Ensuring the quality of global food supplies has emerged as a significant challenge in recent times. Overseeing perishable items' excellence, freshness, and longevity poses considerable intricacy. A special kind of system established on electronic scent detection systems has been engaged for quality assessment. Recent advancements have concentrated on integrating electronic scent detection systems with machine learning (ML) and deep learning (DL), which comprise encouraging remedies to meet these hurdles. Mainly, this investigation aims to present a pioneering strategy for addressing this issue by binding DL with electronic olfaction technology. Gated recurrent units (GRU) were used for classification actions. The research entails examining from the literature a benchmark dataset acquired from electronic noses (E-noses) across beef cuts. These cuts are allocated into four classes: i) outstanding, ii) satisfactory, iii) passable, and iv) spoiled, depending on their quality. The proposed model, exploiting a GRU for classification tasks, was developed with active dataset attributes identified over the analysis of variance (ANOVA) feature selection method. As a consequence, three key features were selected and employed for the classification process, such as MQ5, MQ137, and total volatile content (TVC). Experimental outcomes demonstrate an impressive classification accuracy of 99.77%, accomplished by the proposed model across further literature models.

This paper introduces the permutation-byte key cipher with reduced-round advanced encryption standard (PBKC-RRAES), a novel enhancement of the AES designed to significantly improve both security and performance. The proposed algorithm integrates key modifications; i) replacing the computationally intensive MixColumns function with an efficient bit permutation technique that achieves superior diffusion while reducing computational overhad by eliminating complex matrix multiplication operations. This substitution enhances security through improved bit-level scrambling patterns, while simultaneously accelerating processing speed through simpler bitwise operations; ii) the addition of AddRoundKey operations between cipher states, iii) enhanced byte substitution operations and round constant additions in the key schedule algorithm before key expansion, and iv) reducing rounds from 10 to 6. These innovations yield heightened sensitivity to plaintext changes, evidenced by a 54.214% avalanche effect, surpassing the standard 50% threshold. Performance evaluations reveal PBKC-RRAES operates 26.90% improvement in encryption time and a 22.73% improvement in decryption time than standard AES, alongside throughput enhancements of 39.48% in encryption and 31.27% in decryption compared to the original AES, critical improvements for bandwidth-constrained applications. These results demonstrate that PBKC-RRAES is a robust and effective alternative for cryptographic applications, particularly beneficial for real-time video streaming, secure cloud storage, mobile payment systems, and IoT device where both security and processing effectivity are paramount.

Alzheimer’s disease is a progressive neurodegenerative disorder requiring early and accurate detection for effective intervention. Deep learning (DL) techniques, particularly convolutional neural networks (CNNs), have shown promise in medical image classification. However, conventional CNN models often suffer from high computational complexity and inefficiency in handling imbalanced datasets. This study proposes a quad convolutional layers-CNN (QCL-CNN) for Alzheimer’s disease detection using magnetic resonance images (MRI) scans from the open access series of imaging studies (OASIS) dataset, which includes four dementia stages, non-dementia, very mild dementia, mild dementia, and moderate dementia. The QCL-CNN model employs four sequential convolutional layers for enhanced multi-level feature extraction, ensuring efficient classification while minimizing computational overhead. The experimental results demonstrate that QCL-CNN outperforms traditional CNN architectures, achieving an accuracy of 99.90%, recall of 99.89%, specificity of 99.93%, and an F1-score of 99.52%. The model surpasses VGG19, Xception, ResNet50, and DenseNet201 while maintaining a significantly lower parameter count (4.2M), making it computationally efficient. These findings confirm that network optimization is more crucial than model depth, ensuring robust performance even with fewer layers. Future research should explore multi-modal imaging, class balancing techniques, and real-world clinical validation to further improve the model’s diagnostic capabilities. The QCL-CNN model offers a promising artificial intelligence (AI)-powered approach for early Alzheimer’s detection, enabling precise, and efficient medical diagnosis.

Because of the evolution of artificial intelligence (AI), home security has progressed from a basic security system to an active architecture that is responsive and adaptive to real world situations. Due to the rapid adoption of AI in smart systems, there is increasing suspicion surrounding privacy issues and ethical ambiguity, as well as gaps when it comes to regulating these technologies. We provide an overview of AI in smart home security applications and examine the area of security, access control, intrusion detection, human action recognition, and research on intelligent automation. We summarize the last decade of evolution, with some summaries of previous on computer vision, authentication systems, and finding unusual patterns recently. Our key findings include the development of approaches to improve real time security monitoring, dramatic reductions in false alarms, and customization of home access using AI. Improvements in security have also increased risk with respect to ethical ambiguity as well as technical issues in certain cases. In this paper, we offers pathways for improved AI system design, proposed formal data protection regulations, and examples of simplifying complex system for user comprehension, which also establishes the groundwork for future efforts. Home security should balance new opportunities with ethical considerations.

Indoor reconnaissance missions for unmanned aerial vehicles (UAVs) pose significant challenges in scene reconstruction, mapping, and environmental feature extraction. Relying on a single type of sensor often results in limited accuracy, increased susceptibility to environmental noise, and a lack of comprehensive spatial information. To address these issues, this study proposes a mapping method that combines light detection and ranging (LiDAR) and depth camera data. The method collects data from both LiDAR and a depth camera integrated on the UAV, then performs preprocessing on both data sources to construct local 3D maps using the real-time appearance-based mapping (RTAB-Map) algorithm. Subsequently, the local maps are merged using a filtering method to generate a detailed and complete global map. Real-time experiments conducted on Ubuntu 20.04 using the robot operating system (ROS) Noetic libraries demonstrate that this multi-sensor fusion approach provides richer and more comprehensive environmental information, thereby enhancing the effectiveness of mapping tasks in unknown indoor environments.

For 5G communication, this research suggests a small, broad band, 4-port multiple-input multiple-output (MIMO) antenna with an impedance bandwidth of 2.0 GHz (or 3.0-5.0 GHz). The n77, n78, and n79 bands are covered. The single antenna is realized by inserting the stubs and creating the ‘HI’ slot on the rectangle patch with the defect in the ground plane, using FR-4 substrate. Next, four MIMO antennas are built utilizing the reference antenna. Due to mutual interaction, implementing MIMO systems presents a substantial challenge: achieving good isolation between antenna parts in the confined space. To increase isolation with decoupling procedures, the four antennas are placed orthogonally to one another. Because the antennas are positioned orthogonally, the MIMO antenna has an isolation of 28.0 dB. The diversity gains (DG) and envelop correlation coefficient (ECC) are used to analyze the recommended antenna's diversity performance characteristics, and the results show that the values are 9.99 dB and 0.0003, respectively. The simulated S-parameters have been compared with orthogonal and adjacent positions of quad port MIMO antenna. Anritsu MS2037C VNA is used to measure the parameters, and HFSS software is used to simulate it.

This study introduces a novel methodology aimed at minimising total harmonic distortion (THD) in grid-connected photovoltaic (PV) systems (GCPVs) through the implementation of a maximum power point tracking (MPPT) approach based on artificial neural networks (ANN). High THD levels in PV systems can lead to inefficiencies, power quality issues, and potential damage to the grid infrastructure. Although traditional MPPT methods effectively optimise the power output, they often fail to address harmonics. The proposed ANN-based MPPT algorithm improves PV power harvesting while actively minimising the harmonic distortions. The ANN was trained using a comprehensive dataset that included various environmental conditions, ensuring robust performance in diverse operational scenarios. Simulation results demonstrate that the ANN-based MPPT approach significantly reduces THD to below 1% across various irradiance levels, in contrast to the 1.18% to 2.72% observed with conventional methods such as perturb and observe (PO), while simultaneously preserving optimal power output. Reducing harmonic distortion improves the power quality, system efficiency, and lifespan of grid-connected components. This study highlights ANN-based control strategies for addressing the challenge of maximising energy harvesting and maintaining power quality in modern PV systems, offering a solution for the sustainable integration of solar energy into the grid.

Compressed sensing (CS) has been widely applied in magnetic resonance imaging (MRI) to accelerate the image acquisition without significantly reducing its image quality. In Cartesian MRI, acquisition time can be reduced by skipping phase-encoding steps for faster data acquisition. However, the balance between random under-sampling and Nyquist sampling at the k-space center strongly determines image quality. In this study, we systematically evaluate the impact of different random-to-Nyquist sampling ratios for both single-coil (CS-MRI) and multi-coil (CS-pMRI) reconstructions. Simulation results reveal that dense Nyquist sampling around the k-space center is essential for maintaining image fidelity, whereas reconstruction quality deteriorates sharply when random sampling exceeds approximately 60% of the total under-sampled data. Moreover, CS-pMRI consistently outperforms CS-MRI under equivalent under-sampling factors, benefiting from additional coil sensitivity information that improves resilience against aliasing and noise. These findings provide practical guidelines for hybrid under-sampling design, emphasizing that sufficient Nyquist sampling coverage of central k-space is crucial for achieving high-quality reconstructions while enabling high acceleration in CS-MRI.

The adoption of home automation systems in buildings faces limitations due to their cost, integration complexity, and protocol heterogeneity, which hinders the development of accessible solutions based on embedded devices to improve interaction in environments within buildings or homes. The literature review indicates that the selection of hardware and communication protocols in home automation systems considers factors such as cost, available infrastructure, and application context. In addition, approaches are identified that prioritize security, wired or wireless connectivity, and affordability. This paper presents the development of an affordable home automation system for building automation in Lima, using the ESP32 microcontroller and internet of things (IoT) technologies. The objectives focus on hardware design, implementation of control algorithms, remote monitoring interface, and validation in a simulated environment. The solution includes Wi-Fi connectivity, a cloud-based MySQL database, and a web interface. Key findings include the home automation system, integrated with Flask technology and web services, enabling monitoring and control via a responsive web interface, demonstrating its operability and ensuring lossless data transmission.

Artificial intelligence (AI) can manage tourism by optimizing, personalizing the experience, and enhancing user interactions. This research presents the Ayutthaya tourism platform independent model (ATPiM), an intelligent tourism application that integrates a domain-specific language (DSL) designed for chatbot development with machine learning algorithms that generate personalized recommendations based on user preferences, historical data, and real-time contextual influences. This pre-experimental design measures performance on parameters such as response time, recommendation accuracy, and system latency. The outcomes indicate that the mean time taken to respond to a user's query was 2.3 seconds, with 88.5% recommendation accuracy, and no latency. The AI-based recommendation system achieved 89.7% accuracy at destinations, 87.2% at accommodations, 90.3% at itineraries, and 85.6% at activities, with corresponding recalls of 85.4%, 83.5%, 88.1%, and 80.2% respectively. Although these results are promising, a 6.2% error rate for the advanced search, along with data security are some of the remaining issues. The findings reveal that the development of new user-centric and sustainable solutions for tourism, which leverage state-of-the-art natural language processing approaches, can enhance data security and provide additional new technologies, such as augmented reality (AR) and blockchain, for use in tourism.