Статті в журналах з теми "Decision Fusion in adversarial setup"

This paper describes a decision fusion strategy that can integrate multiple individual damage detection measures to form a new measure, and the new measure has higher probability of correct detection than any individual measure. The method to compute the probability of correct selection is presented to measure the system performance of the fusion system that includes the presented fusion strategy. And parametric sensitive studies on system performance are also conducted. The superiority of the fusion strategy herein is that it can be extended to deal with the multiresolution subdecision or blind adaptive detection, and corresponding methodologies are also provided. Finally, an experimental setup was fabricated, whereby the vibration properties of damaged and undamaged structures were measured. The experimental results with the undamaged structural model provide information for producing an improved theoretical and numerical model via model updating techniques. Three existing vibration-based damage detection methods with varied resolutions were utilized to identify the damage that occurred in the structure, based on the experimental results. Then the decision fusion strategy was implemented to join the subdecisions from these three methods. The fused results are shown to be superior to those from single method.

Abstract In a production environment, there are several challenges in meeting the Industry 4.0 (I4.0) standard requirements. Energy efficiency is an essential area of focus. In the production setup, the critical and real-time control systems need to be very efficient while implementing functions, namely, accurate sensing, fast processing and precise actuation. Automated Guided vehicles (AGVs) and Automated Guided Vehicles are an integral part of modern and intelligent manufacturing systems. Power consumption in such systems is directly proportional to the performance level achieved. However, there is a need to evolve strategies to reduce power consumption and attain optimal performance. Field Programmable Gate Array(FPGA) based controller solutions can provide competent performance at optimized power consumption. The proposed work discusses the requirements of I4.0 concerning energy efficiency infrastructures for the intelligent manufacturing setup. The need to develop efficient subsystems for sensing, decision-making and actuation based on FPGA is stressed. Thus the focus is on the FPGA based power-efficient models used for sensor fusion technique in Autonomous Mobile Robots. The fundamentals of sensor fusion technique and the need to fuse sensor data for improved decision making and actuation are emphasized.

Cooperative spectrum sensing (CSS) has the ability to accurately identify the activities of the primary users (PUs). As the secondary users’ (SUs) sensing performance is disturbed in the fading and shadowing environment, therefore the CSS is a suitable choice to achieve better sensing results compared to individual sensing. One of the problems in the CSS occurs due to the participation of malicious users (MUs) that report false sensing data to the fusion center (FC) to misguide the FC’s decision about the PUs’ activity. Out of the different categories of MUs, Always Yes (AY), Always No (AN), Always Opposite (AO) and Random Opposite (RO) are of high interest these days in the literature. Recently, high sensing performance for the CSS can be achieved using machine learning techniques. In this paper, boosted trees algorithm (BTA) has been proposed for obtaining reliable identification of the PU channel, where the SUs can access the PU channel opportunistically with minimum disturbances to the licensee. The proposed BTA mitigates the spectrum sensing data falsification (SSDF) effects of the AY, AN, AO and RO categories of the MUs. BTA is an ensemble method for solving spectrum sensing problems using different classifiers. It boosts the performance of some weak classifiers in the combination by giving higher weights to the weak classifiers’ sensing decisions. Simulation results verify the performance improvement by the proposed algorithm compared to the existing techniques such as genetic algorithm soft decision fusion (GASDF), particle swarm optimization soft decision fusion (PSOSDF), maximum gain combination soft decision fusion (MGCSDF) and count hard decision fusion (CHDF). The experimental setup is conducted at different levels of the signal-to-noise ratios (SNRs), total number of cooperative users and sensing samples that show minimum error probability results for the proposed scheme.

The detection and evaluation of flood damage in rural zones are of great importance for farmers, local authorities, and insurance companies. To this end, the paper proposes an efficient system based on five neural networks to assess the degree of flooding and the remaining vegetation. After a previous analysis the following neural networks were selected as primary classifiers: you only look once network (YOLO), generative adversarial network (GAN), AlexNet, LeNet, and residual network (ResNet). Their outputs were connected in a decision fusion scheme, as a new convolutional layer, considering two sets of components: (a) the weights, corresponding to the proven accuracy of the primary neural networks in the validation phase, and (b) the probabilities generated by the neural networks as primary classification results in the operational (testing) phase. Thus, a subjective behavior (individual interpretation of single neural networks) was transformed into a more objective behavior (interpretation based on fusion of information). The images, difficult to be segmented, were obtained from an unmanned aerial vehicle photogrammetry flight after a moderate flood in a rural region of Romania and make up our database. For segmentation and evaluation of the flooded zones and vegetation, the images were first decomposed in patches and, after classification the resulting marked patches were re-composed in segmented images. From the performance analysis point of view, better results were obtained with the proposed system than the neural networks taken separately and with respect to some works from the references.

Medical activities recommendation is a key aspect of an intelligent healthcare system, which can assist doctors with little clinical experience in clinical decision making. Medical activities recommendation can be seen as a kind of temporal set prediction. Previous studies about them are based on Recurrent Neural Network (RNN), which does not incorporate personalized medical history or differentiate between the impact of medical activities. To address the above-given issues, this paper proposes a Next-Day Medical Activities Recommendation (NDMARec) model. Specifically, our model firstly proposes an inpatient day embedding method based on soft-attention which balances the impact of different medical activities to get a joint representation of medical activities that occurred within the same day. Then, a fusion module is designed to combine features of inpatient day and medical history to achieve personalization. These features are learned by the self-attention mechanism that solves the long-term dependency problem of RNNs. Last, adversarial training is introduced to improve the generalization ability of our model. Extensive experiments on a real dataset from a hospital are conducted to show that NDMARec outperformed both classical and state-of-the-art methods.

Only with new sensor concepts in a network, which go far beyond what the current state-of-the-art can offer, can current and future requirements for flexibility, safety, and security be met. The combination of data from many sensors allows a richer representation of the observed phenomenon, e.g., system degradation, which can facilitate analysis and decision-making processes. This work addresses the topic of predictive maintenance by exploiting sensor data fusion and artificial intelligence-based analysis. With a dataset such as vibration and sound from sensors, we focus on studying paradigms that orchestrate the most optimal combination of sensors with deep learning sensor fusion algorithms to enable predictive maintenance. In our experimental setup, we used raw data obtained from two sensors, a microphone, and an accelerometer installed on a brushless direct current (BLDC) motor. The data from each sensor were processed individually and, in a second step, merged to create a solid base for analysis. To diagnose BLDC motor faults, this work proposes to use data-level sensor fusion with deep learning methods such as deep convolutional neural networks (DCNNs) for their ability to automatically extract relevant information from the input data, the long short-term memory method (LSTM), and convolutional long short-term memory (CNN-LSTM), a combination of the two previous methods. The results show that in our setup, sound signals outperform vibrations when used individually for training. However, without any feature selection/extraction step, the accuracy of the models improves with data fusion and reaches 98.8%, 93.5%, and 73.6% for the DCNN, CNN-LSTM, and LSTM methods, respectively, 98.8% being a performance that, according to our reading, has never been reached in the analysis of the faults of a BLDC motor without first going through the extraction of the characteristics and their fusion by traditional methods. These results show that it is possible to work with raw data from multiple sensors and achieve good results using deep learning methods without spending time and resources on selecting appropriate features to extract and methods to use for feature extraction and data fusion.

This paper explores the automatic prediction of public trust in politicians through the use of speech, text, and visual modalities. It evaluates the effectiveness of each modality individually, and it investigates fusion approaches for integrating information from each modality for prediction using a multimodal setting. A database was created consisting of speech recordings, twitter messages, and images representing fifteen American politicians, and labeling was carried out per a publicly available ranking system. The data were distributed into three trust categories, i.e., the low-trust category, mid-trust category, and high-trust category. First, unimodal prediction using each of the three modalities individually was performed using the database; then, using the outputs of the unimodal predictions, a multimodal prediction was later performed. Unimodal prediction was performed by training three independent logistic regression (LR) classifiers, one each for speech, text, and images. The prediction vectors from the individual modalities were then concatenated before being used to train a multimodal decision-making LR classifier. We report that the best performing modality was speech, which achieved a classification accuracy of 92.81%, followed by the images, achieving an accuracy of 77.96%, whereas the best performing model for text-modality achieved a 72.26% accuracy. With the multimodal approach, the highest classification accuracy of 97.53% was obtained when all three modalities were used for trust prediction. Meanwhile, in a bimodal setup, the best performing combination was that combining the speech and image visual modalities by achieving an accuracy of 95.07%, followed by the speech and text combination, showing an accuracy of 94.40%, whereas the text and images visual modal combination resulted in an accuracy of 83.20%.

Modern Machine learning fusion approaches tend to extract features depending on two techniques (hand-crafted feature and representation learning). Hand-crafted features can waste time and are not sufficient for downstream tasks. Unlike representation learning, we automatically learn features with minimum time and effort and are suitable for downstream tasks. In our paper, we provide work on graph neural network methods with details on classical graph embedding approaches and the different methods in neural graph networks such as graph filtering, graph pooling, and the learning parameter for graph following each technique with a general framework or mathematical proof for customer satisfaction. To satisfy customer's feel, this research employs NLP techniques. We describe the adversarial attacks and defenses on graph representation approaches. Also, advanced application of neural graph networks is reviewed, such as combinational optimization, learning program representation, physical system modeling, and natural language processing. Finally, the challenges in geometric neural networks and future research work have been introduced.

Abstract The use of advanced simulation has become increasingly more important in the planning, design, and assessment phases of future fusion plasma diagnostics, and in the interpretation of experimental data from existing ones. The design cycle of complex reflectometry systems, such as the ones being planned for next generation machines (IDTT and DEMO), relies heavily on the results produced by synthetic diagnostics, used for system performance evaluation and prediction, both crucial in the design process decision making. These synthetic diagnostics need realistic representations of all system components to incorporate the main effects that shape their behavior. Some of the most important elements that are required to be well modelled and integrated in simulations are the wave launcher structures, such as the waveguides, tapers, and antennas, as well as the vessel wall structures and access to the plasma. The latter are of paramount importance and are often neglected in this type of studies. Faithfully modelling them is not an easy task, especially in 3D simulations. The procedure herein proposed consists in using CAD models of a given machine, together with parameterizable models of the launcher, to produce a description suited for Finite Difference Time Domain (FDTD) 3D simulation, combining the capabilities of real-world CAD design with the power of simulation. However, CAD model geometric descriptions are incompatible with the ones used by standard FDTD codes. CAD software usually outputs models in a tessellated mesh while FDTD simulators use Volumetric Pixel (VOXEL) descriptions. To solve this interface problem, we implemented a pipeline to automatically convert complex CAD models of tokamak vessel components and wave launcher structures to the VOXEL input required by REFMUL3, a full wave 3D Maxwell FDTD parallel code. To illustrate the full procedure, a complex reflectometry synthetic diagnostic for IDTT was setup, converted and simulated. This setup includes 3 antennas recessed into the vessel wall, for thermal protection, one for transmission and reception, and two just for reception.

The advent of artificial intelligence and deep learning has provided sophisticated functionality for sensor fusion and object detection and classification which have accelerated the development of highly automated and autonomous ships as well as decision support systems for maritime navigation. It is, however, challenging to assess how the implementation of these systems affects the safety of ship operation. We propose to utilize marine training simulators to conduct controlled, repeated experiments allowing us to compare and assess how functionality for autonomous navigation and decision support affects navigation performance and safety. However, although marine training simulators are realistic to human navigators, it cannot be assumed that the simulators are sufficiently realistic for testing the object detection and classification functionality, and hence this functionality cannot be directly implemented in the simulators. We propose to overcome this challenge by utilizing Cycle-Consistent Adversarial Networks (Cycle-GANs) to transform the simulator data before object detection and classification is performed. Once object detection and classification are completed, the result is transferred back to the simulator environment. Based on this result, decision support functionality with realistic accuracy and robustness can be presented and autonomous ships can make decisions and navigate in the simulator environment.

AbstractFacial expression recognition is a fine-grained task because different emotions have subtle facial movements. This paper proposes to learn inter-class optical flow difference using generative adversarial networks (GANs) for facial expression recognition. Initially, the proposed method employs a GAN to produce inter-class optical flow images from the difference between the static fully expressive samples and neutral expression samples. Such inter-class optical flow difference is used to highlight the displacement of facial parts between the neutral facial images and fully expressive facial images, which can avoid the disadvantage that the optical flow change between adjacent frames of the same video expression image is not obvious. Then, the proposed method designs four-channel convolutional neural networks (CNNs) to learn high-level optical flow features from the produced inter-class optical flow images, and high-level static appearance features from the fully expressive facial images, respectively. Finally, a decision-level fusion strategy is adopted to implement facial expression classification. The proposed method is validated on two public facial expression databases, BAUM_1a, SAMM and AFEW5.0, demonstrating its promising performance.

Abstract Load identification is an essential step in Non-Intrusive Load Monitoring (NILM), a process of estimating the power consumption of individual appliances using only whole-house aggregate consumption. Such estimates can help consumers and utility companies improve load management and save power. Current state-of-the-art methods for load identification generally use either steady state or transient features for load identification. We hypothesize that these are complementary features and so a hybrid combination of them will result in an improved appliance signature. We propose a novel hybrid combination that has the advantage of being low-dimensional and can thus be easily integrated with existing classification models to improve load identification. Our improved hybrid features are then used for building appliance identification models using Naive Bayes, KNN, Decision Tree and Random Forest classifiers. The proposed NILM methodology is evaluated for robustness in changing environments. An automated data collection setup is established to capture 7 home appliances aggregate data under varying voltages. Experimental results show that our proposed feature fusion based algorithms are more robust and outperform steady state and transient feature-based algorithms by at least +9% and +15% respectively.

Sentiment analysis can be used to study an individual or a group’s emotions and attitudes towards other people and entities like products, services, or social events. With the advancements in the field of deep learning, the enormity of available information on internet, chiefly on social media, combined with powerful computing machines, it’s just a matter of time before artificial intelligence (AI) systems make their presence in every aspect of human life, making our lives more introspective. In this paper, we propose to implement a multimodal sentiment prediction system that can analyze the emotions predicted from different modal sources such as video, audio and text and integrate them to recognize the group emotions of the students in a classroom. Our experimental setup involves a digital video camera with microphones to capture the live video and audio feeds of the students during a lecture. The students are advised to provide their digital feedback on the lecture as ‘tweets’ on their twitter account addressed to the lecturer’s official twitter account. The audio and video frames are separated from the live streaming video using tools such as lame and ffmpeg. A twitter API was used to access and extract messages from twitter platform. The audio and video features are extracted using Mel-Frequency Cepstral Co-efficients (MFCC) and Haar Cascades classifier respectively. The extracted features are then passed to the Convolutional Neural Network (CNN) model trained on the FER2013 facial images database to generate the feature vector for classification of video-based emotions. A Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM), trained on speech emotion corpus database was used to train on the audio features. A lexicon-based approach with senti-word dictionary and learning based approach with custom dataset trained by Support Vector Machines (SVM) was used in the twitter-texts based approach. A decision-level fusion algorithm was applied on these three different modal schemes to integrate the classification results and deduce the overall group emotions of the students. The use-case of this proposed system will be in student emotion recognition, employee performance feedback, monitoring or surveillance-based systems. The implemented system framework was tested in a classroom environment during a live lecture and the predicted emotions demonstrated the classification accuracy of our approach.

AbstractMultiple predominant instrument recognition in polyphonic music is addressed using decision level fusion of three transformer-based architectures on an ensemble of visual representations. The ensemble consists of Mel-spectrogram, modgdgram, and tempogram. Predominant instrument recognition refers to the problem where the prominent instrument is identified from a mixture of instruments being played together. We experimented with two transformer architectures like Vision transformer (Vi-T) and Shifted window transformer (Swin-T) for the proposed task. The performance of the proposed system is compared with that of the state-of-the-art Han’s model, convolutional neural networks (CNN), and deep neural networks (DNN). Transformer networks learn the distinctive local characteristics from the visual representations and classify the instrument to the group where it belongs. The proposed system is systematically evaluated using the IRMAS dataset with eleven classes. A wave generative adversarial network (WaveGAN) architecture is also employed to generate audio files for data augmentation. We train our networks from fixed-length music excerpts with a single-labeled predominant instrument and estimate an arbitrary number of predominant instruments from the variable-length test audio file without any sliding window analysis and aggregation strategy as in existing algorithms. The ensemble voting scheme using Swin-T reports a micro and macro F1 score of 0.66 and 0.62, respectively. These metrics are 3.12% and 12.72% relatively higher than those obtained by the state-of-the-art Han’s model. The architectural choice of transformers with ensemble voting on Mel-spectro-/modgd-/tempogram has merit in recognizing the predominant instruments in polyphonic music.

We consider a class of min-max robust problems in which the functions that need to be “robustified” can be decomposed as the sum of arbitrary functions. This class of problems includes many practical problems, such as the lot-sizing problem under demand uncertainty. By considering a Lagrangian relaxation of the uncertainty set, we derive a tractable approximation, called the dual Lagrangian approach, that we relate with both the classical dualization approximation approach and an exact approach. Moreover, we show that the dual Lagrangian approach coincides with the affine decision rule approximation approach. The dual Lagrangian approach is applied to a lot-sizing problem, in which demands are assumed to be uncertain and to belong to the uncertainty set with a budget constraint for each time period. Using the insights provided by the interpretation of the Lagrangian multipliers as penalties in the proposed approach, two heuristic strategies, a new guided iterated local search heuristic, and a subgradient optimization method are designed to solve more complex lot-sizing problems in which additional practical aspects, such as setup costs, are considered. Computational results show the efficiency of the proposed heuristics that provide a good compromise between the quality of the robust solutions and the running time required in their computation. Summary of Contribution: The paper includes both theoretical and algorithmic contributions for a class of min-max robust optimization problems where the objective function includes the maximum of a sum of affine functions. From the theoretical point of view, a tractable Lagrangian dual model resulting from a relaxation of the well-known adversarial problem is proposed, providing a new perspective of well-known models, such as the affinely adjustable robust counterpart (AARC) and the dualization technique introduced by Bertsimas and Sim. These results are particularized to lot-sizing problems. From the algorithm point of view, efficient heuristic schemes—which exploit the information based on the interpretation of the Lagrangian multipliers to solve large size robust problems—are proposed, and their performance is evaluated through extensive computational results based on the lot-sizing problem. In particular, a guided iterated local search and a subgradient optimization method are proposed and compared against the dualization approach proposed by Bertsimas and Sim and with several heuristics based on the AARC approach, which include an iterated local search heuristic and a Benders decomposition approach. Computational results show the efficiency of the proposed heuristics, which provide a good compromise between the quality of the robust solutions and the running time.

Following in the footsteps of the protagonists of the Italian architectural debate is a mark of culture and proactivity. The synthesis deriving from the artistic-humanistic factors, combined with the technical-scientific component, comprises the very root of the process that moulds the architect as an intellectual figure capable of governing material processes in conjunction with their ability to know how to skilfully select schedules, phases and actors: these are elements that – when paired with that magical and essential compositional sensitivity – have fuelled this profession since its origins. The act of X-raying the role of architecture through the filter of its “autonomy” or “heteronomy”, at a time when the hybridisation of different areas of knowledge and disciplinary interpenetration is rife, facilitates an understanding of current trends, allowing us to bring the fragments of a debate carved into our culture and tradition up to date. As such, heteronomy – as a condition in which an acting subject receives the norm of its action from outside itself: the matrix of its meaning, coming from ancient Greek, the result of the fusion of the two terms ἕτερος éteros “different, other” and νόμος nómos “law, ordinance” – suggests the existence of a dual sentiment now pervasive in architecture: the sin of self-reference and the strength of depending on other fields of knowledge. Difference, interpreted as a value, and the ability to establish relationships between different points of observation become moments of a practice that values the process and method of affirming architecture as a discipline. The term “heteronomy”, used in opposition to “autonomy”, has – from the time of Kant onwards – taken on a positive value connected to the mutual respect between reason and creativity, exact science and empirical approach, contamination and isolation, introducing the social value of its existence every time that it returns to the forefront. At the 1949 conference in Lima, Ernesto Nathan Rogers spoke on combining the principle of “Architecture is an Art” with the demands of a social dimension of architecture: «Alberti, in the extreme precision of his thought, admonishes us that the idea must be translated into works and that these must have a practical and moral purpose in order to adapt harmoniously ‘to the use of men’, and I would like to point out the use of the plural of ‘men’, society. The architect is neither a passive product nor a creator completely independent of his era: society is the raw material that he transforms, giving it an appearance, an expression, and the consciousness of those ideals that, without him, would remain implicit. Our prophecy, like that of the farmer, already contains the seeds for future growth, as our work also exists between heaven and earth. Poetry, painting, sculpture, dance and music, even when expressing the contemporary, are not necessarily limited within practical terms. But we architects, who have the task of synthesising the useful with the beautiful, must feel the fundamental drama of existence at every moment of our creative process, because life continually puts practical needs and spiritual aspirations at odds with one another. We cannot reject either of these necessities, because a merely practical or moralistic position denies the full value of architecture to the same extent that a purely aesthetic position would: we must mediate one position with the other» (Rogers, 1948). Rogers discusses at length the relationship between instinctive forces and knowledge acquired through culture, along with his thoughts on the role played by study in an artist’s training. It is in certain debates that have arisen within the “International Congresses of Modern Architecture” that the topic of architecture as a discipline caught between self-sufficiency and dependence acquires a certain centrality within the architectural context: in particular, in this scenario, the theme of the “autonomy” and “heteronomy” of pre-existing features of the environment plays a role of strategic importance. Arguments regarding the meaning of form in architecture and the need for liberation from heteronomous influences did not succeed in undermining the idea of an architecture capable of influencing the governing of society as a whole, thanks to an attitude very much in line with Rogers’ own writings. The idea of a project as the result of the fusion of an artistic idea and pre-existing features of an environment formed the translation of the push to coagulate the antithetical forces striving for a reading of the architectural work that was at once autonomous and heteronomous, as well as linked to geographical, cultural, sociological and psychological principles. The CIAM meeting in Otterlo was attended by Ignazio Gardella, Ernesto Nathan Rogers, Vico Magistretti and Giancarlo De Carlo as members of the Italian contingent: the architects brought one project each to share with the conference and comment on as a manifesto. Ernesto Nathan Rogers, who presented the Velasca Tower, and Giancarlo De Carlo, who presented a house in Matera in the Spine Bianche neighbourhood, were openly criticised as none of the principles established by the CIAM were recognisable in their work any longer, and De Carlo’s project represented a marked divergence from a consolidated method of designing and building in Matera. In this cultural condition, Giancarlo De Carlo – in justifying the choices he had made – even went so far as to say: «my position was not at all a flight from architecture, for example in sociology. I cannot stand those who, paraphrasing what I have said, dress up as politicians or sociologists because they are incapable of creating architecture. Architecture is – and cannot be anything other than – the organisation and form of physical space. It is not autonomous, it is heteronomous» (De Carlo, 2001). Even more so than in the past, it is not possible today to imagine an architecture encapsulated entirely within its own enclosure, autoimmune, averse to any contamination or relationships with other disciplinary worlds: architecture is the world and the world is the sum total of our knowledge. Architecture triggers reactions and phenomena: it is not solely and exclusively the active and passive product of a material work created by man. «We believed in the heteronomy of architecture, in its necessary dependence on the circumstances that produce it, in its intrinsic need to exist in harmony with history, with the happenings and expectations of individuals and social groups, with the arcane rhythms of nature. We denied that the purpose of architecture was to produce objects, and we argued that its fundamental role was to trigger processes of transformation of the physical environment that are capable of contributing to the improvement of the human condition» (De Carlo, 2001). Productive and cultural reinterpretations place the discipline of architecture firmly at the centre of the critical reconsideration of places for living and working. Consequently, new interpretative models continue to emerge which often highlight the instability of built architecture with the lack of a robust theoretical apparatus, demanding the sort of “technical rationality” capable of restoring the centrality of the act of construction, through the contribution of actions whose origins lie precisely in other subject areas. Indeed, the transformation of the practice of construction has resulted in direct changes to the structure of the nature of the knowledge of it, to the role of competencies, to the definition of new professional skills based on the demands emerging not just from the production system, but also from the socio-cultural system. The architect cannot disregard the fact that the making of architecture does not burn out by means of some implosive dynamic; rather, it is called upon to engage with the multiple facets and variations that the cognitive act of design itself implies, bringing into play a theory of disciplines which – to varying degrees and according to different logics – offer their significant contribution to the formation of the design and, ultimately, the work. As Álvaro Siza claims, «The architect is not a specialist. The sheer breadth and variety of knowledge that practicing design encompasses today – its rapid evolution and progressive complexity – in no way allow for sufficient knowledge and mastery. Establishing connections – pro-jecting [from Latin proicere, ‘to stretch out’] – is their domain, a place of compromise that is not tantamount to conformism, of navigation of the web of contradictions, the weight of the past and the weight of the doubts and alternatives of the future, aspects that explain the lack of a contemporary treatise on architecture. The architect works with specialists. The ability to chain things together, to cross bridges between fields of knowledge, to create beyond their respective borders, beyond the precarity of inventions, requires a specific education and stimulating conditions. [...] As such, architecture is risk, and risk requires impersonal desire and anonymity, starting with the merging of subjectivity and objectivity. In short, a gradual distancing from the ego. Architecture means compromise transformed into radical expression, in other words, a capacity to absorb the opposite and overcome contradiction. Learning this requires an education in search of the other within each of us» (Siza, 2008). We are seeing the coexistence of contrasting, often extreme, design trends aimed at recementing the historical and traditional mould of construction by means of the constant reproposal of the characteristics of “persistence” that long-established architecture, by its very nature, promotes, and at decrypting the evolutionary traits of architecture – markedly immaterial nowadays – that society promotes as phenomena of everyday living. Speed, temporariness, resilience, flexibility: these are just a few fragments. In other words, we indicate a direction which immediately composes and anticipates innovation as a characterising element, describing its stylistic features, materials, languages and technologies, and only later on do we tend to outline the space that these produce: what emerges is a largely anomalous path that goes from “technique” to “function” – by way of “form” – denying the circularity of the three factors at play. The threat of a short-circuit deriving from discourse that exceeds action – in conjunction with a push for standardisation aimed at asserting the dominance of construction over architecture, once again echoing the ideas posited by Rogers – may yet be able to finding a lifeline cast through the attempt to merge figurative research with technology in a balanced way, in the wake of the still-relevant example of the Bauhaus or by emulating the thinking of certain masters of modern Italian architecture who worked during that post-war period so synonymous with physical – and, at the same time, moral – reconstruction. These architectural giants’ aptitude for technical and formal transformation and adaptation can be held up as paradigmatic examples of methodological choice consistent with their high level of mastery over the design process and the rhythm of its phases. In all this exaltation of the outcome, the power of the process is often left behind in a haze: in the uncritical celebration of the architectural work, the method seems to dissolve entirely into the finished product. Technical innovation and disciplinary self-referentiality would seem to deny the concepts of continuity and transversality by means of a constant action of isolation and an insufficient relationship with itself: conversely, the act of designing, as an operation which involves selecting elements from a vast heritage of knowledge, cannot exempt itself from dealing in the variables of a functional, formal, material and linguistic nature – all of such closely intertwined intents – that have over time represented the energy of theoretical formulation and of the works created. For years, the debate in architecture has concentrated on the synergistic or contrasting dualism between cultural approaches linked to venustas and firmitas. Kenneth Frampton, with regard to the interpretative pair of “tectonics” and “form”, notes the existence of a dual trend that is both identifiable and contrasting: namely the predisposition to favour the formal sphere as the predominant one, rejecting all implications on the construction, on the one hand; and the tendency to celebrate the constructive matrix as the generator of the morphological signature – emphasised by the ostentation of architectural detail, including that of a technological matrix – on the other. The design of contemporary architecture is enriched with sprawling values that are often fundamental, yet at times even damaging to the successful completion of the work: it should identify the moment of coagulation within which the architect goes in pursuit of balance between all the interpretative categories that make it up, espousing the Vitruvian meaning, according to which practice is «the continuous reflection on utility» and theory «consists of being able to demonstrate and explain the things made with technical ability in terms of the principle of proportion» (Vitruvius Pollio, 15 BC). Architecture will increasingly be forced to demonstrate how it represents an applied and intellectual activity of a targeted synthesis, of a complex system within which it is not only desirable, but indeed critical, for the cultural, social, environmental, climatic, energy-related, geographical and many other components involved in it to interact proactively, together with the more spatial, functional and material components that are made explicit in the final construction itself through factors borrowed from neighbouring field that are not endogenous to the discipline of architecture alone. Within a unitary vision that exists parallel to the transcalarity that said vision presupposes, the technology of architecture – as a discipline often called upon to play the role of a collagen of skills, binding them together – acts as an instrument of domination within which science and technology interpret the tools for the translation of man’s intellectual needs, expressing the most up-to-date principles of contemporary culture. Within the concept of tradition – as inferred from its evolutionary character – form, technique and production, in their historical “continuity” and not placed in opposition to one other, make up the fields of application by which, in parallel, research proceeds with a view to ensuring a conforming overall design. The “technology of architecture” and “technological design” give the work of architecture its personal hallmark: a sort of DNA to be handed down to future generations, in part as a discipline dedicated to amalgamating the skills and expertise derived from other dimensions of knowledge. In the exercise of design, the categories of urban planning, composition, technology, structure and systems engineering converge, the result increasingly accentuated by multidisciplinary nuances in search of a sense of balance between the parts: a setup founded upon simultaneity and heteronomous logic in the study of variables, by means of translations, approaches and skills as expressions of multifaceted identities. «Architects can influence society with their theories and works, but they are not capable of completing any such transformation on their own, and end up being the interpreters of an overbearing historical reality under which, if the strongest and most honest do not succumb, that therefore means that they alone represent the value of a component that is algebraically added to the others, all acting in the common field» (Rogers, 1951). Construction, in this context, identifies the main element of the transmission of continuity in architecture, placing the “how” at the point of transition between past and future, rather than making it independent of any historical evolution. Architecture determines its path within a heteronomous practice of construction through an effective distinction between the strength of the principles and codes inherent to the discipline – long consolidated thanks to sedimented innovations – and the energy of experimentation in its own right. Architecture will have to seek out and affirm its own identity, its validity as a discipline that is at once scientific and poetic, its representation in the harmonies, codes and measures that history has handed down to us, along with the pressing duty of updating them in a way that is long overdue. The complexity of the architectural field occasionally expresses restricted forms of treatment bound to narrow disciplinary areas or, conversely, others that are excessively frayed, tending towards an eclecticism so vast that it prevents the tracing of any discernible cultural perimeter. In spite of the complex phenomenon that characterises the transformations that involve the status of the project and the figure of the architect themselves, it is a matter of urgency to attempt to renew the interpretation of the activity of design and architecture as a coherent system rather than a patchwork of components. «Contemporary architecture tends to produce objects, even though its most concrete purpose is to generate processes. This is a falsehood that is full of consequences because it confines architecture to a very limited band of its entire spectrum; in doing so, it isolates it, exposing it to the risks of subordination and delusions of grandeur, pushing it towards social and political irresponsibility. The transformation of the physical environment passes through a series of events: the decision to create a new organised space, detection, obtaining the necessary resources, defining the organisational system, defining the formal system, technological choices, use, management, technical obsolescence, reuse and – finally – physical obsolescence. This concatenation is the entire spectrum of architecture, and each link in the chain is affected by what happens in all the others. It is also the case that the cadence, scope and intensity of the various bands can differ according to the circumstances and in relation to the balances or imbalances within the contexts to which the spectrum corresponds. Moreover, each spectrum does not conclude at the end of the chain of events, because the signs of its existence – ruins and memory – are projected onto subsequent events. Architecture is involved with the entirety of this complex development: the design that it expresses is merely the starting point for a far-reaching process with significant consequences» (De Carlo, 1978). The contemporary era proposes the dialectic between specialisation, the coordination of ideas and actions, the relationship between actors, phases and disciplines: the practice of the organisational culture of design circumscribes its own code in the coexistence and reciprocal exploitation of specialised fields of knowledge and the discipline of synthesis that is architecture. With the revival of the global economy on the horizon, the dematerialisation of the working practice has entailed significant changes in the productive actions and social relationships that coordinate the process. Despite a growing need to implement skills and means of coordination between professional actors, disciplinary fields and sectors of activity, architectural design has become the emblem of the action of synthesis. This is a representation of society which, having developed over the last three centuries, from the division of social sciences that once defined it as a “machine”, an “organism” and a “system”, is now defined by the concept of the “network” or, more accurately, by that of the “system of networks”, in which a person’s desire to establish relationships places them within a multitude of social spheres. The “heteronomy” of architecture, between “hybridisation” and “contamination of knowledge”, is to be seen not only an objective fact, but also, crucially, as a concept aimed at providing the discipline with new and broader horizons, capable of putting it in a position of serenity, energy and courage allowing it to tackle the challenges that the cultural, social and economic landscape is increasingly throwing at the heart of our contemporary world.