In this work, a cradle wave ring-shape multiband novel design terahertz antenna employed and excited with a microstrip feed is proposed. The regular deca-shape ring evolutions develop the final proposed novel antenna design. The proposed deca-shape ring antenna demonstrates good performance at 1 THz-5 THz with a good reflection loss, which is less than - 10 dB. The complete geometrical dimensions of the antenna design are 120 x 200 x 10 mu m(3). The MIMO parameters are interpreted, and good performance is achieved. The resonating bands of the antenna are 1.66 THz, 2.37 THz, 2.90 THz, 3.07 THz, and 3.56 THz with reflection coefficients of - 31.7 dB, - 19.3 dB, - 16.4 dB, - 18.6 dB, and - 28.5 dB. The antenna featuring dual ports with a novel geometry demonstrates good MIMO performance. The cradle wave ring shape, unique design, and uniform spacing, as well as the radiation characteristics, make the antenna a good candidate for emerging 5G applications. The proposed antenna is composed of two ports and exhibits satisfactory MIMO performance. With its special cradle wave ring design geometry, it can provide very efficient performance such as radiation properties at Port 1 and Port 2. The gain achieved across the operating frequencies is greater than 7 dBi. The proposed novel design is intended for and suitable for 5G, wearable electronics, military communication, and ultrafast short-range wireless high-speed high-resolution radar applications.
Speech emotion recognition (SER) has become an important area of research due to its wide applications in human-computer interaction, affective computing, and mental health. However, most existing studies focus heavily on adults, with limited attention given to children. This review highlights the urgent need to advance research on children’s SER, as detecting emotions in children poses unique challenges, such as limited labeled datasets, evolving vocal patterns, and the dynamic nature of childhood emotions. We examine both traditional feature-based approaches and recent developments in raw waveform modeling for SER. While handcrafted features have long dominated the field, very few studies have explored raw speech models despite their potential to capture nuanced emotional cues. Moreover, this review synthesizes SER research from 2014 to 2025, encompassing both adults and children to contextualize the current landscape. Notably, it devotes focused attention to children’s SER, outlining its distinctive challenges and key gaps that hinder progress. This child-centered perspective complements the broader discussion on adult SER, fostering an inclusive and age-diverse understanding of emotional speech modeling.
Railway transportation demands constant safety and efficiency, which hinge on real-time identification of crucial infrastructure components such as track gauges (ties and width) and rolling stock (locomotives, freight, and passenger cars). Manual monitoring methods often fall short in ensuring timely detection of issues like track width deviation or rolling stock damage, which can lead to service interruptions or worse—accidents. To address this, we propose an intelligent AI-based system leveraging a Pyramid Attention Network (PAN) decoder, fused with advanced encoders like EfficientNet B4, NFNet integrated with Efficient Channel Attention (ECA), and SE-ResNet. These models extract intricate features from visual data to facilitate accurate detection and classification. The approach is reinforced by ensemble modeling, where multiple models team up to counterbalance individual flaws, thus amplifying prediction accuracy and system robustness. This model ensemble excels in flagging anomalies in track infrastructure and rolling stock with high precision. The proposed system outperforms traditional single-model setups, offering a scalable and real-time monitoring solution. By integrating this AI-powered framework into railway systems, we reduce emergency risks, minimize downtime, and step boldly into a future of smarter, safer train operations.
Random Forest plays an important role in different fields like Healthcare, Image, and Speech Recognition, among these Dermatological Disease detection is expensive due to Advanced Laser Technology. It’s critical to have affordable illness detection. Machine learning algorithms are used to accomplish it. An algorithm for machine learning used for classification is called Random Forest. The algorithm is a type of ensemble learning technique that combines different decision trees to create a more accurate as well as reliable model. The proposed approach can provide high accuracy and classify into either psoriasis or eczema diseases.
In this book chapter the intersection of artificial intelligence (AI) and circular economy is invented, which focuses on durable business models. As the global economy turns to a circular to reduce environmental influence, AI emerges as a major technique that facilitates this transition. The chapter is investigated how AI enables resource efficiency, waste reduction and closed-loop systems in industries. The main subjects include AI-powered forecast maintenance, smart resource allocation and advanced recycling processes. Case Studies Circular Explains the successful integration of AI in professional models, highlighting benefits such as cost savings, enhanced production life cycle management and improved environmental metrics. The chapter ends with the insights of the future AI application, challenges and circular businesses.
