Relevant bibliographies by topics / On device AI

Contents

  1. Journal articles
  2. Dissertations / Theses
  3. Books
  4. Book chapters
  5. Conference papers
  6. Reports

Academic literature on the topic 'On device AI'

Author: Grafiati
Published: 30 June 2021
Last updated: 15 February 2022

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'On device AI.'

Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.

You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.

Journal articles on the topic "On device AI"

1

Kulsha, A. Y., M. A. Klimovich, M. V. Sterjanov, V. N. Tesluk, and N. G. Egorova. "Mechatronic device of AI systems." Doklady BGUIR 18, no. 4 (June 25, 2020): 28–35. http://dx.doi.org/10.35596/1729-7648-2020-18-4-28-35.

Full text
Abstract:
The purpose of this work is to demonstrate the phased development of a mechatronic device, to describe the development process of the device design and software, to demonstrate the application of the theory of selected sections of mathematics and physics in robotics, and, in particular, linear algebra, geometry, computational mathematics, discrete mathematics and mechanics. The study was based on the mechatronic device, which had been designed by the youth team of the Republic of Belarus in preparation for the international robotics competition “First Global Challenge 2019”, which became the winner of this event. The article describes in detail the statement of the problem at this competition, identifies the basic requirements for the robot being built, provides a general description of the stages of building the device both during the design process and during the immediate implementation of the project, as well as substantiates the engineering decisions that were made during the design process. The stages that are of the greatest interest in terms of applying the theory of applied physics and mathematics are described in more detail. Particular attention is paid to the design and development of structural modules, as well as to the development of software for controlling the device. The robot is an experimental model that can be used in further research in the field of artificial intelligence, machine learning, automation systems, and is also a potential platform for teaching robotics at the level of specialized secondary and higher education.
APA, Harvard, Vancouver, ISO, and other styles
2

Mohd Shith Putera, Nurus Sakinatul Fikriah, Sarah Munirah Abdullah, Noraiza Abdul Rahman, Rafizah Abu Hassan, Hartini Saripan, and Imam Haryanto. "Malaysian Medical Device Regulation for Artificial Intelligence in Healthcare: Have all the pieces fallen into position?" Environment-Behaviour Proceedings Journal 6, no. 16 (March 28, 2021): 137–44. http://dx.doi.org/10.21834/ebpj.v6i16.2635.

Full text
Abstract:
Artificial Intelligence (AI) ability of self-learning and adaptation has challenged the medical device regulation in overseeing the safety and effectiveness of medical devices. Thus, this research aims to evaluate the adequacy of the pre-market requirements under the Medical Device Act 2012 in governing AI modification. Employing the doctrinal research methodology, systematic means of legal reasoning pertinent to AI for healthcare applications are produced. An effective medical device regulation is pivotal to foster trustworthiness in the governance and adoption of AI. However, the research findings indicate the deficiency of the current conformity assessment for medical devices in addressing AI modifications. Keywords: Artificial Intelligence and Law, Artificial Intelligence and Medical Device Regulation, Malaysian Medical Device Regulation eISSN: 2398-4287© 2021. The Authors. Published for AMER ABRA cE-Bs by e-International Publishing House, Ltd., UK. This is an open access article under the CC BYNC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). Peer–review under responsibility of AMER (Association of Malaysian Environment-Behaviour Researchers), ABRA (Association of Behavioural Researchers on Asians/Africans/Arabians) and cE-Bs (Centre for Environment-Behaviour Studies), Faculty of Architecture, Planning & Surveying, Universiti Teknologi MARA, Malaysia. DOI: https://doi.org/10.21834/ebpj.v6i16.2635
APA, Harvard, Vancouver, ISO, and other styles
3

Hernandez-Boussard, Tina, Matthew P. Lundgren, and Nigam Shah. "Conflicting information from the Food and Drug Administration: Missed opportunity to lead standards for safe and effective medical artificial intelligence solutions." Journal of the American Medical Informatics Association 28, no. 6 (March 1, 2021): 1353–55. http://dx.doi.org/10.1093/jamia/ocab035.

Full text
Abstract:
Abstract The Food & Drug Administration (FDA) is considering the permanent exemption of premarket notification requirements for several Class I and II medical device products, including several artificial Intelligence (AI)–driven devices. The exemption is based on the need to rapidly more quickly disseminate devices to the public, estimated cost-savings, a lack of documented adverse events reported to the FDA’s database. However, this ignores emerging issues related to AI-based devices, including utility, reproducibility and bias that may not only affect an individual but entire populations. We urge the FDA to reinforce the messaging on safety and effectiveness regulations of AI-based Software as a Medical Device products to better promote fair AI-driven clinical decision tools and for preventing harm to the patients we serve.
APA, Harvard, Vancouver, ISO, and other styles
4

Gutierrez, Gregory M., and Thomas Kaminski. "A Novel Dynamic Ankle-Supinating Device." Journal of Applied Biomechanics 26, no. 1 (February 2010): 114–21. http://dx.doi.org/10.1123/jab.26.1.114.

Full text
Abstract:
Lateral ankle sprains (LAS) are among the most common joint injuries, and although most are resolved with conservative treatment, others develop chronic ankle instability (AI). Considerable attention has been directed toward understanding the underlying causes of this pathology; however, little is known concerning the neuromuscular mechanisms behind AI. A biomechanical analysis of the landing phase of a drop jump onto a device that simulates the mechanism of a LAS may give insight into the dynamic restraint mechanisms of the ankle by individuals with AI. Furthermore, work evaluating subjects who have a history of at least one lateral ankle sprain, yet did not develop AI, may help elucidate compensatory mechanisms following a LAS event. Identifying proper neuromuscular control strategies is crucial in reducing the incidence of AI.
APA, Harvard, Vancouver, ISO, and other styles
5

Kohno, Hiroki, Goro Matsumiya, Yoshiki Sawa, Norihide Fukushima, Yoshikatsu Saiki, Akira Shiose, and Minoru Ono. "Can the intermittent low-speed function of left ventricular assist device prevent aortic insufficiency?" Journal of Artificial Organs 24, no. 2 (January 9, 2021): 191–98. http://dx.doi.org/10.1007/s10047-020-01234-4.

Full text
Abstract:
AbstractAortic insufficiency (AI) is known to associate with a persistently closed aortic valve during continuous-flow ventricular assist device support. Some devices carry an intermittent low-speed (ILS) function, which facilitates aortic valve opening, but whether this function prevents AI is unknown. In this study, the Jarvik 2000 device, which is programmed to reduce the pump speed each minute for 8 s, was chosen to examine this potential effect. Prospectively collected data of 85 heart transplant-eligible Jarvik 2000 recipients who met the study criteria (no pre-existing AI and aortic valve surgery) were retrospectively analyzed for the incidence, correlating factors, and clinical outcomes of de novo AI. All data were provided by the Japanese Registry for Mechanically Assisted Circulatory Support. De novo AI occurred in 58 patients, 23 of whom developed at least moderate AI during a median support duration of 23.5 months. Freedom from moderate or greater AI was 84.4%, 66.1% and 60.2% at 1, 2 and 3 years, respectively. Multivariate analyses revealed that progressive AI was correlated with decreased pulse pressure after implantation (hazard ratio 1.060, 95% confidence interval 1.001–1.127, p = 0.045). No correlation was found for mortality or other adverse events, including stroke, bleeding, infection, pump failure, hemolysis, and readmission. The benefit of the Jarvik 2000′s current ILS mode against AI appears to be minimal. However, in this limited cohort where all recipients underwent implantation as a bridge to transplantation, the impact of de novo progressive AI on other clinical adversities was also minimal.
APA, Harvard, Vancouver, ISO, and other styles
6

Zoppo, Gianluca, Francesco Marrone, Monica Pittarello, Marco Farina, Alberto Uberti, Danilo Demarchi, Jacopo Secco, Fernando Corinto, and Elia Ricci. "AI technology for remote clinical assessment and monitoring." Journal of Wound Care 29, no. 12 (December 2, 2020): 692–706. http://dx.doi.org/10.12968/jowc.2020.29.12.692.

Full text
Abstract:
Objective: To report the clinical validation of an innovative, artificial intelligence (AI)-powered, portable and non-invasive medical device called Wound Viewer. The AI medical device uses dedicated sensors and AI algorithms to remotely collect objective and precise clinical data, including three-dimensional (3D) wound measurements, tissue composition and wound classification through the internationally recognised Wound Bed Preparation (WBP) protocol; this data can then be shared through a secure General Data Protection Regulation (GDPR)- and Health Insurance Portability and Accountability Act (HIPAA)-compliant data transfer system. This trial aims to test the reliability and precision of the AI medical device and its ability to aid health professionals in clinically evaluating wounds as efficiently remotely as at the bedside. Method: This non-randomised comparative clinical trial was conducted in the Clinica San Luca (Turin, Italy). Patients were divided into three groups: (i) patients with venous and arterial ulcers in the lower limbs; (ii) patients with diabetes and presenting with diabetic foot syndrome; and (iii) patients with pressure ulcers. Each wound was evaluated for area, depth, volume and WBP wound classification. Each patient was examined once and the results, analysed by the AI medical device, were compared against data obtained following visual evaluation by the physician and research team. The area and depth were compared with a Kruskal–Wallis one-way analysis of variations in the obtained distribution (expected p-value>0.1 for both tests). The WBP classification and tissue segmentation were analysed by directly comparing the classification obtained by the AI medical device against that of the testing physician. Results: A total of 150 patients took part in the trial. The results demonstrated that the AI medical device's AI algorithm could acquire objective clinical parameters in a completely automated manner. The AI medical device reached 97% accuracy against the WBP classification and tissue segmentation analysis compared with that performed in person by the physician. Moreover, data regarding the measurements of the wounds, as analysed through the Kruskal–Wallis technique, showed that the data distribution proved comparable with the other methods of measurement previously clinically validated in the literature (p=0.9). Conclusion: These findings indicate that remote wound assessment undertaken by physicians is as effective through the AI medical device as bedside examination, and that the device was able to assess wounds and provide a precise WBP wound classification. Furthermore, there was no need for manual data entry, thereby reducing the risk of human error while preserving high-quality clinical diagnostic data.
APA, Harvard, Vancouver, ISO, and other styles
7

Zwiefelhofer, E. M., S. X. Yang, M. Asai-Coakwell, M. G. Colazo, J. Hellquist, M. L. Zwiefelhofer, M. Anzar, and G. P. Adams. "118 A comparison of intravaginal progesterone devices for fixed-time artificial insemination in beef cattle." Reproduction, Fertility and Development 33, no. 2 (2021): 167. http://dx.doi.org/10.1071/rdv33n2ab118.

Full text
Abstract:
Intravaginal progesterone (P4) devices used for ovarian synchronization before fixed-time AI (FTAI) differ in drug release, which may influence fertility outcome. A 2×2 study was designed to determine the effects of different intravaginal devices (PRID Delta, 1.55g of P4 vs. CIDR, 1.38g of P4) and parity (heifers vs. cows) on follicular dynamics, expression of oestrus, and pregnancy per AI (P/AI). At random stages of the oestrous cycle, nulliparous beef heifers and lactating cows were given 100µg of gonadorelin (gonadotrophin-releasing hormone, GnRH) intramuscularly (IM) and assigned randomly to either the PRID (n=76 heifers, 76 multiparous, 27 primiparous) or CIDR (n=76 heifers, 73 multiparous, 32 primiparous) group. Devices were removed 5 days later, an oestrus-detection patch was applied just cranial to the tail head, and 500µg of cloprostenol was given IM at the time of device removal and again 24h later. At 72h after device removal, cattle were inseminated and given 100µg of GnRH IM. Transrectal ultrasonography was used to determine the diameter of the largest follicle on the day of device removal and at FTAI, ovulation time, and pregnancy status 30 days after FTAI. A colour change of ≥50% of the oestrus-detection patch at FTAI was taken as expression of oestrus. Data were compared among groups by 2-way ANOVA using MIXED and GLIMMIX procedures. There were no interactions between P4 device and parity for any endpoint. The diameter of the largest follicle (mean±s.e.m.) was not different between PRID and CIDR groups on either the day of device removal (10.6±0.1 vs. 10.9±0.1mm) or the day of FTAI (13.7±0.1 vs. 13.9±0.1mm). The proportion displaying oestrus did not differ between P4 device groups, but was greater in heifers than in cows [121/152 (79.6%) vs. 135/207 (65.2%); P<0.01], and the interval from FTAI to ovulation was shorter in heifers than in cows (27.8±1.2 vs. 32.0±1.1 h; P=0.01). The P/AI was not different between P4 device groups or parity groups (overall 67.0%, 238/355). However, among lactating cows, the P/AI tended to be greater in the PRID vs. CIDR group [75/102 (73.5%) vs. 64/105 (61.0%); P=0.10], and was greater in multiparous vs. primiparous cows [106/148 (71.6%) vs. 33/59 (55.9%); P=0.04]. Among cattle that displayed oestrus, the P/AI tended to be greater in the PRID vs. CIDR group [92/123 (74.8%) vs. 85/131 (64.9%); P=0.09]. Among lactating cows that displayed oestrus, the P/AI was greater in multiparous vs. primiparous cows [74/94 (78.2%) vs. 24/42 (57.1%); P<0.01]. In summary, follicular dynamics and expression of oestrus did not differ between PRID and CIDR groups, but the P/AI tended to be greater in PRID-treated lactating cows and in cattle that displayed oestrus. This research was supported by CEVA Animal Health, Saskatchewan ADF, Agriculture and Agri-Foods Canada, and Rockway Inc.
APA, Harvard, Vancouver, ISO, and other styles
8

Zwiefelhofer, E. M., S. X. Yang, M. Asai-Coakwell, M. G. Colazo, J. Hellquist, M. L. Zwiefelhofer, M. Anzar, and G. P. Adams. "118 A comparison of intravaginal progesterone devices for fixed-time artificial insemination in beef cattle." Reproduction, Fertility and Development 33, no. 2 (2021): 167. http://dx.doi.org/10.1071/rdv33n2ab118.

Full text
Abstract:
Intravaginal progesterone (P4) devices used for ovarian synchronization before fixed-time AI (FTAI) differ in drug release, which may influence fertility outcome. A 2×2 study was designed to determine the effects of different intravaginal devices (PRID Delta, 1.55g of P4 vs. CIDR, 1.38g of P4) and parity (heifers vs. cows) on follicular dynamics, expression of oestrus, and pregnancy per AI (P/AI). At random stages of the oestrous cycle, nulliparous beef heifers and lactating cows were given 100µg of gonadorelin (gonadotrophin-releasing hormone, GnRH) intramuscularly (IM) and assigned randomly to either the PRID (n=76 heifers, 76 multiparous, 27 primiparous) or CIDR (n=76 heifers, 73 multiparous, 32 primiparous) group. Devices were removed 5 days later, an oestrus-detection patch was applied just cranial to the tail head, and 500µg of cloprostenol was given IM at the time of device removal and again 24h later. At 72h after device removal, cattle were inseminated and given 100µg of GnRH IM. Transrectal ultrasonography was used to determine the diameter of the largest follicle on the day of device removal and at FTAI, ovulation time, and pregnancy status 30 days after FTAI. A colour change of ≥50% of the oestrus-detection patch at FTAI was taken as expression of oestrus. Data were compared among groups by 2-way ANOVA using MIXED and GLIMMIX procedures. There were no interactions between P4 device and parity for any endpoint. The diameter of the largest follicle (mean±s.e.m.) was not different between PRID and CIDR groups on either the day of device removal (10.6±0.1 vs. 10.9±0.1mm) or the day of FTAI (13.7±0.1 vs. 13.9±0.1mm). The proportion displaying oestrus did not differ between P4 device groups, but was greater in heifers than in cows [121/152 (79.6%) vs. 135/207 (65.2%); P<0.01], and the interval from FTAI to ovulation was shorter in heifers than in cows (27.8±1.2 vs. 32.0±1.1 h; P=0.01). The P/AI was not different between P4 device groups or parity groups (overall 67.0%, 238/355). However, among lactating cows, the P/AI tended to be greater in the PRID vs. CIDR group [75/102 (73.5%) vs. 64/105 (61.0%); P=0.10], and was greater in multiparous vs. primiparous cows [106/148 (71.6%) vs. 33/59 (55.9%); P=0.04]. Among cattle that displayed oestrus, the P/AI tended to be greater in the PRID vs. CIDR group [92/123 (74.8%) vs. 85/131 (64.9%); P=0.09]. Among lactating cows that displayed oestrus, the P/AI was greater in multiparous vs. primiparous cows [74/94 (78.2%) vs. 24/42 (57.1%); P<0.01]. In summary, follicular dynamics and expression of oestrus did not differ between PRID and CIDR groups, but the P/AI tended to be greater in PRID-treated lactating cows and in cattle that displayed oestrus. This research was supported by CEVA Animal Health, Saskatchewan ADF, Agriculture and Agri-Foods Canada, and Rockway Inc.
APA, Harvard, Vancouver, ISO, and other styles
9

López-Helguera, Irene, Fernando López-Gatius, Irina Garcia-Ispierto, Beatriz Serrano-Perez, and Marcos G. Colazo. "Effect of PRID-Delta devices associated with shortened estrus synchronization protocols on estrous response and fertility in dairy cows." Annals of Animal Science 17, no. 3 (July 26, 2017): 757–70. http://dx.doi.org/10.1515/aoas-2016-0083.

Full text
Abstract:
Abstract This study evaluated the effect of a once-used progesterone (P4) intravaginal device (PRID) associated with four different shortened P4-based estrus synchronization (ES) protocols on estrous response (ER) and pregnancy per AI (P/AI) in cyclic and acyclic lactating dairy cows. Cows (n=465) were randomly assigned to one of the following protocols: 1) 2PGG, cows were given a PRID-Delta and 100 μg GnRH i.m. at PRID insertion (day 0). The PRID was left for 5 d, and 25 mg of dinoprost (PGF2α) i.m. given twice at PRID removal and 24 h later; 2) 2PGGe, same treatments as 2PGG plus 500 IU of eCG i.m. at PRID removal; 3) 2PGe, same treatments as 2PGGe, except GnRH was not given at PRID insertion; 4) PGe, same treatments as 2PGe, except PGF was only given at PRID removal. A total of 258 cows received a new PRID-Delta containing 1.55 g of P4, whereas 207 cows received a once-used PRID. Estrus was determined from P4 device removal until 96 h after using an automated heat detection system. Cows in estrus were given a second GnRH at AI and those without signs of estrus by 96 h after PRID removal were given GnRH and timed-AI (TA I). All inseminations were performed by one technician with commercially available frozen-thawed semen. Ultrasonography was performed at initiation of protocol and 28-34 days post AI to determine cyclicity and pregnancy status, respectively. Cows receiving once-used P4 devices had greater ER than cows receiving a new device (59.9 vs. 50.0; P=0.029), but P/AI did not differ between P4 devices, respectively (P>0.1; 40.6 vs 40.7%). Cyclic cows were less likely to display estrus than acyclic cows by a factor of 0.66 (P=0.036). Cows subjected to the 2PGe (2.41; P<0.01) protocol were more likely to display estrus than cows subjected to the 2PGG, whereas cows subjected to the PGe protocol did not differ (0.94; P=0.8) from those in the 2PGG group. Despite differences in ER, neither cyclicity nor estrus synchronization protocol affected P/AI (overall 40.6%). In summary, cyclic cows, those given a new P4 device and those subjected to either 2PGG or PGe protocol had reduced ER. However, all the factors examined had no significant effect on P/AI. All the estrus synchronization protocols resulted in acceptable fertility.
APA, Harvard, Vancouver, ISO, and other styles
10

Park, Seong Ho, Jaesoon Choi, and Jeong-Sik Byeon. "Key principles of clinical validation, device approval, and insurance coverage decisions of artificial intelligence." Journal of the Korean Medical Association 63, no. 11 (November 10, 2020): 696–708. http://dx.doi.org/10.5124/jkma.2020.63.11.696.

Full text
Abstract:
Artificial intelligence (AI) will likely affect various fields of medicine. This article aims to explain the fundamental principles of clinical validation, device approval, and insurance coverage decisions of AI algorithms for medical diagnosis and prediction. Discrimination accuracy of AI algorithms is often evaluated with the Dice similarity coefficient, sensitivity, specificity, and traditional or free-response receiver operating characteristic curves. Calibration accuracy should also be assessed, especially for algorithms that provide probabilities to users. As current AI algorithms have limited generalizability to real-world practice, clinical validation of AI should put it to proper external testing and assisting roles. External testing could adopt diagnostic case-control or diagnostic cohort designs. A diagnostic case-control study evaluates the technical validity/accuracy of AI while the latter tests the clinical validity/accuracy of AI in samples representing target patients in real-world clinical scenarios. Ultimate clinical validation of AI requires evaluations of its impact on patient outcomes, referred to as clinical utility, and for which randomized clinical trials are ideal. Device approval of AI is typically granted with proof of technical validity/accuracy and thus does not intend to directly indicate if AI is beneficial for patient care or if it improves patient outcomes. Neither can it categorically address the issue of limited generalizability of AI. After achieving device approval, it is up to medical professionals to determine if the approved AI algorithms are beneficial for real-world patient care. Insurance coverage decisions generally require a demonstration of clinical utility that the use of AI has improved patient outcomes.
APA, Harvard, Vancouver, ISO, and other styles
More sources

Dissertations / Theses on the topic "On device AI"

1

TRIACCA, SERENA. "DIDATTICA DELL'IMMAGINE. DALLA FOTOGRAFIA AI DIGITAL DEVICE." Doctoral thesis, Università Cattolica del Sacro Cuore, 2016. http://hdl.handle.net/10280/10969.

Full text
Abstract:
La presente ricerca intende portare l'attenzione sulla necessità di integrare in maniera consape-vole le immagini nelle pratiche didattiche e di fondarne l'uso sul piano neuroscientifico. Da sempre l'insegnante se ne serve per supportare l'esposizione orale, per rendere visibili e si-tuati i concetti, per facilitare la messa a fuoco di elementi rilevanti. Gli studi sul cervello visivo (ci riferiamo in particolare alla teoria della visione del neurobiolo-go Semir Zeki) rendono ragione a ciò che l'insegnante ha sempre saputo: fornire ai discenti una rappresentazione grafica o iconica di un determinato concetto, tema, argomento sostiene il lavoro del cervello, normalmente impegnato in una ricerca dell'essenziale, entro il fluire incessante del mondo. La rappresentazione proposta dall'insegnante consentirebbe dunque di lavorare su uno scenario semplificato, favorendo la comprensione dell'oggetto dell'insegnamento da parte dell'alunno. Alcune tipologie di immagini, tuttavia, non riducono la complessità, a causa della propria "ambiguità semantica": molte interpretazioni sarebbero possibili, tutte egualmente valide. Tale caratteristica potrebbe essere sfruttata dall'insegnante al fine di accendere la curiosità, stimolare la discussione, la presa di posizione, la riflessione, la costruzione di ipotesi interpretative. Tramite quattro studi di caso, si è inteso fare luce sulle concrete modalità di impiego della fotografia (fruita e prodotta) nella scuola primaria. A partire dalle riflessioni pedagogiche stimolate dai casi, la ricerca si propone di aggiornare il quadro di consapevolezze della ricerca didattica relativamente all'uso delle immagini fotografi-che in classe, fornendo alcuni suggerimenti per integrarle nella didattica e operando in ultima battuta una mappatura di applicativi digitali che consentano di lavorare con e sulle immagini.
This research project aims to focus on the need of conscious pictures' integration into the teaching and learning activities (TLA) and to base the use at a neuroscientific level. The teacher usually adopts visuals to support oral presentations, to make the concepts clear and situated, to facilitate focusing of relevant elements. Studies on the visual brain (mainly referring to the recent theory of vision by neurobiologist Semir Zeki) validate what the teacher has always known: providing learners with visuals of a particular concept, theme, topic supports the brain's work, normally engaged in looking for the essential, within the non-stop flow of the world. The teacher's representations would enable the pupils' brain to work on a simplified scenario, facilitating the understanding of the object of teaching. However, certain kinds of images do not reduce the complexity, because of their "semantic ambiguity": many interpretations would be possible, all equally strong. The teacher could take advantage of this feature in order to turn on the curiosity, to encourage the discussion, the reflective thinking or interpretative hypothesis. Through four case studies, we aimed to explore the actual use of photography in primary school. Starting from the pedagogical reflections about the cases, the research intends to increase the educational research's awareness about the use of photographic images in the classroom, sug-gesting some tips for designing TLA and developing a review of appropriate digital apps.
APA, Harvard, Vancouver, ISO, and other styles
2

Kim, Sun Ho. "Role of AI-2 in oral biofilm formation using microfluidic devices." [College Station, Tex. : Texas A&M University, 2008. http://hdl.handle.net/1969.1/ETD-TAMU-2665.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Björklund, Pernilla. "The curious case of artificial intelligence : An analysis of the relationship between the EU medical device regulations and algorithmic decision systems used within the medical domain." Thesis, Uppsala universitet, Juridiska institutionen, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-442122.

Full text
Abstract:
The healthcare sector has become a key area for the development and application of new technology and, not least, Artificial Intelligence (AI). New reports are constantly being published about how this algorithm-based technology supports or performs various medical tasks. These illustrates the rapid development of AI that is taking place within healthcare and how algorithms are increasingly involved in systems and medical devices designed to support medical decision-making.  The digital revolution and the advancement of AI technologies represent a step change in the way healthcare may be delivered, medical services coordinated and well-being supported. It could allow for easier and faster communication, earlier and more accurate diagnosing and better healthcare at lower costs. However, systems and devices relying on AI differs significantly from other, traditional, medical devices. AI algorithms are – by nature – complex and partly unpredictable. Additionally, varying levels of opacity has made it hard, sometimes impossible, to interpret and explain recommendations or decisions made by or with support from algorithmic decision systems. These characteristics of AI technology raise important technological, practical, ethical and regulatory issues. The objective of this thesis is to analyse the relationship between the EU regulation on medical devices (MDR) and algorithmic decision systems (ADS) used within the medical domain. The principal question is whether the MDR is enough to guarantee safe and robust ADS within the European healthcare sector or if complementary (or completely different) regulation is necessary. In essence, it will be argued that (i) while ADS are heavily reliant on the quality and representativeness of underlying datasets, there are no requirements with regard to the quality or composition of these datasets in the MDR, (ii) while it is believed that ADS will lead to historically unprecedented changes in healthcare , the regulation lacks guidance on how to manage novel risks and hazards, unique to ADS, and that (iii) as increasingly autonomous systems continue to challenge the existing perceptions of how safety and performance is best maintained, new mechanisms (for transparency, human control and accountability) must be incorporated in the systems. It will also be found that the ability of ADS to change after market certification, will eventually necessitate radical changes in the current regulation and a new regulatory paradigm might be needed.
APA, Harvard, Vancouver, ISO, and other styles
4

Milette, Greg P. "Analogical matching using device-centric and environment-centric representations of function." Link to electronic thesis, 2006. http://www.wpi.edu/Pubs/ETD/Available/etd-050406-145255/.

Full text
Abstract:
Thesis (M.S.)--Worcester Polytechnic Institute.
Keywords: Analogy, Design, Functional Modeling, Functional Reasoning, Knowledge Representation, Repertory Grid, SME, Structure Mapping Engine, AI in design. Includes bibliographical references (p.106).
APA, Harvard, Vancouver, ISO, and other styles
5

Ringenson, Josefin. "Efficiency of CNN on Heterogeneous Processing Devices." Thesis, Linköpings universitet, Programvara och system, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-155034.

Full text
Abstract:
In the development of advanced driver assistance systems, computer vision problemsneed to be optimized to run efficiently on embedded platforms. Convolutional neural network(CNN) accelerators have proven to be very efficient for embedded camera platforms,such as the ones used for automotive vision systems. Therefore, the focus of this thesisis to evaluate the efficiency of a CNN on a future embedded heterogeneous processingdevice. The memory size in an embedded system is often very limited, and it is necessary todivide the input into multiple tiles. In addition, there are power and speed constraintsthat needs to be met to be able to use a computer vision system in a car. To increaseefficiency and optimize the memory usage, different methods for CNN layer fusion areproposed and evaluated for a variety of tile sizes. Several different layer fusion methods and input tile sizes are chosen as optimal solutions,depending on the depth of the layers in the CNN. The solutions investigated inthe thesis are most efficient for deep CNN layers, where the number of channels is high.
APA, Harvard, Vancouver, ISO, and other styles
6

Hettiarachchi, Salinda. "Analysis of different face detection andrecognition models for Android." Thesis, Mittuniversitetet, Institutionen för informationssystem och –teknologi, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-42446.

Full text
Abstract:
Human key point tracking such as face detection and recognition has become an increasingly popular research topic. It is a platform independent functionality and already being implemented on a wide range of platforms. Android is one such platform that runs on mobile phones and top of many edge devices such as car devices and smart home appliances. In the current times, AI and ML related applications are slightly moving into those edge devices due to various reasons such as security and low latency. The hardware enhancements are also backing this trend that happened over the last few years. Many solutions and algorithms have been proposed in this context, and various frameworks and models have also been developed. Even though there are different models available, they tend to deliver varying results in terms of performance. Evaluating these different alternatives to find an optimized solution is a problem worth addressing. In this thesis project, several selected face detection and recognition models have been implemented in an Android device, and their performance been evaluated. Google ML Kit showed the best results among the face detection methods since it took only around 68 milliseconds on average to detect a face. Out of the three face recognition algorithms evaluated, FaceNet was the most accurate as it showed an accuracy above 95% for most cases. Meanwhile, MobileFaceNet was the fastest algorithm, and it took only around 90 milliseconds on average to produce and output. Eventually, a face recognition application was also developed using the best performing models selected from the experiment.
APA, Harvard, Vancouver, ISO, and other styles
7

Nardello, Matteo. "Low-Power Smart Devices for the IoT Revolution." Doctoral thesis, Università degli studi di Trento, 2020. http://hdl.handle.net/11572/274371.

Full text
Abstract:
Internet of Things (IoT) is a revolutionary paradigm approaching both industries and consumers everyday life. It refers to a network of addressable physical objects that contain embedded sensing, communication and actuating technologies, to sense and interact with the environment where being deployed. It can be considered as a modern expression of Mark Weiser's vision of ubiquitous computing where tiny networked computers become part of everyday objects, fusing together the virtual world and the physical word. Recent advances in hardware solutions have led to the emergence of powerful wireless IoT systems that are entirely energy-autonomous. These systems extract energy from their environment and operate intermittently, only as power is available. Battery-less sensors present an opportunity for the pervasive wide-spread of remote sensor deployments that require little maintenance and have low cost. As the number of IoT endpoint grows -- industry forecast trillions of connected smart devices in the next few years -- new challenges to program, manage and maintain such a huge number of connected devices are emerging. Web technologies can significantly ease this process by providing well-known patterns and tools - like cloud computing - for developers and users. However, the existing solutions are often too heavyweight or unfeasible for highly resource-constrained IoT devices. This dissertation presents a comprehensive analysis of two of the biggest problems that the IoT is currently facing: R1) How are we going to provide connectivity to all these devices? R2) How can we improve the quality of service provided by these tiny autonomous motes that rely only on limited energy scavenged from the environment? The first contribution is the study and deployment of a Low-Power Wide-Area-Network as a feasible solution to provide connectivity to all the expected IoT devices to be deployed in the following years. The proposed technology offers a novel communication paradigm to address discrete IoT applications, like long-range (i.e., kilometers) at low-power (i.e., tens of mW). Moreover, results highlight the effectiveness of the technology also in the industrial environment thanks to the high immunity to external noises. In the second contribution, we focus on smart metering presenting the design of three smart energy meters targeted to different scenarios. The first design presents an innovative, cost-effective smart meter with embedded non-intrusive load monitoring capabilities intended for the domestic sector. This system shows an innovative approach to provide useful feedback to reduce and optimize household energy consumption. We then present a battery-free non-intrusive power meter targeted for low-cost energy monitoring applications that lower both installation cost due to the non-intrusive approach and maintenance costs associated to battery replacement. Finally, we present an energy autonomous smart sensor with load recognition capability that dynamically adapts and reconfigures its processing pipeline to the sensed energy consumption. This enables the sensor to be energy neutral, while still providing power consumption information every 5 minutes. In the third contribution, we focus on the study of low-power visual edge processing and edge machine learning for the IoT. Two different implementations are presented. The first one discusses an energy-neutral IoT device for precision agriculture, while the second one presents a battery-less long-range visual IoT system, both leveraging on deep learning algorithms to avoid unnecessary wireless data communication. We show that there is a clear benefit from implementing a first layer of data processing directly in-situ where the data is acquired, providing a higher quality of service to the implemented application.
APA, Harvard, Vancouver, ISO, and other styles
8

Fredriksson, Tomas, and Rickard Svensson. "Analysis of machine learning for human motion pattern recognition on embedded devices." Thesis, KTH, Mekatronik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-246087.

Full text
Abstract:
With an increased amount of connected devices and the recent surge of artificial intelligence, the two technologies need more attention to fully bloom as a useful tool for creating new and exciting products. As machine learning traditionally is implemented on computers and online servers this thesis explores the possibility to extend machine learning to an embedded environment. This evaluation of existing machine learning in embedded systems with limited processing capa-bilities has been carried out in the specific context of an application involving classification of basic human movements. Previous research and implementations indicate that it is possible with some limitations, this thesis aims to answer which hardware limitation is affecting clas-sification and what classification accuracy the system can reach on an embedded device. The tests included human motion data from an existing dataset and included four different machine learning algorithms on three devices. Support Vector Machine (SVM) are found to be performing best com-pared to CART, Random Forest and AdaBoost. It reached a classification accuracy of 84,69% between six different included motions with a clas-sification time of 16,88 ms per classification on a Cortex M4 processor. This is the same classification accuracy as the one obtained on the host computer with more computational capabilities. Other hardware and machine learning algorithm combinations had a slight decrease in clas-sification accuracy and an increase in classification time. Conclusions could be drawn that memory on the embedded device affect which al-gorithms could be run and the complexity of data that can be extracted in form of features. Processing speed is mostly affecting classification time. Additionally the performance of the machine learning system is connected to the type of data that is to be observed, which means that the performance of different setups differ depending on the use case.
Antalet uppkopplade enheter ökar och det senaste uppsvinget av ar-tificiell intelligens driver forskningen framåt till att kombinera de två teknologierna för att både förbättra existerande produkter och utveckla nya. Maskininlärning är traditionellt sett implementerat på kraftfulla system så därför undersöker den här masteruppsatsen potentialen i att utvidga maskininlärning till att köras på inbyggda system. Den här undersökningen av existerande maskinlärningsalgoritmer, implemen-terade på begränsad hårdvara, har utförts med fokus på att klassificera grundläggande mänskliga rörelser. Tidigare forskning och implemen-tation visar på att det ska vara möjligt med vissa begränsningar. Den här uppsatsen vill svara på vilken hårvarubegränsning som påverkar klassificering mest samt vilken klassificeringsgrad systemet kan nå på den begränsande hårdvaran. Testerna inkluderade mänsklig rörelsedata från ett existerande dataset och inkluderade fyra olika maskininlärningsalgoritmer på tre olika system. SVM presterade bäst i jämförelse med CART, Random Forest och AdaBoost. Den nådde en klassifikationsgrad på 84,69% på de sex inkluderade rörelsetyperna med en klassifikationstid på 16,88 ms per klassificering på en Cortex M processor. Detta är samma klassifikations-grad som en vanlig persondator når med betydligt mer beräknings-resurserresurser. Andra hårdvaru- och algoritm-kombinationer visar en liten minskning i klassificeringsgrad och ökning i klassificeringstid. Slutsatser kan dras att minnet på det inbyggda systemet påverkar vilka algoritmer som kunde köras samt komplexiteten i datan som kunde extraheras i form av attribut (features). Processeringshastighet påverkar mest klassificeringstid. Slutligen är prestandan för maskininlärningsy-stemet bunden till typen av data som ska klassificeras, vilket betyder att olika uppsättningar av algoritmer och hårdvara påverkar prestandan olika beroende på användningsområde.
APA, Harvard, Vancouver, ISO, and other styles
9

Arnesson, Pontus, and Johan Forslund. "Edge Machine Learning for Wildlife Conservation : Detection of Poachers Using Camera Traps." Thesis, Linköpings universitet, Reglerteknik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-177483.

Full text
Abstract:
This thesis presents how deep learning can be utilized for detecting humans ina wildlife setting using image classification. Two different solutions have beenimplemented where both of them use a camera-equipped microprocessor to cap-ture the images. In one of the solutions, the deep learning model is run on themicroprocessor itself, which requires the size of the model to be as small as pos-sible. The other solution sends images from the microprocessor to a more pow-erful computer where a larger object detection model is run. Both solutions areevaluated using standard image classification metrics and compared against eachother. To adapt the models to the wildlife environment,transfer learningis usedwith training data from a similar setting that has been manually collected andannotated. The thesis describes a complete system’s implementation and results,including data transfer, parallel computing, and hardware setup. One of the contributions of this thesis is an algorithm that improves the classifi-cation performance on images where a human is far away from the camera. Thealgorithm detects motion in the images and extracts only the area where thereis movement. This is specifically important on the microprocessor, where theclassification model is too simple to handle those cases. By only applying theclassification model to this area, the task is more simple, resulting in better per-formance. In conclusion, when integrating this algorithm, a model running onthe microprocessor gives sufficient results to run as a camera trap for humans.However, test results show that this implementation is still quite underperform-ing compared to a model that is run on a more powerful computer.
APA, Harvard, Vancouver, ISO, and other styles
10

Chen, Wei-Hao, and 陳韋豪. "Circuit Techniques for energy-efficient ReRAM based Non-volatile computing-in-memory macros in AI edge device." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/xk7ux3.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Books on the topic "On device AI"

1

Majer, Katalin, and Luigi Sirianni, eds. Azienda Ospedaliera Universitaria Meyer. Attività sanitaria e scientifica 2011. Florence: Firenze University Press, 2013. http://dx.doi.org/10.36253/978-88-6655-378-6.

Full text
Abstract:
La Relazione sull'attività sanitaria e scientifica dell'Azienda Ospedaliera Universitaria Meyer è uno strumento prezioso di condivisione e diffusione delle informazioni che sintetizzano il modo di lavorare, i risultati e le linee di miglioramento su cui bisogna particolarmente impegnarsi. È uno strumento di conoscenza e di valutazione rivolto, quindi, sia all'interno, sia all'esterno dell'Ospedale. Uno strumento dinamico, che deve perfezionarsi, contestualmente ai miglioramenti perseguiti dall'Ospedale.
APA, Harvard, Vancouver, ISO, and other styles
2

Majer, Katalin, and Luigi Sirianni, eds. Azienda Ospedaliera Universitaria Meyer. Florence: Firenze University Press, 2015. http://dx.doi.org/10.36253/978-88-6655-831-6.

Full text
Abstract:
La Relazione sull'attività sanitaria e scientifica dell'Azienda Ospedaliera Universitaria Meyer è uno strumento prezioso di condivisione e diffusione delle informazioni che sintetizzano il modo di lavorare, i risultati e le linee di miglioramento su cui bisogna particolarmente impegnarsi. È uno strumento di conoscenza e di valutazione rivolto, quindi, sia all'interno, sia all'esterno dell'Ospedale. Uno strumento dinamico, che deve perfezionarsi, contestualmente ai miglioramenti perseguiti dall'Ospedale.
APA, Harvard, Vancouver, ISO, and other styles
3

Thielscher, Michael. AI 2012: Advances in Artificial Intelligence: 25th Australasian Joint Conference, Sydney, Australia, December 4-7, 2012. Proceedings. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
4

Vassilis, Plagianakos, Vlahavas Ioannis, and SpringerLink (Online service), eds. Artificial Intelligence: Theories and Applications: 7th Hellenic Conference on AI, SETN 2012, Lamia, Greece, May 28-31, 2012. Proceedings. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
5

Pavón, Juan. Advances in Artificial Intelligence – IBERAMIA 2012: 13th Ibero-American Conference on AI, Cartagena de Indias, Colombia, November 13-16, 2012. Proceedings. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
6

Diana, Inkpen, and SpringerLink (Online service), eds. Advances in Artificial Intelligence: 25th Canadian Conference on Artificial Intelligence, Canadian AI 2012, Toronto, ON, Canada, May 28-30, 2012. Proceedings. Berlin, Heidelberg: Springer Berlin Heidelberg, 2012.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
7

Sandra, Zilles, and SpringerLink (Online service), eds. Advances in Artificial Intelligence: 26th Canadian Conference on Artificial Intelligence, Canadian AI 2013, Regina, SK, Canada, May 28-31, 2013. Proceedings. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
8

Explore AI: Smart Devices. Hachette Children's Group, 2021.

Find full text
APA, Harvard, Vancouver, ISO, and other styles
9

Boden, Margaret A. 5. Robots and artificial life. Oxford University Press, 2018. http://dx.doi.org/10.1093/actrade/9780199602919.003.0005.

Full text
Abstract:
Artificial life (A-Life) models biological systems. Like AI, it has both technological and scientific aims. ‘Robots and artificial life’ explains that A-Life is integral to AI, because all the intelligence we know about is found in living organisms. AI technologists turn to biology in developing practical applications of many kinds, including robots, evolutionary programming, and self-organizing devices. Robots are quintessential examples of AI, having high visibility and being hugely ingenious—and very big business, too. Evolutionary AI, although widely used, is less well known. Self-organizing machines are even less familiar. Nevertheless, in the quest to understand self-organization, AI has been as useful to biology as biology has been to AI.
APA, Harvard, Vancouver, ISO, and other styles
10

Baecker, Ronald M. Computers and Society. Oxford University Press, 2019. http://dx.doi.org/10.1093/oso/9780198827085.001.0001.

Full text
Abstract:
The last century has seen enormous leaps in the development of digital technologies, and most aspects of modern life have changed significantly with their widespread availability and use. Technology at various scales - supercomputers, corporate networks, desktop and laptop computers, the internet, tablets, mobile phones, and processors that are hidden in everyday devices and are so small you can barely see them with the naked eye - all pervade our world in a major way. Computers and Society: Modern Perspectives is a wide-ranging and comprehensive textbook that critically assesses the global technical achievements in digital technologies and how are they are applied in media; education and learning; medicine and health; free speech, democracy, and government; and war and peace. Ronald M. Baecker reviews critical ethical issues raised by computers, such as digital inclusion, security, safety, privacy,automation, and work, and discusses social, political, and ethical controversies and choices now faced by society. Particular attention is paid to new and exciting developments in artificial intelligence and machine learning, and the issues that have arisen from our complex relationship with AI.
APA, Harvard, Vancouver, ISO, and other styles

Book chapters on the topic "On device AI"

1

Bowley, Sarah Jean, and Kathryn Merrick. "A ‘Breadcrumbs’ Model for Controlling an Intrinsically Motivated Swarm Using a Handheld Device." In AI 2017: Advances in Artificial Intelligence, 157–68. Cham: Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-63004-5_13.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

Anceschi, Emiliano, Gianluca Bonifazi, Massimo Callisto De Donato, Enrico Corradini, Domenico Ursino, and Luca Virgili. "SaveMeNow.AI: A Machine Learning Based Wearable Device for Fall Detection in a Workplace." In Enabling AI Applications in Data Science, 493–514. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-52067-0_22.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Meitiner, Philip, and Pradeeka Seneviratne. "Connecting an Edge Device to the IoT Application." In Beginning Data Science, IoT, and AI on Single Board Computers, 275–93. Berkeley, CA: Apress, 2020. http://dx.doi.org/10.1007/978-1-4842-5766-1_12.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Voznenko, Timofei I., Alexander A. Gridnev, Eugene V. Chepin, and Konstantin Y. Kudryavtsev. "Comparison Between Coordinated Control and Interpretation Methods for Multi-channel Control of a Mobile Robotic Device." In Brain-Inspired Cognitive Architectures for Artificial Intelligence: BICA*AI 2020, 558–64. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-65596-9_68.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Mammas, Constantinos S., and Adamantia S. Mamma. "Prometheus I (PN 1008239) Digital Medical Device Integrated with AI and Robotics Cognitive Ergonomics in Breast Cancer Prevention." In Advances in Intelligent Systems and Computing, 141–49. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-66937-9_16.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Mammas, Constantinos S., and Adamantia S. Mamma. "Prometheus (PN-2003016) Digital Medical Device Collaborative E-Training and Cognitive Ergonomics to Integrate AI and Robotics in Organ Transplantations." In Advances in Intelligent Systems and Computing, 129–40. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-66937-9_15.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Pachore, M. V., and S. S. Shirguppikar. "Covid-19 or Viral Pneumonia Detection Using AI Tools." In Handbook of Smart Materials, Technologies, and Devices, 1–12. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-58675-1_136-1.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Kulkarni, Uday, S. M. Meena, Sunil V. Gurlahosur, Pratiksha Benagi, Atul Kashyap, Ayub Ansari, and Vinay Karnam. "AI Model Compression for Edge Devices Using Optimization Techniques." In Studies in Computational Intelligence, 227–40. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-68291-0_17.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Lee, Kai-Fu. "A Human Blueprint for AI Coexistence." In Robotics, AI, and Humanity, 261–69. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-54173-6_22.

Full text
Abstract:
AbstractThe positive coexistence of humans and AI is possible and needs to be designed as a system that provides for all members of society, but one that also uses the wealth generated by AI to build a society that is more compassionate, loving, and ultimately human. It is incumbent on us to use the economic abundance of the AI age to foster the values of volunteers who devote their time and energy toward making their communities more caring. As a practical measure, to protect against AI/robotics’ labor saving and job displacement effects, a “social investment stipend” should be explored. The stipend would be given to those who invest their time and energy in those activities that promote a kind, compassionate, and creative society, i.e., care work, community service, and education. It would put the economic bounty generated by AI to work in building a better society, rather than just numbing the pain of AI-induced job losses.
APA, Harvard, Vancouver, ISO, and other styles
10

Mdhaffar, Afef, Fedi Cherif, Yousri Kessentini, Manel Maalej, Jihen Ben Thabet, Mohamed Maalej, Mohamed Jmaiel, and Bernd Freisleben. "DL4DED: Deep Learning for Depressive Episode Detection on Mobile Devices." In How AI Impacts Urban Living and Public Health, 109–21. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-32785-9_10.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Conference papers on the topic "On device AI"

1

Zhang, Zhen, Ning Zhang, Hongzhuang Guo, Zhe Wang, and Yuanhua Yu. "An early kidney injury rapid detection device." In AI in Optics and Photonics, edited by Jun Tanida, Yadong Jiang, Dong Liu, John Greivenkamp, HaiMei Gong, and Jin Lu. SPIE, 2019. http://dx.doi.org/10.1117/12.2539380.

Full text
APA, Harvard, Vancouver, ISO, and other styles
2

"DG03 - Device Reliability Constraints for AI." In 2020 IEEE International Integrated Reliability Workshop (IIRW). IEEE, 2020. http://dx.doi.org/10.1109/iirw49815.2020.9312872.

Full text
APA, Harvard, Vancouver, ISO, and other styles
3

Kojima, Keisuke, Yingheng Tang, Toshiaki Koike-Akino, Ye Wang, Devesh K. Jha, Mohammad Tahersima, and Kieran Parsons. "Application of deep learning for nanophotonic device design." In AI and Optical Data Sciences II, edited by Ken-ichi Kitayama and Bahram Jalali. SPIE, 2021. http://dx.doi.org/10.1117/12.2579104.

Full text
APA, Harvard, Vancouver, ISO, and other styles
4

Flores, Huber, Petteri Nurmi, and Pan Hui. "AI-Powered Multi-Device Systems and Applications." In 2019 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops). IEEE, 2019. http://dx.doi.org/10.1109/percomw.2019.8730582.

Full text
APA, Harvard, Vancouver, ISO, and other styles
5

Flores, Huber, Petteri Nurmi, and Pan Hui. "AI on the Move: From On-Device to On-Multi-Device." In 2019 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops). IEEE, 2019. http://dx.doi.org/10.1109/percomw.2019.8730873.

Full text
APA, Harvard, Vancouver, ISO, and other styles
6

Ahmad, Sagheer, Sridhar Subramanian, Vamsi Boppana, Shankar Lakka, Fu-Hing Ho, Tomai Knopp, Juanjo Noguera, Gaurav Singh, and Ralph Wittig. "Xilinx First 7nm Device: Versal AI Core (VC1902)." In 2019 IEEE Hot Chips 31 Symposium (HCS). IEEE, 2019. http://dx.doi.org/10.1109/hotchips.2019.8875639.

Full text
APA, Harvard, Vancouver, ISO, and other styles
7

Eleftheriou, Evangelos. "“In-memory Computing”: Accelerating AI Applications." In 48th European Solid-State Device Research Conference (ESSDERC 2018). IEEE, 2018. http://dx.doi.org/10.1109/essderc.2018.8486900.

Full text
APA, Harvard, Vancouver, ISO, and other styles
8

Hou, Dennis, Tuo Liu, Yen-Ting Pan, and Janpu Hou. "AI on edge device for laser chip defect detection." In 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC). IEEE, 2019. http://dx.doi.org/10.1109/ccwc.2019.8666503.

Full text
APA, Harvard, Vancouver, ISO, and other styles
9

Nokovic, Bojan, and Shucai Yao. "Image Enhancement by Jetson TX2 Embedded AI Computing Device." In 2019 8th Mediterranean Conference on Embedded Computing (MECO). IEEE, 2019. http://dx.doi.org/10.1109/meco.2019.8760100.

Full text
APA, Harvard, Vancouver, ISO, and other styles
10

Atmaja, Prajogo, Dalta Imam Maulana, and Trio Adiono. "AI-based Customer Behavior Analytics System using Edge Computing Device." In 2020 International Conference on Electronics, Information, and Communication (ICEIC). IEEE, 2020. http://dx.doi.org/10.1109/iceic49074.2020.9051138.

Full text
APA, Harvard, Vancouver, ISO, and other styles

Reports on the topic "On device AI"

1

Sayers, Dave, Rui Sousa-Silva, Sviatlana Höhn, Lule Ahmedi, Kais Allkivi-Metsoja, Dimitra Anastasiou, Štefan Beňuš, et al. The Dawn of the Human-Machine Era: A forecast of new and emerging language technologies. Open Science Centre, University of Jyväskylä, May 2021. http://dx.doi.org/10.17011/jyx/reports/20210518/1.

Full text
Abstract:
New language technologies are coming, thanks to the huge and competing private investment fuelling rapid progress; we can either understand and foresee their effects, or be taken by surprise and spend our time trying to catch up. This report scketches out some transformative new technologies that are likely to fundamentally change our use of language. Some of these may feel unrealistically futuristic or far-fetched, but a central purpose of this report - and the wider LITHME network - is to illustrate that these are mostly just the logical development and maturation of technologies currently in prototype. But will everyone benefit from all these shiny new gadgets? Throughout this report we emphasise a range of groups who will be disadvantaged and issues of inequality. Important issues of security and privacy will accompany new language technologies. A further caution is to re-emphasise the current limitations of AI. Looking ahead, we see many intriguing opportunities and new capabilities, but a range of other uncertainties and inequalities. New devices will enable new ways to talk, to translate, to remember, and to learn. But advances in technology will reproduce existing inequalities among those who cannot afford these devices, among the world’s smaller languages, and especially for sign language. Debates over privacy and security will flare and crackle with every new immersive gadget. We will move together into this curious new world with a mix of excitement and apprehension - reacting, debating, sharing and disagreeing as we always do. Plug in, as the human-machine era dawns.
APA, Harvard, Vancouver, ISO, and other styles
You might also be interested in the extended bibliographies on the topic 'On device AI' for particular source types:
Journal articles
We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!

To the bibliography