On the integration of Impact Assessment and Circular Economy: a literature review DOI Creative Commons
Marina Morhy Pereira

Опубликована: Ноя. 17, 2023

Achieving sustainability requires overcoming a series of challenges, among which are rapid population growth, increased climate temperature, and environmental degradation.One the ways to deal with these challenges is transition from linear economy, based on "extract, produce discard, Circular Economy (CE), scenario in flow materials energy as closed possible an image circle.However, not all strategies achieve sustainable result.Therefore, it necessary assess impact circularity ensure that they expected results.In this context, Impact Assessment (IA), process used tool influence decision-making towards decisions promote Sustainability, help more circular mode production.Thus, objective work understand perspectives integration perspective critical review literature.To end, Bibliometric Analysis was initially carried out map areas between two disciplines.A Content results proved need for further investigation.Thus, patterns emerged Analysis, keywords were chosen start Systematic Literature Review (SLR).The SLR aims point how themes IA interact interconnect, analyzing aspects possibilities indicated by relevant literature.In way, will be identify principles relate through identification, literature, different types relationship may exist (for example: seen tool/process assesses strategies/actions or incorporates strategies?).The should contribute area filling gaps such assessment alternatives, cumulative impacts, analysis biodiversity, change, several other can find theoretical practical solution Economy.In addition, we intend demonstrate, ability one many potentialities Assessment, being crucial implementation actions guarantee reach truly result.

Язык: Английский

Advanced RUL Estimation for Lithium-Ion Batteries: Integrating Attention-Based LSTM with Mutual Learning-enhanced Artificial Bee Colony Optimization DOI

Yi-Jun Xu

Journal of The Institution of Engineers (India) Series B, Год журнала: 2024, Номер unknown

Опубликована: Авг. 4, 2024

Язык: Английский

Процитировано

3
Integrating static and dynamic game theory with complex networks: Enhancing strategy dynamics through adaptive update rules DOI

Reza Hakhamanesh,

Javad Mohammadzadeh,

Hadi Gholami Khaibary

и другие.

Chaos Solitons & Fractals, Год журнала: 2025, Номер 192, С. 116063 - 116063

Опубликована: Янв. 31, 2025

Язык: Английский

Процитировано

0
A proximal policy optimisation algorithm-based algorithm for cardiovascular disorders detection DOI
Yingjie Niu,

Xianchuang Fan,

Rui Xue

и другие.

Journal of Medical Engineering & Technology, Год журнала: 2025, Номер unknown, С. 1 - 20

Опубликована: Март 11, 2025

Cardiovascular diseases (CVDs) significantly impact athletes, impacting the heart and blood vessels. This article introduces a novel method to assess CVD in athletes through an artificial neural network (ANN). The model utilises mutual learning-based bee colony (ML-ABC) algorithm set initial weights proximal policy optimisation (PPO) address imbalanced classification. ML-ABC uses learning enhance process by updating positions of food sources with respect best fitness outcomes two randomly selected individuals. PPO makes updates ANN stable efficient improve model's reliability. Our approach formulates classification problem as series decision-making processes, rewarding every act higher rewards for correctly identifying instances minority class, hence handling class imbalance. We evaluated performance on diversified medical dataset including 26,002 who were examined within Polyclinic Occupational Health Sports Zagreb, further validated NCAA NHANES datasets verify generalisability. findings indicate that our outperforms existing models accuracies 0.88, 0.86 0.82 respective datasets. These results clinical application advance cardiovascular disorder detection methodologies.

Язык: Английский

Процитировано

0
Relation extraction with enhanced self-attention model for SOV word order languages: Persian case study DOI
Ebrahim Ganjalipour, A. H. Refahi Sheikhani, Sohrab Kordrostami

и другие.

International Journal of Data Science and Analytics, Год журнала: 2025, Номер unknown

Опубликована: Май 13, 2025

Язык: Английский

Процитировано

0
Melanoma classification using generative adversarial network and proximal policy optimization DOI

Xiangui Ju,

Chi‐Ho Lin,

Suan Lee

и другие.

Photochemistry and Photobiology, Год журнала: 2024, Номер unknown

Опубликована: Июль 30, 2024

In oncology, melanoma is a serious concern, often arising from DNA changes caused mainly by ultraviolet radiation. This cancer known for its aggressive growth, highlighting the necessity of early detection. Our research introduces novel deep learning framework classification, trained and validated using extensive SIIM-ISIC Melanoma Classification Challenge-ISIC-2020 dataset. The features three dilated convolution layers that extract critical feature vectors classification. A key aspect our model incorporating Off-policy Proximal Policy Optimization (Off-policy PPO) algorithm, which effectively handles data imbalance in training set rewarding accurate classification underrepresented samples. this framework, visualized as an agent making series decisions, where each sample represents distinct state. Additionally, Generative Adversarial Network (GAN) augments to improve generalizability, paired with new regularization technique stabilize GAN prevent mode collapse. achieved F-measure 91.836% geometric mean 91.920%, surpassing existing models demonstrating model's practical utility clinical environments. These results demonstrate potential enhancing detection informing more treatment approaches, significantly advancing combating cancer.

Язык: Английский

Процитировано

2
A Multi-Channel Advertising Budget Allocation Using Reinforcement Learning and an Improved Differential Evolution Algorithm DOI Creative Commons
Mengfan Li, Jian Zhang, Roohallah Alizadehsani

и другие.

IEEE Access, Год журнала: 2024, Номер 12, С. 100559 - 100580

Опубликована: Янв. 1, 2024

Budget allocation across multiple advertising channels involves periodically dividing a fixed total budget among various channels. Yet, the challenge of making sequential decisions to optimize long-term benefits rather than short-term gains is often overlooked. Additionally, more apparent connections must be made between actions taken on one channel and outcomes others. Furthermore, limitations narrow down range potential optimal strategies that can pursued. In response these challenges, this study unveils pioneering multi-channel approach leverages reinforcement learning (RL) Q-learning framework enriched with an advanced Differential Evolution (DE) algorithm refine methodology. The RL element makes informed decisions, adeptly adjusting favor rewards by assimilating environmental feedback. Complementing this, enhanced DE introduces inventive clustering-based mutation technique, exploiting key groupings within population generate novel practical solutions. model further bolstered discretization tactic aimed at simplifying streamlining costs. proposed methodology rigorously validated using two extensive datasets: Chinese Internet Company Advertising Dataset (CICAD) CRITEO-UPLIFT v2, employing metrics like Area Under Cost Curve (AUCC) Expected Outcome Metric (EOM) as measures performance. empirical results affirm superiority model, showcasing its exceptional performance significant scores (AUCC =0.750 EOM =0.736 for CICAD; AUCC =0.813 =0.829 v2), thereby illustrating model's proficiency in navigating multifaceted challenges associated establishing new benchmark field.

Язык: Английский

Процитировано

1
Postpartum Depression Identification: Integrating Mutual Learning-based Artificial Bee Colony and Proximal Policy Optimization for Enhanced Diagnostic Precision DOI Open Access
Y. A. Tang, Tangsen Huang, Xiangdong Yin

и другие.

International Journal of Advanced Computer Science and Applications, Год журнала: 2024, Номер 15(6)

Опубликована: Янв. 1, 2024

Postpartum depression (PPD) affects approximately 12% of mothers, posing significant challenges for maternal and child health. Despite its prevalence, many affected women lack adequate support. Early identification those at high risk is cost-effective but remains challenging. This study introduces an innovative model PPD detection, combining the Mutual Learning-based Artificial Bee Colony (ML-ABC) method with Proximal Policy Optimization (PPO). uses a PPO-based algorithm tailored to imbalanced dataset characteristics, employing artificial neural network (ANN) policy formation in categorization tasks. PPO enhances stability by preventing drastic shifts during training, treating training process as series interconnected decisions, each data point considered state. The network, acting agent, improves recognizing fewer common classes through rewards or penalties. incorporates advanced pre-training strategy using ML-ABC adjust initial weight configurations increase classification precision, enhancing early pattern recognition. Evaluated on Swedish (2009-2018) comprising 4313 cases, demonstrates superior precision accuracy, accuracy F-measure scores 0.91 0.88, respectively, proving highly effective identifying PPD.

Язык: Английский

Процитировано

0
Smartphone detector examination for transportation mode identification utilizing imbalanced maximizing-area under the curve proximal support vector machine DOI

Zhenhua Dai,

Tangsen Huang

Signal Image and Video Processing, Год журнала: 2024, Номер 18(11), С. 8361 - 8377

Опубликована: Авг. 13, 2024

Язык: Английский

Процитировано

0
Object Recognition from Scientific Document Based on Compartment and Text Blocks Refinement Framework DOI
Jinghong Li, Wen Gu, Koichi Ota

и другие.

SN Computer Science, Год журнала: 2024, Номер 5(7)

Опубликована: Авг. 23, 2024

Язык: Английский

Процитировано

0
Aspect term extraction and optimized deep learning for sentiment classification DOI

Konda Adilakshmi,

M. Srinivas,

K. Anuradha

и другие.

Social Network Analysis and Mining, Год журнала: 2024, Номер 14(1)

Опубликована: Ноя. 24, 2024

Язык: Английский

Процитировано

0