Android applications are developing rapidly across the mobile ecosystem, but Android malware is also emerging in an endless stream. Many researchers have studied the problem of Android malware detection and have put forward theories and methods from different perspectives. Existing research suggests that machine learning is an effective and promising way to detect Android malware. Notwithstanding, there exist reviews that have surveyed different issues related to Android malware detection based on machine learning. We believe our work complements the previous reviews by surveying a wider range of aspects of the topic. This paper presents a comprehensive survey of Android malware detection approaches based on machine learning. We briefly introduce some background on Android applications, including the Android system architecture, security mechanisms, and classification of Android malware. Then, taking machine learning as the focus, we analyze and summarize the research status from key perspectives such as sample acquisition, data preprocessing, feature selection, machine learning models, algorithms, and the evaluation of detection effectiveness. Finally, we assess the future prospects for research into Android malware detection based on machine learning. This review will help academics gain a full picture of Android malware detection based on machine learning. It could then serve as a basis for subsequent researchers to start new work and help to guide research in the field more generally.
Little
is known about the efficacy of deep brain stimulation (DBS)
as an effective treatment for Parkinson’s Disease (PD) because
of the lack of multichannel neural electrical and chemical detection
techniques at the cellular level. In this study, a 7-mm-long and 250-μm-wide
microelectrode array (MEA) was fabricated to provide real-time monitoring
of dopamine (DA) concentration and neural spike firings in the caudate
putamen (CPU) of rats with PD. Platinumn nanoparticles and reduced
graphene oxide nanocomposites (Pt/rGO) were modified onto the sensitive
microelectrode sites. The detection limit (50 nM) and sensitivity
(8.251 pA/μM) met the specific requirements for DA detection
in vivo. A single neural spike was isolated due to the high signal-to-noise
ratio of the MEA. DBS was applied in the affected side of the globus
pallidus internal (GPi) in PD rats. After DBS, the concentration of
DA in the bilateral CPU increased markedly. The mean increment of
the ipsilateral DA was 7.33 μM (increasing from 0.54 μM
to 7.87 μM), which was 2.2-fold higher than the increment in
the contralateral side. The mean amplitude of neural spikes in the
bilateral CPU decreased more than 10%, and was more obvious in the
ipsilateral side where the spike amplitude changed from 169 μV
to 134 μV. Spike firing rate decreased by 65% (ipsilateral side)
and 51% (contralateral side). The power of the local field potential
decreased to 940 μW (ipsilateral side) and 530 μW (contralateral
side) in 0–30 Hz. Collectively, our data show that the GPi-DBS
plays a significant regulatory role in the bilateral CPU in terms
of DA concentration, spike firing, and power; furthermore, the ipsilateral
variations of the dual mode signals were more significant than those
in the contralateral side. These results provide new detection and
stimulation technology for understanding the mechanisms underlying
Parkinson’s disease and should, therefore, represent a useful
resource for the design of future treatments.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.