Field Of AI Research Articles

Generative models for protein sequence modeling: recent advances and future directions.

The widespread adoption of high-throughput omics technologies has exponentially increased the amount of protein sequence data involved in many salient disease pathways and their respective therapeutics and diagnostics. Despite the availability of large-scale sequence data, the lack of experimental fitness annotations underpins the need for self-supervised and unsupervised machine learning (ML) methods. These techniques leverage the meaningful features encoded in abundant unlabeled sequences to accomplish complex protein engineering tasks. Proficiency in the rapidly evolving fields of protein engineering and generative AI is required to realize the full potential of ML models as a tool for protein fitness landscape navigation. Here, we support this work by (i) providing an overview of the architecture and mathematical details of the most successful ML models applicable to sequence data (e.g. variational autoencoders, autoregressive models, generative adversarial neural networks, and diffusion models), (ii) guiding how to effectively implement these models on protein sequence data to predict fitness or generate high-fitness sequences and (iii) highlighting several successful studies that implement these techniques in protein engineering (from paratope regions and subcellular localization prediction to high-fitness sequences and protein design rules generation). By providing a comprehensive survey of model details, novel architecture developments, comparisons of model applications, and current challenges, this study intends to provide structured guidance and robust framework for delivering a prospective outlook in the ML-driven protein engineering field.

Improving diagnosis and prognosis of lung cancer using vision transformers: a scoping review

BackgroundVision transformer-based methods are advancing the field of medical artificial intelligence and cancer imaging, including lung cancer applications. Recently, many researchers have developed vision transformer-based AI methods for lung cancer diagnosis and prognosis.ObjectiveThis scoping review aims to identify the recent developments on vision transformer-based AI methods for lung cancer imaging applications. It provides key insights into how vision transformers complemented the performance of AI and deep learning methods for lung cancer. Furthermore, the review also identifies the datasets that contributed to advancing the field.MethodsIn this review, we searched Pubmed, Scopus, IEEEXplore, and Google Scholar online databases. The search terms included intervention terms (vision transformers) and the task (i.e., lung cancer, adenocarcinoma, etc.). Two reviewers independently screened the title and abstract to select relevant studies and performed the data extraction. A third reviewer was consulted to validate the inclusion and exclusion. Finally, the narrative approach was used to synthesize the data.ResultsOf the 314 retrieved studies, this review included 34 studies published from 2020 to 2022. The most commonly addressed task in these studies was the classification of lung cancer types, such as lung squamous cell carcinoma versus lung adenocarcinoma, and identifying benign versus malignant pulmonary nodules. Other applications included survival prediction of lung cancer patients and segmentation of lungs. The studies lacked clear strategies for clinical transformation. SWIN transformer was a popular choice of the researchers; however, many other architectures were also reported where vision transformer was combined with convolutional neural networks or UNet model. Researchers have used the publicly available lung cancer datasets of the lung imaging database consortium and the cancer genome atlas. One study used a cluster of 48 GPUs, while other studies used one, two, or four GPUs.ConclusionIt can be concluded that vision transformer-based models are increasingly in popularity for developing AI methods for lung cancer applications. However, their computational complexity and clinical relevance are important factors to be considered for future research work. This review provides valuable insights for researchers in the field of AI and healthcare to advance the state-of-the-art in lung cancer diagnosis and prognosis. We provide an interactive dashboard on lung-cancer.onrender.com/.

Tracing a new path in the field of AI and robotics: mimicking human intelligence through chemistry. Part I: molecular and supramolecular chemistry.

Chemical Artificial Intelligence (CAI) is a brand-new research line that exploits molecular, supramolecular, and systems chemistry in wetware (i.e., in fluid solutions) to imitate some performances of human intelligence and promote unconventional robotics based on molecular assemblies, which act in the microscopic world, otherwise tough to be accessed by humans. It is undoubtedly worth spreading the news that AI researchers can rely on the help of chemists and biotechnologists to reach the ambitious goals of building intelligent systems from scratch. This article reports the first attempt at building a Chemical Artificial Intelligence knowledge map and describes the basic intelligent functions that can be implemented through molecular and supramolecular chemistry. Chemical Artificial Intelligence provides new tools and concepts to mimic human intelligence because it shares, with biological intelligence, the same principles and materials. It enables peculiar dynamics, possibly not accessible in software and hardware domains. Moreover, the development of Chemical Artificial Intelligence will contribute to a deeper understanding of the strict link between intelligence and life, which are two of the most remarkable emergent properties shown by the Complex Systems we call biological organisms.

인공지능 기반 한문 번역을 위한 코퍼스 추출 및 정제 과정

It is fun to imagine how good it would be to be able to translate a lot of Chinese classics by using AI in an era where the field of AI is expanding day by day. This is why commercialization of machine translation called artificial intelligence can drastically reduce the manpower and time spent on classical Chinese translation. To this end, various institutions are improving their performance by developing artificial intelligence Chinese character recognition and Chinese character translation programs. AI-based Chinese character translation, research is concentrated in the field of technology, and there are no reported studies on the corpus extraction process and purification process.
 For deep learning, which trains artificial intelligence, automatic translation data, that is, corpus that connects Chinese text and translations in parallel, must be created. In order to make a corpus, a lot of corpus data is extracted through human translation, and a high-quality corpus is made through refining based on detailed guidelines. Here, we tried to confirm the purification process of how the extracted corpus data were selected.
 As a result of checking the corpus purification process, words such as various titles, items, and names, metrological units or number of people were all excluded. Short sentences containing place names, human names, government posts, places, products, dates, and proper nouns were also removed because they were not appropriate as corpus. In addition, prefixes consisting of one or two letters, such as adverbs, conjunctions, tense, and pronounciation at the beginning of the sentence, were deleted. In the future, it is expected that the time and expense of translation will be greatly reduced if extraction is carried out in consideration of these contents in the construction of corpus for AI-based Chinese character translation.

Ethical Plateaus in Danish Child Protection Services

This paper analyses how controversies shape an emerging field of AI in Danish child protection services. In a context of high controversiality, we examine how algorithmic systems evolve in conjunction with changing ethical stakes. Empirically, we report a study comprising all Danish attempts (n=4) to develop algorithmic models for child protection services. These attempts were never fully implemented and have been either cancelled, paused or changed significantly since their outset. Combining Fischer’s (2004) notion of ‘ethical plateaus’ with insights from valuation studies, we propose that public controversies shape how organisations enact their algorithms as ethically ‘good’. Our findings demonstrate how valuations of ethically contestable algorithms involve the very distribution of agency across humans and algorithms, i.e., how much power and agency should be delegated to algorithmic models. In the case of Danish child protection services, this moves towards reducing their agency.

Large Language Models: Their Success and Impact

ChatGPT, a state-of-the-art large language model (LLM), is revolutionizing the AI field by exhibiting humanlike skills in a range of tasks that include understanding and answering natural language questions, translating languages, writing code, passing professional exams, and even composing poetry, among its other abilities. ChatGPT has gained an immense popularity since its launch, amassing 100 million active monthly users in just two months, thereby establishing itself as the fastest-growing consumer application to date. This paper discusses the reasons for its success as well as the future prospects of similar large language models (LLMs), with an emphasis on their potential impact on forecasting, a specialized and domain-specific field. This is achieved by first comparing the correctness of the answers of the standard ChatGPT and a custom one, trained using published papers from a subfield of forecasting where the answers to the questions asked are known, allowing us to determine their correctness compared to those of the two ChatGPT versions. Then, we also compare the responses of the two versions on how judgmental adjustments to the statistical/ML forecasts should be applied by firms to improve their accuracy. The paper concludes by considering the future of LLMs and their impact on all aspects of our life and work, as well as on the field of forecasting specifically. Finally, the conclusion section is generated by ChatGPT, which was provided with a condensed version of this paper and asked to write a four-paragraph conclusion.

Sensitivity of CNN image analysis to multifaceted measurements of neurite growth

Quantitative analysis of neurite growth and morphology is essential for understanding the determinants of neural development and regeneration, however, it is complicated by the labor-intensive process of measuring diverse parameters of neurite outgrowth. Consequently, automated approaches have been developed to study neurite morphology in a high-throughput and comprehensive manner. These approaches include computer-automated algorithms known as 'convolutional neural networks' (CNNs)—powerful models capable of learning complex tasks without the biases of hand-crafted models. Nevertheless, their complexity often relegates them to functioning as 'black boxes.' Therefore, research in the field of explainable AI is imperative to comprehend the relationship between CNN image analysis output and predefined morphological parameters of neurite growth in order to assess the applicability of these machine learning approaches. In this study, drawing inspiration from the field of automated feature selection, we investigate the correlation between quantified metrics of neurite morphology and the image analysis results from NeuriteNet—a CNN developed to analyze neurite growth. NeuriteNet accurately distinguishes images of neurite growth based on different treatment groups within two separate experimental systems. These systems differentiate between neurons cultured on different substrate conditions and neurons subjected to drug treatment inhibiting neurite outgrowth. By examining the model's function and patterns of activation underlying its classification decisions, we discover that NeuriteNet focuses on aspects of neuron morphology that represent quantifiable metrics distinguishing these groups. Additionally, it incorporates factors that are not encompassed by neuron morphology tracing analyses. NeuriteNet presents a novel tool ideally suited for screening morphological differences in heterogeneous neuron groups while also providing impetus for targeted follow-up studies.

A novel application of XAI in squinting models: A position paper

Artificial Intelligence, and Machine Learning especially, are becoming increasingly foundational to our collective future. Recent developments around generative models such as ChatGPT, and DALL-E represent just the tip of the iceberg in new gadgets that will change the way we live our lives. Convolutional Neural Networks (CNNs) and Transformer models are at the heart of advancements in the autonomous vehicles and health care industries as well. Yet these models, as impressive as they are, still make plenty of mistakes without justifying or explaining what aspects of the input or internal state, was responsible for the error. Often, the goal of automation is to increase throughput, processing as many tasks as possible in a short a period of time. For some use cases the cost of mistakes might be acceptable as long as production is increased above some set margin. However, in health care, autonomous vehicles, and financial applications, the cost of a mistake might have catastrophic consequences. For this reason, industries where single mistakes can be costly are less enthusiastic about early AI adoption. The field of eXplainable AI (XAI) has attracted significant attention in recent years with the goal of producing algorithms that shed light into the decision-making process of neural networks. In this paper we show how robust vision pipelines can be built using XAI algorithms with the goal of producing automated watchdogs that actively monitor the decision-making process of neural networks for signs of mistakes or ambiguous data. We call these robust vision pipelines, squinting pipelines.

Benchmarking, ethical alignment, and evaluation framework for conversational AI: Advancing responsible development of ChatGPT

Conversational AI systems like ChatGPT have seen remarkable advancements in recent years, revolutionizing human–computer interactions. However, evaluating the performance and ethical implications of these systems remains a challenge. This paper delves into the creation of rigorous benchmarks, adaptable standards, and an intelligent evaluation methodology tailored specifically for ChatGPT. We meticulously analyze several prominent benchmarks, including GLUE, SuperGLUE, SQuAD, CoQA, Persona-Chat, DSTC, BIG-Bench, HELM and MMLU illuminating their strengths and limitations. This paper also scrutinizes the existing standards set by OpenAI, IEEE’s Ethically Aligned Design, the Montreal Declaration, and Partnership on AI’s Tenets, investigating their relevance to ChatGPT. Further, we propose adaptive standards that encapsulate ethical considerations, context adaptability, and community involvement. In terms of evaluation, we explore traditional methods like BLEU, ROUGE, METEOR, precision–recall, F1 score, perplexity, and user feedback, while also proposing a novel evaluation approach that harnesses the power of reinforcement learning. Our proposed evaluation framework is multidimensional, incorporating task-specific, real-world application, and multi-turn dialogue benchmarks. We perform feasibility analysis, SWOT analysis and adaptability analysis of the proposed framework. The framework highlights the significance of user feedback, integrating it as a core component of evaluation alongside subjective assessments and interactive evaluation sessions. By amalgamating these elements, this paper contributes to the development of a comprehensive evaluation framework that fosters responsible and impactful advancement in the field of conversational AI.

Reshaping Tourist Experience with AI-Enabled Technologies: A Comprehensive Review and Future Research Agenda

This study consolidates the existing literature and develops a conceptual framework for a holistic understanding of the tourist experience with AI-enabled technologies. It entails performance analysis of scientific actors, thematic analysis, and content analysis of the intellectual structure of the research. The key technologies shaping the tourist experience include service robots, personalized recommender systems, IoT, chatbots, AR/VR, big data analytics, text mining, text analytics, and NLP. The study contributes by offering performance and science mapping in the field of AI for the tourist experience. Accordingly, several future research directions and a consolidated conceptual framework are proposed.

Simple Knowledge Graph Completion Model Based on Differential Negative Sampling and Prompt Learning

Knowledge graphs (KGs) serve as a crucial resource for numerous artificial intelligence tasks, significantly contributing to the advancement of the AI field. However, the incompleteness of existing KGs hinders their effectiveness in practical applications. Consequently, researchers have proposed the task of KG completion. Currently, embedding-based techniques dominate the field as they leverage the structural information within KGs to infer and complete missing parts. Nonetheless, these methods exhibit limitations. They are limited by the quality and quantity of structural information and are unable to handle the missing entities in the original KG. To overcome these challenges, researchers have attempted to integrate pretrained language models and textual data to perform KG completion. This approach utilizes the definition statements and description text of entities within KGs. The goal is to compensate for the latent connections that are difficult for traditional methods to obtain. However, text-based methods still lag behind embedding-based models in terms of performance. Our analysis reveals that the critical issue lies in the selection process of negative samples. In order to enhance the performance of the text-based methods, various types of negative sampling methods are employed in this study. We introduced prompt learning to fill the gap between the pre-training language model and the knowledge graph completion task, and to improve the model reasoning level. Simultaneously, a ranking strategy based on KG structural information is proposed to utilize KG structured data to assist reasoning. The experiment results demonstrate that our model exhibits strong competitiveness and outstanding inference speed. By fully exploiting the internal structural information of KGs and external relevant descriptive text resources, we successfully elevate the performance levels of KG completion tasks across various metrics.

International Soft Law Governance of Artificial Intelligence: Advantages, Approaches, and Credibility

Given the transnational nature of data and algorithms associated with artificial intelligence, individual countries often face challenges in developing an effective governance system. Ensuring a healthy, stable, and sustainable AI ecosystem requires international communication, cooperation, and interaction. However, in the emerging and fast-changing interdisciplinary field of AI, internationally binding laws like treaties and agreements cannot be easily established overnight. Multilateral negotiations and local consultations are necessary, as each provision must be carefully considered and weighed, a process that is time-consuming and slow in yielding results. Therefore, it is clear that non-coercive soft law methods are necessary to achieve rapid international consensus and facilitate action. Soft law intervention provides practical space in the current landscape of Internet governance and is both necessary and feasible. At the very least, soft law can initiate the process of legalizing Internet governance. The application of soft law can encourage countries to reach some foundational and framework agreements, enabling practical and effective preparations for future, more comprehensive agreements that may be reached.

A Prescriptive Framework for Selecting Optimal Machine Learning Algorithms for Enterprise-level Problems

We are living in a world where data is touted to be the new oil and analytics is the combustion engine. Analytics or data science comprises a number of tools and techniques from the fields of statistics, machine learning and broader AI. While there is no dearth of such tools and techniques ranging from random forests to neural networks, problems most enterprises face is that of identify the most suitable tool (s) for a business problem at hand. This paper aims to address this problem by developing a novel, comprehensive framework that identifies the optimal data science tools given the nature and type of the business problem and the constraints on the underlying data used. This framework can be an effective device for enterprises to select the suitable data science tools and techniques to apply to their problems. The intention is to empirically test this framework in future research and develop a Natural language Processing (NLP) implementation of this prescriptive framework.

Application of artificial intelligence technologies in HR management

Objective. The purpose of the study is to analyze the possibility of using AI technologies to solve problems related to the selection of employees in project teams, based on production indicators and HR metrics of personnel.Method. Based on the fact that in the field of AI, methods mean algorithms by which tasks are solved, the following number of methods related to AI theory were identified: neural networks, fuzzy logic, expert systems, evolutionary modeling, Machine Learning.Result. An example of the use of AI is given in a situation where it is necessary to recruit personnel for a project based on the length of service and the degree of workload (where a scale with values from “highly loaded” to “not loaded” is used for workload). For the described example, an explanation is given that reveals the use of AI technologies (such as question-and-answer systems) in order to form HR metrics and production indicators. Additionally, the process of applying the objective function to obtain a numerical coefficient based on individual metrics or a combination of them is described in order to make a decision corresponding to its value based on the resulting indicator of the function.Conclusion. Within the framework of the conducted research, the historical patterns that led the field of personnel management to transformation and which made the use of AI technologies relevant in this area were considered. Continuous development and implementation of intelligent tools in the practice of project management facilitates HR processes and increases the efficiency of employee management. The use of AI technologies considered in the study will help to successfully monitor the state of both the project and the project team, which will have a positive impact on the productivity and profit of the enterprise.

Real Time Data Processing and Predictive Analytics Using Cloud Based Machine Learning

Lately, the expansion of constant checking frameworks and the rise of the Modern Web of Things (IIoT) have uncovered the need of creating calculations that are both adaptable and lined up to gauge mechanical disappointments and decide the excess helpful existence of assembling frameworks and the parts that make up those frameworks. Information driven approaches, for example, AI have acquired importance in the field of prognostics and wellbeing the executives (PHM), as opposed to customary model-based prognostic strategies, which need a significant perception of the actual elements of the framework and frequently rely upon specific stochastic cycles. The critical measure of preparing information that is required, then again, is a hindrance to the computational productivity of AI calculations for information driven PHM. To tackle this trouble, the reason for this study is to give a remarkable strategy to hardware prognostics that utilizes a cloud-based equal AI calculation. In particular, the expectation of hardware wear in dry processing processes is achieved by the utilization of the irregular backwoods strategy, which is a method that is generally used in the field of AI. What's more, an equal irregular woods method is built by utilizing the MapReduce structure, and it is then conveyed on the Amazon Flexible Register Cloud. It has been shown by means of the consequences of the trials that the arbitrary woodland calculation is compelling in delivering expectations that are extremely exact. Likewise, the execution of the equal irregular woods strategy brings about impressive execution gains, which gives additional proof of the calculation's true capacity for functional use in modern settings. DOI: https://doi.org/10.52783/tjjpt.v42.i4.6757

Enhanced LDR Detail Rendering for HDR Fusion by TransU- Fusion Network

High Dynamic Range (HDR) images are widely used in automotive, aerospace, AI, and other fields but are limited by the maximum dynamic range of a single data acquisition using CMOS image sensors. High dynamic range images are usually synthesized through multiple exposure techniques and image processing techniques. One of the most challenging task in multiframe Low Dynamic Range (LDR) images fusion for HDR is to eliminate ghosting artifacts caused by motion.In traditional algorithms, optical flow is generally used to align dynamic scenes before image fusion, which can achieve good results in cases of small-scale motion scenes but causes obvious ghosting artifacts when motion magnitude is large. Recently, attention mechanisms have been introduced during the alignment stage to enhance the network’s ability to remove ghosts. However, significant ghosting artifacts still occur in some scenarios with large-scale motion or oversaturated areas. We proposea novel Distilled Feature TransformerBlock (DFTB) structure to distill and re-extract information from deep image features obtained after U-Net downsampling, achieving ghost removal at the semantic level for HDR fusion. We introduce a Feature Distillation Transformer Block (FDTB), based on the Swin-Transformer and RFDB structure. FDTB uses multiple distillation connections to learn more discriminative feature representations. For the multiexposure moving scene image fusion HDR ghost removal task, in the previous method, the use of deep learning to remove the ghost effect in the composite image has been perfect, and it is almost difficult to observe the ghost residue of moving objects in the composite HDR image. The method in this paper focuses more on how to save the details of LDR image more completely after removing the ghost to synthesize high-quality HDR image. After using the proposed FDTB, the edge texture details of the synthesized HDR image are saved more perfectly, which shows that FDTB has a better effect in saving the details of image fusion. Futhermore, we propose a new depth framework based on DFTB for fusing and removing ghosts from deep image features, called TransU-Fusion. First of all, we use the encoder in U-Net to extract image features of different exposures and map them to different dimensional feature spaces. By utilizing the symmetry of the U-Net structure, we can ultimately output these feature images as original size HDR images. Then, we further fuse high-dimensional space features using Dilated Residual Dense Block (DRDB) to expand the receptive field, which is beneficial for repairing over-saturated regions. We use the transformer in DFTB to perform low-pass filtering on low-dimensional space features and interact with global information to remove ghosts. Finally, the processed features are merged and output as an HDR image without ghosting artifacts through the decoder. After testing on datasets and comparing with benchmark and state-of-the-art models, the results demonstrate our model’s excellent information fusion ability and stronger ghost removal capability.

Increasing the Value of XAI for Users: A Psychological Perspective

AbstractThis paper summarizes the psychological insights and related design challenges that have emerged in the field of Explainable AI (XAI). This summary is organized as a set of principles, some of which have recently been instantiated in XAI research. The primary aspects of implementation to which the principles refer are the design and evaluation stages of XAI system development, that is, principles concerning the design of explanations and the design of experiments for evaluating the performance of XAI systems. The principles can serve as guidance, to ensure that AI systems are human-centered and effectively assist people in solving difficult problems.

Machine learning methods for control of non-playable characters behaviour in multiplayer RPG

This article covers the problem of developing a control system for non-player characters in a multiplayer RPG. Commercial projects in the field of videogames and RPG (Role-Playing Game) projects in particular seldom use machine learning models for the implementation of character behaviour. The most common approach is to use primitive preprogrammed rules, or to implement a finite state machine. Such approaches ruin the immersion of playing with real creatures, since various predefined rules make the characters predictable. A good game AI is supposed to give the player an impression of interacting with real characters, that make various decisions, sometimes unpredictable. To achieve this goal, this article covers an approach with using various machine learning models in conjunction with a traditional finite state machine. A videogame developed earlier is used as the basis for problem solution. The article conducts an analysis of the existing works in the field of videogame AI. Next, the implementation of control system is described. This system utilizes a couple selected and successfully trained machine learning models. A multitude of models were tested, eventually a decision tree model and a neural network were selected, since they yielded the best results. The process of development and implementation of a control system involving machine learning models is then described. The approaches of teaching such models are described, and finally the achieved results are analyzed. To gauge the results, different models were compared against each other in test battles. The decision tree model showed results slightly better than the traditional finite state machine. Meanwhile, the neural network performed significantly better, beating other models far more often. Achieved results can be developed further, utilizing more complex models and improving training methods, which will result in even more sophisticated characters. Presence of such characters in the game will qualitatively improve the gameplay. Obtained system was integrated into the videogame, that may potentially become a commercial product.

A Systematic Study on Reproducibility of Reinforcement Learning in Recommendation Systems

Reproducibility is a main principle in science and fundamental to ensure scientific progress. However, many recent works point out that there are widespread deficiencies for this aspect in the AI field, making the reproducibility of results impractical or even impossible. We therefore studied the state of reproducibility support on the topic of Reinforcement Learning & Recommender Systems to analyse the situation in this context. We collected a total of 60 papers and analysed them by defining a set of variables to inspect the most important aspects that enable reproducibility, such as dataset, pre-processing code, hardware specifications, software dependencies, algorithm implementation, algorithm hyperparameters, and experiment code. Furthermore, we used the ACM Badges definitions assigning them to the selected papers. We discovered that, like in many other AI domains, the Reinforcement Learning & Recommender Systems field is grappling with a reproducibility crisis, as none of the selected papers were reproducible when strictly applying the ACM Badges definitions according to our analysis.

Prediction of Kidney Stones Using Machine Learning

Kidney stones are a prevalent disease all over the world, resulting in many of us being rushed to the hospital in excruciating pain. Calculus illness is diagnosed using a variety of imaging modalities. For the interpretation and thorough diagnosis of the photos, specialists are required. Computer-aided diagnosis systems are practical ways that can be utilized as supplemental tools to aid clinicians in their diagnosis. During this project, the deep learning (DL) technique was used to propose an automatic diagnosis of kidney stones using coronal X-ray (CT) pictures, which has made a great advances in the field of AI. Keywords: Kidney stone, medical image, Deep learning, Computed tomography