Decoding Speech from Labial Movements

This paper focuses on the problem of environmental noises in human-human communication and in automatic speech recognition. To deal with this problem, the use of alternative acoustic sensors -which are attached to the talker and receive the uttered speech through skin or bones- is investigated. In the current study, throat microphones and ear bone microphones are integrated with standard microphones using several fusion methods. The results obtained show that the recognition rates in noisy environments are drastically increased when these sensors are integrated with standard microphones. Moreover, the system does not show any recognition degradations in clean environments. In fact, recognition rates also increase slightly in clean environments. Using late fusion to integrate a throat microphone, an ear bone microphone, and a standard microphone, we achieved a 44% relative improvement in recognition rate in a noisy environment and a 24% relative improvement in recognition rate in a clean environment.

Recognising the Bangla alphabet remains a significant challenge within the fields of computational linguistics and artificial intelligence, primarily due to the script’s inherent structural complexity and wide variability in writing styles. The Bangla script is characterised by intricate ligatures, overlapping diacritics, and visually similar graphemes, all of which complicate automated recognition tasks. Despite ongoing advancements in deep learning (DL), machine learning (ML), and image processing (IP), accurately identifying Bangla characters continues to be a demanding and unresolved issue. A key limitation lies in the absence of robust detection frameworks capable of accommodating the script’s complex visual patterns and nuances. To address this gap, we propose an enhanced object detection model based on the YOLOv11 architecture, incorporating a ResNet50 backbone for improved feature extraction. The YOLOv11 framework is particularly effective in capturing discriminative features from input images, enabling real-time detection with high precision. This is especially beneficial in overcoming challenges such as character overlap and stylistic diversity, which often hinder conventional recognition techniques. Our approach was evaluated on a custom dataset comprising 50 primary Bangla characters (including vowels and consonants) along with 10 numerical digits. The proposed model achieved a recognition confidence of 99.9%, markedly outperforming existing methods in terms of accuracy and robustness. This work underscores the potential of single-shot detection models for the recognition of complex scripts such as Bangla. Beyond its technical contributions, the model has practical implications in areas including the digitisation of historical documents, the development of educational tools, and the advancement of inclusive multilingual technologies. By effectively addressing the unique challenges posed by the Bangla script, this research contributes meaningfully to both computational linguistics and the preservation of linguistic heritage.

The rapid advancements in deep learning (DL) and artificial intelligence (AI) have led to transformative applications across various domains. Edge devices, including mobile and embedded systems, are crucial for the widespread adoption of machine intelligence. However, training and deploying deep neural networks (DNNs) require substantial computational resources, resulting in high energy consumption. This energy often stems from non-renewable sources, leading to significant carbon dioxide emissions and environmental damage. With the emergence of large-scale models for AI-generated content (AIGC), such as large language models and diffusion models, the energy consumption issue has intensified, creating an urgent demand for sustainable AI solutions. These challenges motivate my research on energy-efficient deep learning toward sustainable AI. To build sustainable AI systems, this thesis works on promoting AI sustainability and using AI for sustainability purposes. To promote AI sustainability, a hardware-software co-design approach is adopted, integrating both bottom-up and top-down strategies for practical, energy-efficient deep learning deployments.The first part of the thesis introduces the bottom-up approach, emphasizing AI algorithm-aware efficient system design. Specifically, edge devices utilize dynamic power management strategies, such as dynamic voltage and frequency scaling (DVFS), to manage energy consumption by adjusting voltage-frequency (VF) levels. System-level configurations, including CPU cores, CPU VF levels, and GPU VF levels, significantly impact both latency and power consumption during DNN inference. Developing effective strategies for these configurations enables system-level optimizations, providing a path to deal with the efficiency challenge. The second part of the thesis presents the top-down approach, which focuses on designing hardware-driven efficient AI algorithms. Given the hardware constraints in AI application environments, this approach explores efficient compression techniques, such as weight pruning and knowledge distillation, to create lightweight models with reduced computational demands, thereby enhancing efficiency. The third part of the thesis examines the efficiency challenges posed by the evolution of large-scale models, which have greatly enhanced the capabilities of AIGC for text and image generation. While these models offer substantial generative potential, they also exacerbate the efficiency dilemma. This section explores strategies to optimize the efficiency of these large-scale models based on their unique characteristics. Beyond efficiency, the deployment of AI in real-world applications, such as autonomous vehicles, underscores the importance of prioritizing safety. The fourth part of the thesis addresses issues of AI fairness, trustworthiness, and security to ensure sustainable AI. This section investigates the potential to reverse-engineer adversarial attacks to infer the adversary's underlying information. In conclusion, this thesis works on building energy-efficient DL for sustainable AI. The objective of the work is not only to enhance the efficiency of AI systems but also to address broader concerns of fairness, trust, and security, paving the way for responsible and sustainable AI deployment in real-world scenarios.--Author's abstract

The research relevance is determined by the importance of a thorough study of methods, schemes and models used by artificial intelligence to mechanise creativity in modern conditions of active technological development. The study aims to analyse the main processes taking place in modern art in connection with active technologization of work processes, to identify the leading concepts regarding the possibility of creating machine art in the future, etc. The employed methods are theoretical, such as analysis, systematisation, generalisation, etc., for studying key problems and further development of creativity based on artificial intelligence. The study examines in detail the main developments of Artificial General Intelligence and Artificial Narrow Intelligence, in particular the achievements of Generative adversarial networks and Creative adversarial networks. Artificial intelligence-generated art demonstrates the remarkable capabilities of technologies. The evolving artificial intelligence in the arts introduces “digital art”. Generative Adversarial Networks are used as a foundational tool for artists who use digital methods and texture generation to create unique compositions. Furthermore, sculptors collaborate with artificial intelligence tools to convert drawings into 3D models or transform historical art databases into sculptures. Creative thinking, a hallmark of human intelligence, is determined as artificial intelligence’s ability to generate new and original ideas. The development of emotional intelligence in artificial intelligence enables empathetic responses and the identification of human emotions through voice and facial expressions. The issues of authorised internationality, awareness of the creative process, psychological foundations of artificial empathy and emotional intelligence define the prospects for the development of neuroscience. Challenges persist in defining creativity, authorship, and legal aspects of artificial intelligence-generated art. The study materials may be useful for artists, art educators, technologists, and researchers interested in the intersection of technology and art, legal professionals (especially intellectual property law), and individuals involved in artificial intelligence development may find these findings valuable

The integration of Artificial Intelligence (AI) into financial forecasting has transformed traditional stock market prediction methods. This research paper explores the effectiveness of AI techniques in forecasting stock trends within the Indian stock market over the last few years. We examine AI methodologies, including machine learning (ML), deep learning (DL), and hybrid models applied to the Bombay Stock Exchange (BSE) and the National Stock Exchange (NSE). By comparing historical data with AI-predicted trends, this study evaluates prediction accuracy and market relevance (Patel et al., 2015). Furthermore, the research outlines existing study gaps and proposes a future scope of integrating AI with behavioral finance and real-time analytics (Chen et al., 2022). The prediction of stock market trends remains a significant challenge due to the stochastic and non-linear nature of financial time series data (Zhang & Zhou, 2020). With the proliferation of Artificial Intelligence (AI), particularly Machine Learning (ML) and Deep Learning (DL) techniques, there has been a paradigm shift in the modeling and forecasting of stock price movements (Fischer & Krauss, 2018). This paper presents a comprehensive study on the effectiveness of AI in predicting stock market trends within the Indian financial ecosystem, focusing on a comparative analysis of AI models implemented over the last five years (2018–2023) on major indices and stocks listed on the NSE and BSE. This research evaluates the performance of multiple AI algorithms—including Support Vector Machines (SVM), Random Forests (RF), Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRU), and hybrid ensemble models—in forecasting short- and medium-term price trends using historical stock data (Krauss et al., 2017; Chen & He, 2021). Standard evaluation metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and classification accuracy are employed to assess model efficacy. The results indicate that while traditional machine learning algorithms offer moderate predictive power, advanced deep learning and hybrid models significantly outperform them, particularly during periods of high market volatility, such as the COVID-19 pandemic and post-lockdown recovery phases (Weng et al., 2018; Jain & Jain, 2021). The study identifies key research gaps, including limited sectoral diversification in datasets, inadequate integration of sentiment and behavioral data, overfitting issues in complex models, and the lack of real-time prediction systems in the Indian context (Gupta & Pathak, 2022). Furthermore, current models often ignore nonquantitative factors such as investor sentiment, macroeconomic indicators, and global events, which can critically impact prediction accuracy (Nassirtoussi et al., 2014). These limitations suggest the need for a more holistic and interdisciplinary approach to AI-driven financial forecasting. The scope for future research includes the development of real-time, adaptive AI systems using high-frequency trading data, the incorporation of behavioral finance through social media and news analytics, and the exploration of quantum computing-based AI models (Liu et al., 2023). From a practical standpoint, the findings of this study offer valuable insights for institutional investors, financial analysts, regulatory bodies, and developers of AIpowered trading platforms. The study concludes that while AI is not a definitive solution for market prediction, it provides a powerful augmentative tool that, when designed with robustness, transparency, and adaptability, can significantly enhance decision-making in India’s fastevolving financial markets.

Captcha’s are random significant challenges, used to differentiate between humans and bots in order to prevent unauthorized access to web services. Over a decade lots of research have been carried out for generating numerous types of Captcha’s; specially using image and face detection and recognition techniques. Rather than machine, humans are outstandingly good at several things, including pattern recognition, linguistic abilities, and innovative thinking. Although, computers are rapidly improving the same, but most programs still don’t recognize as well as a child. Humans are inherently capable of detecting faces in a variety of contexts; even parts of face portions are not visible yet. Modern advancement in Artificial Intelligence, Deep Learning and advanced Image Processing techniques have made the Captcha based security system unsecure and vulnerable. However, as the time progresses Captcha’s are equipped with high usability, robustness and producing new unique challenges. This paper proposes a novel face point based Captcha, which employs various face points detection as its test, where user will ask to click on correct face points of all human faces presented in the Captcha challenge; which comprises of real and fake face images, with balanced noise and distortions, embedded in a composite background. Over 100 unique and random FP-Captcha’s are generated and solved by 115 UG-students, with accuracy of 97.39% for correct responses. Consequently, the probability of passing a FP-Captcha test by random guessing attack was 0.00000245%. Therefore, we conclude that, FP-Captcha is secure and robust against malicious attacks and offer better human accuracy.

Chapter 10 - Artificial intelligence and the interplay between tumor and immunity

Artificial Intelligence (AI) is emerging as a key driver at the intersection of nutrition and food systems, offering scalable solutions for precision health, smart manufacturing, and sustainable development. This study aims to present a comprehensive review of AI-driven innovations that enable precision nutrition through real-time dietary recommendations, meal planning informed by individual biological markers (e.g., blood glucose or cholesterol levels), and adaptive feedback systems. It further examines the integration of AI technologies in food production, such as machine learning–based quality control, predictive maintenance, and waste minimization, to support circular economy goals and enhance food system resilience. Drawing on advances in deep learning, federated learning, and computer vision, the review outlines how AI transforms static, population-level dietary models into dynamic, data-informed frameworks tailored to individual needs. The paper also addresses critical challenges related to algorithmic transparency, data privacy, and equitable access, and proposes actionable pathways for ethical and scalable implementation. By bridging healthcare, nutrition, and industrial domains, this study offers a forward-looking roadmap for leveraging AI to build intelligent, inclusive, and sustainable food–health ecosystems.

The cross-fusion research of artificial intelligence technology and spinal surgery represented by machine learning and neural network model is a new research direction and hot issue in the field of artificial intelligence in recent years. The anatomy and disease symptoms of the spine are complex, and the diagnosis and treatment of spinal surgery require rich clinical experience. However, the distribution of medical resources in China is seriously uneven. How to improve the ability of primary medical services so that the most extensive patient groups can benefitis still an urgent problem to be solved. Artificial intelligence is a technical science that researches and develops theories, methods, technologies, and application systems for simulating, extending and expanding human intelligence. With the advent of the era of big data medical technology, artificial intelligence technology may solve this problem by transforming experts sinking into tech sinking . At present, technologies such as confrontation learning, weakly supervised learning, intensive learning and graph neural networks have become research hotspots in the field of artificial intelligence, and have also played an important role in many fields of clinical medicine. Based on the advantages of deep learning and neural network in disease learning, many spine surgeons combine it with the diagnosis and treatment of cervical spondylosis, low back pain, lumbar degenerative diseases, spinal deformity, spinal tumors, and other spine-related diseases. The rapid location and accurate diagnosis of the disease not only makes it an effective tool for the comprehensive diagnosis of spinal diseases but also provides the basis for the most reasonable treatment options for spinal diseases. In the domestic application of artificial intelligence in the diagnosis and treatment of spinal surgery, it can also solve the problems of difficult diagnosis and complicated treatment of spinal diseases faced by primary doctors, reduce the rate of misdiagnosis and missed diagnosis, and effectively reduce the economic and social burden of spinal diseases. This paper reviews the research progress of artificial intelligence represented by deep learning in the field of diagnosis and treatment of spinal surgery at home and abroad, and the advantages and application prospects of artificial intelligence in the diagnosis and treatment of spinal surgery.

A conversational agent (chatbot) is computer software capable of communicating with humans using natural language processing. The crucial part of building any chatbot is the development of conversation. Despite many developments in Natural Language Processing (NLP) and Artificial Intelligence (AI), creating a good chatbot model remains a significant challenge in this field even today. A conversational bot can be used for countless errands. In general, they need to understand the user's intent and deliver appropriate replies. This is a software program of a conversational interface that allows a user to converse in the same manner one would address a human. Hence, these are used in almost every customer communication platform, like social networks. At present, there are two basic models used in developing a chatbot. Generative based models and Retrieval based models. The recent advancements in deep learning and artificial intelligence, such as the end-to-end trainable neural networks have rapidly replaced earlier methods based on hand-written instructions and patterns or statistical methods. This paper proposes a new method of creating a chatbot using a deep neural learning method. In this method, a neural network with multiple layers is built to learn and process the data.

The rapid advancement of artificial intelligence (AI) and deep learning (DL) has catalyzed the emergence of several optimization-driven subfields, notably neuromorphic computing and quantum machine learning. Leveraging the differentiable nature of hybrid models, researchers have explored their potential to address complex problems through unified optimization strategies. One such development is the Spiking Quantum Neural Network (SQNN), which combines principles from spiking neural networks (SNNs) and quantum computing. However, existing SQNN implementations often depend on pretrained SNNs due to the non-differentiable nature of spiking activity and the limited scalability of current SNN encoders. In this work, we propose a novel architecture—Spiking-Quantum Data Re-upload Convolutional Neural Network (SQDR-CNN)—that enables joint training of convolutional SNNs and quantum circuits within a single backpropagation framework. Unlike its predecessor, SQDR-CNN allow convergence to reasonable performance without the reliance of pretrained spiking encoder and subsetting datasets. We also clarified some theoretical foundations, testing new design using quantum data-reupload with different training algorithm-initialization and evaluate the performance of the proposed model under noisy simulated quantum environments. As a result, we were able to achieve 86% of the mean top-performing accuracy of the state of the art (SOTA) SNN baselines, yet uses only 0.5% of the smallest spiking model’s parameters. Through this integration of neuromorphic and quantum paradigms, we aim to open new research directions and foster technological progress in multi-modal, learnable systems.

White light cystoscopy is the current standard for primary diagnosis and surveillance of bladder cancer. However, cancer changes can be subtle and may be easily missed. With the advancement of deep learning (DL), image recognition by artificial intelligence (AI) proves a high accuracy for image-based diagnosis. AI can be a solution to enhance bladder cancer diagnosis on cystoscopy. An algorithm that classifies cystoscopic images into normal and tumour images is essential for AI cystoscopy. To develop this AI-based system requires a training dataset, an appropriate type of DL algorithm for the learning process and a specific outcome classification. A large data volume with minimal class imbalance, data accuracy and representativeness are pre-requisite for a good dataset. Algorithms developed during the past two years to detect bladder tumour achieved high performance with a pooled sensitivity of 89.7% and specificity of 96.1%. The area under the curve ranged from 0.960 to 0.980, and the accuracy ranged from 85.6 to 96.9%. There were also favourable results in the various attempts to enhance detection of flat lesions or carcinoma-in-situ. AI cystoscopy is a possible solution in clinical practice to enhance bladder cancer diagnosis, improve tumour clearance during transurethral resection of bladder tumour and detect recurrent tumours upon surveillance.

In recent years, Artificial Intelligence (AI) has experienced remarkable growth, influencing a wide range of industries, particularly the educational sector, this became more noticeable with the appearance of the pandemic, forcing distance learning. Therefore, the incorporation of AI-driven educational platforms has enabled continuous assistance to both students and educators, largely fueled by advancements in Deep Learning. In addition, within engineering education, AI-based learning platforms have emerged as pivotal tools for customizing educational experiences, boosting academic outcomes, and enhancing administrative processes. Research indicates that these platforms can elevate student engagement by up to 23% and significantly improve knowledge retention. Nonetheless, their widespread adoption also introduces challenges, such as fostering technological dependency and diminishing critical thinking skills, particularly in self-directed learning environments. As these systems become increasingly embedded in academic settings, it is essential to assess their real impact on both learners and faculty members. Moreover, the flexibility of Natural Language Processing (NLP) technologies, while powerful, may lead to misuse in academic contexts due to limited oversight and insufficient technical literacy, potentially compromising the quality of education. Although numerous publications have explored AI's role in education, few have provided a thorough analytical approach regarding its consequences. This research aims to fill that gap by evaluating how AI-powered platforms can be better leveraged to support balanced, responsible, and effective learning practices in engineering higher education.

Credit card fraud has become a major challenge in the digital payment ecosystem, leading to significant financial losses for banks and customers. Traditional rulebased fraud detection systems are limited in identifying complex and evolving fraud patterns. This research proposes a machine learning-based fraud detection system that analyzes transaction behavior, spending patterns, and user activity to detect fraudulent transactions in real time. Various supervised learning models including Logistic Regression, Random Forest, and Gradient Boosting are evaluated for fraud classification. The system addresses class imbalance using SMOTE and improves detection accuracy while reducing false positives. Results demonstrate that machine learning techniques significantly enhance financial security and enable proactive fraud prevention. Artificial Intelligence (AI) and Machine Learning (ML) have rapidly transformed numerous industries by enabling systems to learn from data and make intelligent decisions with minimal human intervention. This research paper explores the development and evaluation of a novel machine learning framework designed to improve predictive accuracy and computational efficiency in large-scale data environments. The proposed model integrates deep learning architectures with adaptive optimization techniques to enhance performance across diverse datasets. Experimental results demonstrate significant improvements in accuracy, training speed, and generalization compared to traditional machine learning approaches. Furthermore, the study analyzes ethical considerations, model interpretability, and scalability challenges associated with modern AI systems. The findings contribute to advancing robust, efficient, and responsible AI applications in fields such as healthcare, finance, and autonomous systems. Recent advancements in deep learning have significan

The aging global population is experiencing a rising prevalence of age-related hearing loss. Conventional hearing aids often fail in noisy environments, leading to user dissatisfaction. Recent advancements in deep learning, particularly in automatic speech recognition (ASR) and smart filter, highlight the potential for a new generation of hearing aids. This paper explores the transformative potential of evolving deep learning architectures to address the critical limitation of noise suppression. We review the progression of models specifically for auditory processing: from Deep Neural Networks (DNNs) for basic noise reduction, to Convolutional Neural Networks (CNNs) which analyse spectral features in audio spectrograms. Recurrent Neural Networks (RNNs) and sequence-to-sequence (seq2seq) models and transformer models which is a improved version of the Seq2Seq that further improved the handling of temporal speech patterns. We conclude that integrating these sophisticated models into next-generation hearing aids is essential for dramatically improving speech intelligibility in complex settings. This technological evolution promises to enhance the quality of life for the aging population by reducing hearing effort and promoting social engagement.