Abstract Current research on explainable and white-box artificial intelligence faces prominent issues: conceptual disarray, divergent perspectives, and a disconnect between theory and practice. The foremost priority is therefore to return to the field’s purest objectives and explore its most fundamental questions. To this end, this paper introduces the axiomatic criterion of white-box completeness (WBC). Specifically, an agent is white-box complete if and only if its behavior can be bidirectionally approximated by human interpretable and manipulable mathematical forms with bounded error. It is a formalization for realizing three ultimate objectives for trustworthy AI: discernible learned knowledge and behaviors, knowledge extraction from AI, and human knowledge injection. Therefore, the ultimate pursuit of explainable AI has been transformed from the vague goal of “making AI interpretable” into a precise mathematical problem. Keywords: White-box completeness; Interpretability; Explainable artificial intelligence; Trustworthy artificial intelligence; Knowledge extraction and injection.
Wen‐Xuan Wang, Yu-Die Zhang, Xin-Ting Li et al.· Zenodo (CERN European Organi...· 0 citations
Explainable Artificial Intelligence (XAI) has been increasingly applied in image aesthetic quality evaluation. However, it remains unclear how perceived explainability influences users’ decision adoption and what specific explanation requirements shape this perception. This study develops and tests a multi-stage model of XAI-supported human–AI decision-making in aesthetic evaluation based on Task–Technology Fit theory with a self-developed AI aesthetic evaluation system and PLS-SEM analysis (N = 494). Our findings reveal that perceived explainability does not exert a direct effect on perceived fairness, but influences it indirectly through two underlying psychological mechanisms: functional understanding and affective satisfaction. Furthermore, perceived fairness serves as a critical mediating mechanism linking explainability perceptions to decision outcomes. Extending this framework, a second online questionnaire study(N = 313) investigates the specific explanation requirements of the users in AI-assisted aesthetic evaluation. The results reveal seven categories of explanation needs and develop a corresponding question bank to guide the design and evaluation of XAI systems. This study contributes to a unified theoretical understanding of explainable human–AI decision-making in aesthetic quality evaluation and provides practical guidance for researchers, developers, and organizations designing XAI-assisted aesthetic quality evaluation systems.
Explainable Artificial Intelligence (XAI) has been increasingly applied in image aesthetic quality evaluation. However, it remains unclear how perceived explainability influences users’ decision adoption and what specific explanation requirements shape this perception. This study develops and tests a multi-stage model of XAI-supported human–AI decision-making in aesthetic evaluation based on Task–Technology Fit theory with a self-developed AI aesthetic evaluation system and PLS-SEM analysis (N = 494). Our findings reveal that perceived explainability does not exert a direct effect on perceived fairness, but influences it indirectly through two underlying psychological mechanisms: functional understanding and affective satisfaction. Furthermore, perceived fairness serves as a critical mediating mechanism linking explainability perceptions to decision outcomes. Extending this framework, a second online questionnaire study(N = 313) investigates the specific explanation requirements of the users in AI-assisted aesthetic evaluation. The results reveal seven categories of explanation needs and develop a corresponding question bank to guide the design and evaluation of XAI systems. This study contributes to a unified theoretical understanding of explainable human–AI decision-making in aesthetic quality evaluation and provides practical guidance for researchers, developers, and organizations designing XAI-assisted aesthetic quality evaluation systems.
The growing use of Artificial Intelligence (AI) in organisations is changing how employees perform, organise, and experience their work. AI-supported systems can automate routine activities, assist with information processing and improve the speed of task completion. These advantages have created expectations that AI may help employees manage their professional responsibilities more efficiently and achieve a healthier work-life balance. At the same time, increased dependence on AI can introduce new pressures, including higher performance expectations, continuous technological adaptation, work intensification and technology-related stress. The present paper examines the relationship between AI adoption, workload, stress, work-life balance and employee well-being. Drawing on the Job Demands-Resources (JD-R) perspective, the paper conceptualises AI as a workplace resource when it reduces unnecessary effort and supports employees, while recognising that it may become a job demand when it increases pressure and complexity. The paper proposes an empirical framework in which workload and stress explain how AI adoption may influence work-life balance and employee well-being. Recent research indicates that AI can improve task optimisation and work-life outcomes under supportive conditions, while AI-related technostress may contribute to exhaustion and work-family conflict. (DOI) The study provides a foundation for future empirical investigation and highlights the need for organisations to evaluate AI not only through productivity indicators but also through employee health, balance and sustainable work practices.
Roli Mishra· Zenodo (CERN European Organi...· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
This research presents a comprehensive framework for integrating Explainable Artificial Intelligence (XAI) into Intrusion Detection Systems (IDS) to address the critical challenge of AI model opacity in cybersecurity. Traditional AI-based IDS models function as "black boxes," limiting trust, accountability, and practical deployment. The proposed XAI-IDS framework combines machine learning-based intrusion detection (Random Forest, XGBoost, Neural Networks) with explainability mechanisms including SHAP, LIME, and feature importance analysis. Experimental evaluation using benchmark datasets (KDD Cup 99, UNSW-NB15, CIC-IDS-2017) demonstrates that the XAI-enabled system achieves high detection accuracy (96-98%) while providing transparent, human-interpretable explanations for each security decision. The framework significantly reduces false positives, enhances auditability, and improves security analyst trust and response effectiveness without substantial performance degradation.
Muhammad Haris Khan· Zenodo (CERN European Organi...· 0 citations
Why is time one-dimensional? The answer offered here is that no law decrees it; the requirement that one be able to predict allows nothing else. The equations of a universe with two times can be written, and their solutions exist. What breaks is prediction. No new mathematical theorem and no new law is claimed. Scope of this paper (scope note): no new mathematical theorem and no new law is claimed. Hadamard's three conditions for well-posedness, the ill-posedness of the Cauchy problem for Laplace's equation, the ill-posedness of the backward heat equation, the Cauchy problem for ultrahyperbolic equations, and the classification of second order operators by signature are all standard. It is not proved that spacetime must be 3+1 ── the discipline is that of Paper 69, and what is done here is to add one entry to its ledger. No anthropic argument is made ── the phrase because there are observers is never used. No measured value is cited ── every number is computed from a definition. No theory of partial differential equations is built ── only exact solutions and a finite Fourier representation are used. Prediction is not defined ── what is treated is the single point of continuous dependence on the data. It is not claimed that ultrahyperbolic equations have no solutions ── solutions exist; what fails is uniqueness and continuous dependence. The arrow of time is not solved ── what Paper 98 recorded as open is left untouched. Quantum theory is not treated. The relation to earlier papers. Paper 69 wrote why 3+1 as an overdetermination and assembled five independent roots selecting four dimensions; not one of them selects which of the four is time, and this paper fills that empty place. Paper 159 showed that ill-posed is not one word and placed the separator in the decay of the singular values; this paper applies that same separator to the number of time dimensions. Paper 154 showed that a limit without its order is not a quantity; that concerns the order of limits and this the signature. Papers 118, 119 and 122 showed that the one word time covers four logical types; what is asked here is not the type but the number. Paper 251 separated special in two dimensions; this paper stands beside it, on the side of special in one. First, being solvable and being predictable are different demands. Hadamard wrote what it is for a problem to be well-posed as three conditions: that a solution exists, that it is unique, and that it depends continuously on the data. The three are independent; the first two are about whether it can be solved, and what corresponds to prediction is the third alone. Why the third is prediction: initial data is measured and then entered, and measurement always carries error. If the error changes the answer, then holding a formula for the solution one still cannot state tomorrow's value. Second, with no time dimension the initial value problem explodes. Take Laplace's equation and, treating the vertical coordinate as the time, solve it as an initial value problem (Hadamard's example). With data of size one over n, the amplification at unit height is 1.101 times ten to the third at n=10, 1.213 times ten to the seventh at n=20, 2.942 times ten to the fifteenth at n=40, and 3.463 times ten to the thirty-second at n=80. The data tends to zero and the solution diverges. Neither existence nor uniqueness has failed ── there is a solution and it is unique. What has failed is the third condition alone. Third, with one time dimension the same procedure stays bounded. Change the equation to the wave equation; one sign has been changed and nothing else. With the same data the amplification is 0.0544 at n=10, 0.0457 at n=20, 0.0186 at n=40 and 0.0124 at n=80. At the same n=80 that is 3.463 times ten to the thirty-second against 0.0124 ── thirty-four orders of magnitude. What changed is one sign in the equation, and not the data, not the method, not the precision. What makes the difference is the signature. Fourth, this is the core. One and the same heat equation exchanges well-posedness for ill-posedness when only its direction is reversed. Mode n is multiplied by the exponential of minus n squared t. At n=80 that is 1.604 times ten to the minus twenty-eighth forwards against 6.235 times ten to the twenty-seventh backwards. Running it on a grid of 512 points, the maximum going forwards stays below one at 0.9759, 0.8944 and 0.8165, while backwards it grows to 2.073 times ten to the eleventh, 2.417 times ten to the hundred and twenty-third, and 1.304 times ten to the two hundred and sixty-fourth, overflowing double precision before reaching t=0.05. To measure what this means for prediction, relative noise of ten to the minus tenth ── standing for observational error ── is added to the data and that component alone is sent both ways: forwards it decays to 9.398, 5.403 and 3.835 times ten to the minus eleventh, while backwards it has grown to 4.135 times ten to the seventeenth already at t=0.001. The signal is buried; one holds the same formula for the solution and cannot state a value. Here is the core: there is no asymmetry on the side of the law. The heat equation is one equation, and reversing time does not turn it into another. The asymmetry is on the side of well-posedness. This does not explain the arrow of time ── as Paper 98 recorded honestly, why there is a low entropy past is unsolved. What can be said here is one step short of that: the phenomenon of being able to predict one way and not the other does not itself require an asymmetric law. Fifth, with two time dimensions what happens next is not determined. Giving time two dimensions, a plane wave gives the dispersion relation that the sum of the squares of the two frequencies equals the square of the wave number. With one time the same procedure returns two values, plus and minus the wave number; with two it returns a whole circle in the frequency plane, a continuum. So the data does not determine what happens next. What has failed this time is uniqueness ── in the third section it was continuous dependence. One word, ill-posed, is naming two different failures (Paper 159). Sixth, one measure separates them: the signature of the principal symbol. Counting the signs of the eigenvalues, (4,0) is elliptic and ill-posed, (3,1) is hyperbolic and well-posed, and (2,2) and (1,3) are ultrahyperbolic and ill-posed. Only one time dimension is well-posed. Since (1,3) is (3,1) with the overall sign reversed and means the same physics, what is to be counted is the size of the smaller sign class. One thing follows: it is not that time is special. The sign class with only one member is what we call time. The direction looks reversed because the definition comes first and time second. Seventh, one independent entry is added to the census of Paper 69. The roots it assembled ── conformal invariance of the Maxwell action, graviton degrees of freedom, exotic four-space, Bertrand and Ehrenfest stability, the maximum of the ball volume ── all select how many, and not one of them selects which of them is time. That is the empty place this paper fills. And this root cannot be derived from the other five: conformal invariance, graviton degrees of freedom and exotic four-space are all statements made after a signature has been assumed, and well-posedness stands on the side of that assumption. They are distinct roots (Paper 58). Even so, 3+1 is not proved here. What can be said reaches no further than that prediction is not an available activity unless there is exactly one time dimension, and adds nothing about why space has three. Closing. Time is one-dimensional, and not because time is special. The equations of a two-time universe can be written and their solutions exist. What breaks is prediction ── add a dimension and the answer stops being unique; remove one and measurement error buries it. There is exactly one signature in which the word tomorrow means anything. And the fifth section showed that even inside that one, one direction permits prediction and the other does not ── without once invoking an asymmetric law. On the making of this work: The ideas and content of this work stem from the author's own considerations. Assistance from an AI (a large language model) was used for structuring, English translation, and checking the algebra. Any remaining errors or misinterpretations are solely the author's. Feedback and corrections are sincerely appreciated. ----- 時間はなぜ一本なのか。本稿の答は、そう決めた法則があるからではなく、「予言できる」という要求がそれしか許さないから、である。時間が二本ある宇宙の方程式は書ける。解も存在する。壊れるのは予言のほうである。新しい数学定理も新しい法則も主張しない。 本稿の射程(射程注記):新しい数学定理も新しい法則も主張しない。アダマールの適切性の三条件、ラプラス方程式のコーシー問題の不適切性、後ろ向き熱方程式の不適切性、超双曲型方程式のコーシー問題、二階作用素の符号数による分類は、いずれも標準的である。時空が 3+1 でなければならないとは証明しない──論文69 と同じ規律であり、本稿がするのはその台帳に一本足すことだけである。人間原理を立てない──「観測者がいるから」とは一度も言わない。測定値を引かない──本稿の数はすべて定義から計算したものである。偏微分方程式の理論を作らない──使うのは厳密解と有限次元のフーリエ表示だけである。「予言」を定義しない──扱うのは初期条件への連続依存という一点であって、認識論には立ち入らない。超双曲型方程式に解が無いとは言わない──解は存在する。壊れるのは一意性と連続依存である。時間の矢を解かない──論文98 が未解決と書いたことに手をつけない。量子論を扱わない。 既刊との関係。論文69 は「なぜ 3+1 次元か」を過剰決定として書き、D=4 を選ぶ五つの独立な根を並べた。だがそのどれも、四つのうちどれが時間かを選んでいない。本稿はその空いた位置に一本足す。論文159 は「不適切」が一語でないことを示し、分離子を特異値の落ち方に置いた。本稿は同じ分離子を時間の本数に当てる。論文154 は順序を書かない極限は量ではないと示した。あちらは極限の順序、こちらは符号数であり、別の軸である。論文118・119・122 は「時間」という一語が四つの論理型を覆うことを示した。本稿が問うのは型ではなく本数である。論文251 は「二次元だけ特別」を分けた。本稿はその隣、一次元だけ特別の側に立つ。 第一に、「解ける」と「予言できる」は別の要求である。アダマールは、問題が適切であることを三つの条件で書いた──解が存在すること、解が一つに決まること、初期条件に連続に依存すること。三つは独立であり、前二つは解けるかどうかの話で、予言に対応するのは三つ目だけである。なぜ三つ目が予言なのか。初期条件は測って入れるものであり、測定には必ず誤差がある。誤差が答を変えてしまうなら、解の式を持っていても、明日の値を言うことができない。 第二に、時間が 0 本だと初期値問題が爆発する。ラプラス方程式を取り、縦の座標を時間だと思って初期値問題として解く(アダマールの例)。初期値の大きさが 1/n のとき、y=1 での増幅率は n=10 で 1.101×10^3、n=20 で 1.213×10^7、n=40 で 2.942×10^15、n=80 で 3.463×10^32 であった。初期値は 0 に向かっているのに、解は発散する。しかも存在も一意性も壊れていない──解はあり、一つに決まる。壊れているのは三つ目だけである。 第三に、時間が 1 本だと同じ手順が有界に収まる。方程式を波動方程式に替える。符号を一つ変えただけである。同じ初期値を入れると、増幅率は n=10 で 0.0544、n=20 で 0.0457、n=40 で 0.0186、n=80 で 0.0124 になった。同じ n=80 で 3.463×10^32 と 0.0124 ──34 桁の差である。替えたのは方程式の一つの符号であって、初期条件でも解き方でも精度でもな
Yuuki Yamagishi· Zenodo (CERN European Organi...· 0 citations
--- AUTHOR'S NOTE: These concepts are shared openly to inspire new perspectives and further research in theoretical astrophysics. This work is dedicated to the public domain.Everyone is completely free to utilize, build upon, or incorporate these ideas into their own research. The author wishes to remain anonymous. The underlying physical concepts were conceived by the author and structured/formulated with the assistance of an AI. (The document is presented first in English, followed by the German version below.) --- ================================================================================english================================================================================THE GEOMETRIC-TEMPORAL GRAVITATIONAL TRIAD:Non-Linear Geometry, Spacetime Inertia, and Temporal Self-Interference as a Complete Alternative to Hypothetical Dark Matter================================================================================Author: Asgrim42Field: Theoretical Astrophysics / General Relativity / Cosmology --------------------------------------------------------------------------------ABSTRACT--------------------------------------------------------------------------------This paper proposes a purely geometric and dynamical resolution to the discrepancies observed in galactic rotation curves and gravitational lensing anomalies (such as the Bullet Cluster) without invoking hypothetical non-baryonic Dark Matter (WIMPs/axions). The model relies on a triad of three emergent spacetime phenomena:1. Non-linear collective spacetime curvature (Macroscopic potential well)2. Spacetime inertia and dynamical wave-lag (Geometric phase shift)3. Temporal worldline self-interference (Bidirectional gravitational coupling) Together, these mechanisms eliminate the need for Dark Matter across both galactic and cosmological cluster scales. ================================================================================1. INTRODUCTION & PROBLEM STATEMENT================================================================================Standard cosmology (ΛCDM) posits that approximately 85% of cosmic matter consists of invisible, weakly interacting particles. Despite decades of ultra-sensitive detection experiments, direct empirical confirmation remains entirely absent. This hypothesis shifts the paradigm away from microphysical particle searches toward a more rigorous utilization of the intrinsic degrees of freedom of four-dimensional spacetime geometry itself. ================================================================================2. PILLAR I: COLLECTIVE NON-LINEAR SPACETIME CURVATURE (Macro-Potential Well)================================================================================[Plain-Language Summary] If a single person stands on a trampoline, they make a small dent. But if hundreds of people stand close together, their individual dents do not merely add up; the entire fabric sags deeply as a collective whole. In galaxies, billions of stars together create a vast, shared "gravitational basin" that pulls far more strongly than simply summing up the stars one by one. [Technical Formulation for Physicists] In the Newtonian limit, gravitation is treated as a linear superposition field (Φ_tot = ∑ Φ_i). However, Einstein's field equations G_μν = (8πG/c⁴) T_μν are fundamentally non-linear: gravitational field energy possesses an energy-momentum equivalent and acts back on spacetime geometry ("gravity gravitates"). When scaling N-body systems to galactic dimensions (N > 10¹¹), the non-linear superposition of curvature tensors induces a global deepening of the potential well. The resulting effective potential Φ_eff(r) departs from the purely Keplerian 1/r falloff and establishes a logarithmic plateau in the outskirts: Φ_eff(r) ≈ - (G M_bar / r) * [1 + α * ln(r / r_0)]This naturally explains the flatness of galactic rotation curves v(r) ≈ const. beyond a critical transition radius r_0 without requiring missing mass. ================================================================================3. PILLAR II: SPACETIME INERTIA & WAVE-LAG (The Bullet Cluster Phenomenon)================================================================================[Plain-Language Summary] Imagine a heavy bowling ball rolling along a thick rubber sheet, pushing a wave ahead of itself. If the ball hits a barrier and stops abruptly, the dented wave in the elastic rubber will keep rolling forward for a bit due to its momentum. This is precisely what happens in colliding galaxies: the gas crashes and brakes, but the distortion in space keeps moving ahead, creating the illusion of "invisible matter." [Technical Formulation for Physicists] Observations such as the Bullet Cluster (1E 0657-56) are widely considered the primary empirical proof for Dark Matter, as the gravitational lensing centroid is spatially displaced from the collisional X-ray gas. This hypothesis posits that the metric tensor g_μν exhibits dynamic impedance and a finite relaxation time τ_space. In high-energy cluster collisions, the baryonic plasma undergoes ram-pressure stripping and is decelerated dissipatively (a_gas << 0). The field momentum stored within the Riemann curvature tensor R^ρ_σμν decouples ballistically and continues propagating as a coherent spacetime soliton wave at the initial velocity v_0: □ g_μν + γ * ∂_t g_μν = - (8πG/c⁴) T_μν(t - τ)Gravitational lensing in such systems does not measure missing particle mass, but rather the transient geometric afterglow of a dissipating spacetime curvature wake. ================================================================================4. PILLAR III: TEMPORAL WORLDLINE INTERFERENCE (Wheeler-Feynman Gravity)================================================================================[Plain-Language Summary] A galaxy does not merely exist in the present moment; in four-dimensional spacetime, it forms a continuous "world-tube" stretching from the past into the future. Because gravity can propagate bidirectionally across time, the galaxy at this very moment feels the gravitational echo of its own existence from both the past and the future. It pulls on itself across time. [Technical Formulation for Physicists] In analogy to the time-symmetric Wheeler-Feynman absorber theory of electrodynamics, the gravitational propagator is formulated as a symmetric Green's function comprising retarded (D_ret) and advanced (D_adv) potentials: G(x - x') = 1/2 [ D_ret(x - x') + D_adv(x - x') ] Within the 4D block universe, a galaxy constitutes a quasi-stationary worldline W(τ) with continuous energy-momentum distribution. Along the temporal coordinate, a resonant self-interference emerges: g_μν(x^α, t_0) = ∫ d⁴x' G(x - x') T_μν(x'^α, t') Baryonic matter thereby interacts with its own advanced and retarded curvature wake. This "pre-echo" effect generates a self-induced gravitational potential channel that strictly correlates with the observed baryonic morphology, reproducing the apparent "dark halo" without requiring non-baryonic matter fields. ================================================================================5. SYNTHESIS AND OUTLOOK================================================================================The integration of these three mechanisms constitutes a parsimonious, unified framework:1. Non-linearity accounts for the static baseline force enhancement in galaxies.2. Spacetime inertia explains apparent mass-lensing offsets during high-velocity collisions.3. Temporal self-interference dynamically stabilizes spiral structures and halo profiles. Future work requires quantitative numerical simulations employing time-nonlocal integro-differential field equations to benchmark against high-resolution empirical datasets (e.g., the SPARC catalog).================================================================================ ================================================================================deutsch (German)================================================================================DIE GEOMETRISCH-TEMPORALE GRAVITATIONS-TRIADE:Nicht-lineare Geometrie, Raumzeit-Trägheit und temporale Selbst-Interferenz als vollständiger Ersatz hypothetischer Dunkler Materie================================================================================Autor: Asgrim42Themenbereich: Theoretische Astrophysik / Allgemeine Relativitätstheorie / Kosmologie --------------------------------------------------------------------------------ABSTRACT--------------------------------------------------------------------------------Die vorliegende Arbeit postuliert eine rein geometrisch-dynamische Lösung für die Diskrepanzen in galaktischen Rotationskurven und gravitativen Linsen-anomalien (wie dem Bullet-Cluster) ohne den Rückgriff auf hypothetische nicht-baryonische Dunkle Materie (WIMPs/Axionen). Das Modell stützt sich auf eine Triade aus drei emergenten Phänomenen der Raumzeit:1. Nicht-lineare kollektive Raumzeitkrümmung (Makroskopisches Potentialbett)2. Raumzeit-Trägheit und dynamische Wellennacheilung (Geometrische Phasenverschiebung)3. Temporale Weltlinien-Interferenz (Bidirektionale gravitative Selbst-Kopplung) Gemeinsam eliminieren diese Mechanismen die Notwendigkeit von Dunkler Materie sowohl auf galaktischer als auch auf kosmologischer Cluster-Skala. ================================================================================1. EINLEITUNG & PROBLEMSTELLUNG================================================================================Die Standardkosmologie (ΛCDM) postuliert ca. 85 % der kosmischen Materie als unsichtbare, schwach wechselwirkende Teilchen. Trotz jahrzehntelanger hochempfind-licher Experimente fehlt jeder direkte Nachweis. Diese Hypothese verschiebt den Fokus von der mikrophysikalischen Teilchensuche hin zu einer präziseren Ausnutzung der inhärenten Freiheitsgrade der vier-dimensionalen Raumzeit-Geometrie se
Asgrim Mimersson· Zenodo (CERN European Organi...· 0 citations
The proposed ecosystem automaticallygenerates anonymized source code minimaps directly from files be-ing edited across different development environments and submitsthem to deep learning models previously trained on large-scaleminimap datasets containing hundreds of thousands of source coderepresentations spanning 10 programming languages, includingJava, Python, JavaScript, C, PHP, Go, Ruby, and Kotlin. The back-end architecture supports detection of type classification, projectidentification, and author-style analysis using convolutional neuralnetworks and explainable AI techniques derived from prior researchon source code minimaps.
Munif Gebara Junior, Lucas Neo, Vitor Teodoro et al.· Zenodo (CERN European Organi...· 0 citations
This research presents a comprehensive framework for integrating Explainable Artificial Intelligence (XAI) into Intrusion Detection Systems (IDS) to address the critical challenge of AI model opacity in cybersecurity. Traditional AI-based IDS models function as "black boxes," limiting trust, accountability, and practical deployment. The proposed XAI-IDS framework combines machine learning-based intrusion detection (Random Forest, XGBoost, Neural Networks) with explainability mechanisms including SHAP, LIME, and feature importance analysis. Experimental evaluation using benchmark datasets (KDD Cup 99, UNSW-NB15, CIC-IDS-2017) demonstrates that the XAI-enabled system achieves high detection accuracy (96-98%) while providing transparent, human-interpretable explanations for each security decision. The framework significantly reduces false positives, enhances auditability, and improves security analyst trust and response effectiveness without substantial performance degradation.
Muhammad Haris Khan· Zenodo (CERN European Organi...· 0 citations
Cardiovascular disease (CVD) are a leading cause of global morbidity and mortality, making early and accurate detection essential for improving patient outcomes. The electrocardiogram (ECG) is one of the most important diagnostic tools for identifying various cardiac abnormalities. Recent advances in machine learning (ML) and deep learning (DL) have shown strong potential for improving ECG-based CVD detection. This review critically analyzes recent ECG-based ML/DL models for CVD prediction, with particular attention to model performance, dataset characteristics, preprocessing strategies, and the integration of explainable artificial intelligence (XAI). The review covers a broad range of ECG-related applications, including arrhythmia, myocardial infarction, atrial fibrillation, heart failure, pediatric and fetal ECG analysis, wearable ECG monitoring, ECG image analysis, and ECG-centered multimodal approaches. Across the 75 included studies, reported diagnostic performance was generally high, with accuracy commonly ranging from approximately 90 to 99%, sensitivity from approximately 81 to 99%, specificity from approximately 84 to 99%, AUROC values reaching up to approximately 0.98–0.99, and F1-scores exceeding 0.90 in several benchmark datasets. However, these results varied substantially according to dataset characteristics, disease category, preprocessing strategy, model architecture, validation protocol, and evaluation metrics. Although many studies reported excellent internal validation performance, relatively few performed external or prospective clinical validation, highlighting an important gap in the translation of AI-assisted ECG models into routine clinical practice. The most frequently used datasets included MIT-BIH, PTB-XL, PhysioNet, CPSC, and UK Biobank, while dominant model families included CNN, LSTM, Transformer, SVM, RF, and hybrid CNN-LSTM architectures. Although ML/DL models have reported promising diagnostic performance, several challenges remain, including class imbalance, data quality variation, limited generalizability, model interpretability, and the limited availability of external and prospective clinical validation, which remain major barriers to the widespread clinical adoption of AI-assisted ECG diagnostic systems. In addition, ethical, legal, and social issues, such as data bias, privacy, transparency, and clinical trust, must be addressed before these models can be reliably and responsibly deployed in clinical practice. This review provides an integrated overview of ECG-based AI models for CVD prediction and highlights future research directions for developing more interpretable, generalizable, and clinically trustworthy AI-assisted ECG diagnostic systems.
Sabit Ahamed Preanto, Md. Hasan Imam Bijoy, Tapon Paul et al.· Discover Artificial Intellig...· 0 citations
The rapid advancement of artificial intelligence, particularly in large language models, has brought significant challenges in decoding methods that balance performance with interpretability. This paper presents a comprehensive analysis of advanced decoding techniques that enhance both model capabilities and explainability. We explore novel approaches including adaptive temperature sampling, nucleus sampling with dynamic thresholds, and hybrid decoding methods that combine multiple strategies. Our research demonstrates that these advanced techniques can significantly improve model performance metrics while maintaining or enhancing interpretability. Through extensive experimentation across diverse datasets, we show that our proposed hybrid decoding method achieves a 12.3% improvement in perplexity scores while maintaining competitive computational efficiency. The findings contribute to the growing body of research on transparent AI systems and provide practical insights for practitioners aiming to deploy more reliable and interpretable AI models in high-stakes applications.
Zen Revista, 10 IA· Zenodo (CERN European Organi...· 0 citations
This paper proposes a novel deep learning model incorporating symbolic reasoning for enhanced visual understanding. The core idea is to bridge the gap between deep learning's ability to extract intricate visual features and symbolic reasoning's capacity for logical deduction. The model consists of two key components: a deep learning module for feature extraction and a symbolic reasoning engine for logical inference. We explore the architecture and training strategies to effectively integrate these components, aiming to achieve more robust and explainable visual understanding. The model is designed to handle tasks requiring not just pattern recognition, but also the ability to interpret relationships and constraints expressed in symbolic form. This work represents a significant step towards more intelligent and reliable AI systems by combining the strengths of both paradigms.
Jincheng Zhang· Zenodo (CERN European Organi...· 0 citations
