Fusion: Practice and Applications

Anomaly detection in pedestrian walkways is a vital research area, widely employed to enhance the safety of the pedestrians. Because of the widespread usage of the video surveillance systems and the increasing number of captured videos, the conventional manual examination of labeling abnormal events is a laborious process. Therefore, an automatic surveillance system to accurately detect anomalies becomes essential among computer vision researchers. Presently, the development of deep learning (DL) models has gained significant interest in different computer vision processes namely object classification and object detection, and these applications were depending on supervised learning that required labels. This article develops an Improved Meta-heuristic with Parallel Features Fusion Model for Anomaly Detection in Pedestrian Walkways (IMPFF-ADPW) method. The main aim of the IMPFF-ADPW approach is to recognize the existence of anomalies in pedestrian walkways. To obtain this, the IMPFF-ADPW method applies a joint bilateral filter (JBF) for the process of noise removal. Besides, a parallel fusion process comprising NasNet Mobile and Darknet-53 models can be utilized for feature extraction. For the anomaly detection method, the deep autoencoder (DAE) model is applied and its hyperparameters are finetuned by using an improved sparrow search algorithm (ISSA). A wide of experimental outcomes can be applied to the UCSD database to illustrate the betterment of the IMPFF-ADPW methodology. The simulation values indicated the enhanced performance of the IMPFF-ADPW method over other existing techniques.

Depression is one of the common psychological disorders that affects many people all over the world. The primary typical behavior of depression is persistent low mood, and it is one of the main reasons for disability worldwide. Due to the lack of awareness, treatment, and social stigma, it is leading to suicide and self-harm. It is necessary to identify the depression at a very initial stage to overcome further complications that may lead to suicide. In recent years, certain studies have been done on identifying depression through Machine Learning and Deep Learning techniques. Electroencephalogram (EEG) can be used to detect depression since it is easy to record and non-invasive. The current paper focuses on developing an algorithm that will use the brain signals received through EEG and predict the person as Healthy or with Major Depressive Disorder (MDD) with the help of CNN through an asymmetry matrix, which achieved an accuracy of 89.5%, and it outperformed the previous traditional models. The current study shows that depression detection through EEG is one of the efficient techniques for detecting depression at its early stages.

Digital document helps as the lifeblood of present communication, yet their vulnerability to tampering poses major safety anxieties. Digital text watermarking is an effective mechanism to protect the reliability of text-based data in the digital. Introducing a hidden layer of accountability and safety, allows individuals and organizations to trust the written word and make sure the truth behind all the files. Watermarking model identifies the tampering attack by inspecting the embedded signature for distortions or alterations. Watermarks can able to mechanically classify and repair themselves once tampered with, improving document resilience. Watermarking acts as a powerful tool to detect tampering attacks in digital document. By embedding strong and imperceptible watermarks in document distribution or creation, alterations are recognized by specialized procedure. This study introduces an Evolutionary Optimizer-powered Watermarking for Tampering Attack Detection in Digital Document (EO-WTAD3) model. The main intention of EO-WTAD3 approach is to support textual integrity using the applications of metaheuristic optimizer algorithm based watermarking technique for detecting tampering attacks in digital document. In the EO-WTAD3 method, a digital watermarking method has been proposed for the ownership verification and document copyright protection using data mining concept. Moreover, the EO-WTAD3 technique utilizes the concepts of data mining to define appropriate characteristics from the document for embedding watermarks. Moreover, fractional gorilla troops optimization (FGTO) algorithm can be applied for the assortment of optimal situation of watermarks in the content, ensuring both imperceptibility and strong to tamper. The performance validation of the EO-WTAD3 methodology takes place employing multiple datasets. The extensive result analysis portrayed that the EO-WTAD3 system accomplishes improve solution with other existing approaches with respect distinct aspects.

Autism, a developmental and neurological disorder, impacts communication, interaction, and behavior, setting individuals with it apart from those without. This spectrum disorder affects various aspects of an individual's life, including social, cognitive, emotional, and physical health. Early detection and intervention are crucial for symptom reduction and facilitating learning and development. Recent advancements in machine learning and deep learning have facilitated the diagnosis of Autism by analyzing brain signals. This current study introduces an approach for Autism detection utilizing functional Magnetic Resonance Imaging (fMRI) data. The Autism Brain Imaging Data Exchange (ABIDE) dataset serves as the foundation, employing hierarchical graph pooling to abstract brain images into a graph structure. Graph Convolutional Networks are then used to learn node embeddings derived from sparse feature vectors. The model attains an accuracy of 87% on the 10-fold cross-validation dataset. This study proves to be cost-effective and efficient in identifying Autism through fMRI, making it suitable for near real-time applications.

This research introduces a novel technique for determining numerous fusion score levels that works with many datasets and purposes. Each of the four system pieces works together. These are Feature Engineering, Ensemble Learning, deep neural networks (DNNs), and Transfer Learning. In feature engineering, raw data is totally transformed. This stage stresses the importance of PCA and MI for predictive power. AdaBoost is added during ensemble learning. It repeatedly teaches weak learners and adjusts weights depending on errors to create a strong ensemble model. Weighted input processing, ReLU activation, and dropout layers smoothly integrate DNNs. These reveal minor data patterns and correlations. In transfer learning (fine-tuning), a trained model is modified for the feature-engineered dataset. In comparative testing, the recommended technique had greater accuracy, precision, recall, F1 score, AUC-ROC, and training duration. Efficiency measures reduce reasoning time, memory, parameter count, model size, and energy utilization. Visualizations demonstrate resource consumption, method scores, and reasoning time distribution in research. This mathematical framework improves multilayer fusion score level computations, performs well, and is versatile in many scenarios, making it a good choice for large and diverse datasets.

Smart sustainable cities rely on the latest technologies and apply recent knowledge like Information and Communication Technologies (ICT), BIM, and lean construction to expand people's eminence of life, smooth urban maneuvers and facilities more competent, and develop their competitiveness while confirming that they achieve the economic, social, environmental, and cultural demands of current and forthcoming generations. This paper explores the synergies between Building Information Modelling (BIM) visualisation and Lean construction practices to enhance Architecture, Engineering, and Construction (AEC) industry performance. A structured questionnaire was distributed among BIM and lean experts and analysed by SPSS. The study uses descriptive and correlation analyses to assess ten key lean practices, revealing high industry adoption and favorable mean scores. Notably, BIM-enhanced clash detection and coordination lead with a score of 4.4 out of 5. Correlation analysis establishes significant positive associations between BIM visualisation and practices such as just-in-time production, value stream mapping, lean pull systems, work sequencing, standardised work, and continuous improvement. The findings accentuate the pivotal role of BIM in optimising lean practices, offering valuable insights for practitioners seeking to elevate AEC industry performance through strategic integration. Future studies endeavors are recommended to investigate several alternative avenues to enhance the integration between BIM and Lean practices in the AEC industry. Furthermore, the forthcoming researchers are advised to validate the proposed framework.

Integrating the Internet of Things (IoT) with smart fueling systems has the potential to revolutionize the fuel industry, leading to better resource management and increased operational efficiency. With the increasing integration of machine learning techniques, these systems are capable of self-learning, adaptation, and predictive decision making. However, the effectiveness of these advanced systems in real-life situations remains an area of intense interest and research. in operational efficiency and reduces resource waste by 10% compared to conventional systems. Additionally, system bottlenecks were identified mainly in data trans- mission  (delayed by up to 20% in high  traffic cases) and hardware malfunctions due  to environmental factors. End user feedback  indicates a satisfaction level of 85%, with an emphasis on system responsiveness and fuel prediction recommendations. Challenges mainly come from software issues, unwanted environmental interference and  ’some initial resistance from users accustomed to conventional systems. However, with data in hand, the benefits of integrating intelligence into IoT-based fueling systems offer a sustainable and efficient future for the fuel industry. Recommendations are made to improve data transmission channels, develop  robust hardware for extreme conditions, and conduct targeted user education campaigns.

Dementia is a brain disorder, if not prevented; takes the form of various types of diseases that have no cure yet. Accurate classification of multiple types of dementia diseases is required to provide proper medication to the patient so that growth of that disease can be delayed. This study analyzes EEG signal for the classification of multiple dementia diseases such as Alzheimer’s disease (AD), Fronto-temporal dementia (FTD) and control normal (CN) subjects using machine learning (ML) algorithms. Each of the 19 channels of EEG dataset is analyzed separately in this work to perform the classification. Combination of parameters like Hjorth Activity, Mobility and Complexity along with kurtosis value of the data has been extracted in time-frequency domain for each EEG frequency band (Delta, Theta, Alpha, Beta and Gamma) is applied to the machine learning algorithms. This research is focused on classification of multiple dementia classes (ADvsFTD) as well as three-way (ADvsFTDvsCN) classification. This research is validated using public EEG dataset with 23 participants of each category. Best classification result is achieved using random forest classifier and leave-one-subject-out (LOSO) cross validation method. The three-way classification i.e., ADvsCNvsFTD achieved best accuracy of 75.29%, whereas binary classifications i.e. ADvsCN, ADvsFTD and CNvsFTD achieved best accuracy of 88.90%, 88.44% and 84.10% respectively. The proposed framework shows better results than existing work on dementia classification using machine learning. The results obtained from proposed framework showed that combination of EEG frequency band features can be utilized for the classification of multiple dementia diseases with greater accuracy.

This study presents a hybrid recognition system for multi-class compound Marathi characters, which addresses the problem of handwritten Marathi character recognition. The methodology efficiently bridges the gap between feature extraction and classification by integrating a Convolutional Neural Network (CNN) and Support Vector Machine (SVM). The first step is gathering and preprocessing a wide range of handwritten Marathi compound characters that are written in different styles. Using conventional supervised learning methods, the CNN is trained on this dataset, paying special attention to data augmentation and validation in order to reduce overfitting. High-level features taken from the final fully connected layer of the CNN are fed into an SVM classifier in the next step. By using these features in its training, the SVM improves prediction accuracy. For multi-class classification, the one-vs-all method is used. The hybrid CNN-SVM algorithm demonstrates its effectiveness in the crucial phases of feature extraction and classification by identifying handwritten compound Marathi characters with remarkable accuracy. Evaluation metrics, such as accuracy, precision, recall, F1-score, and confusion matrix analysis, are employed in the process of evaluating the effectiveness of the model. This assessment is carried out on a different testing dataset, offering a thorough examination of the model's functionality. The proposed algorithm demonstrates its superior performance and potential for improved character recognition by achieving training accuracy of 98.60% and validation accuracy of 97.69%. The development of handwriting recognition systems has benefited greatly from this research, especially when it comes to intricate scripts like Marathi. The suggested hybrid algorithm shows encouraging outcomes and has a great deal of potential for use in document processing, natural language comprehension, and character recognition in languages that use the Marathi script. Subsequent efforts will centre on refining the model and investigating ensemble methods to increase the robustness and accuracy of recognition.

This research offers four work and computer tool setups. The dynamic Resource Allocation Algorithm is crucial to the system.  This lets you manage changing supply. Once the PWMA knows how much work is coming up, it may divide resources and plan. The Load Balancing Algorithm (LBA) distributes work evenly to avoid over- or under-utilization and it also provides access content faster via the Adaptive Caching Algorithm (ACA). The proposed system surpasses the top alternative in several domains, such as data transmission, reaction time, energy conservation, load distribution effectiveness, and recovery time from failures. This is because the suggested solution incorporates many disparate approaches. Graphs and charts are visual representations that effectively illustrate the similarities and differences between the two methodologies. The hybrid technique is especially beneficial when the workload is unpredictable and prone to fluctuations. To do this, it instructs you on the fundamentals of efficient and adaptable computer resource management.