Inverse Planning Research Articles

Improving VMAT dose calculation accuracy and planning quality via a GPU-accelerated Fourier transform dose calculation algorithm.

Inverse planning typically utilizes fast, less accurate dose calculation algorithms during the iterative optimization process, thus leading to dose calculation errors (DCEs) and suboptimal plans that often require dose normalization and/or plan re-optimization. A graphic processing unit (GPU) accelerated Fourier transform dose calculation (FTDC) was recently commissioned at our institution during the Eclipse treatment planning system (Varian Medical Systems) v18.0 upgrade. We hypothesize that FTDC could reduce DCEs and planning failure rates (PFRs) compared to its predecessor, multi-resolution dose calculation (MRDC), while improving efficiency through utilization of GPUs. Fifty lung SBRT plans were optimized with MRDC and FTDC dose calculation algorithms. Acuros XB (AXB) was then used for final dose calculations. DCEs for target and organ-at-risk (OAR) were calculated as the percent difference between AXB and dose calculated at the final optimization step. Plan quality was assessed using an in-house planning scorecard where PFRs were calculated as the percentage of plans that had a plan score less than 90% with optimal plans scored at 100%. FTDC showed excellent agreement with AXB in terms of planning target volume (PTV) coverage, as PTV D95% DCEFTDC averaged 0.8%±0.9%, compared to DCEMRDC's -2.5%±3.2%. DCEs for thoracic OARs were reduced with less variation when optimizing with FTDC as compared to MRDC. FTDC had a PFR of 10% (5 out of 50) versus MRDC's 32% (16 out of 50). The subsequent re-optimization rate resulted from a plan normalization of 3% or greater was 4% for FTDC compared to MRDC's 38%. FTDC with GPU acceleration reduced optimization time by 75% on average compared to MRDC without GPU acceleration. FTDC shows more accurate dose calculation accuracy compared to MRDC. Its use during the optimization process improved planning quality and efficiency assisted with GPUs.

Pulse-by-pulse treatment planning and its application to generic observations of ultra-high dose rate (FLASH) radiotherapy with photons and protons

Objective.The exact temporal characteristics of beam delivery affect the efficacy and outcome of ultra-high dose rate (UHDR or 'FLASH') radiotherapy, mainly due to the influence of the beam pulse structure on mean dose rate. Single beams may also be delivered in separate treatment sessions to elevate mean dose rate. This paper therefore describes a model for pulse-by-pulse treatment planning and demonstrates its application by making some generic observations of the characteristics of FLASH radiotherapy with photons and protons.Approach.A beam delivery model was implemented into the AutoBeam (v6.3) inverse treatment planning system, so that the individual pulses of the delivery system could be explicitly described during optimisation. The delivery model was used to calculate distributions of time-averaged and dose-averaged mean dose rate and the dose modifying factor for FLASH was then determined and applied to dose calculated by a discrete ordinates Boltzmann solver. The method was applied to intensity-modulated radiation therapy with photons as well as to passive scattering and pencil beam scanning with protons for the case of a simple phantom geometry with a prescribed dose of 36 Gy in 3 fractions.Main results.Dose and dose rate are highest in the target region, so FLASH sparing is most pronounced around the planning target volume (PTV). When using a treatment session per beam, OAR sparing is possible more peripherally. The sparing with photons is higher than with protons because the dose to OAR is higher with photons.Significance.The framework provides an efficient method to determine the optimal technique for delivering clinical dose distributions using FLASH. The most sparing occurs close to the PTV for hypofractionated treatments.

Influence of planning target volume margins using various prescription isodoses in gamma knife radiosurgery for single brain metastasis: a phantom study

Abstract Objective: The study seeks to evaluate the influence of planning target volume (PTV) margins on plan parameters during inverse planning of brain metastases with the Gamma Knife treatment unit, considering various prescription isodose levels (PIL). Material & Method: CT scan images of a STEEV anthropomorphic phantom were transferred into the GAMMA PLAN Treatment Planning System. A target measuring a volume of 4·9cc was centrally contoured. Plans with a 0 mm volume margin at five prescription isodose levels from 50% to 70% at 5% increment were created. With 0.5 mm, 1 mm, 1.5 mm and 2 mm PTV margins, identical plans were regenerated. Adjustments were made to each plan when necessary to achieve same target coverage. One-way ANOVA test was used to analyse the influence of PTV margins on parameters including Selectivity[S], Gradient index [GI], V12, Paddick’s conformal index [PCI] and Treatment time [TI]. Results: Margin addition resulted in PTV volume increase. The findings indicated that the PTV margin of 2.0 mm exhibited the highest mean selectivity of (0.93 ± 0.00), PCI (0.92 ± 0.01), GI (2.50 ± 0.04), V12 (16.17 ± 0.38) and treatment time (118.32 ± 2.91 min). The 0.0 mm PTV margin had the lowest mean value for all the parameters except for the treatment time (105.58 ± 3.48 min) which was slightly higher compared to the 0.5 mm PTV margin (M = 86.36 ± 4.13 min). Conclusion: Incremental increases in PTV margins for Gamma knife radiosurgery though a relatively controversial concept influence all dosimetric parameters, which may pose potential detrimental effects and thus need to be carefully evaluated for brain metastasis treatment.

Modeling and Simulation Method of Coordinated Manipulator Based on Robotic Toolbox and ADAMS

Abstract The coordinator was an important component of the automatic ammunition loading system of large-caliber artillery. In this paper, kinematics and dynamics of a coordination manipulator with five degrees of freedom were carried out. The forward and inverse kinematics analysis and motion trajectory planning of the simplified coordination manipulator under different firing angles were carried out with Robotic Toolbox to obtain the motion parameters of angular displacement, angular velocity and angular acceleration at each driving joint of the manipulator. Using the motion parameters obtained from the trajectory planning, the inverse dynamics of the manipulator was analyzed by ADAMS, and the driving torque curves of each joint were calculated, which provided a reference for the subsequent prototype development and simulation control of the manipulator.

IMPROVING PLAN QUALITY IN CERVICAL CANCER BRACHYTHERAPY USING KNOWLEDGE-BASED PLANNING FOR DIRECTION MODULATED BRACHYTHERAPY TANDEM APPLICATOR

The bladder and rectal toxicities in cervical cancer brachytherapy are positively correlated with the DVH parameter: D2cc. This study evaluates the feasibility of knowledge-based planning to predict the D2cc, identify suboptimal plans, and improve the plan quality with Direction Modulated Brachytherapy (DMBT) applicators using knowledge-based planning based on linear relationship between overlap distances and D2cc. The overlap volume histogram (OVH) method was used to determine the distances for 2 cm3 of overlap between the Organs at Risks (OAR) and High-Risk Clinical Target Volume (CTVHR). Linear plots were utilized to model the OAR D2cc and 2 cm3 overlap distances. Two datasets from 45 patients (125 plans) were used to create 2 independent models: Model 1 from 59 Intracavitary (IC) and Model 2 from 66 Intracavitary-Interstitial (ICIS) plans. Performances were compared using 5-fold cross-validation. The predicted D2cc values were used as the maximum constraints in the inverse planning optimization. The mean bladder D2cc decreased by 4.3% and 10.3% for conventional applicators, and 4.4% and 3.6% for DMBT applicators for Models 1 and 2, respectively. The rectum D2cc decreased by 3.4% and 10.7% for conventional and 3.0% and 5.0% for DMBT applicators, respectively. The sigmoid D2cc decreased by 3.1% and 6.9% for conventional and 3.2% and 5.9% for DMBT applicators, respectively. There were also significant reductions for the recto-vaginal (RV-RP) point and posterior-inferior border of symphysis (PIBS) reference points: PIBS+2cm, PIBS+1cm, PIBS-1cm, and PIBS-2cm, for both models as well. A knowledge-based planning method successfully predicted D2cc and optimized brachytherapy plans for cervical cancer. The proposed model demonstrates the feasibility of predicting D2cc, detecting suboptimal plans, and improving the plan quality especially for DMBT where cumulative clinical experience is limited.

Infrastructuring informal urbanism: Negotiation of water, electricity, and natural gas in urban villages in Chengdu, China

Infrastructure such as water, electricity, and natural gas fundamentally underpins informal housing and industrial development in urban villages. Yet how the infrastructure is built, maintained, and governed, and what are the underlying mechanisms, remain peripheral to existing literature and policy agenda. This study addresses this gap by incorporating a socio-technical approach to infrastructure into informal urbanism to understand the negotiation of water, electricity, and natural gas in two neighboring urban villages in Chengdu, China. Four rounds of fieldwork and in-depth interviews with various stakeholders found highly precarious provision of infrastructure in urban villages. Its spatial layout, facilities, charges, quality control, and maintenance rest uneasily on, and then in turn shape, the development of informal renting markets and industries in different urban villages, especially when considering the cross-sectional interactions between different types of infrastructure. These processes are dominated by stakeholders’ commercial logics embedded in informal urbanism, including the urban village and infrastructure providers’ profit-seeking strategies, enterprises and migrants’ cost-saving behaviors, and the governments’ purposive absence in governing infrastructure, which leads to difficulties in meeting urban village residents’ needs for qualified infrastructure. This study unravels the “black box” of infrastructure in urban villages and puts forward inclusive planning strategies to promote infrastructure in urban villages.

Impacts of Large Hydropower Projects on the Ecological Environment of Watersheds: A Case Study of Ertan Reservoir Area

Ertan Hydroelectric Power Station was the first large-scale water conservancy facility in western China, and with its completion, the ecological pattern of the reservoir area has changed dramatically; however, the changes in habitat quality before and after the completion of the reservoir have not yet been systematically monitored and evaluated. In this study, we analyzed the spatial and temporal characteristics of the remote sensing ecological index (RSEI), used CA-Markov model and GeoDetector, evaluated the ecological environment of the Ertan Reservoir area in each five-year period from 1995 to 2020, simulated the ecological quality of the Ertan Reservoir area in 2025, and revealed the nine drivers and their interactions affecting ecological quality of the watershed from a geologic point of view, and finally put forward reasonable planning and targeted protection suggestions. Finally, rational planning and targeted protection recommendations were proposed. The main results were as follows: (1) After the completion of the Ertan Hydropower Station, the spatial distribution of the RSEI in the reservoir area varied significantly, with a trend of “rising-declining-rising” in time, and the area share of “good” area increased the most, by 19.83%. (2) The degree of grading of each driving factor had different degrees of influence on the size of the RSEI value, and its interaction enhanced the spatial differentiation of the RSEI. (3) The average value of the RSEI is 0.66 in 2025, and the ecological environment quality will show a steady improvement in five years. The results of the study can provide a reference for constructing RSEI indicators for large hydropower facilities.

Bidirectional Planning for Autonomous Driving Framework with Large Language Model.

Autonomous navigation systems often struggle in dynamic, complex environments due to challenges in safety, intent prediction, and strategic planning. Traditional methods are limited by rigid architectures and inadequate safety mechanisms, reducing adaptability to unpredictable scenarios. We propose SafeMod, a novel framework enhancing safety in autonomous driving by improving decision-making and scenario management. SafeMod features a bidirectional planning structure with two components: forward planning and backward planning. Forward planning predicts surrounding agents' behavior using text-based environment descriptions and reasoning via large language models, generating action predictions. These are embedded into a transformer-based planner that integrates text and image data to produce feasible driving trajectories. Backward planning refines these trajectories using policy and value functions learned through Actor-Critic-based reinforcement learning, selecting optimal actions based on probability distributions. Experiments on CARLA and nuScenes benchmarks demonstrate that SafeMod outperforms recent planning systems in both real-world and simulation testing, significantly improving safety and decision-making. This underscores SafeMod's potential to effectively integrate safety considerations and decision-making in autonomous driving.

Inverse versus convolution treatment planning algorithms for gamma knife radiosurgery.

To compare the convolution and inverse algorithm plans. The cross-sectional study was conducted from January to May 2022 at the Icon Gamma Knife Centre, Al- Taj Hospital, Baghdad, Iraq, and comprised patients with malignant and benign brain tumours who underwent gamma knife therapy. Each patient's brain was imaged using computed tomography and magnetic resonance imaging. The neurosurgeon prescribed the dose depending on the tumour volume and type, while the medical physicist generated the two plans based on inverse and convolution algorithms. The prescribed dose was delivered to 50% of the isodose line of the tumour. Each plan was evaluated with respect to tumour conformity index, coverage, gradient index, number of shots, and time of treatment. Of the 30 patients, 17(56.7%) were males and 13(43.3%) were females. The overall mean age was 46.29±15.20 years (range: 10-71 years). The mean dose delivered was 15.86±3.86Gy, and the mean number of gamma radiation shots was 12.56±6.95. There was significant difference between the two algorithm plans for all dosimetric parameters, with the inverse plan providing higher coverage and selectivity than convolution plan, but taking longer time(p<0.05), while plan was inverse plan better than convolution plan in terms of gradient and conformity (p<0.05). With more extended treatment, the inverse plan was found to have superior selectivity, coverage, gradient index and Paddick conformity index values compared to the convolution plan.

Deep learning-based prediction of the dose-volume histograms for volumetric modulated arc therapy of left-sided breast cancer.

The advancements in artificial intelligence and computational power have made deep learning an attractive tool for radiotherapy treatment planning. Deep learning has the potential to significantly simplify the trial-and-error process involved in inverse planning required by modern treatment techniques such as volumetric modulated arc therapy (VMAT). In this study, we explore the ability of deep learning to predict organ-at-risk (OAR) dose-volume histograms (DVHs) of left-sided breast cancer patients undergoing VMAT treatment based solely on their anatomical characteristics. The predicted DVHs could be used to derive patient-specific dose constraints and dose objectives, streamlining the treatment planning process, standardizing the quality of the plans, and personalizing the treatment planning. This study aimed to develop a deep learning-based framework for the prediction of organ-specific dose-volume histograms (DVH) based on structures delineated for left-sided breast cancer treatment. We used a dataset of 249 left-sided breast cancer patients treated with tangential VMAT fields. We extracted delineated structures and dose distributions for each patient and derived slice-by-slice DVHs for planning target volume (PTV) and organs-at-risk. The patients were divided into training (70%, n=174), validation (10%, n=24), and test (20%, n=51) sets. Collected data were used to train a deep learning model for the prediction of the DVHs based on the delineated structures. The developed deep learning model comprised a modified DenseNet architecture followed by a recurrent neural network. In the independent test set (n=51), the point-wise differences in the slice-by-slice DVHs between the clinical and predicted DVHs were small; the mean squared errors were 3.53, 1.58, 2.28, 3.37, and 1.44 [×10-4] for PTV, heart, ipsilateral lung, contralateral lung, and contralateral breast, respectively. With the derived cumulative DVHs, the mean absolute difference±standard deviation of mean doses between the clinical and the predicted DVH were 0.08± 0.04Gy, 0.24± 0.22Gy, 0.73± 0.46Gy, 0.07± 0.06Gy, and 0.14± 0.14Gy for PTV, heart, ipsilateral lung, contralateral lung, and contralateral breast, respectively. The deep learning-based approach enabled automatic and reliable prediction of the DVH based on delineated structures. The predicted DVHs could potentially serve as patient-specific clinical goals used to aid treatment planning and avoid suboptimal plans or to derive optimization objectives and constraints for automated treatment planning.

Investigating the neural computations underlying visual social inference with graph neural network and inverse planning models

Investigating the neural computations underlying visual social inference with graph neural network and inverse planning models

High Performance Computing for Large Scale Civil Engineering Simulations

High performance Computing (HPC) may be a key portion of progressing large-scale models in respectful designing. It makes modeling complicated buildings and frameworks more precise and effective than ever some time recently. This paper looks at how HPC can be utilized in respectful designing models, particularly how it can be utilized to arrange, analyze, and move forward enormous ventures. We see at diverse HPC plans, such as dispersed computing, cloud-based arrangements, and how they can be utilized for fluid-structure intelligent, auxiliary flow, and geotechnical ponders. The think about appears how HPC makes it simpler to work with exceptionally expansive datasets and complicated models, like those required for considering seismic tremors, figuring out how much wind loads an region, and keeping an eye on the wellbeing of foundation. Engineers can do more precise real-time models, move forward plans, and foresee how buildings will carry on in cruel circumstances by utilizing high-performance strategies and adaptable computer apparatuses. The study moreover talks almost the problems and restrictions that come with HPC, just like the require for specialized program, the tall costs, and issues with overseeing information. A few thoughts are given for getting around these issues, such as making equipment more productive, making advance on parallel strategies, and utilizing open-source HPC devices. Proposed strategy appears how HPC can change the field of respectful designing through case thinks about and real-life cases. The ponder appears how it can offer assistance make building ventures more secure, more ecologically neighborly, and superior at what they do. The final portions of the paper talks almost future study objectives and patterns. It stresses the significance of proceeding to come up with unused thoughts in arrange to completely utilize HPC for respectful building errands.

Patient perspective on adapting to bowel dysfunction after rectal cancer surgery.

Bowel dysfunction continues to be a clinically significant consequence of rectal cancer surgery, affecting quality of life. Rectal cancer patients value self-empowerment and adaptation to change to improve their quality of life in the context of bowel dysfunction. There are limited qualitative data addressing patients' perspectives on adapting to bowel dysfunction. The aim of this study is to evaluate patients' perspectives on adapting to bowel dysfunction after rectal cancer surgery. Adult patients who underwent rectal cancer surgery with sphincter preservation at a single colorectal referral centre from July 2017 to July 2020 were included. Patients were excluded if they had surgery <1 year since recruitment, received a permanent stoma or developed recurrence or metastasis. Semistructured interviews were held by phone and transcribed verbatim. Bowel dysfunction was assessed via the low anterior resection syndrome (LARS) score. Thematic analysis was used to identify adaptations which patients found helpful for improving bowel dysfunction after rectal cancer surgery. A total of 54 patient interviews were included. The distribution of patients with no, minor and major LARS was 39%, 22% and 39%, respectively. Four main themes were conceived from the analysis: implementing lifestyle changes, fostering supportive relationships and self-compassion, communication and access to resources, and adapting to social and cultural challenges. Associated subthemes were identified, namely forward planning, self-compassion and addressing social stigma. Patients' valuable perspective on adapting to bowel dysfunction involve subtle themes which expand the existing literature. These themes inform a patient-centred approach, which may improve outcomes and quality of care for rectal cancer patients.

Education that lacks access to deaf experience: odd situations in Sweden

ABSTRACT This paper discusses disadvantaging situations that deaf students encounter in higher education in Sweden. We report two recent cases of deaf students’ academic welfare being put at risk. We foreground in these cases the ‘odd situations’ that arise when provisions that fail to access the particular nature of deaf experience also fail to secure deaf students’ participation rights, to be and become the deaf person they wish to be, lead the life they wish to live, and so on. Often, the ‘oddness’ of the situations that arise is in part indicated by no-one involved lacking in good intentions or not doing their very best: there is no lack of good will, but a lack of shared understanding. What deaf students know differently is rarely present in deliberation and not part of forward planning. We infer that situations of this sort reflect epistemic injustice. We propose that this form of formative epistemic injustice – educators not taking on board what deaf students know – can perhaps be overcome by higher education institutions proactively involving deaf students in matters that concern both them and future deaf students.

The Security Threat and Precautionary Measures of QR Code of Internet of Things Technology

The Internet of Things (IoT) is the expansion and extension of the traditional network. It is a network that connects goods and objects, which has been widely used in today's social development process. It occupies an important position in various industries. The emergence of the Internet of Things has greatly improved the refinement level of human management. The QR code (Quick Response Code) is a part of the perception layer of the IoT, which belongs to the perception and recognition technology of the IoT. The QR code not only brings convenience to users but also becomes the carrier and disseminator of malware, phishing, and other attacks. Therefore, it is of great significance for the security of the IoT to understand the potential threats of the QR code, analyze its potential attack methods, and put forward defense plans. This paper briefly introduces the basic characteristics of the QR code, as well as some attack methods and potential threats against the QR code, and put forward some preventive measures from both technical and non-technical aspects. The technical aspect includes the combination of cryptography and the introduction of third-party management. The non-technical aspects are discussed at the national and individual user levels.

Joint modeling of choices and reaction times based on Bayesian contextual behavioral control.

In cognitive neuroscience and psychology, reaction times are an important behavioral measure. However, in instrumental learning and goal-directed decision making experiments, findings often rely only on choice probabilities from a value-based model, instead of reaction times. Recent advancements have shown that it is possible to connect value-based decision models with reaction time models. However, typically these models do not provide an integrated account of both value-based choices and reaction times, but simply link two types of models. Here, we propose a novel integrative joint model of both choices and reaction times by combining a computational account of Bayesian sequential decision making with a sampling procedure. This allows us to describe how internal uncertainty in the planning process shapes reaction time distributions. Specifically, we use a recent context-specific Bayesian forward planning model which we extend by a Markov chain Monte Carlo (MCMC) sampler to obtain both choices and reaction times. As we will show this makes the sampler an integral part of the decision making process and enables us to reproduce, using simulations, well-known experimental findings in value based-decision making as well as classical inhibition and switching tasks. Specifically, we use the proposed model to explain both choice behavior and reaction times in instrumental learning and automatized behavior, in the Eriksen flanker task and in task switching. These findings show that the proposed joint behavioral model may describe common underlying processes in these different decision making paradigms.

Feasibility and Safety of the “One-Week Breast Radiation Therapy” Program

AimsFAST-Forward and UK-FAST-trials have demonstrated the safety and efficacy of five-fraction breast adjuvant radiation therapy (RT) and have become the standard of care for selected early breast cancer patients. In response to the additional burden caused by the COVID-19 pandemic, we implemented “One-Week Breast RT,” an innovative program delivering five-fraction whole breast RT in a complete 5-day workflow. The primary objective of this study was to demonstrate the feasibility and safety of our program. The secondary objective was to evaluate cosmetic results. Material and methodsA total of 120 patients treated from February 2021 to March 2022, received whole breast RT without lymph node irradiation nor boost, with 26 Gy in five fractions over one week. Inverse planning with restricted optimization parameters offers systematic deep inspiration breath-hold aimed to provide treatment plans compliant with FAST-Forward recommendations. Toxicity and cosmetic evaluations were prospectively registered prior (pre-RT), at the end (end-RT), and 6 months after RT (6 months) based on Common Terminology Criteria for Adverse Events v. 4.03 and Harvard scale. ResultsWith a median age of 70 years (interquartile range (IQR): 66–74) and a median follow-up of 6 months (IQR: 6.01–6.25), most patients (93.3%) completed their RT in one week from baseline to the end of the treatment consultation. The most common acute toxicities (at end-RT) were skin-related: radio-dermatitis (72%), induration (35%), hyperpigmentation (8%), and breast edema (16%). The rate of radio-dermatitis decreased from end-RT to 6 months (71.7% vs 5.4%, P< 0.001). No patient experienced grade ≥3 toxicity. At 6 months, cosmetic results were generally good or excellent (94.1%). ConclusionThis study confirms the feasibility and acute safety of the “One-Week Breast RT” in real life. Favorable toxicity profiles and good cosmetic outcomes are in line with FAST-Forward results. A prospective national cohort, aimed at decreasing treatment burden, maintaining safety, efficacy, and improving RT workflow efficiency with longer follow-up is ongoing.

Farmers’ perceived effect of the COVID-19 pandemic and its relationship to preparedness and risk perception

The impact of the COVID-19 pandemic across the agri-food sector was significant and pervasive, challenging farmers' resilience through multiple disruptions to the supply chain. To support forward planning in face to future shocks, this research examines the perceived impacts of the COVID-19 pandemic by farmers themselves, providing insights from the UK. Using a nation-wide online survey carried out during two distinct waves of the pandemic in 2021, the study reveals changing perceptions and the relationship between preparedness and perceived impacts. Results indicate that perceptions of both the severity of the COVID-19 impacts and preparedness for such impacts in the future, were scaled down as the pandemic evolved. Findings suggest that a farmer feeling more prepared in the present to withstand shocks is positively influenced by them perceiving the impact of COVID-19's in their business as severe. This effect is reinforced for farmers that felt more prepared to withstand COVID-19's impacts when the pandemic unfolded, as well as for those that perceive the impact of COVID-19 as long-term. Farmers in our sample appear to have adapted to the shocks to their businesses through supply-side interventions, focusing on having higher flexibility in delivery of products and diversifying their supply networks. Doing so requires them to absorb an increase in both fixed and variable costs, which can end-up been transferred to the consumer. Government support moving forward should focus on strengthening and, perhaps, re-imagining the whole supply industry and re-defining the role of farmers as more than food producers, but also as stewards of climate and food resilience.

Customer Acquisition via Explainable Deep Reinforcement Learning

Effective customer acquisition is crucial for digital platforms, with sequential targeting ensuring that marketing messages are both timely and relevant. The proposed deep recurrent Q-network with attention (DRQN-attention) model enhances this process by optimizing long-term rewards and increasing decision-making transparency. Tested with a data set from a digital bank, the DRQN-attention model has proven to enhance clarity in decision making and outperform traditional methods in boosting long-term rewards. Its attention mechanism acts as a strategic tool for forward planning, pinpointing crucial ad marketing channels that are likely to engage and convert prospects. This capability enables marketers to understand the dynamic targeting strategies of the proposed model that align with customer profiles, dynamic behaviors, and the seasonality of the markets, thereby boosting confidence and effectiveness in their customer acquisition strategies.

Thorns of Failures: Views of Non-Passers of Criminology Board Examination

Philippine Regulation Commission (PRC) records show that the national passing percentage in the Criminologist Licensure Examination (CLE) is deteriorating. The number of unlicensed Criminology graduates throughout the country is increasing. This study explored the lived experiences of non-passers of the Criminologist Licensure Examination (CLE) through a qualitative research method. The informants of this study were 10 board exam flunkers throughout the Province of Cebu. Four informants were used for the in-depth interview, and six were used for the focus group discussion. Eight (8) emergent themes described the positive and negative experiences of the informants before, during, and after the board exam. For the positive experiences, four (4) themes were developed, namely: Take a Trip Down Memory Lane, Licensure Examination: The Main Event, Acceptance and Moving Forward and Contingency Plan: Look for a Job. For the negative experiences, four (4) themes were formulated, namely: The Chronicles of Review, Test Anxiety: The Feeling of Taking the Licensure Examination, Board Exam Result: A Flunker’s Nightmare and Mission Unsuccessful. For the plights of the informants before, during, and after taking the licensure examination, eight (8) emergent themes were formulated, namely: Procrastination and Idleness, Indiscretion of Reviewees, Financial Struggle: A Dilemma to Board Exam Takers, Family Problems: A Heavy Load to Carry, The Answer Sheet: A Fragile Piece of Paper, Bad Luck: In the Wrong Place at the Wrong Time, Examinee’s Inability to Comprehend Questions: A Tough Assignment, The Fallen Leaves, and Disappointments and Failure to Meet Expectations: Adding Insult to Injury. For the reasons of the informants for not retaking the exam, two (2) themes were developed, namely: Age Limit in the Tri-Bureau: Crashing the Flunker’s Aspirations and Making a Fresh Start.