نشریه کارافن
سال بیست و یکم شماره 68 (پاییز 1403)

This research delves into the complex dynamics of human-artificial intelligence interaction, a field that has been growing exponentially in recent years. This study is mixed-methods (quantitative-qualitative) research in the field of human interaction and artificial intelligence. It includes a methodical review of articles from the past five years in the Web of Science database to identify and understand the evolving dynamics in this field. The current research employed bibliometric analysis with a co-occurrence technique. After examining related theories, a conceptual model corresponding to co-occurrence clusters is presented. The article provides an integrated analysis that identifies artificial intelligence and its interaction with humans, and its relationship to perception, technology acceptance, behavior, and satisfaction. It offers an overview of human-artificial intelligence interaction studies' current state and prospects. The findings of this study indicated a significant shift towards human-centered artificial intelligence, emphasizing the importance of cognitive and social dimensions in the design and implementation of artificial intelligence systems. These insights are invaluable to researchers and designers of enterprise systems who aim to align AI advancements with human-centered approaches and ensure that AI advancements are in harmony with human needs and values.

Caring for neonatals and reducing mortality rates is a critical health and social priority today. Statistics indicate that many infant deaths each year result from preventable issues. Advances in technology and the Internet of Things (IoT) present new opportunities to enhance newborn healthcare and monitoring. This article discusses the necessity of developing a comprehensive IoT-based system for neonatal care. If effectively designed and implemented, this system can enable continuous health monitoring, timely alerts, and improved neonatal safety. The current study demonstrated that new technologies can significantly lower infant mortality and enhance quality of life. Its goal was to empower doctors, nurses, parents, and stakeholders to remotely monitor newborns' conditions using appropriate sensors. The Internet of Things was employed to continuously monitor a baby's vital signs, alertness, and health through sensors that track temperature, movement, and ambient light.

Deep learning is a subset of machine learning that is widely used in the field of artificial intelligence such as natural language processing and machine vision. As a subset of machine vision, image segmentation is one of the most common steps in digital image processing, which divides a digital image into different segments. In this research, a new method based on deep learning for image segmentation was presented. The "Adaption Ahead" algorithm was introduced and used as a new optimization algorithm to optimize the proposed model. In previous optimization algorithms, the most important factor in reducing accuracy was extracting low-level features of images and not reducing the semantic distance between human perception and features. In this study, hierarchical and deep feature extraction from images was carried out with the help of deep learning. The "Adaption Ahead" optimization algorithm, in which a deep model based on a convolutional neural network is used, extracted higher-level features and achieved optimal accuracy. By using the Nestrov technique in calculating the gradient by the proposed algorithm, the best result, i.e. 91.1 accuracy, was obtained for the Dice similarity measure. Another advantage of this algorithm over other methods was using uncomplicated calculations. The comparison of the proposed optimization algorithm with other commonly used methods demonstrated the improvement in the performance of this network on relatively large data sets. Furthermore, the more accurate performance of this network, as a result of its hierarchical and deep extraction, was compared to other methods.

Due to the increasing importance of identity recognition to increase the security of organizations, the importance of identity recognition methods such as biometric indicators and radio waves is also increasing. The purpose of this research was to provide a systematic way of improving authentication based on radio waves and biometric index using a fuzzy expert system for use in the field of information and communication security (cyber security). In this research, the impact of biometric indicators and radio waves on the improvement of identity authentication was investigated, and finally, a fuzzy expert system was designed, which showed the impact on each of the components. The population studied in this research included experts in the field of biometric indicators and radio waves of Tehran municipality. The results of the research showed a correlation between all research variables, and considering the high correlation, it can be said that by managing the security of the components of radio waves, it is possible to improve authentication based on identification through radio waves. The expert system for improving authentication based on identification through radio waves and biometric index can help managers to make decisions related to the issues of improving authentication, lead to improving the efficiency of decision making in improving authentication through radio waves and biometric index, and also make it more effective.

What guarantees the survival of organizations in today's world is the degree of success in meeting the needs and demands of customers, and this is not possible except through the flexibility of products and services, as well as the design of systems to create flexibility in providing goods and services. Service flexibility is one of the most important and influential success factors of today's organizations and companies. The purpose of this research was to provide a model to identify the factors affecting the flexibility of services and to identify how these factors behave in financial institutions. Therefore, the main indicators affecting the performance of an organization's services were extracted from the research literature, then using the opinions of experts, the relationships and the effectiveness of each of these variables were determined to be used as input in building the simulation model. In the simulation stage, the flow diagram was drawn using Vensim software. Finally, the model of the effectiveness of flexibility in services was presented. According to the flow diagram and the proposed scenarios, it was found that in the studied time period, the flexibility of services increased by approximately 14% through the proposed scenario. The results obtained from this research can be a basis for explaining service flexibility strategies in other financial institutions.

Examining the mechanical properties of polymer materials has particular importance due to the increasing usage of these materials. In this paper, the crack development process was identified using the experimental data obtained from the tensile tests of polyvinyl chloride polymer (PVC) to reduce the experimental test number. Some pre-cracks were created on the experimental samples by slotting and broaching methods and the experimental results of force versus displacement were recorded for each sample. In the next step, some mathematical pre-processing operations including equating the sampling intervals using interpolation and integration using trapezoidal methods were performed on the experimental data. In the third stage, by using the pre-processed data and the Least Squares (LS) identification method, the mathematical model of the system, the frequency domain discrete transfer function of the crack development process, was obtained. Finally, after evaluating and verifying the obtained mathematical model with other experimental results, it was proposed to predict the crack development process. The obtained results showed that by identifying the crack development process for limited samples, it is possible to avoid the number of experimental tests that are time-consuming and costly. In addition, the second-order two-stage least squares method with five unknown parameters was promisingly able to estimate crack development dynamics with acceptable accuracy, particularly in the first half of the development process.

The Joints are important elements of engineered structures. Sandwich and polymer structures utilize insert joints. The design of these joints, like other ones, must prevent damage in the connection area. Several studies have been conducted on insert joints to improve their load capacity. It is recommended that telecommunications structures consider the use of non-metallic connections to prevent interference with wave transmission and unwanted radiation effects. One potential solution for addressing environmental conditions and reducing metal in telecommunications radiation is the use of composite metal connections. In this article, the possibility of replacing metal samples with composite insert joints reinforced with alumina nanoparticles is explored. To evaluate the efficacy of composite samples in varying environmental conditions, an analysis of their moisture absorption was conducted. The outcomes of both the strength and environmental tests provided evidence that composite samples can serve as a viable substitute for metal-embedded joints.

Different types of aerodynamic forces such as drag, lift, and side forces are induced in a car. Reducing drag force is necessary to improve fuel consumption and driving characteristics. The compressor of the car cooler is connected to the car engine through a belt and takes part of the power of the car engine and increases fuel consumption. Some drivers, particularly public transport drivers, turn down car windows to varying degrees instead of turning on the car cooler which increases drag coefficient and fuel consumption. In the present article, to experimentally investigate the effect of low car windows on the drag coefficient and fuel consumption, the drag coefficient of five different modes of a sedan car (1- All windows are closed; 2- All windows are open 3- The windows of the two front doors are open and the windows of the two rear doors are closed 4- Half-open windows of the two front doors and closed windows of the two rear doors 5- All the windows are half open) was measured in a subsonic wind tunnel. Because the drag coefficient is a dimensionless number, to reduce the testing costs, a scaled-down model of the car with a scale of 1:30 was used. By comparing model 2 to model 1, the drag coefficient increased by 43%. By comparing models 3, 4 and 5 to model 1, the drag coefficient increased by 30%.

The driving and traffic cycle in cities is one of the most important and complex challenges in urban management. For the data collection process, the chasing vehicle moved in a certain route in the city through the selected time period, and data collection was conducted with software installed on a mobile phone. This research investigated the driving cycle in Semnan city using the chasing method and the K-means clustering technique. The distance covered during data collection was approximately 12 km for each route. Additionally, the total distance covered for the data collection in this study was approximately 130 km. The car model information, age, and gender of chased drivers were recorded as the influential parameters. Then, using the K-means technique, the data collected for different routes were analyzed to extract the behavioural patterns in the routes of Semnan city. Furthermore, in this study, the appropriate number of groups for data clustering was investigated, and considering the standard deviation of the data, it was concluded that the optimal number of clusters was 5. Increasing the number of clusters, despite improving the accuracy of calculations, led to longer processing times. Therefore, by clustering with 2, 3, 4, 5, and 6 groups, it was observed that these numbers of clusters improved by approximately 40, 80, 90, 98, and 99%, respectively, indicating that increasing the number of clusters showed a significant improvement in the results. These clusters included urban roads, secondary roads, highways, motorways with light traffic, and start-stop. This information can help city officials and traffic managers with traffic and safety improvement programs, according to the specified patterns, and provide a deeper understanding of driving behaviour in Semnan city.

In studies with a quantitative approach to human walking stability, it is essential to quantitatively know how good the balance is at a body posture or every moment along a path. To predict and maintain a stable situation, it is necessary to develop a method that can measure stability and indicate the condition of dynamic balance along the path. In this paper, a new measure of postural stability was presented called the probability of motion realization based on the kernel density estimation, which assigns a value to the body motion based on the avoidance of a fall along a path. The issue of balance maintenance was examined for a population sample using a database and a motion capture technique for recording kinematic information of the gait cycle, and the probability of successful balance maintenance was calculated for the population. In addition, the probability of motion realization was calculated through a seven-link body model in all states for three age groups of men and women at different step lengths. The results were compared to the margin of stability, which is a conventional metric. The findings demonstrated that the margin of stability may be very low for a path on which most people can maintain their stability easily, whereas the probability of motion realization is high.

In 3D printing technologies, producing polymer parts with desirable mechanical properties is crucial. The fused deposition modeling (FDM) technique is one of the most common 3D printing processes for manufacturing polymeric parts. However, due to the weak interlayer bonding of the printed parts and consequently inferior mechanical properties, enhancing interlayer bonding is necessary. This study investigated the combination of 3D printing parameters (printing angle) and post-processing via hot pressing (temperature and pressing force). Additionally, the simultaneous optimization of these parameters was conducted to achieve the highest tensile strength in parts made of polylactic acid (PLA). To this end, an experimental design was conducted using the response surface methodology (RSM), and changes in tensile properties concerning the studied parameters were evaluated. The results indicated an interaction between the studied parameters. The optimal values for the raster angle, pressing temperature, and pressure were 90 degrees, 70 degrees Celsius, and 25 N, respectively. Under these conditions, the highest tensile strength of 33 MPa was achieved, showing an approximately 22% increase compared to the initial sample.

In this article, the modelling and implementation of the Agropv intelligent agricultural system for the optimal use of agricultural land is discussed. This system was designed in such a way that it is possible to optimally use agricultural land under photovoltaic panels and simultaneously use solar energy for the electricity required for intelligent irrigation management and plant temperature control. This system was implemented in such a way that the humidity sensor measured the soil bed and if the soil was dry, it activated the pump and delivered water to the plant by collecting the surface water stored on the surface of the panel, and by measuring the pH of the soil, the required solution was obtained. The advantage of the proposed method over the existing methods is the use of shading solar panels on the products to make the plants sweat more but prevent their evaporation and it is designed with optimal use of solar energy to illuminate the agricultural environment and supply the electricity required by two fans. Using a fan to remove dust from the surface of the panel and another fan to cool the panels led to a decrease in the temperature of the panel, and also by using the Internet of Things, the growth speed and quality of the plant improved.

The Alzheimer's disease, a progressive brain disorder, necessitates timely detection for effective management due to the current diagnostic methods' limitations. The study presents an efficient convolutional neural network (CNN) designed for classifying brain magnetic resonance imaging (MRI) images into four categories related to Alzheimer's disease. To enhance diagnosis, this study proposes two distinct approaches at different stages: (1) using optimized data pre-processing; and (2) designing a lightweight CNN architecture with low complexity and fewer parameters that simultaneously possesses good accuracy, computational efficiency, and excellent performance. The proposed method achieved outstanding results, with a final accuracy of 99.22%, a macro average F1 score of 0.99, an MCC of 0.9870, and a Cohen kappa score (CKS) of 0.9870. In addition to accuracy, the complexity of the proposed model, including the comparison of model size, time elapsed, the number of FLOPs, and the trainable and non-trainable parameters of the proposed method were also thoroughly investigated. This model, with the advantages of high accuracy, reduced FLOPs, faster execution time, and lower memory requirements outperforms other deep learning methods used in recent studies.

In terms of power density, supercapacitors exhibit excellent performance like conventional capacitors and high energy density like batteries. In addition, supercapacitors offer unprecedented applications and development prospects in the field of energy storage due to their fast charging, simple manufacturing technology, safety, and environmental compatibility. The use of supercapacitors is sometimes limited by the poor electrochemical performance and low cyclic stability of the electrode materials. To achieve very high performance and stability, which are crucial criteria for supercapacitor applications, the fabrication of nanostructured materials to improve the specific surface area and electrical conductivity is crucial. In the present work, a simple and economical hydrothermal route was used for the synthesis of Cu2SnS4 nanoparticles. The structure, chemical composition, and morphology of the synthesized materials were investigated by scanning electron microscopy (SEM) and transmission electron microscopy (TEM), as well as X-ray energy diffraction (EDX), and elemental mapping to confirm the elemental composition of the prepared electrode. The electrode fabricated in this research was able to exhibit a high capacitance of 2076.9 F g-1 at a current density of 1 A g-1 and a stability of 90.44% after 10000 cycles. In addition, the asymmetric supercapacitor Cu2SnS4//AC provides a capacitance of 246.93 F g-1 at a current density of 1 A g-1 and a stability of 82.32% after 10000 cycles. The excellent electrochemical performances of Cu2SnS4 nanostructure will have significant technological applications in the future.

Cement is known as the main building material in concrete production. Due to its high cost and environmental pollution and damage during the production process, researchers are always searching for suitable alternatives to cement. Silica fume waste powder from the sandblasting factory, due to its silica content, can be a suitable substitute and was the subject under investigation in the present study. 164 specimens were prepared to measure and evaluate the effect of substituting 5%, 7.5%, and 10% by weight of cement with silica waste powder in two mix designs of 410 and 460 kilograms per cubic meter. The 90-day compressive strength of concrete with 5% substitution in the 460-kilogram mix design showed an increase of 10% in strength, and in other mix designs, no significant change in strength was observed, indicating the acceptability of silica waste powder as a suitable substitute for cement in terms of strength. The water absorption percentage of concrete decreased significantly by 20% with the increase of silica waste powder due to its fine structure and filling the pores and voids of concrete. Based on the results, if silica waste powder, which itself is an environmental problem in the industry, can be used as a cement substitute, it is possible to use 5% less cement in concrete economically and help prevent environmental pollution.