Structured Form Research Articles

A Direct Observation Form for Evaluation of the Psychiatric Interview: Pilot Testing During the Psychiatry Clerkship.

The authors evaluated the validity of a structured direct observation form (DOF) to assess medical student performance on psychiatric interviews for use in the psychiatry clerkship. One hundred and forty-eight third-year medical students were evaluated by two DOFs completed by a supervising resident, fellow, attending, or another team member. One DOF was completed early (time 1) and the other late (time 2) during a 4-week psychiatry clerkship. The DOF showed good internal consistency (Cronbach's alpha = 0.88-0.89). DOFs submitted at time 2 were positively associated with end-of-course clinical grades (p < 0.001); this association remained significant while controlling for time of academic year the course was completed, rater rank, complexity of the case, and difficulty of the interview (time 2 p < 0.001). Mean scores from the DOF were associated with the time of year students took the course with students assessed early in the academic year having lower average scores (p-values = 0.01 at time 1, 0.002 at time 2). Scores on time 1 DOFs were positively associated with rater rank (p = 0.005; residents gave higher scores than faculty). DOFs also correlated with an Entrustable Professional Activity (EPA) assessment of the interview (time 1 r = 0.76, p < 0.001; time 2 r = 0.79, p < 0.001), but not with shelf exam scores (time 1 r = 0.10, p = 0.24; time 2 r = 0.11, p = 0.21). A brief structured form evaluating medical student performance on psychiatric interviews provided valid information about performance by third-year medical students during the psychiatry clerkship.

Hospital Acquired Infections during Patient Incubation at Tertiary Care Hospital of Northern India

Health care associated infection (HAI) can be defined as an infection acquired in hospital by a patient who was admitted for a reason other than that of infection or an infection occurring in a patient in the hospital or other health care facility in whom the infection was not present or incubating at the time of admission. Infections occurring more than 48 hours after admission is considered as HAI. Bacteria, fungi, viruses, or other, less common pathogens can cause HAIs. Patients being susceptible to common infections due to diminished immune responses and infections at surgery sites (SSIs), many HAIs are due to implants and prostheses. These include central line-associated bloodstream infections (CLABSIs), catheter-associated UTIs (CAUTIs), and ventilator-associated pneumonia (VAP). This study was conducted from October 2021 to October 2022 in a tertiary care hospital. All wards of SSB Heart and Multispecialty Hospital were included. The incidence, prevalence and risk factors of healthcare associated infection were determined and analyzed. The specimens were processed by standard microbiological methods to isolate and identify etiology. Clinical and laboratory data were collected using structured case report formats. HAIs (CAUTI, CLABSI, VAP, SSI) data from the month of October 2021 to October 2022 has been described in Table 1 to Table 5. In a period of one year a total of 5 cases of Ventilator associated pneumonia from 1124 ventilator days and 7 cases of CAUTI out of which 4731 catheter days. Highest incidence of HAI were 10 cases of CLABSI out of which 1421 central line days in a year and lowest HAI was 1 case of SSI in 3853 days of patients susceptible to SSI in a year. This study reveled that infections rate were very less in ICU because of patient care and well mange infection rate and well defined infection guidelines at SSB Heart and Multispecialty hospital, Faridabad.

Tuberculosis Treatment Outcomes and Its Predictors among Tuberculosis Patients Registered at Tefera Hailu Memorial General Hospital, Sekota Town, Northeast Ethiopia: A Seven-Year Retrospective Study.

Despite the availability of effective medications, tuberculosis (TB) continues to be a serious global public health problem, primarily affecting low and middle-income nations. Measuring and reporting TB treatment outcomes and identifying associated factors are fundamental parts of TB treatment. The goal of this study was to look at the outcomes of TB treatment and the factors that influence them in Sekota, Northeast Ethiopia. A facility-based retrospective study was conducted in Tefera Hailu Memorial General Hospital, Sekota town, Northeast Ethiopia. All TB patients who registered in the TB log book and had known treatment outcomes at the treatment center between January 1, 2015, and December 30, 2021, were included in this study. The data was gathered utilizing a pretested structured data extraction format that comprised demographic, clinical, and treatment outcome characteristics. Data were entered, cleaned, and analyzed using SPSS version 25. Descriptive statistics and logistic regression analysis were employed. A p value of less than 0.05 was considered statistically significant. A total of 552 registered TB patients' data were reviewed. Of these, 49.6% were male, 94.4% were new cases, 64.9% were presented with pulmonary TB, and 18.3% were HIV positive. Regarding the treatment outcome, 11.6% were cured, 82.2% completed their treatment, 1.1% had failed treatment, 1.3% were lost to follow-up, and the remaining 3.8% died during the follow-up. The overall treatment success rate among TB patients was 93.8%. The maximum number of successful treatment outcomes was 94.9% in 2021, while the lowest was 86.7% in 2020. The pattern of successful treatment results changes with the number of years of treatment. In the current study, being a new TB patient (AOR = 1.75, 95% CI: 1.31-7.32) and being an HIV-negative patient (AOR = 2.64, 95% CI: 1.20-5.8) were factors independently associated with a successful treatment outcome. The rate of successful TB treatment outcomes in the current study was satisfactory. This achievement should be maintained and enhanced further by developing effective monitoring systems and educating patients about medication adherence.

Examining the effectiveness of the primary education curriculum in terms of leisure education: an overview of learning outcomes in the Turkish public education system

ABSTRACT The aim of this study is to examine the compulsory and elective course learning outcomes that indicate the goals of the primary education curriculums in terms of leisure education. The data were collected using a structured content form based on qualitative research methodology and were analysed using content analysis, which is a quantitative method. A total of 3013 learning outcomes in the primary curriculum in the 2017–2018 academic year were separately examined and coded by three researchers. Of the 2160 compulsory courses, 326 (15%) included direct leisure education outcomes, and 456 (21.1%) included indirect leisure education outcomes. Of the 853 elective courses, 90 (10.5%) included direct leisure education outcomes, and 182 (21.3%) included indirect leisure education outcomes. The highest learning outcomes of leisure education in the compulsory courses were in Physical Education and Sports and Games and Physical Activities courses, while the highest learning outcomes of leisure education in the elective courses were in Visual Arts and Intelligence Games courses. In conclusion, approximately 25%of the primary education curriculum courses provide learning outcomes in terms of leisure education, but the learning outcomes are focused on awareness and leisure skills, and there is no balanced distribution of leisure education dimensions.

Digital Humanities Projects in Educational Process

The purpose of the study is to outline the main directions and prospects of digital humanities development; to find out the main principles of the scientific space transformation, caused by the implementation of digital humanities; to define the transdisciplinary ontology as digital humanities important tool. Methodology of the article is based on implementation of principle of information systematicity and its further modeling in educational and scientific aspects. The information is being analysed for distinguishing its structural components and their semantic and functional coherence. According to the structural and semantic analysis of information, the modeling of information representation is performed. As the productive way of modeling is the transdisciplinary ontology, so principle of transdisciplinarity is one of the basical principle in the study. Transdisciplinary ontology seems to be an important tool of digital humanities. Using ontology it is possible to perform educational information in structured form with all its components, organized in hierarchical construction, and their correlation depiction. Transdisciplinary ontology provides various forms of information graphical display, perception of which helps to understand essential causal factors, principles of information arrangement, its regularities Recommendation for further transdisciplinary ontology application is based on the possible ontology extention by new elements adding according to the enrichment of educational material being learned.

Evaluation of platelet indices in dengue fever in a tertiary care hospital in Bangladesh

Background: Dengue fever is the most rapidly spreading mosquito-borne viral diseases in the world. Some evidence suggests that platelet indices may have diagnostic and prognostic value in Dengue fever. The aim of the study is to evaluate platelet indices and to find their correlation between platelet count in Dengue fever. Methods: This retrospective cross-sectional study was conducted through the use of stored data in Bangabandhu Sheikh Mujib Medical University (BSMMU) dengue cell from July 2019 to September 2019 at department of laboratory medicine and department of internal medicine, BSMMU, Dhaka. Among them, clinical records of 260 cases are preserved in a structured clinical record form (CRF). After ethical clearance from institutional review board (IRB), form clinical records of 260 cases which were preserved in a structured CRF patients who fulfilled the inclusion and exclusion criteria was selected as study population. Results: Platelet indices (MPV and PDW) were statistically significant difference among different platelet counts (p&lt;0.05). There was significant negative correlation between platelet count and PDW (r=-0.228, p≤0.001). There was also negative correlation between platelet count and MPV (r=-0.106) which was not statistically significant (p=0.088). Conclusions: Platelet indices are useful parameters in dengue infection. Other than platelet count, PDW and MPV are useful to monitor dengue fever.

Lyrics Analysis of the Arab Singer Abdel ElHalim Hafez

In this work we analyze the lyrics of one of the most famous and influential Arab artists in the twentieth century, namely, (Abdel ElHalim Hafez). Lyrics analysis provides a deep insight into the artist’s career evolution and his interactions with the surrounding environment including the social, political, and economic conditions. In order to perform such analysis we had to collect and compile the lyrics of Abdel ElHalim accompanied with the necessary metadata into an organized and structured form. The data are preprocessed by removing stop words and doing some normalization operations over the songs’ prose. We did not perform any lemmatization or stemming as the original form of the tokens convey much more information than the source words. We performed a lexical analysis in order to study both the lexical density and diversity over the course of Abdel ElHalim’s career life. We have as well studied the most significant words, idioms, and terms played in the songs using tools such as word clouds and more quantitative measures such as term frequency-inverse document frequency. We have divided the career life of Abdel ElHalim into sub-decades of length 5 years and all analyses are done both in a yearly fashion and more coarsely over such sub-decades. We have found a strong correlation between our statistical analysis and the socio-political status in Egypt and the Arab world during that time. This is especially relevant knowing that Abdel ElHalim is very much truly considered the son of the generation of the 1952 revolution in Egypt. The significance of Abdel ElHalim and his lyrics stem essentially from being contemporaneous to radical changes in Egypt across all sectors including political (support of liberation movements across the world, and the conflict with Israel), and socio-economic (especially changing the social class structure in Egypt). We also investigated the potential effectiveness of PoS (Part of Speech) tagging in genre analysis and classification.

"Take up to eight tablets per day": Incorporating free-text medication instructions into a transparent and reproducible process for preparing drug exposure data for pharmacoepidemiology.

Routinely collected prescription data provides drug exposure information for pharmacoepidemiology, informing start/stop dates and dosage. Prescribing information includes structured data and unstructured free-text instructions, which can include inherent variability, such as "one to two tablets up to four times a day". Preparing drug exposure data from raw prescriptions to a research ready dataset is rarely fully reported, yet assumptions have considerable implications for pharmacoepidemiology. This may have bigger consequences for "pro re nata" (PRN) drugs. Our aim was, using a worked example of opioids and fracture risk, to examine the impact of incorporating narrative prescribing instructions and subsequent drug preparation assumptions on adverse event rates. R-packages for extracting free-text medication prescription instructions in a structured form (doseminer) and an algorithm for transparently processing drug exposure information (drugprepr) were developed. Clinical Practice Research Datalink GOLD was used to define a cohort of adult new opioid users without prior cancer. A retrospective cohort study was performed using data between January 1, 2017 and July 31, 2018. We tested the impact of varying drug preparation assumptions by estimating the risk of opioids on fracture risk using Cox proportional hazards models. During the study window, 60 394 patients were identified with 190 754 opioid prescriptions. Free-text prescribing instruction variability, where there was flexibility in the number of tablets to be administered, was present in 42% prescriptions. Variations in the decisions made during preparing raw data for analysis led to marked differences impacting the event number (n= 303-415) and person years of drug exposure (5619-9832). The distribution of hazard ratios as a function of the decisions ranged from 2.71 (95% CI: 2.31, 3.18) to 3.24 (2.76, 3.82). Assumptions made during the drug preparation process, especially for those with variability in prescription instructions, can impact results of subsequent risk estimates. The developed R packages can improve transparency related to drug preparation assumptions, in line with best practice advocated by international pharmacoepidemiology guidelines.

Influence of metformin on hyperandrogenism in women with polycystic ovary syndrome: a systematic review and meta-analysis of randomized clinical trials.

To summarize the effects of metformin treatment on markers of hyperandrogenism in patients diagnosed with polycystic ovary syndrome (PCOS). A systematic review, with meta-analysis, of randomized placebo-controlled clinical trials that evaluated the effects of metformin treatment in adult patients with PCOS on the levels of hyperandrogenism markers was conducted. The literature search, data extraction, risk of bias, and the assessment of certainty of evidence were performed independently by two reviewers using a structured form. The results were combined by applying the random effect, and the effect measure presented as a standardized mean difference (SMD). Significant values were considered as p < 0.05 with 95% CI. Furthermore, sensitivity analyses were performed in order to explore possible heterogeneity between studies. Were included 18 studies in the quantitative evaluationand 17 studies (23 reports) in the quantitative evaluation. A significant reduction in total testosterone levels was seen in the metformin-treated group when compared to the control group after combining the results by the sensitivity analysis [SMD: - 0.46 (95% CI: - 0.89 to - 0.02)]. Therefore, FAI values were also regulated by metformin treatment. We showed that metformin proved to be effective in reducing total testosterone levels, and the same was observed for free androgen index (FAI) values-a measure influenced by testosterone levels. The protocol of this study was registered at Prospero (CRD42021235761).

LecturePlus: a learner-centered teaching method to promote deep learning.

A new teaching format, the LecturePlus was formulated as a lecture followed by small group learning activities. This study assessed the effectiveness of LecturePlus in medical education. An interventional study was conducted among final-year medical students with 74 students in the experimental group and 96 students in the control group. Each LecturePlus lasted about 1 hour and was conducted with 12 to 18 students. A LecturePlus session comprised of a lecture followed by small-group problem-solving exercises. The exercises were clinical cases with open-ended short-answer questions. Students were divided into groups of three each (triads) for these exercises. A faculty tutor assisted the small groups as needed. Closure was achieved through a discussion moderated by the tutor. Learning outcomes were assessed via the National Board of Medical Examiners (NBME) subject scores and compared with those of the preceding academic year. An additional multiple-choice questions (MCQ) test was administered before and after the clerkship. The MCQ test showed improvement in knowledge application (p < 0.001, partial eta squared, 0.42). There was a statistically significant improvement in adjusted NBME scores among female students (74.8 vs. 71.8; p = 0.017) but not among male students. An anonymous written questionnaire survey showed high ratings for LecturePlus (95% selecting yes or partly yes to overall satisfaction). LecturePlus is an instructional strategy that integrates a lecture with learning activities. It can be scaled to large class sizes facilitated by one teacher. By combining didactic teaching with problem solving, this new instructional strategy may foster application of knowledge.

CROP RECOMMENDER SYSTEM

The development of farming techniques improved food supply to the nation's GDP and made it simpler for farmers to grow the precise and suitable crop without any risk or loss in productivity. Agriculture is important to human existence and livelihood because it has become a necessary and crucial part of our daily lives. To maintain the sustainability in rate and quality of production, we need to involve and introduce the best portable and noncomplex strategies such as machine learning tools to carry on the needed operations and procedures to get desired and expected crop by coordinating and initiating data exchange between the scientific and practical platforms which is the trending existing system. The idea behind this project, called the crop recommendation system, is to define and state that the appropriate crop should be grown based on a number of relative parameters, including soil features like nitrogen, phosphorus, and potassium that are extracted from the soil through filtration, and weather conditions that are embedded in a dataset in the form of structured data. This dataset is taken over by machine learning algorithms that will perform some operations like classification and will be finding the accuracy where in detail to be explained we will be splitting the given dataset into training and testing data and compare the results of those algorithms based on accuracy that each model gives and that will be our preferred algorithm. Along with a few dimensionality reduction techniques including PCA, LDA, andcross validation, we applied machine learning techniques like Decision Tree, Random Forest, and KNN.

Built-In Self Test (BIST) Architecture Simulation for Testing Crosstalk Effects in Array Structured Through Silicon Vias (TSV) in 3DICs

In this research, a BIST (built in self test) architecture for testing crosstalk effects in highly dense Through Silicon Via (TSV) placed in structured array form, in 3DICs (Three Dimensional integrated circuits), designed and simulated using the Xilinx ISE tool and the VHDL language. A novel methodology is proposed, and simulated, to observe the test responses of the victim TSVs in the chosen group simultaneously. Boundary-scan cell structures are modified, created for the purpose of operating in different modes such as shift, update and capture in either conventional serial shift mode as well as in proposed parallel broadcasting mode. Output Response Analyzers (ORA), or signature analyzers that have been simulation-verified. In this study, we suggested a novel encoder-based signature generator to locate faulty TSVs in the parallel-observed TSVs. This paper discusses the whole BIST architecture, the BIST controller built on an algorithmic state machine, the design of TPG (Test Pattern Generator), and the faulty TSV signature generator. Comparing the BIST architecture, to serial shift based interconnect tests done by IEEE 1149.1 (JTAG) such as EXTEST and IEEE 1838 standards, the test’s time complexity of BIST is relatively very low. The entire TSV array test is completed in just 32 clock cycles. The design is adaptable and can be used to broadcast test patterns to a group or to transmit test patterns serially using IEEE 1838 or 1149.1.

Incidence and risk factors for norovirus-related diarrhea in Japanese geriatric intermediate care facilities: A prospective cohort study.

The risk of developing infectious diarrhea among elderly residents at Japanese geriatric intermediate care facilities is unclear. We investigated the incidence rate and risk factors of norovirus-related diarrhea at such facilities. This prospective cohort study followed 1727 residents from November 2018 to April 2020 at 10 geriatric intermediate care facilities in Osaka, Japan regarding the occurrence of diarrhea. Resident data were collected from their medical records using structured forms at two to three of the following three time points: at recruitment, if they developed diarrhea, and when they left the facility. Residents who developed diarrhea were tested using rapid diagnostic tests for norovirus. Cox proportional hazard model was employed to hazard ratios (HRs) with 95% confidence intervals (CIs) to estimate the risk factors for norovirus-related diarrhea. During the study period, 74 residents developed diarrhea, 13 of whom were norovirus positive. The incidence rate of norovirus-related diarrhea was 10.11 per 1000 person-years (95% CI: 4.61-15.61). In terms of risk factors, people with care-needs level 3 were at a higher risk for developing norovirus-related diarrhea (adjusted HR [aHR]=7.35, 95% CI: 1.45-37.30). Residents with hypertension (aHR=3.41, 95% CI: 1.05-11.04) or stroke (aHR=8.84, 95% CI: 2.46-31.83), and those who walked with canes (aHR=16.68, 95% CI: 1.35-206.52) also had a significantly higher risk for norovirus-related diarrhea. Throughout the study period, the incidence of development of diarrhea was low. Care-needs level 3, stroke, hypertension and use of a cane were identified as risk factors for norovirus-related diarrhea in Japanese geriatric intermediate care facilities. Geriatr Gerontol Int 2023; 23: 179-187.

Automatic knowledge graph population with model-complete text comprehension for pre-clinical outcomes in the field of spinal cord injury

The paradigm of evidence-based medicine requires that medical decisions are made on the basis of the best available knowledge published in the literature. Existing evidence is often summarized in the form of systematic reviews and/or meta-reviews and is rarely available in a structured form. Manual compilation and aggregation is costly, and conducting a systematic review represents a high effort. The need to aggregate evidence arises not only in the context of clinical trials, but is also important in the context of pre-clinical animal studies. In this context, evidence extraction is important to support translation of the most promising pre-clinical therapies into clinical trials or to optimize clinical trial design. Aiming at developing methods that facilitate the task of aggregating evidence published in pre-clinical studies, in this paper a new system is presented that automatically extracts structured knowledge from such publications and stores it in a so-called domain knowledge graph. The approach follows the paradigm of model-complete text comprehension by relying on guidance from a domain ontology creating a deep relational data-structure that reflects the main concepts, protocol, and key findings of studies. Focusing on the domain of spinal cord injuries, a single outcome of a pre-clinical study is described by up to 103 outcome parameters. Since the problem of extracting all these variables together is intractable, we propose a hierarchical architecture that incrementally predicts semantic sub-structures according to a given data model in a bottom-up fashion. At the heart of our approach is a statistical inference method that relies on conditional random fields to infer the most likely instance of the domain model given the text of a scientific publication as input. This approach allows modeling dependencies between the different variables describing a study in a semi-joint fashion. We present a comprehensive evaluation of our system to understand the extent to which our system can capture a study in the depth required to enable the generation of new knowledge. We conclude the article with a brief description of some applications of the populated knowledge graph and show the potential implications of our work for supporting evidence-based medicine.

The Infantile Amnesia Phenomenon and the Beginning of Autobiographical Memories

The first years of life are characterized by an absence or paucity of memories, a condition known as infantile amnesia (IA). This study examines the distribution of the early memory recall of young adults, considering the distinction between the first (0–3) and the second (4–6) epoch of IA. We used five categories to classify memories: Perceptual-Visual Fragment, General Semantic Memory, Episodic Fragment, Repeated Episode, Single Episode. Fifty-five students (20 males; mean age = 20.85) were asked to remember their earliest events. We were also interested in understanding the presence of content features. Remembering at first epoch were low; in the second epoch, the frequency of memory increased. Results showed as the presence and number of different types of memory decrease the likelihood of memory being structured as episodic. The participants reported more elements of perceptual-visual fragments, episodic fragments, semantic memories, or repeated events when a well-organized episodic memory does not emerge. These results suggest that the episodic system assumes the role of organizer of the experience and becomes the most relevant form of memory with respect a less structured form of partial remembering. Significant differences were observed in the content features of the different memory types. The offset of IA has a complex articulation, and the complete episodic memories are the last step in the different development stages.

Clinical features and outcome of human Mpox (Monkeypox) in Saudi Arabia: An observational study of travel-related cases

BackgroundThe 2022 Monkeypox virus (Mpox) outbreak had involved multiple countries around the globe. Here, we report clinical features and outcome of human Mpox of the first cases in Saudi Arabia. MethodsWe obtained records of confirmed Mpox cases in Saudi Arabia from the public electronic health information system, Health Electronic Surveillance Network (HESN) and the healthcare providers completed a de-identified structured clinical data collection form. ResultsThe reported seven cases were travel-related and all were males between 24 and 41 years of age (mean age + SD) was 30.14 (+ 6.69) years. Of the cases, three (43 %) had heterosexual contact and the others had other intimate encounters while traveling abroad. They presented with skin lesions (100 %), fever (86 %), and lymphadenopathy (71 %). The illness was mild to moderate, did not require antiviral medications, and lasted 7–15 days. The mean duration of skin rash (+ SD) was 10 (+ 2.68) days. Routine laboratory tests (CBC, BUN, serum electrolytes, and liver enzymes) were within normal limits, and initial screening for HIV was negative. Expanded contact tracing did not reveal secondary cases of Mpox in the community or the healthcare setting. ConclusionThe current study showed heterosexual transmission of Mpox and the clinical course was mild and non-complicated. Therefore, clinicians and public health professionals should consider Mpox among individuals presenting with skin rash especially in the context of the investigation of HIV and other sexually transmitted diseases.

Automated wearable cameras for improving recall of diet and time use in Uganda: a cross-sectional feasibility study

BackgroundTraditional recall approaches of data collection for assessing dietary intake and time use are prone to recall bias. Studies in high- and middle-income countries show that automated wearable cameras are a promising method for collecting objective health behavior data and may improve study participants’ recall of foods consumed and daily activities performed. This study aimed to evaluate the feasibility of using automated wearable cameras in rural Eastern Ugandan to collect dietary and time use data.MethodsMothers of young children (n = 211) wore an automated wearable camera on 2 non-consecutive days while continuing their usual activities. The day after wearing the camera, participants’ dietary diversity and time use was assessed using an image-assisted recall. Their experiences of the method were assessed via a questionnaire.ResultsMost study participants reported their experiences with the automated wearable camera and image-assisted recall to be good (36%) or very good (56%) and would participate in a similar study in the future (97%). None of the eight study withdrawals could be definitively attributed to the camera. Fifteen percent of data was lost due to device malfunction, and twelve percent of the images were "uncodable" due to insufficient lighting. Processing and analyzing the images were labor-intensive, time-consuming, and prone to human error. Half (53%) of participants had difficulty interpreting the images captured by the camera.ConclusionsUsing an automated wearable camera in rural Eastern Uganda was feasible, although improvements are needed to overcome the challenges common to rural, low-income country contexts and reduce the burdens posed on both participants and researchers. To improve the quality of data obtained, future automated wearable camera-based image assisted recall studies should use a structured data format to reduce image coding time; electronically code the data in the field, as an output of the image review process, to eliminate ex post facto data entry; and, ideally, use computer-assisted personal interviews software to ensure completion and reduce errors. In-depth formative work in partnership with key local stakeholders (e.g., researchers from low-income countries, representatives from government and/or other institutional review boards, and community representatives and local leaders) is also needed to identify practical approaches to ensuring that the ethical rights of automated wearable camera study participants in low-income countries are adequately protected.

Sign Language Recognition using Deep Neural Network

Abstract—Sign language recognition is an attractive research field with a wide range of applications including telesurgery techniques. Another important application of hand gesture recognition is the translation of sign language, which is a complicated structured form of hand gestures. In sign language, the fingers’ configuration, the hand’s orientation, and the hand’s relative position to the body are the basis of structured expressions. The importance of hand gesture recognition has increased due to the prevalence of touchless applications and the rapid growth of the hearing-impaired population. However, developing an efficient recognition system needs to overcome the challenges of hand segmentation, local hand shape representation, global body configuration representation, and gesture sequence modeling. In this paper, a novel system is proposed for dynamic hand gesture recognition using multiple deep learning architectures for hand segmentation, local and global feature representations, and sequence feature globalization and recognition. The proposed system is evaluated on a very challenging dataset, which consists of dynamic hand gestures performed by subjects in an uncontrolled environment. The results show that the proposed system outperforms state-of- the-art approaches, demonstrating its effectiveness.

Knowledge graph extension with a pre-trained language model via unified learning method

Knowledge graphs (KGs) are collections of real-world knowledge that is represented by a structured form of triples. Since they are manually built in their nascent stage, there is a common problem that some links (triples) are missing. Knowledge graph completion (KGC) aims to find those missing links and thereby complete the KGs. However, as knowledge increases through diverse sources, new entities have explosively emerged and they are needed to be connected to existing KGs. Thus, open-world KGC is targeted on extending KGs to those new entities. Dealing with those new entities is challenging because they do not have any connection with entities in the existing KGs. One way to handle the new ones is to embed them with their textual descriptions with pre-trained word embeddings and score them in the graph-vector space with the existing typical KGC models. These models have resulted in meaningful results but there is still a lack of studies on utilizing the latest neural networks, such as pre-trained language models which are known to be better at capturing contexts than pre-trained word embeddings. This paper proposes a novel model that effectively connects new entities and existing KGs through a pre-trained language model. To effectively handle the problem, we utilize two learning methods; one is the classification method of the masked language model (MLM) that predicts a word among a huge vocabulary set with a given context, and the other is multi-task learning based on the Multi-Task for Deep Neural Networks (MT-DNN). Based on the methods, the model first generates an embedding of a new entity using its textual description and then uses the embedding to find one of the existing entities from a KG where the new entity can be connected. The experimental results on three benchmark datasets, DBPedia50k, FB15k-237-OWE, and FB20k, show that the proposed model improves performances by 9.2%p, 4.4%p, and 11.1%p, respectively, and achieves new state-of-the-art performance for all datasets.

Diamond Message Set Groupcasting: From an Inner Bound for the DM Broadcast Channel to the Capacity Region of the Combination Network

Multiple groupcasting over the broadcast channel (BC) is studied in a special setting. In particular, an inner bound is obtained for the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -receiver discrete memoryless (DM) BC for the diamond message set which consists of four groupcast messages: one desired by all receivers, one by all but two receivers, and two more desired by all but each one of those two receivers. The inner bound is based on rate-splitting and superposition coding and is given in explicit form herein as a union over coding distributions of four-dimensional polytopes. This inner bound is then shown to be the capacity for a certain class of partially ordered DM BCs with order defined via the less noisy condition. When specialized to the so- called combination network, which is a class of three-layer (two-hop) broadcast networks parameterized by <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$2^{K}{-}1$ </tex-math></inline-formula> finite-and-arbitrary-capacity noiseless links from the source node in the first layer to as many nodes of the second layer, our top-down approach from the DM BC to the combination network yields an explicit inner bound as a single polytope via the identification of a single coding distribution. This inner bound consists of inequalities which are then identified to be within the class of generalized cut-set outer bounds recently obtained by Salimi et al for broadcast networks. We hence establish the capacity region of the general <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -user combination network for the diamond message set, and do so in explicit and structured form. Such a result implies a certain strength of our inner bound for the DM BC in that it (a) produces a hitherto unknown capacity region when specialized to the combination network and (b) may capture many combinatorial aspects of the capacity region of the <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$K$ </tex-math></inline-formula> -receiver DM BC itself for the diamond message set. Moreover, we extend that inner bound by adding binning to it. As in the no-binning case, we provide the more general inner bound in explicit form.