Cultural awareness plays a vital role in making AI systems beneficial for a globalized audience. This cultural awareness is lacking in modern decision-support systems and in the current state of the work, where explainability is the paramount requirement now from all AI systems. To address this, the article introduces CRIXP, a framework with decisive cultural knowledge and the capability to explain the reasoning behind its suggestions. CRIXP comprises: 1) a cultural ontology (CRO); 2) a cultural knowledge graph (CKG); 3) a general-purpose adaptable algorithm providing recommendations and explanations; and 4) a CKG enrichment module. The cultural traits of all the locales are consolidated and represented as an ontology and a knowledge graph. A cultural shift suggestion system has been demonstrated for recommendations and explanations. The response generated is compared with ChatGPT. CRIXP is found to outperform ChatGPT by providing more relevant recommendations with inherent explainability.

ABSTRACT Ontology engineering is crucial for many areas such as information retrieval systems, data integration facilities, and basic decision support systems. Nevertheless, estimating the cost of ontology engineering projects is notoriously difficult to achieve. This challenge stems from the complexity and evolving nature of such projects. To solve this difficulty, we propose to improve the accuracy of cost estimation through a hybrid methodology that combines Fuzzy Ontology Cost Estimation Model (F‐ONTOCOM) and Artificial Neural Networks (ANN). Fuzzy logic is used in our model to capture linguistic variables and other complex relationships within the scope of cost estimation. At the same time, ANN allows for the recognition of complex nonlinear interactions, enhancing the overall accuracy of prediction. This integration of fuzzy logic and neural networks leads to enhancements in the model's robustness, adaptability, and precision. Our approach features a methodology for 148 ontology engineering projects that include, but are not limited to, data scraping and preprocessing, fuzzy inference system design, neural network training, and validation processes. The results showed that the hybrid approach was champion over the traditional estimation approach in terms of effort estimation, Mean Relative Error (MRE), Mean Magnitude of Relative Error (MMRE), and the predictive accuracy over 21 randomly selected ontology projects.

A large population embraced social media to share thoughts, emotions, and daily experiences through text, images, audio, or video posts. This user-generated content (UGC) serves various purposes, including user profiling, sentiment analysis, and disease detection or tracking. Notably, researchers recognized the potential of UGC for assessing mental health due to its unobtrusive and real-time monitoring capabilities. Recent reviews on depression identification from textual UGC using AI models covered tools and techniques but overlooked critical components such as datasets, lexicons, features, and subtasks, which are essential for understanding the progress and tasks undertaken. This survey adopts a systematic approach and formulates five research questions to examine the relevant literature concerning these elements. Additionally, it organizes machine learning and deep learning (ML/DL) training features from textual UGC in a hierarchical manner and maps the literature on depression detection into various subtasks. The review highlights that despite the prevalence studies, datasets are limited in both quantity and size, with many relying on less reliable ground truth collection methods such as self-reported diagnosis statements (SRDS). Furthermore, the review identifies an overemphasis on certain textual features, such as n-grams and affective elements, while others, such as life events, egocentric graphs, and intervention/coping style, remain largely unexplored. It is crucial for practical AI depression detection systems to develop expertise in tasks such as severity, symptom detection, and explainable/interpretable depression analysis to instill confidence and trust among users.

The lack of explainability in using relevant clinical knowledge hinders the adoption of artificial intelligence-powered analysis of unstructured clinical dialogue. A wealth of relevant, untapped Mental Health (MH) data is available in online communities, providing the opportunity to address the explainability problem with substantial potential impact as a screening tool for both online and offline applications. Inspired by how clinicians rely on their expertise when interacting with patients, we leverage relevant clinical knowledge to classify and explain depression-related data, reducing manual review time and engendering trust. We developed a method to enhance attention in contemporary transformer models and generate explanations for classifications that are understandable by mental health practitioners (MHPs) by incorporating external clinical knowledge. We propose a domain-general architecture called ProcesS knowledgeinfused cross ATtention (PSAT) that incorporates clinical practice guidelines (CPG) when computing attention. We transform a CPG resource focused on depression, such as the Patient Health Questionnaire (e.g. PHQ-9) and related questions, into a machine-readable ontology using SNOMED-CT. With this resource, PSAT enhances the ability of models like GPT-3.5 to generate application-relevant explanations. Evaluation of four expert-curated datasets related to depression demonstrates PSAT's applicationrelevant explanations. PSAT surpasses the performance of twelve baseline models and can provide explanations where other baselines fall short.

Abstract The Internet of Things (IoT) paradigm is redefining our lives, allowing us to make “smart” decisions. This boom has also gained popularity in academic research, one of the core goals being to make IoT research more accessible to students and early researchers, while making sure that experienced researchers keep up with the changes happening in the research area. A large number of review papers are available covering surveys related to IoT vision enabling technologies, applications, key features, and future directions. Nevertheless, there is a lack of analysis of these reviews. This study provides a scientometric analysis of already available reviews in the field of IoT to identify upcoming research needs and bring simplicity to literature research. In total, 964 review articles in the field of IoT written in English and published in peer-reviewed journals and conferences from 2010 to April 2023 have been finalized from the Google Scholar database. Three broad categories of analysis have been performed on the 964 relevant collected literature, namely (a) statistical; (b) machine learning-based; and (c) evaluative analysis. An important differentiating feature of the current study is the use of machine learning for data exploration, thereby providing better interpretation. We find that the trend to review the field of IoT has increased in the last five years with only one article in 2010. This article identifies and quantifies the knowledge gaps to inform the community, industry, and government authorities about research directions for IoT. Furthermore, this scientometric analysis serves as a foundational resource for IoT researchers in identifying relevant and important survey papers that target their research fields in IoT.

Every day, web credibility is becoming an increasingly important. It affects how we interact with information on the internet as well as the quality of those interactions. Web credibility also spills into the real world, as misinformation from the internet can have very real consequences and catastrophic losses. It also sets an aggressive challenge of choice among different web services in the internet user community. In this paper, we investigate the existing practice and research work on evaluating web service credibility. We classify the available techniques and discuss their capabilities and impacts on user/web interactions. This work will help discover the venues for credibility measures and highlight the effective techniques in different web service domains. It will also help build more rigorous techniques to disseminate credibility measures and support internet user choices.

Estimating effort is an essential prerequisite for the wide-scale dispersal of ontologies. Not much attention has yet been paid to this essential aspect of ontology building. To date, ONTOCOM is the most prominent model for ontology cost estimation. Many factors influencing the building cost of an ontology are depicted by linguistic terms like Very High, High, . . . and so on; making them vague and indistinct. This fuzziness is quite uncertain and must be taken into consideration. The available effort estimation models do not consider the uncertainty of fuzziness. In this work, we propose an effort estimation methodology for ontology engineering using Fuzzy Logic i.e. F-ONTOCOM (Fuzzy-ONTOCOM) to overcome of uncertainty and imprecision. We have defined the corresponding Fuzzy sets for each effort multiplier and its associated linguistic value, and represented the same by triangular membership functions. F-ONTOCOM is applied to a dataset of 148 ontology projects and evaluated over various evaluation criteria. FONTOCOM outperforms the existing effort-estimation models; it has been concluded that F-ONTOCOM improves the cost estimation accuracy and estimated cost is very close to actual cost.

In service to the state of the art, advances are required toward redesigning the framework over which web applications are built.The semantic web lies at the intersection of web and machine understandable meaningful data, turning it into intelligent 'web of data'.The key requirement with any intelligent system has been to find a concrete knowledge representation that can make the inferences within time and space constraints; that is, reasoning effectively and efficiently within the resource constraints posed to the problem at one hand and with insufficient data as well as incomplete knowledge on the other hand.Various Knowledge representation schemes have been proposed in the literature, each having its limitation over the others.Ontology is the key component for semantic web engineering.Ontologies are conceptual knowledge bases providing a systematic and taxonomical description of the concepts and instances under consideration.Conceptual clarity in the computational representation of a concept is vital for holistic thinking and knowledge engineering.In order to meet the needs of an application/enterprise, knowledge should be presented taking care of all possible perspectives; and represented in a hierarchical structure with differing levels of granularity.This paper discusses about bringing all the manifestations of an ontological

Healthcare is a significant domain having a huge knowledge base, a significant part which comes from medical, diagnostic and imaging devices and sensors.The health status of patients may be monitored and managed remotely by performing reasoning over this knowledge base.Specialists in HealthCare facilities are required to handle large quantity of data generated and make decisions.However, the heterogeneous and complex nature and the huge amount of data generated; the way it is represented and presented; and the security challenges may overburden the core abilities of thinking and reasoning of even highly skilled and knowledgeable experts putting the lives of patients at risk.The situation may become even worse when data is coming from various healthcare devices and sensors which are themselves characterized by a number of representation and serialization formats.To address the various challenges in healthcare, this paper tries to represent and hence exchange the data collected by healthcare devices meaningfully and securely.This allows all healthcare devices to operate in conjunction with each other facilitating deeper insights and enabling generation of intelligent recommendations.

The Extended Hierarchical Censored Production Rules (EHCPRs) system is presented here as an underlying methodology for representation, reasoning, learning, etc., of the proposed live multilingual thinking machine. Enriched representation scheme is a very important aspect and central to all the successful and effective Artificial Intelligence systems. An EHCPR is presented here as a unit of represented knowledge (i.e. an artificial neuron) in the knowledge treasure distributed over globally spread servers. An EHCPR is implemented with the help of extensive set of predefined pointers like dendrites in a neuron and various nodes like nucleus in a neuron, which would span a huge but efficient multilingual hierarchical network as knowledge structure. The EHCPRs system is started live at www.live-ehcprs-system.com with multilingual representation and storage at word level only. But construction of words is by starting at character level without repetition in representation of a character. It displays the stored information of any stored concept in any of the selected language. To begin with, English, French and Hindi are offered to the user which would be extended to all the languages in future.

The vast and complex oceans that are optically opaque are acoustically transparent, enabling characterization of physical and biological bodies and processes of sea using sound as a premier tool. Lack of direct observations of vertical profiles of velocimeters and/or temperature and salinity, from which sound speed can be calculated, limits specifications and investigation of temporal and spatial variabilities of the three-dimensional structure of the sound speed in the oceans. In this study, the authors demonstrate estimation of sound speed profiles (SSPs) from surface observations using an artificial neural network (ANN) method. Surface observations from a mooring in the central Arabian Sea are used as a proxy to the satellite observations. The ANN-estimated SSPs had a root-mean-square error of 1.16 m/s and a coefficient of determination of 0.98. About 76% (93%) of the estimates lie within$pm$1 m/s ($pm$2 m/s) of the SSPs obtained from in situ temperature and salinity profiles.