Journal of Intelligent Systems and Internet of Things

The Comment Feedback Optimization Algorithm (CFOA) presented a novel feedback-driven model for solving optimization problems, incorporating ideas based on positive and negative feedback loops. Unlike other optimization algorithms, CFOA includes feedback adjustments for better tuning the exploration-exploitation trade-off, thus making CFOA less sensitive to the dimensions of problems and their nonlinearity. Some proposed features include feedback dynamics for adaptive search options, parameter control by a decay function, and mechanisms for escaping local optima. CFOA’s performance has been benchmarked on CEC 2005 test cases with many evaluations. The results demonstrate better convergence speed, solution quality, and computational complexity compared with the Sine Cosine Algorithm (SCA), Gravitational Search Algorithm (GSA), and Tunicate Swarm Algorithm (TSH). The efficiency of the approach used by CFOA makes it an indispensable tool for solving real-world optimization problems across various application domains such as machine learning, engineering, and logistics.

Nixi black pottery has a unique place in Chinese black pottery art. In this article, we have developed a style transfer model based on deep learning, which automatically transforms Nixi black pottery into images of other styles. This is of great value for the dissemination of this art. In this paper, we propose a method called DualTrans that utilizes a pure Transformer architecture to enable context-aware image processing, effectively addressing the issue of low receptive field. Additionally, we introduce a Location Information Encoding Module (LIM) and a Style Transfer Control Module (STCM) to tackle the problem of long-range dependencies while ensuring that the generated target image remains structurally and stylistically consistent throughout the style transfer process, without being influenced by the content and style images. During the mapping process, the LIM encodes the original image block information and concatenates it with the projected image block information. To alter the final produced style of the picture, the STCM leverages a set of learnable style-controllable factors. Extensive trials have shown that DualTrans exceeds previous approaches in terms of stability.

With the acceleration of modern urbanisation, the demand for energy by the state and society is increasing. In order to maintain the sustainable availability of energy, it is necessary to establish an energy sustainability indicator system. To address this issue, this paper proposes an innovative evaluation method for energy sustainability indicator system, which aims to provide a multi-scale and more comprehensive assessment of energy sustainability indicators, as well as to ensure the accuracy and reliability of the evaluation results. This paper proposes to use genetic algorithm and local support vector regression (SGA-LSVM) to optimise the projective fuzzy clustering solution model (PPFCM), to establish a new evaluation method of energy sustainability index system based on genetic algorithm and local support vector regression. Based on this method, energy sustainability in different regions is analyzed according to three indicators: energy supply side, demand side and affordability, and the validity of this evaluation method is tested. The study found that, in terms of zoning: the eastern region is in the lead in energy demand side, energy supply side and energy affordability, and the western region has a rising trend in recent years; in terms of population density: the indices of energy demand side, energy supply side and energy affordability of densely populated areas are much higher than the rest of the areas compared to the sparsely populated areas, and the difference between the indices of energy supply side and energy affordability of the sparsely populated and moderately populated areas and the difference between the indices is not significant. The energy supply-side index is slightly higher than that of the medium-population area; Economy and carbon emission: due to China's focus on environmental protection, carbon emission is kept within a stable range while the economy is developing rapidly. By PC≥0.80, PE≥0.45 and XB≤0.1, it shows that the method of evaluating the energy sustainable development index system using the fuzzy projection-seeking clustering energy sustainable development evaluation model based on genetic algorithm and local vector regression optimization is reliable.

    This research creates an innovative EfficientNet-B7-based Facial Expression Recognition model that delivers maximum accuracy performance for detecting emotions. Successful classification performance benefits substantially from EfficientNet-B7's application of compound scaling techniques which balances the entire network dimensions depth width and resolution. The characteristic distinctive to EfficientNet-B7 over standard architectural models involves its dual capability to perform accurate computations at reduced complexity levels. The model receives evaluation using KDEF at high-resolution as well as FER2013 at low-resolution through usage of SGD, Adam, and RMSprop optimizers. Experimental tests confirmed that EfficientNet-B7 operates with RMSprop optimizer to recognize emotions on KDEF at 91.78% accuracy superior to ResNet152's highest recorded accuracy of 88.77%. Performance levels declined to 57.56% on FER2013 because low-resolution images represent a great challenge to the model. Internal Batch Normalization (IBN) enters the model as an issue solution to halt gradient descent problems, which results in better model training stability and enhanced accuracy-loss patterns. The research demonstrates that FER performance benefits greatly when EfficientNet-B7 works in combination with IBN for high-resolution image processing. The research proves that EfficientNet-B7 stands as a reliable FER solution that shows potential usage in affective computing and human-computer interaction domain.  

Breast cancer (BC) is one of the most common invasive cancers, which cause thousands of women's deaths globally. Therefore, prompt detection is a cure for reducing the rate of death. Therefore, screening of BC in its initial phase is of utmost vital. Physically segmenting breast lesion imaging appears a time-consuming and expensive pursuit for radiologists. Hence, the adoption of automatic analytic techniques becomes vital, directing to exactly segment lesions of the breast and mitigate the associated tasks. The segmentation of malignant areas is an essential procedure in the complete inspection of breast image data. To achieve the segmentation and recognition of BC, numerous computer-aided diagnosis (CAD) techniques were presented for the investigation of mammogram imaging. The CAD models are employed to mainly analyze the disorder and provide the best treatment. Currently, deep learning (DL) techniques are superior and provide promising results in the early recognition of BC. In this paper, we design a Leveraging Quantum Algorithms for Edge Detection in Mammograms to Improve Breast Cancer Screening (LQAEDM-IBCS) model. The main intention of the LQAEDM-IBCS is to provide an accurate and effective technique for the detection and segmentation process of breast cancer using advanced algorithms. Initially, the image pre-processing stage applies the adaptive bilateral filtering (ABF) method to eliminate the unwanted noise in input image data.  Next, the segmentation process is implemented by the Otsu threshold method for edge detection. To improve the segmentation performance, the parameter tuning process is performed through the quantum spotted hyena optimizer (QSHO) algorithm. Besides, the proposed LQAEDM-IBCS technique designs the DenseNet-121 method for the extraction of feature procedure. Eventually, the quantum neural network (QNN) method has been deployed for the BC classification process. The simulating validation of the LQAEDM-IBCS system is verified on a benchmark image database and the outcomes are dignified under numerous measures. The experimental outcome emphasized the enlargement of the LQAEDM-IBCS approach in the BC diagnosis process.

The representational and learning power of tree-based deep-learning (DL) classification models makes them a popular choice for dimensional sentiment analysis (DSA). One variant, Tree-structured Convolutional neural network with long short-term Memory (TCL) stands out among many others for its ability to handle uncertainties and unexpected changes in input data while still producing promising Valence-Arousal (VA) predictions for text or image classes. However, the high memory complexity of this model becomes a challenge when dealing with large image/text datasets. To address this issue, this manuscript introduces a Lightweight Adversarial Attention TCL (LAATCL) model for DSA. The proposed model includes a clustering layer in conjunction with the ATCL to decrease memory complexity and enhance performance through reliable sample selection. This model comprises multi-convolution with a clustering layer that utilizes Group-Sparse Non-negative Matrix Factorization (GSNMF) for clustering highly correlated samples. By learning informative and discriminative latent variables across labels, GSNMF helps identify and select samples closest to the cluster centroid for input to the LSTM network, resulting in reduced memory complexity and improved accuracy. The LATCL model outperformed traditional models in experiments conducted on the SST and CIFAR-10 datasets, with accuracies of 93.57% and 95.25%, respectively, demonstrating its usefulness.

For public health systems worldwide, the COVID-19 epidemic has presented hitherto unheard-of difficulties. Rapid and accurate virus detection is essential for successful treatment and containment. This paper explores the transformative potential of Artificial Intelligence (AI) and Big Data in public health, focusing on applying deep learning techniques for COVID-19 detection in medical imaging. We discuss the integration of AI-driven solutions in healthcare, the role of big data in enhancing diagnostic accuracy, and the implications for future public health strategies. The COVID-19 pandemic started in Dec 2019 and has wreaked havoc on our lives ever since. One such youngest addition to the coronavirus family has claimed the lives of almost half the world's population. With the introduction of constantly evolving forms of this infection, locating the infection early on would still be essential. Even though the PCR test is the best and most utilized approach for identification, non-contact procedures such as chest radiography and CT scans have always been recommended. In this context, artificial intelligence is integral to the early and precise diagnosis of COVID-19 via lung image processing. The primary aim of this study is to evaluate and contrast multiple deep learning improved strategies for detecting COVID-19 in CT and X-Ray medical images. We employed four strong CNN methods for the COVID-19 images of the binary classification challenge: ResNet152, VGG16, ResNet50, and DenseNet121. The suggested Attention-based ResNet framework is created to choose the appropriate architecture and training settings for models automatically. In the diagnosis of COVID-19 utilizing CT-scan images, the accuracy and F1-score are over 96 percent. In addition, transfer-learning methods were used to address the lack of information and shorten the training time. Enhanced VGG16 deep transfer learning design was used to accomplish multi-class categorization of X-ray imaging tasks. Enhanced VGG16 was shown to have 99 percent accuracy in detecting X-ray imaging from three classes: Normal, COVID-19, and Pneumonia. The algorithms' accuracy and validity were tested on well-known public datasets of X-ray and CT scans. For COVID-19 diagnosis, the presented approaches outperform previous methods in the literature. In the fight against COVID-19, we believe our research will aid virologists and radiologists in making better and faster diagnoses.

In this research, we provide a CNN-based system that can reliably identify the dorsal veins of the hand. In order to get better results on different picture quality datasets, the suggested model makes use of refined variants of the pre-trained VGG Net-16 and VGG Net-19 designs. We use the BOSPHORUS dataset, which provides medium-quality photos, in addition to two self-constructed datasets that provide good- and low-quality images. By using state-of-the-art augmenting image methods, streamlined pre-processing procedures, and meticulously designed CNN designs, the fine-tuned VGG Net-16 model achieves superior performance in comparison to all other models. Using ROI pictures with a resolution of 224×224 pixels, a multi-class technique is employed for arranging the vein patterns. Improving data quality during training makes the approach more broad, which helps prevent over fitting. On every dataset, the proposed method achieves better results than standard ML models like K-NN and SVM, and the experimental outcomes demonstrate significant improvements in accuracy. The modifying process led to a considerable decrease in the equal error rates (EER) when compared to benchmark methods. The structure enhances efficiency in computing with GPU-accelerated studying. It was built with the help of Python extensions like as OpenCV, Keras, and TensorFlow. Results from extensive testing of the proposed method show an accuracy of 99.98%, a precision of 98.98%, and a recall of 98.8%. From what we can see, the technique is both adaptable and dependable; making it well suited for use in practical biometrics vein recognition applications.

One of the most significant issues affecting the majority of countries in the world today is resource conservation. Water is the most vital component for all life, hence protecting it is crucial. Optimal use of water maintains its sustainability and leads to energy savings. Educational institutions are considered among the largest institutions that use water because of the presence of large numbers of students and employees. This research concerned resource management in educational institutions taking into account environmental conditions based on Internet of Things (IoT). The results illustrated that the designed monitoring system for moisture content has the ability to enhance water sustainability by using the optimal water content. A significant efficiency of the proposed monitoring system in controlling the water level was achieved. The maximum error between the monitoring system reading and the actual reading was 2% and 2.44% for moisture content and water level, respectively. The results showed the sensor's high sensitivity to rainfall and the ability of the proposed monitoring system to save water that exceeds the need of soil