-sized enterprises, and to examine their impact on operational and environmental performance. Responses from 45 agri-food companies were collected through a questionnaire. The results show that the degree of implementation of lean practices in the Moroccan food industry is generally average. On the other hand, some lean practices are implemented more frequently compared to others., e.g. customer involvement, employee involvement, supplier involvement and total productive maintenance are the most implemented. On the other hand, pull and setup are not used very much. The findings also demonstrate the positive impact of lean practices on both operational and environmental performance.

Read more…

A 2-dimensional numerical data set X = {x1,…,xn} with associated category labels {l1,…,ln} can be accurately represented in a 2-dimensional scatterplot where color is used to represent each datum’s label. The colorized scatterplot indicates the presence or absence of spatial clusters in X and any special distribution of labels among those clusters. The same approach can be used for 3-dimensional data albeit with some additional difficulty, but it cannot be used for data sets of dimensions 4 or greater. For higher dimensional data, the improved Visual Assessment of cluster Tendency (iVAT) image can be used to indicate the presence or absence of cluster structure. In this paper we propose several new types of colorized iVAT images, which like the 2-dimensional colorized scatterplot, can be used to represent both spatial cluster structure and the distribution of labels among clusters.

Read more…

“Seven ReImagined” is an innovative transmedia storytelling project that reshapes the exploration of the seven deadly sins in a modern context. Building upon the original artwork “Seven”, this venture incorporates traditional media, digital tools, and the latest immersive technologies to cultivate profound user engagement and interaction. The project’s objective is to enhance understanding of timeless moral themes, encourage self-reflection, and foster communal participation. The project centres around a physical and virtual exhibition (via Metaverse), where the artworks dedicated to each sin invite viewers into a reflective and immersive journey. The inclusion of a confessional booth enriches the narrative by allowing viewers to anonymously express and share their interpretation of their own sins. The journey further extends to a dedicated website and a podcast series, serving as a hub for a comprehensive narrative, providing in-depth information about each artwork, and fostering an engaging global dialogue around these universal themes. Engagement through social media platforms allows the project to reach varied audiences, harnessing the participatory culture of these platforms to stimulate reflections and dialogues. By marrying artistic creativity with technological innovation, “Seven ReImagined”, creates a multifaceted dialogue on ancient moral wisdom in our contemporary society, providing a profound platform for self-reflection and communal participation. The project’s innovation lies in seamlessly blending traditional art with cutting-edge immersive technologies, offering a fresh perspective on ancient moral concepts. Future iterations hold the potential for enhanced sensory experiences, collaborative educational initiatives, data-driven insights, and diverse exhibition formats. In summary, “Seven ReImagined” creatively fuses art and technology, engaging in multifaceted dialogues about ancient moral wisdom. Serving as a platform for introspection and global discourse, the project reaffirms the enduring relevance of fundamental human themes.

Read more…