Importance Weights Research Articles

Rehabilitation Assessment System for Stroke Patients Based on Fusion-Type Optoelectronic Plethysmography Device and Multi-Modality Fusion Model: Design and Validation.

This study aimed to propose a portable and intelligent rehabilitation evaluation system for digital stroke-patient rehabilitation assessment. Specifically, the study designed and developed a fusion device capable of emitting red, green, and infrared lights simultaneously for photoplethysmography (PPG) acquisition. Leveraging the different penetration depths and tissue reflection characteristics of these light wavelengths, the device can provide richer and more comprehensive physiological information. Furthermore, a Multi-Channel Convolutional Neural Network-Long Short-Term Memory-Attention (MCNN-LSTM-Attention) evaluation model was developed. This model, constructed based on multiple convolutional channels, facilitates the feature extraction and fusion of collected multi-modality data. Additionally, it incorporated an attention mechanism module capable of dynamically adjusting the importance weights of input information, thereby enhancing the accuracy of rehabilitation assessment. To validate the effectiveness of the proposed system, sixteen volunteers were recruited for clinical data collection and validation, comprising eight stroke patients and eight healthy subjects. Experimental results demonstrated the system's promising performance metrics (accuracy: 0.9125, precision: 0.8980, recall: 0.8970, F1 score: 0.8949, and loss function: 0.1261). This rehabilitation evaluation system holds the potential for stroke diagnosis and identification, laying a solid foundation for wearable-based stroke risk assessment and stroke rehabilitation assistance.

IVPF-AHP integrated VIKOR methodology in supplier selection of three-dimensional (3D) printers

Complex geometries, fine details, and various designs that are difficult to create using traditional methods can easily be turned into a tangible object with Three-Dimensional (3D) printers. 3D printers have advantages such as providing design flexibility, obtaining prototypes in the shortest possible time, allowing for personalization, and reducing waste through the use of advanced technology. These advantages emphasize the significance of 3D printers in a sustainable production model. The widespread usage of 3D printers leads to increased efficiency and cost reduction in production. When the literature is examined, it is observed that there are limited studies on the evaluation of supplier performances for company using 3D printers. The aim of this study is to address 3D printers, which are highly significant for sustainable production, and to reveal the criteria that companies utilizing these printers need to consider for determining their suppliers. As a result of the literature review and expert interviews, a model has been developed that gathers the criteria to be considered for supplier selection, which is an important cost factor for companies involved in designing and producing 3D printers under five main and 18 sub-criteria. The importance weights of the criteria have been determined using the Interval Valued Pythagorean Fuzzy Analytic Hierarchy Process (IVPF-AHP) method, and the most suitable supplier among alternative suppliers has been selected using the Vise Kriterijumska Optimizacija I Kompromisno Resenje (VIKOR) method. Finally, the supplier scores have been statistically analyzed to show the validation of the results of the proposed method. According to the results, it has been concluded that for company using 3D printers, quality and technical service criteria are more important in the supplier selection. Additionally, cost of the material/equipment, product price and easy maintenance criteria also play a critical role in the supplier selection of 3D printer.

Screening-Evaluation of Regional Investment Projects for the Provision of State Financial Support Measures

The object of the study is regional investment projects (RIPS). The subject of the study is a methodological toolkit for assessing the investment attractiveness of regional projects, including criteria, indicators, methods and stages of making informed decisions about government financial support measures in relation to them. The relevance of the study is due to the state’s interest in the socio-economic development of regions under the conditions of sanctions pressure and the need to ensure effective spending of budget funds allocated to regional investment projects, which requires the formation of new methodological recommendations for evaluating projects implemented within the framework of state financial support measures. The purpose of the study is to develop methodological recommendations for screening and evaluating regional investment projects in order for public authorities to make informed decisions on providing financial support. The methods of comparative analysis, classification, regulatory regulation, statistical indicators, screening and investment assessment, and the method of hierarchy analysis were used. Methodological recommendations on screening assessment of regional investment projects are proposed, within the framework of which: 1) the characteristics of RIP are identified and their classification is considered; 2) the criteria for assessing the investment attractiveness of the project and its contractor (partner) are defined: general (the purpose of the RIP, its significance, the quality of project documentation) and special (economic, budgetary, social, environmental efficiency, performance feasibility, compliance with ESG principles of doing business, business image); 3) evaluation indicators and their thresholds, the achievement of which means the expediency of investing budget funds in the project. It is concluded that in order to make a decision on the provision of state financial support to RIP, it is necessary to achieve target values by indicators corresponding to three components: “State” (customer), “Project” and “Partner (contractor). At the same time, using the hierarchy analysis method, it was found that the investment attractiveness of the contractor has the greatest importance (weight) when choosing a project. The choice of the performer is based on screening of applicants according to the specified criteria.

Design of urban road fault detection system based on artificial neural network and deep learning.

In urban traffic management, the timely detection of road faults plays a crucial role in improving traffic efficiency and safety. However, conventional methods often fail to fully leverage the information from road topology and traffic data. To address this issue, we propose an innovative detection system that combines Artificial Neural Networks (ANNs), specifically Graph Convolutional Networks (GCN), Bidirectional Gated Recurrent Units (BiGRU), and self-attention mechanisms. Our approach begins by representing the road topology as a graph and utilizing GCN to model it. This allows us to learn the relationships between roads and capture their structural dependencies. By doing so, we can effectively incorporate the spatial information provided by the road network. Next, we employ BiGRU to model the historical traffic data, enabling us to capture the temporal dynamics and patterns in the traffic flow. The BiGRU architecture allows for bidirectional processing, which aids in understanding the traffic conditions based on both past and future information. This temporal modeling enhances our system's ability to handle time-varying traffic patterns. To further enhance the feature representations, we leverage self-attention mechanisms. By combining the hidden states of the BiGRU with self-attention, we can assign importance weights to different temporal features, focusing on the most relevant information. This attention mechanism helps to extract salient features from the traffic data. Subsequently, we merge the features learned by GCN from the road topology and BiGRU from the traffic data. This fusion of spatial and temporal information provides a comprehensive representation of the road status. By employing a Multilayer Perceptron (MLP) as a classifier, we can effectively determine whether a road is experiencing a fault. The MLP model is trained using labeled road fault data through supervised learning, optimizing its performance for fault detection. Experimental evaluations of our system demonstrate excellent performance in road fault detection. Compared to traditional methods, our system achieves more accurate fault detection, thereby improving the efficiency of urban traffic management. This is of significant importance for city administrators, as they can promptly identify road faults and take appropriate measures for repair and traffic diversion.

Optimal bipartite graph matching-based goal selection for policy-based hindsight learning

The sparse reward problem stands as a significant challenge in the field of reinforcement learning. Hindsight Experience Replay (HER) addresses this by goal relabeling, allowing the agent to learn from unsuccessful experiences. Some studies combine policy gradient methods with HER, resulting in policy-based hindsight learning algorithms. However, Policy-based hindsight learning involves the use of importance sampling, where the distribution of hindsight goals and the distribution of desired goals contribute to the computation of importance weights. When there is a significant difference between the two distributions, importance weights may become skewed, thereby impacting the evaluation of the policy and leading to suboptimal policies. To address this, we propose modeling the goal selection as an optimization problem for distribution matching. After we augment the original desired goals using Kernel Density Estimation (KDE), we further convert the optimization problem for distribution matching into a bipartite graph matching problem that minimizes the sum of weights. Our optimal bipartite graph matching-based hindsight goal selection method can select hindsight goals that are the most closely aligned with the original goals. Experimental results show that algorithms combined with the optimal bipartite graph matching-based hindsight goal selection outperform the original algorithms. Visualizations also demonstrate the superiority of our method in selecting hindsight goals.

Study on the Development Strategy of China’s Health Care Industry from the Perspective of Active Ageing: Based on Public Cognition Survey

With an aging population currently posing a challenge, China must accelerate the construction of a health development model with "prevention as the main focus" from the perspective of active aging. This development requirement is exactly met by the growth of health care industry, which is highly significant strategically to cope with the dual challenges of aging populations and public health issues. The study construct an evaluation index system of influencing factors for the development of health care industry, and further empirically analyse the influencing factors of China’s health care industry by using Analytic Hierarchy Process (AHP) and Entropy Weight Method (EWM), and calculate the relative importance weights of 18 influencing factors of perceptual indicators under the four levels of economy, environment, products and individuals. Lastly, countermeasures are made for the superior growth of China’s health care industry based on the results of the weighing analysis.

Long-Term Efficacy and Safety of Once-Weekly Semaglutide for Weight Loss in Patients Without Diabetes: A Systematic Review and Meta-Analysis of Randomized Controlled Trials

Semaglutide, a glucagon-like peptide-1 receptor agonist, has demonstrated clinically important weight loss effects in patients with type 2 diabetes. However, its effects on sustained weight loss in patients without diabetes remains unclear. Our objective was to examine the long-term efficacy and safety of semaglutide use for weight loss in patients with overweight/obesity and without diabetes. MEDLINE, EMBASE, and the Cochrane Libraries were systematically searched to identify randomized controlled trials that randomized participants with overweight/obesity and without diabetes to once-weekly 2.4 mg subcutaneous semaglutide versus placebo, with a follow-up of at least 68 weeks. The primary outcome was a change in relative body weight from baseline to the longest follow-up. Random-effects models with inverse variance weighting were used to estimate the weighted mean differences (WMDs) and relative risks (RRs) with 95% confidence intervals (CIs). A total of 4 randomized controlled trials (n = 3,087) were included. Of the 3 trials that provided body mass index by category (n = 2,783), 94.0% of the participants had a baseline body mass index ≥30 kg/m2. Compared with placebo, the use of semaglutide was associated with substantial decreases in long-term relative (WMD -12.1%, 95% CI -13.5 to -10.7) and absolute body weight (WMD -12.3 kg, 95% CI -13.6 to -11.0). At the longest follow-up, 33.4% of participants randomized to semaglutide achieved ≥20% weight loss compared with 2.2% with placebo (RR 15.08, 95% CI 9.31 to 24.43). The risk of gastrointestinal adverse events was higher in participants who took semaglutide than placebo (RR 1:47, 95% CI 1.28 to 1.68); however, the majority of these events were transient and mild-to-moderate in severity and did not require treatment discontinuation. In conclusion, semaglutide is efficacious for sustained weight loss in patients with overweight/obesity and without diabetes.

Predicting Quality of Modified Product Attributes to Achieve Customer Satisfaction

In the era of the competitive environment, the improvement in current products is ensured through activities aimed at increasing a product’s quality level and, consequently, reducing the amount of waste. The dynamically changing production environment and sudden changes in customer expectations force us to take precise and well-thought-out development steps. Furthermore, it is important to anticipate favourable product changes to prepare for market changes over time. This is still an open problem. The aim of this study was to develop a method to predict the quality of potential product prototypes resulting from the proposed modifications of the product features. This methodology takes into account current customer expectations. The method was created based on the principles of creating Quality Function Deployment (QFD) in the context of taking into account current and future customer expectations regarding product features. This is a new approach to analysing product quality within the principles of the traditional QFD method. The originality of the study is the technique used in the method to estimate the expected values of product features and their importance (weights), taking into account current customer expectations. Its originality is also manifested in drawing conclusions supporting the decision-making process of product improvement, because it involves ensuring the pro-quality modification of selected features of current products in the order that is most advantageous from the customer’s point of view. The use of the proposed method allows for the analysis of the impact of modifying the current value of a product feature. The method is illustrated with an example of a vacuum cleaner for home use. However, the proposed method can be applied to the design of any product to predict products that will meet customer expectations.

Predicting performance in exams and deep approach to learning in first year university students: a new look at academic success

ABSTRACT This study calls for a broadening of the perspective on academic success. While passing exams is an essential objective of higher education, it should not overshadow another important objective which is the development of students’ skills, such as becoming curious, autonomous and reflective in the learning process. This study used Academic Performance in Exams (APE) and Deep Approach to Learning (DAL) as measures related to these two objectives. The aim was to identify and compare the factors that may influence APE and DAL. The study was conducted on first-year students (2011) at a French university. It was based on a random forest algorithm and took into account a wide range of factors belonging to different dimensions: demographics, social background, educational background, context of the educational programme, behavioural engagement, social environment, psychological and cognitive characteristics. The results show that the most important factors in predicting APE are the educational programme undertaken, student’s educational background and parents’ occupation. DAL was not found to be an important factor in APE. Regarding the prediction of DAL, the results point to the predominant weight of intrinsic motivation and the important weight of elaborated epistemic beliefs. In contrast, demographics and behavioural engagement were found to have negligible weight in predicting both APE and DAL. These findings raise questions about the type of success that is valued in the first year of university and call for reflection on assessment methods. They also allow the identification of levers that teachers can activate to support first year students.

A Transformer Heavy Overload Spatiotemporal Distribution Prediction Ensemble under Imbalanced and Nonlinear Data Scenarios

As a crucial component of power systems, distribution transformers are indispensable to ensure the sustainability of power supply. In addition, unhealthy transformers can lead to wasted energy and environmental pollution. Thus, accurate assessments and predictions of their health statuses have become a top priority. Unlike assumed ideal environments, however, some complex data distributions in practical scenarios lead to more difficulties in diagnosis. One challenge here is the potential imbalanced distribution of data factors since sparsely occurring factors along with some Unusual High-Risk (UHR) components, whose appearance may also damage transformer operations, can easily be neglected. Another is that the importance weight of data components is simply calculated according to their frequency or proportion, which may not always be reasonable in real nonlinear data scenes. With such motivations, this paper proposes a novel integrated method combining the Two-fold Conditional Connection Pattern Recognition (TCCPR) and Component Significance Diagnostic (CSD) models. Initially, the likely environmental factors that could result in distribution transformer heavy overloads were incorporated into an established comprehensive evaluation database. The TCCPR model included the UHR time series and factors that are associated with heavy overload in both spatial and temporal dimensions. The CSD model was constructed to calculate the risk impact weights of each risky component straightforwardly, in line with the total risk variation levels of the whole system caused by them. Finally, the results of one empirical case study demonstrated their adaptation capability and enhanced performance when applied in complex and imbalanced multi-source data scenes.

Sharp-SSL: Selective high-dimensional axis-aligned random projections for semi-supervised learning

We propose a new method for high-dimensional semi-supervised learning problems based on the careful aggregation of the results of a low-dimensional procedure applied to many axis-aligned random projections of the data. Our primary goal is to identify important variables for distinguishing between the classes; existing low-dimensional methods can then be applied for final class assignment. To this end, we score projections according to their class-distinguishing ability; for instance, motivated by a generalized Rayleigh quotient, we can compute the traces of estimated whitened between-class covariance matrices on the projected data. This enables us to assign an importance weight to each variable for a given projection, and to select our signal variables by aggregating these weights over high-scoring projections. Our theory shows that the resulting Sharp-SSL algorithm is able to recover the signal coordinates with high probability when we aggregate over sufficiently many random projections and when the base procedure estimates the diagonal entries of the whitened between-class covariance matrix sufficiently well. For the Gaussian EM base procedure, we provide a new analysis of its performance in semi-supervised settings that controls the parameter estimation error in terms of the proportion of labeled data in the sample. Numerical results on both simulated data and a real colon tumor dataset support the excellent empirical performance of the method.

Extended cognitive reliability and error analysis method for advanced control rooms of nuclear power plants

This study proposes a modified extended cognitive reliability and error analysis method (CREAM) for achieving a more accurate human error probability (HEP) in advanced control rooms. The traditional approach lacks failure data and does not consider the common performance condition (CPC) weights in different cognitive functions. The modified extended CREAM decomposes tasks using a method that combines structured information analysis (SIA) and the extended CREAM. The modified extended CREAM performs the weight analysis of CPCs in different cognitive functions, and the weights include cognitive, correlative, and important weights. We used the extended CREAM to obtain the cognitive weight. We determined the correlative weights of the CPCs for different cognitive functions using the triangular fuzzy decision-making trial and evaluation laboratory (TF-DEMATEL), and evaluated the importance weight of CPCs based on the interval 2-tuple linguistic approach and ensured the value of the importance weight using the entropy method in the different cognitive functions. Finally, we obtained the comprehensive weights of the different cognitive functions and calculated the HEPs. The accuracy and sensitivity of the modified extended CREAM were compared with those of the basic CREAM. The results demonstrate that the modified extended CREAM calculates the HEP more effectively in advanced control rooms.

Merchant Fleet Performance of Türkiye: A CRITIC-based TOPSIS Approach

The study focuses on assessing the merchant fleet performance of Türkiye, a country surrounded by seas on three sides and holding a pivotal position in global logistics networks. It considers mean age of vessels, total carrying capacity in dead weight tons, and the number of ships as indicators influencing Türkiye’s merchant fleet performance, with the importance weights of these indicators determined using the CRITIC method. Based on the determined weights, Türkiye’s merchant fleet performance for the years 2011-2023 is evaluated using the TOPSIS method. The findings reveal that mean age of vessels emerges as the indicator with the highest importance weight. The analysis indicates an improvement in Türkiye’s fleet performance between 2011 and 2013, followed by a subsequent decline from 2013 onwards. Notably, there is a significant shift observed in 2016 across all three indicators. Given Türkiye’s aging fleet, the study suggests a focus on acquiring young and high-capacity vessels to enhance fleet performance. This strategic approach can help Türkiye optimize its maritime trade capability and maintain competitiveness in the global shipping industry.

Block chain-based Database Systems by using WSM Method

Block chain technology has surfaced as a transformative influence, revolutionizing the verification and recording of transactions across industries. In to traditional data base systems, presenting a novel approach to database management. The objective is to enhance the trust, transparency, and security of data storage and transactions. Research in this field aims to strengthen data protection, reduce the risk of unauthorized access, and prevent data tampering. By providing a transparent and auditable record of transactions, block chain enhances trust among parties. This is particularly important in industries such as finance, where the integrity of transactions is paramount. The Weighted Sum Model (WSM) stands as a straightforward and widely utilized method of multi-criteria decision-making. It operates by multiplying assigned value of each attribute by the weight of importance designated by the decision maker. Subsequently, it entails aggregating these products across all criteria to compute evaluation scores for each alternative parameters considered in this study include Bitcoin, Ethereum, Biance Smart Chain, Hyperledger Fabric, and Corda, evaluated based on criteria such as Transaction Throughput (tps), Security Level (1-10), Energy Efficiency (kWh/tx), and Initial Setup Cost (USD). the term "Weighted Sum Model (WSM)" is correctly spelled, but the term "multi-Criteria" should be "multi-criteria" for proper phrasing. It involves assigning a value to each attribute, determined by the decision maker, which is then multiplied by a specified importance weight Bitcoin, Ethereum, Binance Smart Chain, Hyperledger Fabric and Corda. Transaction Throughput (tps), Security Level (1-10) Energy, Efficiency (kWh/tx) and Initial Setup Cost (USD). the ranking for blockchain-based database systems. Binance Smart Chain) got the top rank, whereas faculty strength Bitcoin) has a low ranking.

Evaluation of new scintillation crystals with MCDM methods for brain PET

Brain Positron Emission Tomography (PET) imaging has been increasingly important in recent decades for improved detection and staging of brain cancer and other brain illnesses. Many elements, including the choice of radiation detecting medium, contribute to the overall image quality used to characterize a PET system's performance. In our previous study, novel transparent optical scintillator crystals for brain PET system were simulated. Therefore, there is a need to evaluate these materials using advanced computational techniques. Hence, in this study, we evaluated and compared them using two Multi-Criteria Decision-Making (MCDM) techniques, namely Preference Ranking Organization Method for Enrichment Evaluations (PROMETHEE) and Visekriterijumska Optimizacija I Kompromisno Resenje (VIKOR). The crystals used in this study were strontium hafnate (SHO), gadolinium aluminum gallium garget (GAGG), gadolinium yttrium gallium aluminum garget (GYGAG), gadolinium lutetium gallium aluminum garget (GLuGAG), and lastly lutetium oxyorthosilicate (LSO) for comparison. Density, effective atomic number, energy resolution, light output, and decay time were selected as important criteria. Importance weights of each criteria were then assigned by considering the high resolution and high sensitivity detectors. With both MCDM methods, the results showed that SHO outranked the other scintillator materials followed by LSO and GLuGAG. GYGAG, and GAGG is revealed as the least favorable crystals, in agreement with the previous simulation studies. This study can be extended by including more scintillators as they become available in the future.

An analysis of different methods for deep neural network pruning

Neural network pruning, the process of removing unnecessary weights or neurons from a neural network model, has become an essential technique for reducing computational cost and increasing processing speed, thereby improving overall performance. This article has grouped current pruning methods into three classeschannel pruning, filter pruning, and parameter sparsificationand discussed how each method works. Each approach has its own strengths: channel pruning is particularly useful for reducing model depth and width, filter pruning is more suitable for maintaining model depth while decreasing storage requirements, and parameter sparsification can be applied across various network architectures to achieve both storage and computational efficiency. This work will delve into how each method works and highlight key related works of each category. In the future, it is expected that future research in neural network pruning could focus on developing more sophisticated techniques that can automatically identify important weights or neurons within a network.

Collaboration of Vague Theory and Mathematical Techniques for Optimizing Healthcare by Recommending Optimal Blockchain Supplier

The Internet of Medical Things (IoMTs) has the potential to revolutionize healthcare delivery by connecting medical devices and applications to healthcare IT systems via the internet. This connectivity enables the collection, transmission, and analysis of patient data, facilitating remote healthcare delivery and enhancing patient outcomes. However, the security and privacy of the data transmitted and stored within IoMT systems remain critical concerns. Blockchain technology offers a promising solution to address these challenges in IoMTs applications. Blockchain provides a decentralized and immutable ledger where transactions, in this case, patient data, are securely recorded and cannot be altered retroactively. This ensures the integrity and confidentiality of sensitive medical information while eliminating the need for a central authority to manage data exchange. This study proposes a comprehensive fuzzy decision-making framework for selecting the best blockchain provider in the IoMT field. The framework comprises two main steps: Determining the relative importance weights of the criteria utilizing the Stepwise Weight Assessment Ratio Analysis (SWARA) method. Determining the most suitable supplier for blockchain services providers employing the Ranking Alternatives with the Fuzzy ROOT Assessment Method (RAM) technique. A comparison between Fuzzy Multi-Criteria Decision-Making (MCDM) methods is employed to ensure the robustness and validity of the proposed framework.

Efficient low-overlapping point cloud registration based on two-stage network learning

ABSTRACT This letter introduces an efficient registration method for large-scale point clouds with low overlap, which adopts a two-stage transformation learning process. In the first stage, we integrate a point-voxel encoding structure with an attention mechanism to predict rotation and point-wise importance weight. In the second stage, we employ a PointNet-based structure to estimate translation using optimized data. By adopting this two-stage procedure, our model can effectively learn rotation and translation separately, thereby increasing flexibility. We conducted extensive experiments on two large-scale indoor datasets (3Dmatch and S3DIS) and an outdoor dataset (KITTI odometry). The results demonstrate that our method outperforms traditional and deep learning-based approaches, achieving state-of-the-art performance in registration. Furthermore, our method exhibits superior generalization capabilities, highlighting its effectiveness in various registration scenarios.

RG-GAN: Dynamic Regenerative Pruning for Data-Efficient Generative Adversarial Networks

Training Generative Adversarial Networks (GAN) to generate high-quality images typically requires large datasets. Network pruning during training has recently emerged as a significant advancement for data-efficient GAN. However, simple and straightforward pruning can lead to the risk of losing key information, resulting in suboptimal results due to GAN’s competitive dynamics between generator (G) and discriminator (D). Addressing this, we present RG-GAN, a novel approach that marks the first incorporation of dynamic weight regeneration and pruning in GAN training to improve the quality of the generated samples, even with limited data. Specifically, RG-GAN initiates layer-wise dynamic pruning by removing less important weights to the quality of the generated images. While pruning enhances efficiency, excessive sparsity within layers can pose a risk of model collapse. To mitigate this issue, RG-GAN applies a dynamic regeneration method to reintroduce specific weights when they become important, ensuring a balance between sparsity and image quality. Though effective, the sparse network achieved through this process might eliminate some weights important to the combined G and D performance, a crucial aspect for achieving stable and effective GAN training. RG-GAN addresses this loss of weights by integrating learned sparse network weights back into the dense network at the previous stage during a follow-up regeneration step. Our results consistently demonstrate RG-GAN’s robust performance across a variety of scenarios, including different GAN architectures, datasets, and degrees of data scarcity, reinforcing its value as a generic training methodology. Results also show that data augmentation exhibits improved performance in conjunction with RG-GAN. Furthermore, RG-GAN can achieve fewer parameters without compromising, and even enhancing, the quality of the generated samples. Code can be found at this link: https://github.com/IntellicentAI-Lab/RG-GAN

Analysis of the Criminal Offense of Suicide Incitement

Suicide is an individual act that aims to interrupt the continuation of the person's vital activity, mainly driven by psychological circumstances. Suicide is considered as the final act that gives salvation to the solution of internal or interpersonal problems and conflicts, which are evaluated by a deviated subjective situation, in which the person thinks that there is no other solution for his fate. Suicides have a negative impact on society, because the loss of a human being's life not only creates wounds and other spiritual dramas, but creates a psychosis of despair and uncertainty in the social circle and the community as a whole. On the other hand, suicide poses a very big risk, because it gives an unacceptable model for society, appearing as a finding or an easy way to deal with personal weaknesses to face life's challenges. In Albania, there is an increasing number of suicide acts, where from the criminal point of view, the law enforcement bodies have increased attention to the possibility of the involvement of other persons, whose actions or inactions directly affect the self-sacrifice of the victims. In this context, the detection of the criminal offense of causing suicide takes an important weight in the prevention of these degrading and victimizing acts, reducing as much as possible the development of similar and complex cases of suicide. However, proving the effects of systematic psychological or physical violence that has led to suicides remains an extreme difficulty for investigative bodies, which requires not only complex investigative methods, but also a more accurate determination of the content of the concrete criminal offense. Received: 19 February 2024 / Accepted: 15 March 2024 / Published: 23 March 2024