Learning Text-image Joint Embedding for Efficient Cross-modal Retrieval with Deep Feature Engineering

This article introduces a two-phase deep feature engineering framework for efficient learning of semantics enhanced joint embedding, which clearly separates the deep feature engineering in data preprocessing from training the text-image joint embedding model. We use the Recipe1M dataset for the technical description and empirical validation. In preprocessing, we perform deep feature engineering by combining deep feature engineering with semantic context features derived from raw text-image input data. We leverage LSTM to identify key terms, deep NLP models from the BERT family, TextRank, or TF-IDF to produce ranking scores for key terms before generating the vector representation for each key term by using Word2vec. We leverage Wide ResNet50 and Word2vec to extract and encode the image category semantics of food images to help semantic alignment of the learned recipe and image embeddings in the joint latent space. In joint embedding learning, we perform deep feature engineering by optimizing the batch-hard triplet loss function with soft-margin and double negative sampling, taking into account also the category-based alignment loss and discriminator-based alignment loss. Extensive experiments demonstrate that our SEJE approach with deep feature engineering significantly outperforms the state-of-the-art approaches.

Semantic Term-Term Coupling based Feature Enhancement of User Profiles in Recommendation Systems

Content-based recommender system is a subclass of information systems that recommends an item to the user based on its description. It suggests items such as news, documents, articles, webpages, journals, and more to users as per their inclination by comparing the key features of the items with key terms or features of user interest profiles. This paper proposes the new methodology using Non-IIDness based semantic term-term coupling from the content referred by users to enhance recommendation results. In the proposed methodology, the semantic relationship is analyzed by estimating the explicit and implicit relationship between terms. It associates terms that are semantically related in real world or are used inter-changeably such as synonyms. The underestimated features of user profiles have been enhanced after term-term relation analysis which results in improved similarity estimation of relevant items with the user profiles.The experimentation result proves that the proposed methodology improves the overall search and retrieval results as compared to the state-of-art algorithms.

Wonderful Natural Drugs with Surprising Nutritional Values, Rheum Species, Gifts of the Nature

Nutrition therapy on the basis of traditional medicinal plants and herbs is common in many Asian countries, especially Iran and China. Rheum species, especially rhubarbs, belong to plant medicines recognized in 2500 BC. An online search of the literature was carried out at Pubmed/Medline, Scopus, and Google scholar, covering all years until April 2021. The following key terms were used, usually in combinations: Rheum species, rhubarb, natural products, pharmaceutical benefits, anthraquinones and anthranone. After performing the literature search, the bibliographies of all articles were checked for cross-references that were not found in the search databases. Articles were selected if they reported any biological effects, ethnomedicinal uses, phytochemical compounds and botanical description of Rheum species. The most important components of rhubarb are anthraquinones, anthranone, stilbenes, tannins and butyrophenones. Anthraquinones consist of rhein, emodin, aloe-emodin and chrysophanl, and anthranone includes sennosides and rheinosides. The most important health benefits of rhubarb are antioxidant and anticancer activities, antimicrobial activity, wound healing action, hepatoprotective and anti-diabetic effects, and nephroprotective effect, as well as anti-inflammatory, analgesic and antibacterial activities. Integration of both traditional pharmaceutical science and modern medicines may promote sustainability, lead to organic life and promote the cultivation of medicinal plants.

The Use of Humor in Employee-to-Employee Workplace Communication: A Systematic Review With Thematic Synthesis

The aim of this systematic review was to develop a thematic synthesis of existing qualitative studies to explore the use of humor in employee-to-employee workplace communication and provide a greater understanding of this area of research through the experiences of employees. A number of databases were searched using key terms and papers were selected using pre-specified criteria. The thematic synthesis approach of Thomas and Harden was used to review the final 23 papers. The findings from the thematic synthesis resulted in four temporal themes that described how humor was utilized during an employee’s organizational transition: (1) initiation into organizational humor, (2) joining a “tribe”—in-groups and out-groups, (3) exerting influence—humor as power, and (4) using the safety valve—humor to relieve tension. The temporal themes described in this study crossed organizational and cultural divides, where humor formed an essential part of work-based dialog.

Classification and pattern extraction of incidents: a deep learning-based approach

Classifying or predicting occupational incidents using both structured and unstructured (text) data are an unexplored area of research. Unstructured texts, i.e., incident narratives are often unutilized or underutilized. Besides the explicit information, there exist a large amount of hidden information present in a dataset, which cannot be explored by the traditional machine learning (ML) algorithms. There is a scarcity of studies that reveal the use of deep neural networks (DNNs) in the domain of incident prediction, and its parameter optimization for achieving better prediction power. To address these issues, initially, key terms are extracted from the unstructured texts using LDA-based topic modeling. Then, these key terms are added with the predictor categories to form the feature vector, which is further processed for noise reduction and fed to the adaptive moment estimation (ADAM)-based DNN (i.e., ADNN) for classification, as ADAM is superior to GD, SGD, and RMSProp. To evaluate the effectiveness of our proposed method, a comparative study has been conducted using some state-of-the-arts on five benchmark datasets. Moreover, a case study of an integrated steel plant in India has been demonstrated for the validation of the proposed model. Experimental results reveal that ADNN produces superior performance than others in terms of accuracy. Therefore, the present study offers a robust methodological guide that enables us to handle the issues of unstructured data and hidden information for developing a predictive model.

Telehealth for rehabilitation and recovery after stroke: State of the evidence and future directions

Aims: The aim of this rapid review and opinion paper is to present the state of the current evidence and present future directions for telehealth research and clinical service delivery for stroke rehabilitation. Methods: We conducted a rapid review of published trials in the field. We searched Medline using key terms related to stroke rehabilitation and telehealth or virtual care. We also searched clinical trial registers to identify key ongoing trials. Results: The evidence for telehealth to deliver stroke rehabilitation interventions is not strong and is predominantly based on small trials prone to Type 2 error. To move the field forward, we need to progress to trials of implementation that include measures of adoption and reach, as well as effectiveness. We also need to understand which outcome measures can be reliably measured remotely, and/or develop new ones. We present tools to assist with the deployment of telehealth for rehabilitation after stroke. Conclusion: The current, and likely long-term, pandemic means that we cannot wait for stronger evidence before implementing telehealth. As a research and clinical community, we owe it to people living with stroke internationally to investigate the best possible telehealth solutions for providing the highest quality rehabilitation.

Approaches and Practices in Strategic Human Resources Management

This chapter is planned and designed to explore strategic human resources (SHR), key terms, activities, and requirements in organisations. Using various activities and case studies to support the lines of discussion throughout, the chapter is developed for students, professionals, managers, researchers that already have prior knowledge and experience in the field of HR or other associated fields and positions such as being a line manager for a small or large team, or even running own small firm where the aspects of HRM are highly essential and vital for the development and growth of the firm. The chapter is providing identification, exploration, and in-depth discussion of key strategic aspects of HRM such as the following: forecasting external supply, job analysis and workforce profiling, job descriptions and person specifications, competencies, job families (market groups), and redundancy. Furthermore, the chapter is supported by key case studies and identification of current trends to enhance the understanding of key changes and developments in the field.