1. Analyzing information seeking and drug-safety alert response by health care professionals as ew methods for surveillanceAlison Callahan, Igor Pernek, Gregor Štiglic, Jurij Leskovec, Howard Strasberg, Nigam Haresh Shah, 2015, original scientific article Abstract: Background: Patterns in general consumer online search logs have been used to monitor health conditions and to predict health-related activities, but the multiple contexts within which consumers perform online searches make significant associations difficult to interpret. Physician information-seeking behavior has typically been analyzed through survey-based approaches and literature reviews. Activity logs from health care professionals using online medical information resources are thus a valuable yet relatively untapped resource for large-scale medical surveillance.
Objective: To analyze health care professionals% information-seeking behavior and assess the feasibility of measuring drug-safety alert response from the usage logs of an online medical information resource.
Methods: Using two years (2011-2012) of usage logs from UpToDate, we measured the volume of searches related to medical conditions with significant burden in the United States, as well as the seasonal distribution of those searches. We quantified the relationship between searches and resulting page views. Using a large collection of online mainstream media articles and Web log posts we also characterized the uptake of a Food and Drug Administration (FDA) alert via changes in UpToDate search activity compared with general online media activity related to the subject of the alert.
Results: Diseases and symptoms dominate UpToDate searches. Some searches result in page views of only short duration, while others consistently result in longer-than-average page views. The response to an FDA alert for Celexa, characterized by a change in UpToDate search activity, differed considerably from general online media activity. Changes in search activity appeared later and persisted longer in UpToDate logs. The volume of searches and page view durations related to Celexa before the alert also differed from those after the alert.
Conclusions: Understanding the information-seeking behavior associated with online evidence sources can offer insight into the information needs of health professionals and enable large-scale medical surveillance. Our Web log mining approach has the potential to monitor responses to FDA alerts at a national level. Our findings can also inform the design and content of evidence-based medical information resources such as UpToDate
Keywords: internet log analysis, data mining, physicians, information-seeking behavior, drug safety surveillance
Published in DKUM: 02.08.2017; Views: 1858; Downloads: 235
 Full text (4,18 MB)
This document has many files! More... |
2. Exercise repetition detection for resistance training based on smartphonesIgor Pernek, Karin Anna Hummel, Peter Kokol, 2012, original scientific article Abstract: Regular exercise is one of the most important factors in maintaining a good state of health. In the past, different systems have been proposed to assist people when exercising. While most of those systems focus only on cardio exercises such as running and cycling, we exploit smartphones to support leisure activities with a focus on resistance training. We describe how off-the-shelf smartphones without additional external sensors can be leveragedto capture resistance training data and to give reliable training feedback. We introduce a dynamic time warping-based algorithm to detect individual resistance training repetitions from the smartphoneʼs acceleration stream. We evaluate the algorithm in terms of the number of correctly recognized repetitions. Additionally, for providing feedback about the qualityof repetitions, we use the duration of an individual repetition and analyze how accurately start and end times of repetitions can be detected by our algorithm. Our evaluations are based on 3,598 repetitions performed by tenvolunteers exercising in two distinct scenarios, a gym and a natural environment. The results show an overall repetition miscount rate of about 1 %and overall temporal detection error of about 11 % of individual repetition duration.
Keywords: wearable systems, resistance training, smartphone, accelerometer
Published in DKUM: 10.07.2015; Views: 1765; Downloads: 101
 Link to full text |
3. Uporaba vseprisotnega računalništva za kvalitativno vrednotenje vzorcev rekreativne fizične aktivnostiIgor Pernek, 2013, doctoral dissertation Abstract: Vseprisotno računalništvo je v preteklosti postalo popularno tudi v zdravstvu, predvsem na področju podpore rekreativnih fizičnih aktivnosti. Pri tem se je večina preteklih raziskav osredotočala na uporabo vseprisotnih senzorjev in naprav za prepoznavanje tipa ter količine izvedenih aktivnostih, manj pozornosti pa je bilo posvečeno zaznavanju kvalitativnih parametrov vadbe, kot sta pravilnost in intenzivnost vadbe. V doktorskem delu izvedemo analize in predlagamo algoritme za vrednotenje intenzivnosti in pravilnosti različnih tipov rekreativne fizične aktivnosti v realnem času na zmogljivostno omejenih vseprisotnih napravah. Predlagamo algoritem, ki z 99 % natančnostjo prepoznava število ponovitev treninga moči in zaznava njihove mejne točke z napako 215 ms oz. 11 % dolžine posamezne ponovitev. Izvedemo analizo uporabnosti različnih značilk pospeška in metod numeričnega napovedovanja za ocenjevanje intenzivnosti aerobnih aktivnosti. Ugotovimo, da enostavne metode, kot je linearna regresija, z majhnim število natančno izbranih značilk omogočajo napovedovanje srčnega utripa vadbe z napako približno 15 utripov na minuto. Na koncu predlagamo še hierarhični algoritem, ki s podatki, pridobljenimi iz petih nosljivih pospeškometrov, omogoča prepoznavanje intenzivnosti treninga moči. Prepoznavanje intenzivnosti poteka v dveh fazah, pri čemer je v prvi fazi prepoznan tip aktivnosti, v drugi pa je zaznana intenzivnost z ozirom na prepoznano aktivnost. Predlagani algoritem dosega 86 % natančnost prepoznavanja tipa aktivnosti in 6 % napako zaznavanja intenzivnosti. Dodatno analiza različnih konfiguracij senzorjev pokaže, da uporaba podmnožice senzorjev dosega rezultate primerljive natančnosti.
Keywords: vseprisotno računalništvo, prepoznavanje aktivnosti, strojno učenje, vrednotenje kvalitete
Published in DKUM: 11.11.2013; Views: 1956; Downloads: 198
Full text (12,71 MB) |
4. Comprehensive decision tree models in bioinformaticsGregor Štiglic, Simon Kocbek, Igor Pernek, Peter Kokol, 2012, original scientific article Abstract: Purpose Classification is an important and widely used machine learning technique in bioinformatics. Researchers and other end-users of machine learning software often prefer to work with comprehensible models where knowledge extraction and explanation of reasoning behind the classification model are possible. Methods This paper presents an extension to an existing machine learning environment and a study on visual tuning of decision tree classifiers. The motivation for this research comes from the need to build effective and easily interpretable decision tree models by so called one-button data mining approach where no parameter tuning is needed. To avoid bias in classification, no classification performance measure is used during the tuning of the model that is constrained exclusively by the dimensions of the produced decision tree. Results The proposed visual tuning of decision trees was evaluated on 40 datasets containing classical machine learning problems and 31 datasets from the field of bioinformatics. Although we did notexpected significant differences in classification performance, the resultsdemonstrate a significant increase of accuracy in less complex visuallytuned decision trees. In contrast to classical machine learning benchmarking datasets, we observe higher accuracy gains in bioinformatics datasets. Additionally, a user study was carried out to confirm the assumptionthat the tree tuning times are significantly lower for the proposed method in comparison to manual tuning of the decision tree. Conclusions The empirical results demonstrate that by building simple models constrained by predefined visual boundaries, one not only achieves good comprehensibility, but also very good classification performance that does not differ from usually more complex models built using default settings of the classical decision tree algorithm. In addition, our study demonstrates the suitability of visually tuned decision trees for datasets with binary class attributes anda high number of possibly redundant attributes that are very common in bioinformatics.
Keywords: decision tree models, machine learning technique, visual tuning, bioinformatics
Published in DKUM: 05.06.2012; Views: 2305; Downloads: 356
Full text (524,39 KB)
This document has many files! More... |
5. Analysis of gene ranking algorithms with extraction of relevant biomedical concepts from Pubmed publicationsSimon Kocbek, Rune Saetre, Gregor Štiglic, Jin-Dong Kim, Igor Pernek, Yoshimasa Tsuruoka, Peter Kokol, Sophia Ananiadou, Jun-ichi Tsujii, 2011, published scientific conference contribution abstract Keywords: DNA microarray, gene ranking, algorithms, Pubmed publications
Published in DKUM: 05.06.2012; Views: 1900; Downloads: 44
Link to full text |
6. AGRA: analysis of gene ranking algorithmsSimon Kocbek, Rune Saetre, Gregor Štiglic, Jin-Dong Kim, Igor Pernek, Yoshimasa Tsuruoka, Peter Kokol, Sophia Ananiadou, Jun-ichi Tsujii, 2011, other scientific articles Abstract: Often, the most informative genes have to be selected from different gene setsand several computer gene ranking algorithms have been developed to cope with the problem. To help researchers decide which algorithm to use, we developed the Analysis of Gene Ranking Algorithms (AGRA) system that offers a novel technique for comparing ranked lists of genes. The most important feature of AGRA is that no previous knowledge of gene ranking algorithms is needed for their comparison. Using the text mining system FACTA (Tsuruoka et al., 2008), AGRA defines what we call Biomedical Concept Space (BCS) for each gene list and offers comparison of the gene lists in six different BCS categories. The uploaded gene lists can be compared using two different methods. In the first method, the overlap between each pair of two gene lists of BCSs is calculated. The second method offers a text field where specific biomedical concept can be entered. AGRA searches for this concept in each genelistsć BCS, highlights the rank of the concept and offers a visual representation of concepts ranked above and below it.
Keywords: genetic algorithms, genetski algoritmi
Published in DKUM: 05.06.2012; Views: 2291; Downloads: 152
Link to full text |
7. NIŽANJE KOMUNIKACIJSKIH PREGRAD S POMOČJO MOBILNIH SOCIALNIH OMREŽIJIgor Pernek, 2009, undergraduate thesis Abstract: Porast števila socialnih omrežij nakazuje, da lahko tehnologija služi kot sredstvo za vzpodbujanje socialne interakcije. Ob množici spletnih socialnih omrežij so se v zadnjih letih začele pojavljati tudi mobilne različice, ki z vseprisotnostjo mobilnih naprav omogočajo fleksibilnejšo izrabo tehnologije za socializacijska opravila. V okviru te raziskave smo se posvetili nižanju komunikacijskih pregrad v okoljih, kjer je fizičen stik med subjekti še zmeraj prisoten. Razvili smo SocioNet, prototip mobilnega socialnega omrežja, ki omogoča iskanje optimalnih komunikacijskih partnerjev v urbanih središčih.
V skladu z aktualnimi trendi mobilnih aplikacij, ki že v letu 2009 nakazujejo izenačenje mobilnih dostopov do interneta s stacionarnimi, do leta 2020 pa napovedujejo dominanco mobilnih dostopov do medmrežja, smo SocioNet razvili kot platformo, ki omogoča uporabo različnih načinov brezžične in IP komunikacije. Preučili smo obstoječa mobilna in stacionarna socialna omrežja, njihove zmogljivosti, monetizacijski potencial, arhitekture, uporabniške vmesnike in skrb za varnost ter zasebnost.
Ob pregledu obstoječih socialnih omrežij smo ugotovili, da so različna socialna omrežja skozi zgodovino ponujala nabor podobnih zmogljivosti. Tako le-te niso predstavljale ključnega dejavnika uspeha, temveč zgolj dopolnitev k izredno pomembni časovni umestitvi. Friendster, ki velja za eno iz med največjih razočaranj na področju socialnih omrežij, je namreč ponujal zelo podoben nabor zmogljivosti kot dandanes izredno aktualen Facebook. Ob omrežjih, ki so uspela s pridom izrabiti ugodno časovno umestitev, je preboj uspel še nekaterim domensko usmerjenim omrežjem, med drugimi omrežju LinkedIn, ki omogoča vzdrževanje poslovnih kontaktov.
Pomembna aspekta socialnih omrežij sta prav gotovo zasebnost in zaupanje v omrežje samo. Slednje je posebej pomembno v mobilnih socialnih omrežjih, kjer vseprisotnost mobilnih naprav omogoča pridobivanje različnih osebnih podatkov, ki lahko ob nepravilni uporabi predstavljajo vir najrazličnejših zlorab in kraj identitete. Analiza zasebnosti mobilnih socialnih omrežij je pokazala, da obstoječa mobilna omrežja slabo skrbijo za uporabnikov nadzor nad lastnimi osebnimi podatki, prav tako pa ponujajo skope povratne informacije o uporabi in obdelavi uporabnikovih osebnih podatkov.
Skrb za zasebnost podatkov v mobilnih socialnih omrežjih je tesno povezana z arhitekturo omrežja. Dandanes se v mobilnih omrežjih najpogosteje uporabljata:
 P2P arhitektura in
 arhitektura oserednjega strežnika.
Tako ena kot druga ponujata različne prednosti in slabosti. Medtem ko uporaba arhitekture osrednjega strežnika drastično niža stopnjo zaupanja v omrežje na eni strani (množica osebnih podatkov je namreč centralizirana na osrednjem strežniku) ter izboljšuje prepustnost in hitrost omrežja na drugi, so efekti P2P arhitekture skorajda diametralno nasprotni. Ob uporabi P2P arhitekture so osebni podatki porazdeljeni po odjemalcih uporabnikov, kar zmanjšuje tveganje njihove odtujitve in zlorabe, a dodatno obremenjuje omrežje, saj so za obdelavo in uporabo podatkov potrebne neprestane migracije podatkov po omrežju.
Arhitekturo omrežja SocioNet smo zasnovali z mislijo o prednostih in slabostih omenjenih arhitektur. Odločili smo se za uporabo mešanice P2P arhitekture in arhitekture osrednjega strežnika. Osebni podatki uporabnikov se tako hranijo bodisi na uporabnikovi mobilni napravi, bodisi na osrednjem strežniku. Mesto hranjenja osebnih podatkov lahko, glede na kritičnost in željo po stopnji zasebnosti, določa uporabnik sam. Dodatno smo omrežje SocioNet obogatili še s sistemom pravil, ki omogočajo dinamično prestavljanje osebnih podatkov glede na pomembnost dobljenih rezultatov in uporabnikove preference zasebnosti.
Pred zasnovo odjemalčevega uporabniškega vmesnika smo preučili smernice zasnove mobilnih uporabniških vmesnikov. V skladu s smernicami smo izvedli interno analizo željenih zmogljivosti ter preučili različne zaslonske mask
Keywords: mobilne naprave, mobilna socialna omrežja, nižanje komunikacijskih pregrad
Published in DKUM: 02.02.2012; Views: 2169; Downloads: 170
Full text (1013,97 KB) |
