The COVID-19 pandemic has posed an ongoing challenge for public health systems around the globe. Accurate forecasting of daily confirmed COVID-19 cases in Saudi Arabia has remained critical for informed planning and timely interventions. This research explores and compares the predictive performance of two artificial neural network models—Nonlinear Autoregressive Neural Network (NNAR) and Long Short-Term Memory (LSTM)—applied to Saudi Arabia’s COVID-19 case data from March 2020 through December 2021. Using standard evaluation metrics, including MAE, RMSE, MAPE, and Theil’s U, the study demonstrates that the NNAR model provides slightly more stable and accurate predictions in short-term horizons than LSTM. While LSTM models are known for capturing complex temporal patterns, our findings suggest that NNAR may offer a more robust option in volatile epidemiological conditions. These insights contribute to the growing field of epidemic forecasting and provide practical considerations for health policymakers in the region.

In this paper, we dive into designing a Single Precision Floating Point Unit (FPU), a key player in modern processors. FPUs are essential for handling complex numerical calculations with high precision and a broad range, making them indispensable in scientific research, graphics rendering, and machine learning—our design centers around two main components: the Brent-Kung adder and the radix-4 Booth multiplier. The BrentKung adder is our go-to for fast addition and subtraction. Thanks to its clever parallel-prefix structure, it minimises delays even as the numbers get bigger. For multiplication, we turn to the radix-4 Booth multiplier. This powerhouse streamlines the multiplication process by cutting down the number of partial products and operations needed, efficiently handling both positive and negative numbers. By integrating these components, our FPU can handle floating-point arithmetic with excellent efficiency and reliability. In scientific computing, this means more accurate simulations and data analyses. For graphics processing, it translates to better image rendering and smoother visual effects. And in machine learning, it supports robust training and execution of algorithms on massive datasets, ensuring dependable model performance.

We describe a compact planar antenna for enhancing bandwidth, suitable for ultra-wideband devices like smartphones. In order to attain an ultra-wideband response of 6.5478GHz, the partial ground plane structure is applied to the suggested design in this paper. The total dimensions of the proposed antenna are 36× 30×0.79 mm3 (853.2 mm3 ). Throughout the whole frequency range of 2.782GHz to 9.3298GHz, (S11 ≤−10 dB), the antenna's gain and directivity vary from 2.30 dB to 3.72 dB and 2.59 dBi to 3.9 dBi, respectively. The suggested design's performance parameters exhibit a respectable return loss of -26. 983. The VSWR is 1<VSWR<2 across the entire band, and it is 1.087 at 3.33GHz. All of the significant requirements have been satisfied by the time domain and frequency domain analyses. The 2018 edition of the Computer Simulation Technology (CST) Microwave Studio Suite was used to carry out all of the characteristic parameters. This idea will encourage the development of high performance ultra-wideband antennas for 5G devices.

As a part of natural language processing (NLP), machine translation focuses on automated techniques to produce target language text from the source language text. In this study, we combined two approaches: the rule-based MT approach and the statistical MT approach. Sentence reordering, Language model, Translation models, and decoding comprise the system. POS tagging was used to reorder the sentence more comparably, the IRSTLM tool was used to create language models for English, and the Wolaytta, Giza++ tool was used for translation. To ensure mutual translation, two language models have been developed. Four phases of experiments are carried out on the collected dataset. Phases of experimentation include preprocessing on the parallel corpus, language modelling, training the translation model, and tuning the translation system. For both side translations, the BLEU score assessed the translation accuracy from Wolaytta to English as 46.31 % and from English to Wolaytta as 56.56%.

This study presents an advanced deep learning framework for the real-time recognition and translation of Indian Sign Language (ISL). Our approach integrates Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks to capture the spatial and temporal features of ISL gestures effectively. The CNN component extracts rich visual features from the input sign language videos, while the LSTM component models the dynamic temporal patterns inherent in the gesture sequences. We evaluated our system using a comprehensive ISL dataset of 700 fully annotated videos representing 100 spoken language sentences. To assess the effectiveness of our approach, we compared two model architectures: CNN-LSTM and SVM-LSTM. The CNN-LSTM model achieved a training accuracy of 84%, demonstrating superior performance in capturing visual and sequential information. In contrast, the SVM-LSTM model achieved a training accuracy of 66%, indicating comparatively lower effectiveness in this context. One of the key challenges faced during the development of the system was overfitting, primarily due to computational constraints and the limited size of the dataset. Nevertheless, the model exhibited promising results through careful tuning of hyperparameters and various optimisation strategies, suggesting its potential for real-world applications. This paper also discusses the data preprocessing techniques employed, including video frame extraction, normalisation, and data augmentation, which were critical in enhancing model performance. By addressing the complexities of sign language recognition, our work advances communication accessibility for individuals relying on ISL, promoting greater inclusivity through technology.

Election algorithms play a critical role in distributed systems by enabling the selection of a leader among a set of distributed processes, which is essential for achieving consensus and maintaining system reliability. However, traditional election algorithms often have high message complexity, leading to increased communication overhead, bandwidth consumption, and system inefficiency. Furthermore, ensuring fault tolerance in these algorithms remains a significant challenge, especially in network failures or process crashes. This paper proposes an enhanced election algorithm to reduce message complexity while improving fault tolerance in distributed systems. Our approach leverages [insert specific technique, e.g., a hierarchical messagepassing scheme, a hybrid consensus model, or dynamic fault recovery mechanisms], designed to minimize the number of messages exchanged between processes during the election process. Additionally, it incorporates advanced fault-tolerant mechanisms that allow the system to continue operating seamlessly even in the face of process failures or network partitions. Through extensive simulation and comparative analysis, we demonstrate that the proposed algorithm significantly reduces message complexity compared to traditional approaches like the Bully and Ring algorithms, while improving the system’s ability to recover from faults without compromising performance. The results show that our approach enhances the scalability and robustness of distributed systems, making it a promising solution for large-scale, fault-tolerant applications. This research contributes to the ongoing effort to optimize election algorithms in distributed systems, offering practical solutions for real-world deployment scenarios where efficiency and resilience are paramount.

The campus area is gradually expanding with the increasing number of university students. Consequently, it is difficult for freshmen or visiting staff to find a specific building at the campus. The study aimed to Develop a Campus Web GIS Navigation System for the study area using Geospatial technology. The general procedures to create a web map navigation application are Geo-referencing Images, digitization, Road Network Analysis, Overlay Analysis, and finally, a Web GIS Based Campus Navigation System has been developed. The main activity of the system application is the map activity. It displays the campus map of the Wa chemo University. The user can zoom and scroll this map to get to his/her desired places. The building map is the basic layer of this screen. The end user can access it by using this link: https://wcu- webmap.github.io/Web-Map-of-WCU/

Ethiopia’s natural forest cover is declining at an alarming rate due to population-growth-induced factors, other human-caused activities, and natural factors. This study aimed at the evaluation of spatiotemporal natural forest change dynamics by using change analysis. For the study (2000 ETM, 2010 ETM, and 2020 OLI-TIRS Landsat images were used) for change detections. Thus, the study result revealed that the major land use types were natural forests by 2000, but by now (2020), most of the natural forest areas are replaced by other land use classes. Thus, 233.76 ha of natural forest were cleared yearly for the last 20 years, mostly converted to farmland and settlement areas. Forest in the study is a source of energy (fuel wood and charcoal productions), substantial economic importance (timber and other construction material productions), and a source of food and domestic and wildlife habitat. Quantification of land use change detection shows us farmland, human settlement, and plantation areas are showing an increasing trend throughout the study period while natural forests are decreasing trend by 12% during 2000- 2010 and by 14 % from 2010-2020. The main causes of natural forest degradation are the high demand for farmland, housing, and energy mainly due to population growth, shortage of clean energy provision, and low level of awareness. Natural forests will have high economic, ecological, genetic, and medicinal value. Thus, protecting and conserving natural forests is crucial for the study area.

Touchless ATMs, a new technology, offer a contactfree, hygienic, and convenient financial transaction experience. This innovative solution uses Augmented Reality (AR), Timebased One-Time Passwords (TOTP), and the HAAR Cascade Algorithm to create an interactive virtual interface, reducing physical contact and enhancing transaction security. The system uses a dual-layered authentication mechanism, utilizing facial recognition and time-based, one-time passwords (TOTP) to validate user identities and generate dynamic, session-specific codes. Financial institutions can deploy this system to upgrade their ATM networks, catering to diverse user demographics. Challenges include developing robust gesture recognition models, ensuring low latency in AR interactions, and integrating these advanced technologies into existing ATM infrastructures. However, advances in hardware and software, coupled with the decreasing cost of AR and machine learning technologies, make this solution viable and scalable.

Primarily author has already done one fundamental paper work on image clustering and segmentation but here in this paper author has continued that same type of work on clustered and segmented images as a mode of comparative study for author has chosen three different parameters like mean square error, peak SNR and dimensions of images (length, width, height). The author has all three parametric methods on one particular to justify the comparison. So this paper is a cumulative case of a comparative study for which author has chosen the above mentioned parameters