22 research outputs found
AI Based Early Detection Of Hormonal Imbalance And Poly-Cystic Ovary Syndrome In Young Women
No full textA hormonal disorder, Poly-Cystic Ovary Syndrome (PCOS) usually affects women during the reproductive age. It is characterised by imbalances in hormones, particularly a rise in the female body\u27s androgen level (male hormone) and enlarged ovaries with small cysts. PCOS can cause ovarian cysts, weight gain, acne, excessive hair growth, insulin resistance, and irregular menstrual cycles along with other health problems. While the exact origin of PCOS is uncertain and its symptoms are unclear, diagnosing PCOS in real-world conditions is a difficult task. Therefore, prompt and precise PCOS diagnosis is essential for efficient treatment and for averting long-term issues.
Clinicians typically use clinical, hormonal and ultrasound ovary images to manually analyse PCOS, although this method is labor-intensive and unreliable. Thus, the development of effective and automated PCOS classification models becomes essential for optimizing time and medical resources. This work uses the predictive power of Machine Learning (ML) and Deep Learning (DL) approaches to address the need for enhanced PCOS categorization. The goal is to investigate, create and evaluate ML and DL models that can accurately categorize PCOS from clinical, hormonal and ultrasound ovarian images, ultimately improving diagnostic accuracy and enabling timely intervention.
In machine learning, protecting the privacy of sensitive information has always been a top concern, particularly in the healthcare domain. Data may be exposed during various stages of model implementation including data collection, training and even after the release of a trained model. Thus, it is crucial to prevent data leakage and ensure patient privacy concerning Personally Identifiable Information (PII), ML model updates and Personal Health Information (PHI). To address these issues, a Fog-based Federated Learning approach is adopted, enabling collaborative learning where only gradients or updates from locally trained models are shared with the global server.
This research initially proposes a hybrid machine learning model using clinical and hormonal datasets for PCOS classification. Ensemble Feature Selection (FS) methods are used to identify the most significant indicators by selecting relevant features from a large feature set. A common issue in real-world applications is the instability of FS algorithms when applied repeatedly on the same or slightly modified datasets. Therefore, assessing FS robustness is crucial. In this study, Jensen–Shannon Divergence (JSD), an information-theoretic measure, is used along with ensemble FS to manage diverse outputs such as complete rankings, top-k lists and partial rankings. The resulting high-stability features are then used for training, and the proposed hybrid model achieved a remarkable accuracy of 97.81% using the AdaBoost classifier.
Although hormonal data contributes to PCOS diagnosis, it alone is insufficient. Ultrasound ovary images provide crucial visual information such as follicle size, count, shape and texture, essential for accurate diagnosis. A CNN-based Automated High-Precision PCOS Detection model is developed using ESRGAN for image resolution enhancement and SAM for cyst segmentation. Using VGG-19 with enhanced and segmented images, the model achieved an impressive 99.31% accuracy. Furthermore, a Differential Privacy (DP)-enabled Federated Learning framework is implemented for decentralized model training to ensure privacy and prevent data leakage. To balance the trade-off between privacy budget and utility, DP is applied only to the top-k participants, enabling the global model to achieve 87.29% accuracy with 0.3 top participants. The proposed model is also validated against two major attacks: gradient-based data reconstruction and model inversion
Protestant letter networks in the reign of Mary I: A quantitative approach
No full textSebastian E. Ahnert was supported by The Royal Society, UK
Geochemical Sourcing of Lithic Raw Materials from Secondary Deposits in South Serbia. Implications for Early Neolithic Resource Management Strategies. Archaeologia Austriaca|Archaeologia Austriaca Band 102/2018|
No full textThe valleys of the South Morava River and its tributaries in the region of Pusta Reka around the cities of Leskovac and Lebane in southern Serbia are notable for the high density of early prehistoric settlements identified archaeologically. The area represents a link between the Mediterranean and the (northern) Balkans and is therefore of key importance for understanding the processes of Neolithisation in south-eastern and central Europe, which commenced at the beginning of the 6th millennium BC. The current study is part of a larger project which aims to address issues concerning Early Neolithic resource management and production strategies, and specifically the use of the prehistoric landscape, through the characterisation of lithic materials in archaeological assemblages from this region. Lithic raw materials used for chipped stone tool production in the Pusta Reka region include a wide range of cryptocrystalline SiO2 modifications of volcanic and perivolcanic origin. These materials are found abundantly in secondary alluvial deposits in the extensive Neogene basin complexes of southern Serbia. The current pilot study was undertaken to test the viability of sourcing such lithic materials from secondary deposits to their primary origin using the Multi-Layered Chert Sourcing Approach (MLA), a method developed by the first author of this study, which combines visual, microscopic, and geochemical techniques using Laser Ablation Inductively Coupled Plasma Mass Spectrometry (LA-ICP-MS). In the light of the encouraging results, it is planned to extend the analytical work and to apply this method of provenance study to archaeological materials in order to reconstruct the economic behaviour of the Early Neolithic communities in this region
Geochemical Sourcing of Lithic Raw Materials from Secondary Deposits in South Serbia. Implications for Early Neolithic Resource Management Strategies. Archaeologia Austriaca|Archaeologia Austriaca Band 102/2018|
No full textThe valleys of the South Morava River and its tributaries in the region of Pusta Reka around the cities of Leskovac and Lebane in southern Serbia are notable for the high density of early prehistoric settlements identified archaeologically. The area represents a link between the Mediterranean and the (northern) Balkans and is therefore of key importance for understanding the processes of Neolithisation in south-eastern and central Europe, which commenced at the beginning of the 6th millennium BC. The current study is part of a larger project which aims to address issues concerning Early Neolithic resource management and production strategies, and specifically the use of the prehistoric landscape, through the characterisation of lithic materials in archaeological assemblages from this region. Lithic raw materials used for chipped stone tool production in the Pusta Reka region include a wide range of cryptocrystalline SiO2 modifications of volcanic and perivolcanic origin. These materials are found abundantly in secondary alluvial deposits in the extensive Neogene basin complexes of southern Serbia. The current pilot study was undertaken to test the viability of sourcing such lithic materials from secondary deposits to their primary origin using the Multi-Layered Chert Sourcing Approach (MLA), a method developed by the first author of this study, which combines visual, microscopic, and geochemical techniques using Laser Ablation Inductively Coupled Plasma Mass Spectrometry (LA-ICP-MS). In the light of the encouraging results, it is planned to extend the analytical work and to apply this method of provenance study to archaeological materials in order to reconstruct the economic behaviour of the Early Neolithic communities in this region
Temporal Quantitative Proteomics by iTRAQ 2D-LC-MS/MS and Corresponding mRNA Expression Analysis Identify Post-Transcriptional Modulation of Actin-Cytoskeleton Regulators During TGF-β-Induced Epithelial-Mesenchymal Transition
No full textTo gain insights into how TGF-β regulates epithelial-mesenchymal transition (EMT), we assessed the time course of proteins and mRNAs during EMT by multiplex iTRAQ labeling and 2D-LC-MS/MS, and by hybridization, respectively. Temporal iTRAQ analysis identified 66 proteins as differentially expressed during EMT, including newly associated proteins calpain, fascin and macrophage-migration inhibitory factor (MIF). Comparing protein and mRNA expression overtime showed that all the 14 up-regulated proteins involved in the actin-cytoskeleton remodeling were accompanied by increases in corresponding mRNA expression. Interestingly, siRNA mediated knockdown of cofilin1 potentiated TGF-β-induced EMT. Further analysis of cofilin1 and β-actin revealed an increase in their mRNA stability in response to TGF-β, contributing to the observed increase in mRNA and protein expression. These results are the first demonstration of post-transcriptional regulation of cytoskeletal remodelling and a key role for cofilin1 during TGF-β-induced EMT
Zircon geochronology and geochemistry to constrain the youngest eruption events and magma evolution of the Mid-Miocene ignimbrite flare-up in the Pannonian Basin, eastern-central Europe
No full textA silicic ignimbrite flare-up episode occurred in the Pannonian Basin during the Miocene, coeval with the syn-extensional period in the region. It produced important correlation horizons in the regional stratigraphy; however, they lacked precise and accurate geochronology. Here, we used U-Pb (LA-ICP-MS and ID-TIMS) and (U-Th)/He dating of zircons to determine the eruption ages of the youngest stage of this volcanic activity and constrain the longevity of the magma storage in crustal reservoirs. Reliability of the U-Pb data is supported by (U-Th)/He zircon dating and magnetostratigraphic constraints.
We distinguish four eruptive phases from 15.9±0.3 Ma to 14.1±0.3 Ma, each of which possibly includes multiple eruptive events. Among these, at least two large volume eruptions (>10 km3) occurred at 14.8±0.3 Ma (Demjén ignimbrite) and 14.1±0.3 Ma (Harsány ignimbrite). The in-situ U-Pb zircon dating show wide age ranges (up to 700 kyr) in most of the crystal-poor pyroclastic units, containing few to no xenocrysts, that implies efficient recycling of antecrysts. We propose that long-lived silicic magma reservoirs, mostly kept as high crystallinity mushes, have existed in the Pannonian Basin during the 16-14 Ma period. Small but significant differences in zircon, bulk rock and glass shard composition among units suggest the presence of spatially separated reservoirs, sometimes existing contemporaneously. Our results also better constrain the time frame of the main tectonic events that occurred in the northern Pannonian Basin: we refined the upper temporal boundary (15 Ma) of the youngest counter clockwise block rotation and the beginning of a new deformation phase, which structurally characterised the onset of the youngest volcanic and sedimentary phase
EFEKTIVITAS PASAL 7 UNDANG-UNDANG NEGARA REPUBLIK INDONESIA NOMOR 22 TAHUN 2001 TENTANG MINYAK DAN GAS BUMI TERKAIT STATUS KEGIATAN USAHA POM MINI DALAM PENYELENGGARAAN PERDAGANGAN MIGAS DI INDONESIA (STUDI KASUS POM MINI KOTA BATU)
No full textM. Syahrur Riza, Dr. Bambang Winarno, S.H., MS, Dr. Reka Dewantara, SH, MH, Fakultas Hukum Universitas Brawijaya [email protected]  Abstrak Penelitian ini dititikberatkan pada permasalahan yang dilatarbelakangi dengan kurang efektif efektivitas Pasal 7 UU Migas terkait kegiatan usaha Pom Mini dalam penyelenggaraan perdagangan Migas di kota Batu dan upaya PT Pertamina dalam penyelesaian sengketa kegiatan usaha Pom Mini di kota Batu. Oleh karenanya penulis merumuskan indikator sekurang efektif bagaimanakah Pasal 7 UU Migas dalam perdangan Migas di Kota Batu dan upaya preventif serta represif dalam penyelesaian sengketa antara PT pertamina dengan pelaku usaha Pom Mini di Kota Batu yang sesuai dan tepat sasaran. Penelitian skripsi ini menggunakan metode yuridis empiris dengan metode pendekatan Yuridis Sosiologis. Lokasi penelitian yakni di Kota Batu dan PT Pertamina regional Malang Raya. Kata kunci: Efektifitas, Status Kegiatan Usaha Pom Mini, Perdagangan Migas Di Indonesia  Abstract This research is focused more on the issue related to the effectiveness of Article 7 of Law on Oil and Gas regarding small business activity of mini patrol station as part of oil and gas trading practice in Batu and a measure taken by PT. Pertamina in order to settle dispute these business practices in Batu. The author formulates indicator of how ineffective Article 7 of Law on Oil and Gas in trading practice is in Batu and what appropriate preventive and repressive measures can be taken to settle the dispute between PT Pertamina and business actors of mini patrol station in Batu. This research involved empirical juridical method with socio-juridical approach, in which the research took place in Batu and PT Pertamina Regional in Greater Malang. Key words: Social and Environmental Responsibility, Foreign Capital Investment, Inclusive Econom
Forward genetic analysis of the circadian clock separates the multiple functions of ZEITLUPE
No full textThe circadian system of Arabidopsis ( Arabidopsis thaliana) includes feedback loops of gene regulation that generate 24-h oscillations. Components of these loops remain to be identified; none of the known components is completely understood, including ZEITLUPE (ZTL), a gene implicated in regulated protein degradation. ztl mutations affect both circadian and developmental responses to red light, possibly through ZTL interaction with PHYTOCHROME B (PHYB). We conducted a large-scale genetic screen that identified additional clock-affecting loci. Other mutants recovered include 11 new ztl alleles encompassing mutations in each of the ZTL protein domains. Each mutation lengthened the circadian period, even in darkgrown seedlings entrained to temperature cycles. A mutation of the LIGHT, OXYGEN, VOLTAGE (LOV)/Period-ARNT-Sim ( PAS) domain was unique in retaining wild-type responses to red light both for the circadian period and for control of hypocotyl elongation. This uncoupling of ztl phenotypes indicates that interactions of ZTL protein with multiple factors must be disrupted to generate the full ztl mutant phenotype. Protein interaction assays showed that the ztl mutant phenotypes were not fully explained by impaired interactions with previously described partner proteins Arabidopsis S-phase kinase-related protein 1, TIMING OF CAB EXPRESSION 1, and PHYB. Interaction with PHYB was unaffected by mutation of any ZTL domain. Mutation of the kelch repeat domain affected protein binding at both the LOV/PAS and the F-box domains, indicating that interaction among ZTL domains leads to the strong phenotypes of kelch mutations. Forward genetics continues to provide insight regarding both known and newly discovered components of the circadian system, although current approaches have saturated mutations at some loci
Organic geochemical characterization of the coastal sediments of the Sava River and the wetlands of Obrenovac Zabran (Serbia)
No full textIspitivano područje, Obrenovački Zabran (Slika 1), se nalazi na teritoriji opštine
Obrenovac, oko 1,5 km vazdušnom linijom od Obrenovca i administrativno pripada gradu Beogradu. Zbog svojih vrednosti ispitivani lokalitet je, na temelju Zakona o zaštiti prirode Srbije, proglašen prirodnim dobrom III kategorije – Spomenik prirode botaničkog karaktera „Obrenovački Zabran”. Ukupna površina zaštićenog prirodnog dobra iznosi 4777,18 ha. Šire područje na kome je i zaštićena oblast je ravničarskog karaktera i obuhvata aluvijalne ravni reka Save i Kolubare. U okviru rada analizirani su alifatični i aromatični ugljovodonici rastvorne organske supstance, u pet uzoraka priobalnih sedimenata reke Save i sedam uzoraka močvarnog zemljišta Obrenovačkog Zabrana sa ciljem njihove organsko-geohemijske karakterizacije. Velika energija rečnog toka reke Save uzrokuje stalni transport sedimentnog materijala, utičući istovremeno na raspodelu zagađujućih supstanci. Močvarno zemljište je takođe u čestom kontaktu sa vodom, pre svega sa podzemnim vodama Kolubare koje često plave ispitivano područje. Za ekstrakciju rastvorne organske supstance korišćena je azeotropna smeša CH2Cl2/CH3OH, nakon čega su dobijeni ekstrakti razdvojeni hromatografijom na koloni na zasićenu, aromatičnu i NSO-frakciju. Zasićena i aromatična frakcija su potom analizirane pomoću gasnohromatografsko-masenospektrometrijske (GC-MS) tehnike. Grupni i specifični organsko-geohemijski parametri su pokazali da postoji razlika u kvalitetu i sadržaju rastvorne organske supstance između uzoraka močvarnog zemljišta i ispitivanih uzoraka savskog sedimenta. Obe grupe uzoraka u većoj meri sadrže nativnu organsku supstancu, ali je prisutna i organska supstanca antropogenog porekla. Raspodela n-alkana ukazuje da nativna organska supstanca potiče od viših kopnenih biljaka, različitih vrsta trava, kao i od bakterija, algi i fitoplanktona. Ugljovodonici koji su karakteristični za naftu i njene derivate identifikovani su u svim ispitivanim uzorcima, s tim što je u uzorcima savskog sedimenta jasno uočljivo prisustvo geolipidnih hopanskih izomera i u hromatogramu ukupne jonske struje zasićene frakcije, što, pored prisustva nerazložene ugljovodonične smese (UCM), predstavlja potvrdu prisustva naftnog zagađivača, koji je već u nekoj meri podlegao biodegradaciji. Zasićenu frakciju uzoraka močvarnog zemljišta posebno karakteriše prisustvo diploptena (hop-22(29)-ena), što ukazuje na pojačanu mikrobiološku aktivnost u ovom često plavljenom zemljištu. Prisustvo fenantrena i metilovanih fenantrena, vrednosti maturacionih fenantrenskih parametara, kao i prisustvo polikondenzovanih aromatičnih ugljovodonika uz vrednosti njihovih odnosa, jasno ukazuju na prisustvo organske supstance antropogenog porekla koje uključuje i naftno zagađenje i proizvode sagorevanja. Rezultati istraživanja su osnova za dalja sveobuhvatnija istraživanja u Obrenovačkom Zabranu koja bi trebalo usmeriti na detaljnija periodična ispitivanja sedimenata i zemljišta
Miniaturized Bioaffinity Assessment Coupled to Mass Spectrometry for Guided Purification of Bioactives from Toad and Cone Snail
No full textA nano-flow high-resolution screening platform, featuring a parallel chip-based microfluidic bioassay and mass spectrometry coupled to nano-liquid chromatography, was applied to screen animal venoms for nicotinic acetylcholine receptor like (nAChR) affinity by using the acetylcholine binding protein, a mimic of the nAChR. The potential of this microfluidic platform is demonstrated by profiling the Conus textile venom proteome, consisting of over 1,000 peptides. Within one analysis (<90 min, 500 ng venom injected), ligands are detected and identified. To show applicability for non-peptides, small molecular ligands such as steroidal ligands were identified in skin secretions from two toad species (Bufo alvarius and Bufo marinus). Bioactives from the toad samples were subsequently isolated by MS-guided fractionation. The fractions analyzed by NMR and a radioligand binding assay with α7-nAChR confirmed the identity and bioactivity of several new ligands
