Design and implementation of Arduino based robotic arm

<p><span>This study presents the model, design, and construction of the Arduino based robotic arm, which functions across a distance as it is controlled through a mobile application. A six degree of freedom robotic arm has been designed and implemented for the purpose of this research. The design controlled by the Arduino platform receives orders from the user’s mobile application through wireless controlling signals, that is Bluetooth. The arm is made up of five rotary joints and an end effector, where rotary motion is provided by the servomotor. Each link has been first designed using solid works and then printed by 3D printer. The assembly of the parts of the robot and the motor’s mechanical shapes produce the final prototype of the arm. The Arduino has been programmed to provide rotation to each corresponding servo motor to the sliders in the designed mobile application for usage from distance.</span></p>

Develop algorithms to determine the status of car drivers using built-in accelerometer and GBDT

<span>In this paper, we introduce a mobile application called CarSafe, in which data from the acceleration sensor integrated on smartphones is exploited to come up with an efficient classification algorithm. Two statuses, "Driving" or "Not driving," are monitored in the real-time manner. It enables automatic actions to help the driver safer. Also, from these data, our software can detect the crash situation. The software will then automatically send messages with the user's location to their emergency departments for timely assistance. The application will also issue the same alert if it detects a driver of a vehicle driving too long. The algorithm's quality is assessed through an average accuracy of 96.5%, which is better than the previous work (i.e., 93%).</span>

Effect of Artificial Intelligence on Nutritional Status of children post cardiac surgery; A Randomized Controlled Trial (Preprint)

BACKGROUND Malnutrition is the most common problem in congenital heart diseases patients. Health based mobile applications play an important role in planning and tracking of diet for better nutritional status OBJECTIVE To assess the effect of artificial intelligence on nutritional status of children post cardiac surgery in comparison to usual care group. To assess usefulness of diet related mobile application in comparison to usual care group. METHODS This is a two arm randomized controlled trial that was conducted at a Tertiary Care Hospital, Rawalpindi. The study duration was 6 months from February 2021 till July 2021. Sample size was calculated to be 88. Intervention group was given a diet related mobile application and usual care group was handed a pamphlet with diet instructions on discharge. RESULTS Mean weight of all participants was 15 ± 5.7 kg at the time of discharge whereas at the end of 8th week mean weight of the participants in usual care group was 16.5 ± 7.2 kg and intervention group was 17.1 ± 5 kg. Average calories consumed by usual care group was 972 ± 252 kcal and 1000.75 ± 210 kcal by intervention group after 8 weeks of discharge. Average proteins consumed by the usual care group was 34.3 ± 12.5 grams and 39± 6.4 grams by intervention group after 8 weeks of discharge. At the end of intervention preferred diet planning tool for 79% of the participants was mobile application. At 8th week 93% of the participants considered the visual cues useful, 80% think that the mobile application language was understandable, 79% of the participants think nutritional goal setting is a useful feature in mobile application and 55% of the participants think the recipes in the application were useful. CONCLUSIONS The study showed strength for the future of scalable modern technology for self-nutrition monitoring. There was slight increase in the weight and nutritional intake of both groups as interventions period was limited. CLINICALTRIAL Study was registered on clinicaltrial.gov website with trial identity number NCT04782635.

Exploring a Bilingual Next Word Predictor for a Federated Learning Mobile Application

We explore a bilingual next-word predictor (NWP) under federated optimization for a mobile application. A character-based LSTM is server-trained on English and Dutch texts from a custom parallel corpora. This is used as the target performance. We simulate a federated learning environment to assess the feasibility of distributed training for the same model. The popular Federated Averaging (FedAvg) algorithm is used as the aggregation method. We show that the federated LSTM achieves decent performance, yet it is still sub-optimal. We suggest possible next steps to bridge this performance gap. Furthermore, we explore the effects of language imbalance varying the ratio of English and Dutch training texts (or clients). We show the model upholds performance (of the balanced case) up and until a 80/20 imbalance before decaying rapidly. Lastly, we describe the implementation of local client training, word prediction and client-server communication in a custom virtual keyboard for Android platforms. Additionally, homomorphic encryption is applied to provide with secure aggregation guarding the user from malicious servers.

Exploring a Bilingual Next Word Predictor for a Federated Learning Mobile Application

We explore a bilingual next-word predictor (NWP) under federated optimization for a mobile application. A character-based LSTM is server-trained on English and Dutch texts from a custom parallel corpora. This is used as the target performance. We simulate a federated learning environment to assess the feasibility of distributed training for the same model. The popular Federated Averaging (FedAvg) algorithm is used as the aggregation method. We show that the federated LSTM achieves decent performance, yet it is still sub-optimal. We suggest possible next steps to bridge this performance gap. Furthermore, we explore the effects of language imbalance varying the ratio of English and Dutch training texts (or clients). We show the model upholds performance (of the balanced case) up and until a 80/20 imbalance before decaying rapidly. Lastly, we describe the implementation of local client training, word prediction and client-server communication in a custom virtual keyboard for Android platforms. Additionally, homomorphic encryption is applied to provide with secure aggregation guarding the user from malicious servers.

Systematic Review of Mobile Applications to Monitor Symptoms of COVID-19 Using the Mobile Application Rating Scale (Preprint)

BACKGROUND Monitoring acute and long-term symptoms of COVID-19 is critical for personal and public health. Mobile health (mHealth) applications (apps) can be used to support symptom monitoring at the point of need for patients with COVID-19. OBJECTIVE To systematically review and evaluate mHealth apps for quality, functionality, and consistency with guidelines for monitoring symptoms of COVID-19. METHODS We conducted a systematic review of apps for COVID-19 symptom monitoring by searching in two major app stores. The final apps were independently assessed using the Mobile Application Rating Scale (MARS), IMS Institute for Healthcare Informatics functionality score, and guidelines from the Center for Disease Control and World Health Organization. Interrater reliability between the reviewers was calculated. RESULTS A total of 1,017 mobile apps were reviewed and 20 met the inclusion criteria. The majority of the apps (90%, n=18) were designed to track acute COVID-19 symptoms, and only two addressed long-term symptoms. Overall, the apps scored high on quality, with an overall MARS rating of 3.94. The most common functionality among all apps was the instruct function (95%, n=19). The most common symptoms included in the apps for tracking were: fever and dry cough (n=18), aches and pains (n=17), difficulty breathing (n=17), tiredness, sore throat, headache, loss of taste, or smell (n=16), and diarrhea (n=15). CONCLUSIONS mHealth apps designed to monitor symptoms of COVID-19 had high quality, but the majority of apps focused almost exclusively on acute symptoms. Future apps should also incorporate monitoring long-term symptoms of COVID-19. CLINICALTRIAL N/A

EmoMix+: An Approach of Depression Detection Based on Emotion Lexicon for Mobile Application

Emotion lexicon is an important auxiliary resource for text emotion analysis. Previous works mainly focused on positive and negative classification and less on fine-grained emotion classification. Researchers use lexicon-based methods to find that patients with depression express more negative emotions on social media. Emotional characteristics are an effective feature in detecting depression, but the traditional emotion lexicon has limitations in detecting depression and ignores many depression words. Therefore, we build an emotion lexicon for depression to further study the differences between healthy users and patients with depression. The experimental results show that the depression lexicon constructed in this paper is effective and has a better effect of classifying users with depression.

Examination Of Customer Interest In The Use Of The Mandiri Syariah Mobile Application At PT. Bank Syariah Mandiri Bekasi Branch Office

We inspect client premium in the utilization of the Mandiri Syariah Mobile application as a type of improvement in the computerized world at one of the Islamic banks in Indonesia. The reason for this review was to decide the impact of control (age, sex, and experience) on the connection between free factors (execution assumptions, exertion, impact of social beliefs, assistance conditions, decadent inspiration, value esteems ??, and propensities) on the reliant variable (conduct expectations and conduct). utilization conduct) which alludes to the Unified Theory Acceptance and Use of Technology (UTAUT) II model. The technique is a quantitative methodology with an informative examination plan that intends to clarify the factors to be considered and the impact between one variable and another. Social conditions, assistance conditions, indulgent inspiration, value esteems ??, propensities with conduct expectation factors. Given the consequences of the examination, execution assumptions have the most significant relationship, precisely 43.2% on social goals. Subsequently, this review proposes that before expanding the connection between social aims to utilize conduct, PT Bank Syariah Mandiri needs to reinforce the impact of the seven factors on social goals.

A Retrospective Study on “Effectiveness of Remote Patient Monitoring in Covid-19 patients"

Corona virus disease19 has spread over the world, affecting millions of people. It has put enormous strain on the global healthcare system. Due to frequent mutations, the pandemic is spreading rapidly. The world requires a technology that will facilitate the effective diagnosis, treatment, and discharge of COVID19 patients. A model like remote patient monitoring [RPM] makes it easier to handle Covid 19 patients. RPM helps in remotely diagnosis, treatment, as well as allowing for prompt interventions. The RPM makes use of mobile technology and IoT platforms to take clinical interventions. In this study out of 151 covid19 positive subjects 91% of them were shifted to home monitoring within 5 days of MVM monitoring with few readmissions. The study investigated the effectiveness of RPM in the Indian healthcare system, as well as the performance and usability of the Vigocare mobile application by patients and doctors.

Augmented Reality Mobile Application for Children with Autism : Stakeholders’ Acceptance and Thoughts

American Psychiatric Association defined autism spectrum disorder as a neurological disorder due to which a diagnosed child may face difficulty in social communication or have a repeated or restricted set of behaviors. Learners with autism are primarily visual strategy learners, and they tend to learn better through pictures and images. Due to their cognitive disabilities, most learners with autism struggle to acquire new vocabulary. There have been many inventions invented by researchers all over the world to help autistic children with their education; however, not much emphasis put on the interventions that can assist autistic children with their English vocabulary learning process. Hence, this study intends to investigate the stakeholders’ acceptance and thoughts on the use of augmented reality mobile applications for children with autism. This study is a qualitative research study where interviews are used as an instrument to gather stakeholders’ views on the usefulness of the designed and developed augmented reality technology mobile application. This study involved seven respondents who come from different backgrounds and in different field areas. The results have gathered that the designed and developed mobile application has the prospect of helping children with autism with their English language learning process. With further improvements, the designed and developed mobile application is believed to be able to help autistic children to learn English vocabulary in a more exciting yet meaningful manner and at the same time help to spark their interest in their English vocabulary language learning process.