New forms of interaction made possible by developments in special educational technologies can now help students with dyscalculia. Artificial intelligence (AI) has emerged as a promising tool in recent decades, particularly between 2001 and 2010, offering avenues to enhance the quality of education for individuals with dyscalculia. Therefore, the implementation of AI becomes crucial in addressing the needs of students with dyscalculia. Content analysis techniques were used to examine the literature covering the influence of AI on dyscalculia and its potential to assist instructors in promoting education for individuals with dyscalculia. The study sought to create a foundation for a more inclusive dyscalculia education in the future through in-depth studies. AI integration has had a big impact on educational institutions as well as people who struggle with dyscalculia. This paper highlights the importance of AI in improving the educational outcomes of students affected by dyscalculia.

Wireless Sensor Networks (WSNs) play a crucial role in developing the Internet of Things (IoT) by collecting data from hostile environments like military and civil domains with limited resources. IoT devices need edge devices to perform real-time processing without compromising the security with the help of key management and authentication schemes. The above applications are prone to eavesdropper due to cryptographic algorithms' weaknesses for providing security in WSNs. The security protocols for WSNs are different from the traditional networks because of the limited resource of sensor nodes. Existing key management schemes require large key sizes to provide high-security levels, increasing the computational and communication cost for key establishment. This paper proposes a Hybrid Key Management Scheme for WSNs linking edge devices which use Elliptic Curve Cryptography (ECC) and a hash function to generate key pre-distribution keys. The Key establishment is carried out by merely broadcasting the node identity. The main reason for incorporating a hybrid approach in the key pre-distribution method is to achieve mutual authentication between the sensor nodes during the establishment phase. The proposed method reduces computational complexity with greater security and the proposed scheme can be competently applied into resource constraint sensor nodes.

Robust litter detection from photographs is important in realizing cleaner landscapes and efficient waste disposal. Current approaches typically cannot spot small or partly occluded trash in dense backgrounds such as cities and jungles. This research introduces a hybrid detection framework combining Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) via a Cross-Scale Adaptive Attention Fusion (CSAAF) process. While local space information in CNNs is extracted, global contextual knowledge in ViTs is also gained, and adaptive fusion between them increases accuracy and stability. Model assessments with mean Average Precision (mAP), Precision, Recall, and F1-score metrics result in enhanced detection of fine and hidden litter classes. In addition, the architecture keeps a light computational burden, guaranteeing real-time execution in diverse landscapes. This proposed solution demonstrates an efficient and scalable autonomous litter detection solution that enables intelligent environmental observation and waste disposal systems.

Speech synthesis, the technology that converts text into spoken words, has advanced significantly for high-resource languages like English, Spanish, and Mandarin. However, many languages spoken by millions of people are still underserved by speech synthesis systems due to insufficient data to train accurate models. An analysis of current solutions and difficulties in low-resource language speech synthesis development is presented in this paper because these languages have restricted data and linguistic resources. The paper examines different research strategies for advancing speech synthesis techniques in these languages by borrowing data from rich-resource languages to enhance models used in poor-resource systems. The primary method involves the comparison of linguistic models that operate between highly supported languages to adapt them to languages that only have limited information available. Acoustic models requiring advancement represent a crucial need to process correctly the phonetic and prosodic attributes within these languages because their traits lack proper representation in small data collections. The paper investigates different data augmentation methods, which include synthetic data generation and multilingual corpus use to enhance available training resources. These methods enhance the quality of computer-generated speech by making it sound more natural while ensuring that the words remain clear and understandable, even in low-resource languages. Notably, data augmentation techniques expanded dataset sizes by up to 27 times, improving model robustness. Additionally, models like WaveNet achieved a Mean Opinion Score (MOS) of 4.21, while Tacotron-based systems reached MOS scores as high as 4.38, demonstrating high naturalness even with limited training data. Experiments using less than three hours of training data in low-resource settings initially showedWord Error Rates (WER) exceeding 50–80%, but data augmentation and transfer learning significantly reduced these error rates. By reviewing the present state of research, this paper offers an overview of the progress made in low-resource language speech synthesis. It identifies the potential future directions for this field. Ultimately, the goal is to make speech synthesis more accessible for underrepresented languages, helping with language preservation, assistive technologies, and broader accessibility.