28 frames later

PurposeThe purpose of this paper is to analyse the possibilities of mechanical switch replacement by capacitive film touch sensor in applications requiring high reliability and short response time. Advantage of replacing mechanical switch by capacitive touch sensor is no mechanical wear and possible implementation of sensor in application where the switch could not be used or where the flexibility of the sensor substrate is required. The aim of this work is to develop a capacitive touch sensor with the advantage of maximum mechanical resistance, short response time and high sensitivity.Design/methodology/approachBased on various possible sensors layouts, the authors realized 18 different (14 self-capacitance and four mutual capacitance) topologies of capacitive sensor for touch applications. Three different technologies – PCB, LTCC and polymer technology – were used to characterize sensor’s behaviour. For precise characterization of different layouts realized on various substrates, the authors used integrated circuit FDC2214 capacitance-to-digital converter.FindingsSensing range of the capacitive touch (proximity) sensor is affected by the per cent of area covered by the sensor, and it does not depend on topology of sensor. The highest sensing range offers PCB technology. Flexible substrates can be used as proper substituent to rigid PCB.Originality/valueThe novelty of this work lies in finding the touch capacitive sensors that allow shorter switching times compared to standard mechanical switches.

Mobile applications for activity monitoring are regarded as a high potential field for efficient improvement of health care solutions. The measurement of physical activity within every-day conditions should be as easy as using an automatic weighing machine. Up to now physical activity monitoring required special sensor devices and are not suitable for an every day usage. Movement pattern recognition based on acceleration data enables the usage of standard mobile phones for measurement of physical activity. Now, just by carrying a standard phone in a pocket, the device provides information about the type, intensity and duration of the performed activity. Within the project DiaTrace, we developed the method and algorithm to detect activities like walking, jumping, running, cycling or car driving. Based on activity measurement, this application also calculates the consumed calories over the day, shares activity progress with friends or family and might deliver details about different kinds of transportation during a business trip. The DiaTrace application can easily used today by standard phones which are already equipped with the required sensors.

Some studies found that cognitive functions of human beings may be altered while exposed to radiofrequency radiation (RFR) emitted by cellular phones. In two recent studies, we have found that experiment duration and exposure side (i.e., phone's location--right or left) may have a major influence on the detection of such effects. In this brief follow-up experiment, 29 right-handed male subjects were divided into two groups. Each subject had two standard cellular phones attached to both sides of his head. The subjects performed a spatial working memory task that required either a left-hand or a right-hand response under one of the two exposure conditions: left side of the head or right side. Contrary to our previous studies, in this work external antennas located far away from the subjects were connected to the cellular phones. This setup prevents any emission of RFR from the internal antenna, thus drastically reducing RFR exposure. Despite that, the results remain similar to those obtained in our previous work. These results indicate that some of the effects previously attributed to RFR can be the result of some confounders.

We present a novel indoor localisation system that used acoustic sensing. We developed the Acoustic Landmark Locator to determine a person's current room location, within a building. Indoor environments tend to have distinct acoustic properties due to physical structure. Hence rooms in a building can have distinctive acoustic signatures. We found that these acoustic signatures can determine the position of a person. We attempted to identify location based on acoustic sensing of the surrounding indoor environment. We developed a mobile phone application that determined a person's location by measuring the acoustic levels of the surrounding environment. We used a machine learning artificial neural network based algorithm to classify the location of the person, within proximity to a landmark or room. We tested the Acoustic Landmark Locator in an indoor environment. Our tests show that the Acoustic Landmark Locator mobile phone app was able to successfully determine the location of the person carrying the mobile phone, in all test areas. It was also found that background noise caused by the presence of people does distort the landmark acoustic profiles but the artificial neural network based classifier was able to reliably determine the person's room location. Further work will involve investigating how other machine learning approaches can be used to better improve position accuracy.

Poverty is a complex and multidimensional issue that is difficult to measure accurately. While multiple studies have employed traditional econometric methods to analyze poverty, they often overlook the critical roles of electricity, Internet, and cell phone access – factors our study incorporates alongside machine learning to provide deeper and more accurate insights. This study examines the associations between Internet, cell phone, and electricity access and poverty in the poorest region of Luzon, Philippines, aiming to foster connectivity among households to support poverty alleviation. Using probit regression and estimation analyses, we found significant socioeconomic disparities, with many households living below the poverty line. While most households have electricity and cell phones, many lack Internet access. This indicates challenges in infrastructure and digital connectivity that affect living standards and economic opportunities. The analysis reveals important causal relationships between Internet access, cell phone ownership, electricity availability, household size, and the likelihood of being in poverty. Interestingly, the lack of these essential services is linked to higher poverty rates. These results highlight the need for targeted interventions to tackle the root causes of poverty, particularly in bridging the digital divide and improving access to essential services. Machine learning algorithms were employed to effectively predict poverty outcomes based on the results of econometric modeling, where variables with significant coefficients served as a priori inputs. The findings indicate that Extreme Gradient Boosting achieved the lowest mean square error and the highest R2 value among all regression models. Meanwhile, the random forest classifier demonstrated the best overall performance with the highest classification accuracy. The outlined policies support energy affordability, cell phone access, and Internet connectivity through financial aid, solar programs, device provisions, and broadband expansion. Addressing infrastructure gaps and technology access is key to sustainable economic growth, guiding policy makers toward equitable, resilient solutions.

The hands-off detection (HOD) function plays a critical role in accurately identifying driver hand contact in advanced driver assistance systems (ADAS), thereby ensuring system reliability and safety compliance. Capacitive touch pads, which are extensively utilized for this purpose, are prone to various defects arising from their manufacturing process. These defects include pad friction, plating anomalies, pattern deformation, surface scratches, and press gaps. Despite their extensive utilization, a systematic methodology capable of detecting both surface-level and internal microstructural defects remains to be established. The present study proposes a capacitance defect detection algorithm grounded in charge quantity (Q) analysis. A dedicated main control board was developed, integrating signal amplification, analog-to-digital conversion, noise filtering, defect classification logic, and real-time visualization through a graphical user interface (GUI). The system was implemented on an operational automotive production line and validated through the inspection of over 240,000 capacitive touch pads under real-world manufacturing conditions. In this setting, the system successfully identified subtle defects that conventional visual inspection methods failed to detect. The proposed method addresses the limitations of traditional inspection techniques and introduces a structured approach to detecting complex defects in capacitive touch sensors. This research is of practical relevance in industrial settings and contributes a systematic framework for future advancements in HOD system reliability and quality assurance. Subsequent research endeavors will investigate the integration of artificial intelligence (AI) and machine learning techniques to facilitate predictive maintenance and intelligent defect management.

This brief presents a wireless smart glove based on multi-channel capacitive pressure sensors that is able to recognize 10 American Sign Language gestures at the edge. In this system, 16 capacitive sensors are fabricated on a glove to capture the hand gestures. The sensor data is captured by a 16-channel CDMA-like capacitance-to-digital converter for training/inference at the edge device. Unlike the conventional approach where the capacitive information is recovered before further signal processing, our proposed system approach takes advantage of the capability of the machine learning (ML) algorithms and directly processes the code-modulated signals without demodulation. As a result, it reduces the input data throughput fed into the ML algorithms by $20\times $ . The on-site ML implementation significantly reduces decision-making latency and lowers the required data throughput for wireless transmission by at least $4\times $ . The highest testing classification accuracy of our system achieved is 99.7%, with a <0.1% difference from the conventional demodulated sensing scheme.

Over the years, drone usage have become an increasing part of the ever-connected society that we are currently living in. Its usages have proliferated beyond the military sector to various commercial and consumer activities such as package delivery, disaster relief, agriculture and filming. With the rise of Wi-Fi controlled drone. Wi-Fi controlled drone has increased its popularity for personal use due to its affordability, and the ease of operating the drone through smart-devices like mobile phone, tablets and computers. As such, this increases the likelihood of drone presence in various environments, especially in critical government infrastructure, leading to various privacy and security concern by the authorities and the public with malicious intent. Therefore, various signature-based methodology of drone detection has emerged such as the visual and Radio Frequency (RF) signature-based detection method. Visual signature-based detection relies on camera capture and image processing but this is an expensive approach. Whereas, RF signature- based detection relies on the identification of the emission of RF signal by the drone. However, since most commercial electronics devices were built based on Wi-Fi technology, the differentiation of the RF signals transmitted between a drone or a standard Wi-Fi device in a crowded Wi-Fi environment such as a school campus or city area is an challenging task. In this paper, we propose a novel machine learning approach that leverages on the identified unique signatures of Wi-Fi devices in terms of Radio Frequency (RF) and network packets measurement to differentiate the presence of Wi-Fi drone and standard Wi-Fi devices in an urban setting. Furthermore, we also carried out a meticulous pre-processing procedure and a better training scheme of using Stratified K-Fold Cross-Validation (SKFCV), to enhance the richness in the data signature and fully exploit the permutation of the data during training respectively for better performance of the ML models. Two supervised classification Machine Learning (ML) models, namely the Logistic Regression (LR), and Artificial Neural Network (ANN) were applied using the joint data measurements to identify the presence of drone in dense Wi-Fi environment. The experimental results have shown that the proposed novel ML approach of using both RF and network measurement signatures coupled with the pre-processing and training methodology on LR and ANN ML models have outperformed the traditional RF signature-based drone detection ML accuracy results by 15.1% and 21.63% respectively in a crowded Wi-Fi environment.

Women in emerging economies face unique constraints rooted in cultural norms, socio-economic disparities, and limited access to education and technology. Narrowing the digital gender gap by ensuring access to financial services may reduce the economic inequalities for women in these countries. This study examines the influence of digital finance in narrowing the gender gap, guided by the research question: To what extent do digital financial services contribute to narrowing the gender gap in access to and usage of financial services in low-and middle-income economies? Gender inclusion was measured by the ratio of accounts owned by women over the total number of accounts. Digital financial inclusion was constructed based on eight components: mobile money account, storing money in financial institutions, Internet access, mobile phone owned, savings, savings in financial institutions, making or receiving a digital payment, and mobile phone or use of the Internet for shopping. A Bayesian regression approach was computed using the Global Findex Database data for 73 countries classified as low and lower-middle-income economies from 2011 to 2022. The Machine Learning approach evaluates the model’s ability to predict women’s autonomy and the role of digital finance. The results show that digital financial services would reduce the gender gap in low-income economies while augmenting the number of open accounts, especially for women. The results aid in the establishment of policies to reduce the gender gap. These results are relevant to the UNSDG agenda, mainly Goal 5 and Goal 10.

Escherichia coli or E. coli is the dominant pathogen in Urinary Tract Infections (UTIs) in more than 80 % of the cases. Laboratory urine culture is the standard detection method which is expensive and time consuming. This paper studies the possibility of using a capacitive sensor to diagnose UTIs. Experimental tests were carried out to investigate the touch sensor's response to artificially prepared E.coli sample. The capacitive touch sensor gave a consistent result that could be used to design a portable diagnostic device for early detection of UTIs. An exponential response was observed to increasing volume (up to 100 microliter) and E.coli presence in the sample. When the volume reached 100 microliter, the capacitance in average RAW Count Difference value became constant. Urine sample mixed with liquid E. coli gave the highest capacitance change (in average RAW Count Difference value) and the sensitivity at 100 microliter was found to be 22 counts per picofarad (pF).

This focus issue of Physiological Measurement follows the 38th Annual International Computing in Cardiology (CinC) Conference, hosted in Hangzhou, China in September 2011 by Zhejiang University. Each year, the NIH-sponsored PhysioNet resource (http://physionet.org/) runs an open competition lasting several months, aimed at encouraging the development of solutions to an unsolved or poorly solved problem in biomedicine, in most cases making use of relevant clinical and experimental data provided freely by PhysioNet. Participants in these annual challenges discuss their diverse approaches to the Challenge problems during dedicated scientific sessions at CinC. The topics of these PhysioNet/CinC Challenges range from physiologic signal processing and analysis to forecasting and modelling clinically important events and processes.

Recent trends and clustered technology in the IT industries create usage of various hand-held computing devices like mobile phones, digitizer, modem, tablets etc. The Mobile phones are pervasive and inevitable computing devices used for different purposes such as making calls, chart application, games, Online shopping, banking and multimedia broadcasting. To improve its services, many applications are communicating with each other. Example, the banking application may read the OTP message from the messenger automatically leading to security issues. The authorized applications installed in the mobile phones are combined as a group and monitored as secure group communications. Each application in the mobile phone is having its Private Key which is called as Member Key and a common key is shared to all the members in the group which is called as group key. To enhance the security of the group communication, the messages are encrypted using group key and decrypted with member key. In dynamic conditions, the fresh group key is generated whenever there is a change in group strength, directly depending on the computation cost and communication cost because of number of multiplication and key sharing to all the members of the group. Though the Tree Based Key Management System has used to maintain lower computation and communication complexity, this research proposes the novel technique which combines the Tree Based Key Management and Machine Learning Techniques to reduce the key generation cost and correspondingly enrich the key security for information sharing.

In urban regions, individuals predominantly spend their time indoors. Accurately identifying these indoor states is essential for many fields, such as public health and urban planning. Existing methods generally rely on sensors placed at specific locations or on volunteers’ mobile phones, limiting their applicability to those locations and a fraction of the population. To overcome these limitations, we propose a novel framework that leverages cellular signaling data—providing extensive spatio-temporal and population-wide coverage—to identify individuals’ indoor states comprehensively. We extract three types of features: interaction between individuals’ mobile phones and cells, individuals’ moving and stationary, and environmental context. Using these features, we apply three machine learning models—CatBoost, Random Forest (RF) and Support Vector Machine (SVM)—along with an interpretable machine learning model, Associative Tree (AT), to identify the indoor states. Evaluation with a ground truth dataset shows that CatBoost outperforms the other models, with an F1 score of 97.21% in quantifying the time individuals spend indoors. To our knowledge, this is the first study to identify the indoor states of individuals using cellular signaling data. We argue that this study can contribute to advancements in areas such as public health and urban planning.

The release of smart phones equipped with a rich set of sensors has enabled human activity recognition on mobile platforms. Monitoring the daily activities and their levels helps in recognizing the health and wellness of the users as a practical application. Mobile phone’s ubiquity, unobtrusiveness, ease of use, communication channels, and playfulness make mobile phones a suitable platform also for inducing behavior change for a healthier and more active lifestyle. In this paper, we provide a review on the activity recognition systems that use integrated sensors in the mobile phone with a special focus on the systems that target personal health and well-being applications. Initially, we provide background information about the activity recognition process, such as the sensors used, activities targeted, and the steps of activity recognition using machine learning algorithms, before listing the challenges of activity recognition on mobile phones. Next, we focus on the classification of existing work on the topic together with a detailed taxonomy. Finally, we investigate the directions for future research.

Mobile phones have become more popular among all devices, and HTML5-based hybrid applications have become increasingly more famous as a result of their compactness on the various systems. As it is permitted to combine code and data in web technology, code injection attacks like cross-site scripting (XSS) are usually found in HTML5-based applications. Security on mobile phones is a significant issue also. In this paper, convolutional neural network model (CNN) is used to determine whether a hybrid application is normal or vulnerable. JavaScript code of mobile application has been extracted, and abstract syntax tree has been constructed to extract features of the mobile application. Feature selections such as information gain and chi-square test have been used to select appropriate features from the extracted features. Synthetic minority over-sampling technique (SMOTE) is used to balance the data set for doing experiment with different machine learning approaches. Experiments are carried out on 85 mobile applications downloaded, and it is observed that convolutional neural network model with sampling and information gain as feature selection is able to provide better classification accuracy than some machine learning models such as linear support vector classifier (SVC), naive Bayes (NB), and k-nearest neighbor (KNN).KeywordsCode injection attackAbstract syntax treeHybrid applicationSamplingClassifiers