7,898 Hits in 4.6 sec

A First Look at Deep Learning Apps on Smartphones [article]

Mengwei Xu, Jiawei Liu, Yuanqiang Liu, Felix Xiaozhu Lin, Yunxin Liu, Xuanzhe Liu
2021 arXiv   pre-print
To bridge the gap between research and practice, we present the first empirical study on 16,500 the most popular Android apps, demystifying how smartphone apps exploit deep learning in the wild.  ...  On one hand, our findings paint a promising picture of deep learning for smartphones, showing the prosperity of mobile deep learning frameworks as well as the prosperity of apps building their cores atop  ...  In this work, we focus our empirical study on such on-device deep learning for smartphones.  ... 
arXiv:1812.05448v4 fatcat:hyadozcdbza3rf5jwdi5hiqpsa

Self-Detection of Early Breast Cancer Application with Infrared Camera and Deep Learning

Mohammed Abdulla Salim Al Husaini, Mohamed Hadi Habaebi, Teddy Surya Gunawan, Md Rafiqul Islam
2021 Electronics  
A new tool has been adopted based on thermal imaging, deep convolutional networks, health applications on smartphones, and cloud computing for early detection of breast cancer.  ...  Moreover, to verify the proper operation of the app, a set of thermal images was sent from the smartphone to the cloud server from different distances and image acquisition procedures to verify the quality  ...  A comparison of the performance of the three deep learning algorithms implemented on the app is shown in Table 1 below.  ... 
doi:10.3390/electronics10202538 fatcat:evrs4ox7yfctlc4ydaerlzsccq

Service innovation roadmaps and responsible entities learning

Jim Spohrer, G. Di Marzo-Serugendo, M. Drăgoicea, J. Ralyté
2021 ITM Web of Conferences  
Service-Dominant Logic (S-D Logic) and service science provide a way for innovators and learners to look at the world differently and thereby improve quality-of-life for people over time.  ...  This short paper provides context for a research direction to develop further the notions of SIRs and embrace complexity economics as a tool for advancing service science.  ...  Leonard for the invitation to provide a presentation about this topic at IESS 2.1 on March 25, 2021, and the opportunity to create this extended abstract to accompany the presentation [13] .  ... 
doi:10.1051/itmconf/20213801001 fatcat:nmi467y5jrew7ntyxi4cmqsla4

Forensic Insights from Smartphones through Electromagnetic Side-Channel Analysis

Asanka Sayakkara, Nhien-An Le-Khac
2021 IEEE Access  
Later, deep learning models were trained to detect various internal software behaviours running on the SoCs.  ...  Initially, a group of smartphones representing a diverse set of system-on-chip (SoC) processors were used to acquire EM radiation traces.  ...  Therefore, 4 software activities, namely idle device, calendar app, camera app, and email app, were used for training and testing a deep learning model to distinguish between them.  ... 
doi:10.1109/access.2021.3051921 fatcat:4wqs4pyx3nb2ji2ki3qwh5q3ky

Using Deep Neural Network for Android Malware Detection [article]

Abdelmonim Naway, Yuancheng LI
2019 arXiv   pre-print
To contrive with malicious applications that are increased in volume and sophistication, we propose an Android malware detection system that applies deep learning technique to face the threats of Android  ...  Antiviruses software that still relies on a signature-based database that is effective only in identifying known malware.  ...  Dataset Setup For all the experiments, we look at a dataset of real Android apps and malware.  ... 
arXiv:1904.00736v1 fatcat:hdhohtyvqfdbdoccs45tnxpyea

Opening the Doors for Mobile Assisted Language Learning Mobile Apps for ESL : Value and Methods

Fatima Yaqoub Quresh
2017 مجلة جامعة القدس المفتوحة للأبحاث و الدراسات  
How to Utilize Apps and m-learning Getting acquainted with smartphones is the first thing a teacher has to do in order to use in classrooms.  ...  Furthermore, it focuses on embracing applications or apps as a cornerstone in teaching English for their broad availability, deep action and prolonged effect.  ... 
doi:10.12816/0043894 fatcat:ne7zpwfuuzd2bjrrpzf6wwked4

On-Device Deep Learning Inference for Efficient Activity Data Collection

Nattaya Mairittha, Tittaya Mairittha, Sozo Inoue
2019 Sensors  
While mobile and embedded devices are increasingly using deep learning models to infer user context, we propose to exploit on-device deep learning inference using a long short-term memory (LSTM)-based  ...  We compare the proposed method showing estimated activities using on-device deep learning inference with the traditional method showing sentences without estimated activities through smartphone notifications  ...  If we have a look at the confusion matrix of the model's predictions in Figure 4 , we can see that our model performs really well.  ... 
doi:10.3390/s19153434 pmid:31387314 pmcid:PMC6696120 fatcat:nakqwserz5co5lksnjba4uhzye

Editors' Choice—Artificial Intelligence Based Mobile Application for Water Quality Monitoring

Naga Siva Kumar Gunda, Siddharth Hariharan Gautam, Sushanta K. Mitra
2019 Journal of the Electrochemical Society  
sensing parameters and classify the level of the same based on color intensity recognized in the training sets of the captured image using deep convolutional neural networks (CNN).  ...  The automated identification of colors and their intensity from sensor images is a significant interest in field deployable and costeffective smartphone-based water monitoring solutions.  ...  Deep learning is popular due to its simplicity and high accuracy. 0] [31] [32] Whereas, deep learning would require a single model to perform both extraction and classification at once.  ... 
doi:10.1149/2.0081909jes fatcat:epgoqh3yivgynomsqppofsud3m

Simple Smartphone-Based Guiding System for Visually Impaired People

Bor-Shing Lin, Cheng-Che Lee, Pei-Ying Chiang
2017 Sensors  
Therefore, the current study proposes a navigation system for visually impaired people; this system employs a smartphone and deep learning algorithms to recognize various obstacles.  ...  In this study, a computer image recognition system and smartphone application were integrated to form a simple assisted guiding system.  ...  Cheng-Che Lee implemented the Faster R-CNN and YOLO algorithms, and APP. Pei-Ying Chiang provided technical support and conceptual advice.  ... 
doi:10.3390/s17061371 pmid:28608811 pmcid:PMC5492085 fatcat:osxwhnv5vjg27btra53kd5lpd4

Mental health: There's an app for that

Emily Anthes
2016 Nature  
The London-based company's first product is Sleepio, a digital treatment for insomnia that can be accessed online or as a smartphone app.  ...  But when two researchers took a close look at these apps last year, they found that only 4 of the 14 provided any evidence to support their claims 10 .  ... 
doi:10.1038/532020a pmid:27078548 fatcat:wmlh7jyzbvgtznjt3ef5jl5nge

MedicPlant: A mobile application for the recognition of medicinal plants from the Republic of Mauritius using deep learning in real-time

Sameerchand Pudaruth, Mohamad Fawzi Mahomoodally, Noushreen Kissoon, Fadil Chady
2021 IAES International Journal of Artificial Intelligence (IJ-AI)  
A convolutional neural network (CNN) based on the TensorFlow framework has been used to create the classification model. The system has a recognition accuracy of more than 90%.  ...  It is a fast and non-intrusive method to identify medicinal plants.  ...  ACKNOWLEDGEMENTS This material is based on work supported by the tertiary education commission (TEC) under award number INT-2018-16.  ... 
doi:10.11591/ijai.v10.i4.pp938-947 fatcat:ei7tefqcwvdndjjcthdjv6prte

Smartphones, Sensors, and Machine Learning to Advance Real-Time Prediction and Interventions for Suicide Prevention: a Review of Current Progress and Next Steps

John Torous, Mark E. Larsen, Colin Depp, Theodore D. Cosco, Ian Barnett, Matthew K. Nock, Joe Firth
2018 Current Psychiatry Reports  
Recent Findings Advances in smartphone sensing, machine learning methods, and mobile apps directed towards reducing suicide offer promising evidence; however, most of these innovative approaches are still  ...  Purpose of Review As rates of suicide continue to rise, there is urgent need for innovative approaches to better understand, predict, and care for those at high risk of suicide.  ...  A first step is to evaluate the privacy and security of the app.  ... 
doi:10.1007/s11920-018-0914-y pmid:29956120 fatcat:swoe7h3sqnbn7guvlnnd5umi44


Haryadi Haryadi, S, Aprianoto Aprianoto
2020 Journal of Languages and Language Teaching  
In addition, the app brought a positive effect to the establishment of independent learning to a significant number of students.  ...  Forty-eight first-year English department students from two groups of learning involved in this research, aged between 19 to 21. Each group, group A and group B, comprised of 24 students.  ...  In addition, the app is presented with colors, giving more attraction for the learner to look at. Moreover, the color used is not too bright and is safe for eyes to look at even in a quite long time.  ... 
doi:10.33394/jollt.v8i2.2551 fatcat:eijx7tsakfayzld7niy3hbojx4

NAP: Natural App Processing for Predictive User Contexts in Mobile Smartphones

Gabriel S. Moreira, Heeseung Jo, Jinkyu Jeong
2020 Applied Sciences  
Given an arrangement of words, LM can learn how the words are organized in sentences, making it possible to predict the next word given a group of previous words.  ...  A recurrent neural network (RNN) is an artificial neural network associated with sequence models, and it can recognize patterns in sequences. One of the areas that use RNN is language modeling (LM).  ...  Model Details The NAP was developed using a deep learning API written in Python called Keras, running on top of the machine learning platform TensorFlow.  ... 
doi:10.3390/app10196657 fatcat:yv4sopmchjfavdy2kgcespryva

Deep Learning (DL)-Enabled System for Emotional Big Data

Haopeng Wang, Diana P. Tobon V., M. Shamim Hossain, Abdulmotaleb El Saddik
2021 IEEE Access  
The experiments on three strategies showed that the proposed system with deep learning model obtained an accuracy of 95.89%.  ...  The system works with deep learning techniques on emotional big data to extract emotional features and recognize six kinds of facial expressions in real-time and offline.  ...  In the model part, after image preprocessing for the images from dataset, the deep learning model is trained for emotion classification and deployed on a smartphone.  ... 
doi:10.1109/access.2021.3103501 fatcat:pofhf4uov5bgtpjb7o52uhxfgq
« Previous Showing results 1 — 15 out of 7,898 results