In recent years, vehicular licence plate recognition (VLPR) framework has emerged as one of the most significant issues in intelligent transport systems. It has emerged as an important and complicated issue of research in recent times as explorations are carried on this issue with regard to the challenges and diversities of licence plates (LP) including various illumination and hazardous situations. Restricted situations like stationary background, only one vehicle image, fixed illumination, and limited vehicular speed have been focused in most of the approaches. VLPR approaches should be generalised for being capable of identifying LP containing different fonts, colours, languages, complex backgrounds, deformities, hazardous situations, occlusion, speeding vehicles, vertical or horizontal skew, blurriness, and illumination diversions. A comprehensive investigation on the existing VLPR techniques has been carried throughout this study by the aspects of detecting, segmenting, and recognising the plates. Different existing VLPR approaches have been categorised in accordance with the deployed attributes and the classifications have been compared as well on the basis of conveniences, inconveniences, processing time, and recognition rate when available.

Background: DNA Methylation is one of the most important epigenetic processes that are crucial to regulating the functioning of the human genome without altering the DNA sequence. DNA Methylation data for cancer patients are becoming more accessible than ever, which is attributed to newer DNA sequencing technologies, notably, the relatively low-cost DNA microarray technology by Illumina Infinium. This technology makes it possible to study DNA methylation at hundreds of thousands of different loci. Currently, most of the research found in the literature focuses on the discovery of DNA methylation markers for specific cancer types. A relatively small number of studies have attempted to find unified DNA methylation biomarkers that can diagnose different types of cancer (pan-cancer classification). Results: In this study, the aim is to conduct a pan-classification of cancer disease. We retrieved individual data for different types of cancer patients from The Cancer Genome Atlas (TCGA) portal. We selected data for many cancer types: Breast Cancer (BRCA), Ovary Cancer (OV), Stomach Cancer (STOMACH), Colon Cancer (COAD), Kidney Cancer (KIRC), Liver Cancer (LIHC), Lung Cancer (LUSC), Prostate Cancer (PRAD) and Thyroid cancer (THCA). The data was pre-processed and later used to build the required dataset. The system that we developed consists of two main stages. The purpose of the first stage is to perform feature selection and, therefore, decrease the dimensionality of the DNA methylation loci (features). This is accomplished using an unsupervised metaheuristic technique. As for the second stage, we used supervised machine learning and developed deep neural network (DNN) models to help classify the samples’ malignancy status and cancer type. Experimental results showed that compared to recently published methods, our proposed system achieved better classification results in terms of recall, and similar and higher results in terms of precision and accuracy. The proposed system also achieved an excellent receiver operating characteristic area under the curve (ROC AUC) values varying from 0.85 to 0.89. Conclusions: This research presented an effective new approach to classify different cancer types based on DNA methylation data retrieved from TCGA. The performance of the proposed system was compared to recently published works, using different performance metrics. It provided better results, confirming the effectiveness of the proposed method for classifying different cancer types based on DNA methylation data.

Turbochargers reduce fuel consumption and CO₂ emissions from heavy-duty internal combustion engines by enabling downsizing and downspeeding through greater power density. This requires greater pressure ratios and thus air systems with multiple stages and interconnecting ducting, all subject to tight packaging constraints. This paper considers the aerodynamic optimization of the exhaust side of a two-stage air system for a Caterpillar 4.4 l heavy-duty diesel engine, focusing on the high pressure turbine (HPT) wheel and interstage duct (ISD). Using current production designs as a baseline, a genetic algorithm (GA)-based aerodynamic optimization process was carried out separately for the wheel and duct components to evaluate seven key operating points. While efficiency was a clear choice of cost function for turbine wheel optimization, different objectives were explored for ISD optimization to assess their impact. Optimized designs are influenced by the engine operating point, so each design was evaluated at every other engine operating point, to determine which should be carried forward. Prototypes of the best compromise high pressure turbine wheel and ISD designs were manufactured and tested against the baseline to validate computational fluid dynamics (CFD) predictions. The best performing high pressure turbine design was predicted to show an efficiency improvement of 2.15% points, for on-design operation. Meanwhile, the optimized ISD contributed a 0.2% and 0.5% point efficiency increase for the HPT and low pressure turbine (LPT), respectively.

Although the image dehazing problem has received considerable attention over recent years, the existing models often prioritise performance at the expense of complexity, making them unsuitable for real‐world applications, which require algorithms to be deployed on resource constrained‐devices. To address this challenge, we propose WaveLiteDehaze‐Network (WLD‐Net), an end‐to‐end dehazing model that delivers performance comparable to complex models while operating in real time and using significantly fewer parameters. This approach capitalises on the insight that haze predominantly affects low‐frequency information. By exclusively processing the image in the frequency domain using discrete wavelet transform (DWT), we segregate the image into high and low frequencies and process them separately. This allows us to preserve high‐frequency details and recover low‐frequency components affected by haze, distinguishing our method from existing approaches that use spatial domain processing as the backbone, with DWT serving as an auxiliary component. DWT is applied at multiple levels for better information retention while also accelerating computation by downsampling feature maps. Subsequently, a learning‐based fusion mechanism reintegrates the processed frequencies to reconstruct the dehazed image. Experiments show that WLD‐Net outperforms other low‐parameter models on real‐world hazy images and rivals much larger models, achieving the highest PSNR and SSIM scores on the O‐Haze dataset. Qualitatively, the proposed method demonstrates its effectiveness in handling a diverse range of haze types, delivering visually pleasing results and robust performance, while also generalising well across different scenarios. With only 0.385 million parameters (more than 100 times smaller than comparable dehazing methods), WLD‐Net processes 1024 × 1024 images in just 0.045 s, highlighting its applicability across various real‐world scenarios. The code is available at https://github.com/AliMurtaza29/WLD‐Net .

Every year, at least 100 million tons of solid waste globally comes from packaging waste, in which partly created by inefficient packaging. Multiple box arrangement or bin packing solution directly addresses this problem which also affects storing space in production, manufacturing and logistics sector. Smart packing algorithm is designed for solving three-dimensional bin/container packing problem (3DBPP) which has numerous practical applications in various fields including container ship loading, pallet loading, plane cargo, warehouse management and parcel packing. This project investigates the implementation of genetic algorithm (GA) for a smart packing simulator in solving the 3DBPP applications. The smart packing system has an adaptable chromosome length GA for more robust implementation, where chromosome length will be changing with number of boxes. It can optimize multiple box arrangements and the boxes movements and positions are simulated through each GA generations, for realistic adaptation. The system is able to make optimum arrangement for the boxes so they can fit into a smallest container possible. The time taken for GA to converge varies with number of boxes.

Designing a suitable controller for air-conditioning systems to reduce energy consumption and simultaneously meet the requirements of the system is very challenging. Important factors such as stability and performance of the designed controllers should be investigated to ensure the effectiveness of these controllers. In this article, the stability and performance of the fuzzy cognitive map (FCM) controller are investigated. The FCM method is used to control the direct expansion air conditioning system (DX A/C). The FCM controller has the ability to do online learning, and can achieve fast convergence thanks to its simple mathematical computation. The stability analysis of the controller was conducted using both fuzzy bidirectional associative memories (FBAMs) and the Lyapunov function. The performances of the controller were tested based on its ability for reference tracking and disturbance rejection. On the basis of the stability analysis using FBAMS and Lyapunov functions, the system is globally stable. The controller is able to track the set point faithfully, maintaining the temperature and humidity at the desired value. In order to simulate the disturbances, heat and moisture load changed to measure the ability of the controller to reject the disturbance. The results showed that the proposed controller can track the set point and has a good ability for disturbance rejection, making it an effective controller to be employed in the DX A/C system and suitable for a nonlinear robust control system.