Hasil untuk "Islam"

Shariful Islam, Joel Bierman, Yuan Liu

We develop a fermi-bose bootstrap embedding (fb-BE) framework for the ground state of interacting elec- trons coupled to phonon mean field. The method combines bootstrap embedding for correlated electrons with a self-consistent coherent-state mean-field treatment for phonons. This method models the interacting electron-phonon problem as a system of correlated electrons traveling in a self-consistently specified potential landscape, allowing for efficient treatment of large lattice systems. Convergence of the methods for frag- ment size and total system size are demonstrated for one-dimensional Hubbard-Holstein model for up to 350 sites. Finite-size scaling is performed to extrapolate to infinite system size. Benchmarking against density matrix renormalization group for small 8-site system at half- and quarter-filling shows orders-of-magnitude runtime advantage. The comparison further reveals that the method performs best in regimes dominated by localization, such as the Mott insulating phase and the strong-coupling tiny polaron regime, where the local embedding ansatz is still valid. However, due to the mean-field treatment for phonons, we find limitations of our methods in the weakly coupled delocalized region and at the Peierls transition, where quantum phonon fluctuations and long-range kinetic correlations become substantial.

Akif Islam, Sujan Kumar Roy, Md. Ekramul Hamid

Sentiment analysis for the Bengali language has attracted increasing research interest in recent years. However, progress remains constrained by the scarcity of large-scale and diverse annotated datasets. Although several Bengali sentiment and hate speech datasets are publicly available, most are limited in size or confined to a single domain, such as social media comments. Consequently, these resources are often insufficient for training modern deep learning based models, which require large volumes of heterogeneous data to learn robust and generalizable representations. In this work, we introduce BengaliSent140, a large-scale Bengali binary sentiment dataset constructed by consolidating seven existing Bengali text datasets into a unified corpus. To ensure consistency across sources, heterogeneous annotation schemes are systematically harmonized into a binary sentiment formulation with two classes: Not Hate (0) and Hate (1). The resulting dataset comprises 139,792 unique text samples, including 68,548 hate and 71,244 not-hate instances, yielding a relatively balanced class distribution. By integrating data from multiple sources and domains, BengaliSent140 offers broader linguistic and contextual coverage than existing Bengali sentiment datasets and provides a strong foundation for training and benchmarking deep learning models. Baseline experimental results are also reported to demonstrate the practical usability of the dataset. The dataset is publicly available at https://www.kaggle.com/datasets/akifislam/bengalisent140/

Tousif Islam, Digvijay Wadekar

Modeling the remnant recoil velocity (kick) distribution from binary black hole mergers is crucial for understanding hierarchical mergers in active galactic nuclei or globular clusters. Existing analytic models often show large discrepancies with numerical relativity (NR) data, while data-driven models are limited to mass ratios of q<=8 (aligned spins) and q<=4 (precessing spins) and break down when extrapolated outside their training ranges. Using ~5000 of NR simulations from the SXS and RIT catalogs up to q=128 and ~100 black hole perturbation theory simulations up to q=200, we present two classes of models: (i) gwModel_kick_q200 (gwModel_kick_q200_GPR), an analytic (Gaussian process regression) model for aligned-spin binaries. (ii) gwModel_kick_prec_flow, a normalizing-flow model for kick distribution from precessing binaries with isotropic spins. Our approach combines analytic insights from post-Newtonian theory with data-driven techniques to ensure correct limiting behavior and high accuracy across parameter space. Both gwModel_kick_q200 and gwModel_kick_prec_flow are valid from comparable to extreme mass ratios. Extensive validation shows all three models outperform existing ones within their respective domains. Finally, using both back-of-the-envelope estimates and 1404 detailed star cluster simulations incorporating our kick models, we find that the black hole retention probability in low mass globular clusters can vary noticeably when the gwModel_kick_prec_flow model is employed. The models are publicly available through the gwModels package.

Sahil Islam, Mohd. Suhail Rizvi, Anupam Gupta

Embryonic tissues deform across broad spatial and temporal scales and relax stress through active rearrangements. A quantitative link between cell-scale activity, spatial forcing, and emergent tissue-scale mechanics remains incomplete. Here, we use a vertex-based tissue model with active force fluctuations to study how motility controls viscoelastic response. After validation against experimental presomitic mesoderm relaxation dynamics, we extract intrinsic mechanical timescales using stress relaxation and oscillatory shear. The model captures motility-dependent shifts between elastic and viscous behavior and the coexistence of fast relaxation with long-lived residual stress. When subjected to spatially patterned, temporally pulsed forcing, tissues behave as mechanical filters: long-wavelength inputs are accumulated, whereas short-wavelength, cell-scale perturbations are rapidly erased, largely independent of motility. Simulations with localized motility hotspots, motivated by spatially confined FGF signaling reported in vertebrate limb development, produce sustained protrusive tissue deformations consistent with experimentally observed early bud-like morphologies. Together, these results establish a minimal framework linking motility-driven activity to wavelength-selective mechanical memory and emergent tissue patterning.

Hazem Hamoudia, Firdaus Fanny Putera Perdana

This article examines the application of the stock screening tool “purepofo” (www.purepofo.com), which integrates Halal and Environmental, Social, and Governance (ESG) criteria with a comprehensive performance assessment based on widely used financial metrics. The article evaluates Purepofo’s ability to align Shariah compliance and ESG standards with performance-driven investing, addressing ethical and financial imperatives. The study presents a comparative analysis of the financial performance of stocks screened using a combined screening approach versus non-screened counterparts, while also outlining methodological limitations. Key findings reveal that Halal and ESG-screened stocks outperformed peers in several financial dimensions, including operational efficiency, dividend reliability, and resilience to market volatility. Notably, these stocks demonstrated higher Sharpe Ratios, more substantial gross margins, and consistent revenue growth, challenging the perception of a trade-off between ethical compliance and financial performance. However, limitations, such as the underrepresentation of high-growth stocks and valuation complexities, highlight the need for further methodological refinement. The discussion emphasises the potential of a customised financial metrics model to support investors in achieving competitive returns without compromising ethical integrity. The results suggest that Halal-ESG stocks offer more than symbolic ethical Value; they exhibit measurable financial resilience, governance, and sustainability strength. While alignment with Maqasid al-Shariah principles remains central, the data—rather than ideals alone—positions Islamic finance as a leader in sustainable investing. This article contributes to the growing discourse on Halal-ESG integration by offering actionable insights for Islamic finance portfolio managers, Shariah scholars, and thought leaders. Bridging ethical compliance, sustainability, and financial performance highlights the role of integrated tools in advancing innovation and inclusivity in global finance.

Aripin, Nur Azizah Zuhriyah

This study examines the impact of financial literacy, business management skills, and access to capital on the sustainability of women entrepreneurs' businesses. Using a quantitative approach, the findings reveal that financial literacy and business management skills significantly enhance business sustainability, equipping women entrepreneurs with essential decision-making and managerial capabilities. Access to capital also plays a crucial role in sustaining businesses by providing financial resources for growth and risk management. The moderating effects of access to capital present a nuanced dynamic. While access to capital strengthens the positive relationship between business management skills and business sustainability, it unexpectedly weakens the relationship between financial literacy and sustainability. This indicates that although financial resources are necessary, excessive reliance on external funding without strong financial management can hinder business success. These findings align with Resource-Based View, emphasizing the significance of both financial and managerial competencies. The study provides theoretical contributions by refining the understanding of financial literacy's role in business sustainability and highlighting the risks of financial mismanagement. Practically, it emphasizes the need for integrated policies that enhance financial education and managerial skills while ensuring responsible access to capital. Governments, financial institutions, and entrepreneurship programs in Indonesia should adopt a holistic approach by combining financial training with structured capital access. Despite its contributions, this study is limited by its cross-sectional design and geographical scope. Future research should explore longitudinal and qualitative perspectives to gain deeper insights. Overall, this study offers valuable recommendations for fostering sustainable women entrepreneurship, particularly in developing economies.

Mijanur Islam, Saurabh Basu

In this work, we investigate an $α$-$T_3$ lattice in the form of a Corbino disk, characterized by inner and outer radii $R_1$ and $R_2$, threaded by a tunable magnetic flux. Through exact (analytic) solution of the stationary Dirac-Weyl equation, we compute the transmission probability of the carriers and hence obtain the conductance features for $0<α\leq 1$ ($α$ denotes the strength of the hopping between the central atom and one of the other two) which allows ascertaining the role of the flat band, alongwith scrutinizing the transport features from graphene to a dice lattice. Our results reveal periodic Aharonov-Bohm (AB) oscillations in the conductance, reminiscent of the utility of the Corbino disk as an electron pump. Further, these results are strongly influenced by parameters, such as, doping level, ratio of the inner and outer radii, magnetic flux, and $α$. Additionally, complex quantum interference effect resulting in the possible emergence of higher harmonic modes and split-peak structures in the conductance, become prominent for smaller $α$ values and larger ratios of the radii. We also find that, away from the charge-neutrality point (zero doping), the conductance oscillations are more pronounced and sensitive to the various parameters, with the corresponding behaviour largely governed via the evanescent wave transport. The Fano factor reveals distinct transport regimes, transitioning from Poissonian to pseudo-diffusive for $α< 1$, and from ballistic to pseudo-diffusive for $α= 1$. This setup, thus serves as a fertile ground for studying the generation of quantum Hall current and Aharonov-Bohm (AB) oscillations in a flat band system, alongwith demonstrating intricate appearance of higher harmonics in electron transport.

Mirajul Islam, Michael J. Daniels, Zeynab Aghabazaz et al.

Cardiovascular disease (CVD) cohorts collect data longitudinally to study the association between CVD risk factors and event times. An important area of scientific research is to better understand what features of CVD risk factor trajectories are associated with the disease. We develop methods for feature selection in joint models where feature selection is viewed as a bi-level variable selection problem with multiple features nested within multiple longitudinal risk factors. We modify a previously proposed Bayesian sparse group selection (BSGS) prior, which has not been implemented in joint models until now, to better represent prior beliefs when selecting features both at the group level (longitudinal risk factor) and within group (features of a longitudinal risk factor). One of the advantages of our method over the BSGS method is the ability to account for correlation among the features within a risk factor. As a result, it selects important features similarly, but excludes the unimportant features within risk factors more efficiently than BSGS. We evaluate our prior via simulations and apply our method to data from the Atherosclerosis Risk in Communities (ARIC) study, a population-based, prospective cohort study consisting of over 15,000 men and women aged 45-64, measured at baseline and at six additional times. We evaluate which CVD risk factors and which characteristics of their trajectories (features) are associated with death from CVD. We find that systolic and diastolic blood pressure, glucose, and total cholesterol are important risk factors with different important features associated with CVD death in both men and women.

Tunazzina Islam, Dan Goldwasser

The widespread use of social media has led to a surge in popularity for automated methods of analyzing public opinion. Supervised methods are adept at text categorization, yet the dynamic nature of social media discussions poses a continual challenge for these techniques due to the constant shifting of the focus. On the other hand, traditional unsupervised methods for extracting themes from public discourse, such as topic modeling, often reveal overarching patterns that might not capture specific nuances. Consequently, a significant portion of research into social media discourse still depends on labor-intensive manual coding techniques and a human-in-the-loop approach, which are both time-consuming and costly. In this work, we study the problem of discovering arguments associated with a specific theme. We propose a generic LLMs-in-the-Loop strategy that leverages the advanced capabilities of Large Language Models (LLMs) to extract latent arguments from social media messaging. To demonstrate our approach, we apply our framework to contentious topics. We use two publicly available datasets: (1) the climate campaigns dataset of 14k Facebook ads with 25 themes and (2) the COVID-19 vaccine campaigns dataset of 9k Facebook ads with 14 themes. Additionally, we design a downstream task as stance prediction by leveraging talking points in climate debates. Furthermore, we analyze demographic targeting and the adaptation of messaging based on real-world events.

Imam Shidiq, Sri Rohyanti Zulaikha

Indonesia merupakan negeri kepulaun yang berpotensi mengalami bencana alam. Kondisi geografis tersebut menyebabkan Indonesia rawan terjadi bencana. Salah satu bencana yang dihapi oleh manusia adalah bencana kebakaran. Kebakaran terjadi ketika sebuah struktur, seperti rumah atau lingkungan, pabrik, pasar, dan lain-lain, dilanda api yang mengakibatkan kerusakan dan/atau korban jiwa. Maka sangat penting sebuah istansi memiliki kesiapsiagaan dalam menghadapi becana kebakaran. Tujuan penelitian ini untuk memahami kesiapsiagaan perpustakaan dalam menghadapi bencana kebakaran. Data diperoleh melalui sumber referensi termasuk buku, jurnal, dan makalah ilmiah yang relevan dengan tema mitigasi dan kesiapsiagaan perpustaakaan serta literatur tentang bencana kebakaran. Kegiatan kesiapsiagaan bencana dilakukan secara bertahap, yaitu pencegahan, tanggapan, reaksi, dan pemulihan. Kegiatan tersebut meliputi pemeriksaan bangunan, pemeriksaan alat perlindungan kebakaran, penyediaan audio, pembuatan back-up data, pemberian rute evakuasi, melakukan asuransi, penetapan staf, pelatihan staf, pemeliharaan peralatan, sediakan daftar nama dan organisasi penting, menerbitakan SOP, verifikasi apakah lokasi sudah aman, menetapkan masa penutupan perpustakaan, melakukan pencatatan kerusakan, menempatkan koleksi ditempat aman, pemulihan data, dan analisis SOP yang ada.

Basarudin, Suparman Jayadi

Just like in Java there is Kiai, in Sunda there is ajengan, in Sumatra there is buya, in Aceh there is teungku, in Madura there is bindara, and in the Nusa Tenggara region there is Tuan Guru Besar, abbreviated as TGB. He has contributions and thoughts in the educational aspect to guide the elderly and children. This article aims to find out the contributions and thoughts of TGH Muhammad Najmuddin Makmun. This research uses historical research methods which have four stages, namely, heuristics, criticism, interpretation and historiography. In this research, the results can be obtained that, TGH Muhammad Najmuddin Makmun was a scholar who was born in 1920 M and had studied in Mecca for several years with teachers there. In terms of his leadership, he is wise, charismatic, simple and does not differentiate between the social strata of society and the students he teaches, prioritizing equality. TGH Muhammad Najmuddin Makmun educational thought is to improve and increase the existence of Islamic teachings, by referring to the teachings of monotheism education so that it can be used as a process of formation or guidance based on the Islamic religion, so that students are able to carry out their humanitarian duties as well as possible and adhere firmly to strong faith and intentions. In his contribution, he put it into educating the community, both children and the elderly. Through thoriqot establishments to educate the elderly, as well as Islamic boarding schools to educate children.

Md. Khayrul Islam, Md. Golam Kibria, Rizwana Amin et al.

Abstract Background Depression, anxiety, and stress are the commonly encountered mental health conditions among medical students. Overseas environment may add additional burden to the existing environment. However, comparison of the rate and associated factors of depression, anxiety, stress among domestic and overseas students has not been attempted in Bangladesh. We aimed to assess the rate and associated factors of depression, anxiety, stress among domestic and overseas medical students in the country. Methods This cross‐sectional study was conducted among 360 undergraduate medical students in 2021. Data were collected by self‐reporting instruments by a stratified random sampling method by the Depression, Anxiety, and Stress Scale‐21 scale. Bivariable and multivariable binary logistic regression analyses were done by computing crude odds ratio and adjusted odds ratio with 95% confidence interval to identify the associated factors. Results Among the 360 undergraduate medical students, 181 were domestic and 179 overseas ones. 44.8% of domestic students reported depressive symptoms, 45.3% reported anxiety symptoms, and 33.1% reported stress. On the other hand, half of overseas students experienced depression (50.3%) and anxiety (52.5%), and 41.3% experienced stress. Female medical students were found vulnerable for developing depression, anxiety, and stress than males. Conclusions The study revealed higher rates of depression, anxiety, and stress among overseas undergraduate medical students enrolled in a private medical school of Bangladesh. Private medical college authorities could consider special services for overseas students to ensure adequate psychosocial support.

Tousif Islam, Scott E. Field, Gaurav Khanna

Past studies have empirically demonstrated a surprising agreement between gravitational waveforms computed using adiabatic-driven-inspiral point-particle black hole perturbation theory (ppBHPT) and numerical relativity (NR) following a straightforward calibration step, sometimes referred to as $α$-$β$ scaling. Specifically focusing on the quadrupole mode, this calibration technique necessitates only two time-independent parameters to scale the overall amplitude and time coordinate. In this article, part of a special issue, we investigate this scaling for non-spinning binaries at the equal mass limit. Even without calibration, NR and ppBHPT waveforms exhibit an unexpected degree of similarity after accounting for different mass scale definitions. Post-calibration, good agreement between ppBHPT and NR waveforms extends nearly up to the point of the merger. We also assess the breakdown of the time-independent assumption of the scaling parameters, shedding light on current limitations and suggesting potential generalizations for the $α$-$β$ scaling technique.

Muhammed Yusuf Akbak

Sûfîler, tasavvufî hikmetleri aktarırken kelimelerin yetersiz kaldığı yerlerde güzel sanatlardan faydalanmış ve bu sayede düşüncelerini halkın anlayabileceği şekilde aktarmaya gayret etmişlerdir. Tasavvufî düşünceyle inşa edilen sanat eserlerindeki etkileyicilik artmış ve bu eserler daha geniş alanda yayılma fırsatı bulmuşlardır. Geleneksel seyirlik sanatlar arasında yer alan gölge oyunu da sûfîler tarafından yorumlanmış, oyunda kullanılan unsurlar tasavvuf düşüncesinin aktarılması noktasında işlevsel bir araç olarak değerlendirilmiştir. Oyunun temelinin hangi kültüre dayandığı ve çıkış noktasında tasavvufun olup olmadığı tartışmalı bir konudur. Ancak Anadolu coğrafyasında gölge oyununun ortaya çıkışına dair nakledilen rivayetlerin bir kısmının Şeyh Küşterî isimli sûfîye dayanması, tasavvuf ve gölge oyunun bu coğrafya bağlamında temeldeki birlikteliğine işaret eden ögelerden bir tanesidir. Çalışmamızda gölge oyunu temelinde sûfîlerin âlemin varlığına dair değerlendirmeleri ve bu bağlamda gölge oyununun tasavvuf düşüncesini ifade etmedeki işlevselliği ortaya konulmaya çalışılmıştır. Gölge oyununda hem yapısal anlamda hem de oyunda zikredilen perde gazelleri içerisinde pek çok tasavvufî unsurun barındığı görülmektedir. Bu çalışmada oyun sadece yapısal anlamda değerlendirilmiş perde gazellerine yer verilmemiştir. Gazellerdeki tasavvufî unsurlar başlı başına hacimli bir çalışmanın konusu olmaya adaydır. Sadece oyunun çıkış noktasına dair rivayetler değil gazellerdeki bu unsurlar da gölge oyununda tasavvufun ne denli etkin bir rol aldığını sergilemektedir. Çalışmamızın giriş bölümünde gölge oyununun kökeni, Şeyh Küşterî ve oyunun temel karakterleri olan Hacivat ile Karagöz’ün tarihî ve tasavvufî şahsiyetleri incelenmiştir. Bahsi geçen isimlerin sûfî çevrelerle münasebetleri oyundaki tasavvuf düşüncesinin tesirini kavramak adına katkı sağlayacaktır. Ana metinde sûfîlerin gölge oyunu üzerine yaptığı değerlendirmelere yer verilmiştir. Oyunun temel unsurları olan gölge ile ışık metaforlarına dair İbnü’l-Arabî (ö. 638/1240) ve Mevlânâ Celâleddîn-i Rûmî (ö. 672/1273)’nin açıklamalarına değinilerek bahsi geçen sûfîlerin varlık anlayışında bu kavramların konumu incelenmiştir. Çalışmamızın son bölümünde ise sûfîlerin varlık anlayışlarını ifade ederken kullandıkları kavramların gölge oyunundaki karşılıkları ve gölge oyunun tasavvufî yapısı izah edilmiştir.

Joesana Tjahjani, Sonya Sondakh

Bukit Kasih Kanonang (Kanonang Love Hill) is a place of worship for Christians of the Minahasa Regency, North Sulawesi, one of the provinces of Indonesia, which in its development has also become a popular tourist destination. As a site that blends Christian elements, local traditional elements and values of tolerance among the world’s major religions namely Christianity, Islam, Buddhism and Hinduism, this beautiful piece of land includes a number of sites such as a monument to tolerance, a house of worship for each religion, a giant crucifix, statues, and the faces of Minahasan ancestors carved into cliff faces. All these elements suggest that while the people have values of tolerance and religious harmony, nonetheless the 55-meter giant white cross at Bukit Kasih Kanonang is evidence of the dominance of the local people’s Protestant Christian belief. Using the perspective of Hayden’s Antagonistic Tolerance, this paper investigates how people of other religions deal with the issue of dominance and how the social construct in the saying Torang Samua Basudara (we are all family), which has been the way of life of the Minahasan people, supports the concepts of tolerance and harmony.

Mitul Islam, Andrew Zimmer

In this paper we prove a general structure theorem for relatively hyperbolic groups (with arbitrary peripheral subgroups) acting naive convex co-compactly on properly convex domains in real projective space. We also establish a characterization of such groups in terms of the existence of an invariant collection of closed unbounded convex subsets with good isolation properties. This is a real projective analogue of results of Hindawi-Hruska-Kleiner for ${\rm CAT}(0)$ spaces. We also obtain an equivariant homeomorphism between the Bowditch boundary of the group and a quotient of the ideal boundary.

Bohua Peng, Mobarakol Islam, Mei Tu

Curriculum learning needs example difficulty to proceed from easy to hard. However, the credibility of image difficulty is rarely investigated, which can seriously affect the effectiveness of curricula. In this work, we propose Angular Gap, a measure of difficulty based on the difference in angular distance between feature embeddings and class-weight embeddings built by hyperspherical learning. To ascertain difficulty estimation, we introduce class-wise model calibration, as a post-training technique, to the learnt hyperbolic space. This bridges the gap between probabilistic model calibration and angular distance estimation of hyperspherical learning. We show the superiority of our calibrated Angular Gap over recent difficulty metrics on CIFAR10-H and ImageNetV2. We further propose Angular Gap based curriculum learning for unsupervised domain adaptation that can translate from learning easy samples to mining hard samples. We combine this curriculum with a state-of-the-art self-training method, Cycle Self Training (CST). The proposed Curricular CST learns robust representations and outperforms recent baselines on Office31 and VisDA 2017.

Mengya Xu, Mobarakol Islam, Chwee Ming Lim et al.

Generating a surgical report in robot-assisted surgery, in the form of natural language expression of surgical scene understanding, can play a significant role in document entry tasks, surgical training, and post-operative analysis. Despite the state-of-the-art accuracy of the deep learning algorithm, the deployment performance often drops when applied to the Target Domain (TD) data. For this purpose, we develop a multi-layer transformer-based model with the gradient reversal adversarial learning to generate a caption for the multi-domain surgical images that can describe the semantic relationship between instruments and surgical Region of Interest (ROI). In the gradient reversal adversarial learning scheme, the gradient multiplies with a negative constant and updates adversarially in backward propagation, discriminating between the source and target domains and emerging domain-invariant features. We also investigate model calibration with label smoothing technique and the effect of a well-calibrated model for the penultimate layer's feature representation and Domain Adaptation (DA). We annotate two robotic surgery datasets of MICCAI robotic scene segmentation and Transoral Robotic Surgery (TORS) with the captions of procedures and empirically show that our proposed method improves the performance in both source and target domain surgical reports generation in the manners of unsupervised, zero-shot, one-shot, and few-shot learning.

Mobarakol Islam, V Jeya Maria Jose, Hongliang Ren

Segmentation of brain tumor from magnetic resonance imaging (MRI) is a vital process to improve diagnosis, treatment planning and to study the difference between subjects with tumor and healthy subjects. In this paper, we exploit a convolutional neural network (CNN) with hypercolumn technique to segment tumor from healthy brain tissue. Hypercolumn is the concatenation of a set of vectors which form by extracting convolutional features from multiple layers. Proposed model integrates batch normalization (BN) approach with hypercolumn. BN layers help to alleviate the internal covariate shift during stochastic gradient descent (SGD) training by zero-mean and unit variance of each mini-batch. Survival Prediction is done by first extracting features(Geometric, Fractal, and Histogram) from the segmented brain tumor data. Then, the number of days of overall survival is predicted by implementing regression on the extracted features using an artificial neural network (ANN). Our model achieves a mean dice score of 89.78%, 82.53% and 76.54% for the whole tumor, tumor core and enhancing tumor respectively in segmentation task and 67.90% in overall survival prediction task with the validation set of BraTS 2018 challenge. It obtains a mean dice accuracy of 87.315%, 77.04% and 70.22% for the whole tumor, tumor core and enhancing tumor respectively in the segmentation task and a 46.80% in overall survival prediction task in the BraTS 2018 test data set.

Tasnim Sakib Apon, Abrar Islam, MD. Golam Rabiul Alam

Presently online video games have become a progressively favorite source of recreation and Counter Strike: Global Offensive (CS: GO) is one of the top-listed online first-person shooting games. Numerous competitive games are arranged every year by Esports. Nonetheless, (i) No study has been conducted on video analysis and action recognition of CS: GO game-play which can play a substantial role in the gaming industry for prediction model (ii) No work has been done on the real-time application on the actions and results of a CS: GO match (iii) Game data of a match is usually available in the HLTV as a CSV formatted file however it does not have open access and HLTV tends to prevent users from taking data. This manuscript aims to develop a model for accurate prediction of 4 different actions and compare the performance among the five different transfer learning models with our self-developed deep neural network and identify the best-fitted model and also including major voting later on, which is qualified to provide real time prediction and the result of this model aids to the construction of the automated system of gathering and processing more data alongside solving the issue of collecting data from HLTV.